I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
14
,
No
.
6
,
Dec
em
b
er
20
24
,
p
p
.
7
1
6
9
~
7
1
7
7
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
14
i
6
.
pp
7
1
6
9
-
7
1
7
7
7169
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Framewo
rk
for d
etec
ti
ng
and resis
ting cy
bera
tt
a
cks
o
n
cy
ber
-
phy
sica
l sy
stems i
n int
er
net
of
t
hin
g
s
J
y
o
t
i Met
a
n
1
,
M
a
ha
nte
s
h M
a
t
ha
pa
t
i
2
,
P
ra
s
a
d
Ada
g
uru
Yo
g
eg
o
wda
3
,
K
urilin
g
a
Sa
nn
a
lin
g
a
pp
a
A
na
nd
a
K
um
a
r
4
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
,
A
t
r
i
a
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
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
,
A
mr
u
t
a
I
n
st
i
t
u
t
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
M
a
n
a
g
e
me
n
t
S
c
i
e
n
c
e
s
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
JB
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
a
n
d
S
c
i
e
n
c
e
E
n
g
i
n
e
e
r
i
n
g
,
A
t
r
i
a
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
1
3
,
2
0
2
4
R
ev
is
ed
J
u
l 2
9
,
2
0
2
4
Acc
ep
ted
Au
g
6
,
2
0
2
4
Cy
b
e
r
-
p
h
y
sic
a
l
s
y
ste
m
(CP
S
)
is
a
n
i
n
teg
ra
l
p
a
rt
o
f
a
n
i
n
tern
e
t
of
th
in
g
s (Io
T)
with
e
sta
b
li
s
h
e
d
wi
d
e
sp
re
a
d
a
p
p
li
c
a
ti
o
n
s.
An
in
c
re
a
sin
g
c
o
n
c
e
rn
t
o
wa
rd
s
b
e
in
g
h
i
g
h
ly
v
u
ln
e
ra
b
le
to
v
a
rio
u
s
fo
rm
s
o
f
d
y
n
a
m
ic
c
y
b
e
r
-
a
tt
a
c
k
s
h
a
s
b
e
e
n
in
c
re
a
sin
g
ly
e
v
o
lv
i
n
g
.
A
re
v
i
e
w
o
f
e
x
isti
n
g
re
se
a
rc
h
m
e
th
o
d
o
l
o
g
y
sh
o
wc
a
se
s
c
o
m
p
lex
so
lu
t
io
n
s
th
a
t
c
a
n
o
ffe
r
su
b
-
o
p
ti
m
a
l
se
c
u
rit
y
stre
n
g
t
h
wh
e
n
e
x
p
o
se
d
to
d
y
n
a
m
ic
c
y
b
e
r
-
a
tt
a
c
k
fo
rm
s
wh
il
e
i
n
c
re
a
sin
g
th
e
c
o
m
p
u
tati
o
n
a
l
b
u
r
d
e
n
.
T
h
e
re
fo
r
e
,
th
is
m
a
n
u
sc
rip
t
p
re
se
n
ts
a
n
o
v
e
l
y
e
t
sim
p
li
fied
c
o
m
p
u
tatio
n
a
l
fra
m
e
wo
rk
c
a
p
a
b
le
o
f
d
e
term
in
in
g
a
n
d
re
sistin
g
c
rit
ica
l
a
n
o
m
a
li
e
s
with
i
n
i
n
tern
e
t
-
of
-
c
y
b
e
r
p
h
y
sic
a
l
sy
ste
m
s
(Io
CP
S
).
T
h
e
p
re
se
n
ted
sc
h
e
m
e
c
o
n
tri
b
u
tes
t
o
wa
rd
s
p
re
p
ro
c
e
ss
in
g
fo
l
lo
wi
n
g
a
d
isti
n
c
t
o
v
e
rsa
m
p
li
n
g
m
e
th
o
d
targ
e
ti
n
g
b
a
lan
c
in
g
th
e
d
a
ta.
A
n
e
n
se
m
b
l
e
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
l
u
si
n
g
a
d
isc
re
te
v
a
rian
t
o
f
Ad
a
Bo
o
st
a
n
d
n
e
u
ra
l
d
e
c
isio
n
tree
(ND
T)
h
a
s
b
e
e
n
imp
lem
e
n
ted
to
o
p
ti
m
ize
th
e
lea
rn
in
g
p
r
o
c
e
ss
a
n
d
imp
r
o
v
e
th
e
th
re
a
t
d
e
tec
ti
o
n
e
fficie
n
c
y
.
Th
e
c
o
m
p
a
ra
ti
v
e
o
u
tco
m
e
o
f
th
e
p
ro
p
o
se
d
stu
d
y
s
h
o
wc
a
se
s
th
a
t
it
o
ffe
rs
a
p
p
ro
x
ima
tely
7
.
2
%
in
c
re
a
se
d
th
re
a
t
d
e
tec
ti
o
n
a
c
c
u
ra
c
y
a
n
d
a
p
p
ro
x
ima
tely
6
8
%
re
d
u
c
e
d
re
sp
o
n
se
ti
m
e
c
o
m
p
a
re
d
to
fre
q
u
e
n
tl
y
a
d
o
p
ted
lea
rn
in
g
m
e
c
h
a
n
ism
s
to
wa
rd
s
th
re
a
t
d
e
tec
ti
o
n
o
v
e
r
a
n
Io
T
e
n
v
iro
n
m
e
n
t.
K
ey
w
o
r
d
s
:
An
o
m
aly
C
y
b
er
attac
k
s
C
y
b
er
-
p
h
y
s
ical
s
y
s
tem
I
n
ter
n
et
of
th
in
g
s
Ma
ch
in
e
lear
n
in
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
:
J
y
o
ti M
etan
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
,
Atr
ia
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
ASKB
C
am
p
u
s
,
1
st
Ma
in
R
d
,
AGS
C
o
lo
n
y
,
An
an
d
n
ag
ar
,
He
b
b
al,
B
en
g
alu
r
u
-
5
6
0
0
2
4
,
Kar
n
atak
a,
I
n
d
ia
E
m
ail:
jy
o
tim
etan
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
r
ap
id
ad
v
a
n
ce
m
en
t
o
f
tec
h
n
o
lo
g
ies
y
ea
r
af
ter
y
ea
r
h
as
in
tr
o
d
u
ce
d
a
n
ew
s
y
s
tem
o
f
i
n
ter
r
elate
d
o
b
jects
k
n
o
wn
as
th
e
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
.
I
t
aim
s
to
c
o
n
n
ec
t
m
u
ltip
le
elec
tr
o
n
ic
e
q
u
ip
m
en
t
an
d
s
m
ar
t
d
ev
ices
to
t
h
e
I
n
ter
n
et
t
o
a
u
to
m
ate
th
e
s
y
s
tem
[
1
]
.
Ho
wev
er
,
th
e
lar
g
e
-
s
ca
le
c
o
n
n
ec
tio
n
o
f
s
u
ch
elec
tr
o
n
ics
an
d
s
m
ar
t
d
e
v
ices
r
eq
u
i
r
es
m
ass
iv
e
s
to
r
ag
e
s
p
ac
e
an
d
c
o
m
p
u
tin
g
p
o
wer
[
2
]
.
T
h
er
e
f
o
r
e,
th
e
cy
b
er
-
p
h
y
s
ical
s
y
s
tem
(
C
P
S)
cr
ea
tes
a
h
u
g
e
s
to
r
ag
e
s
p
ac
e
an
d
h
ig
h
co
m
p
u
tin
g
p
o
wer
th
r
o
u
g
h
clo
u
d
co
m
p
u
tin
g
tech
n
o
lo
g
y
[
3
]
.
C
PS
r
ef
er
s
to
an
in
ter
c
o
n
n
ec
ted
en
v
ir
o
n
m
e
n
t
o
f
co
m
m
u
n
icatio
n
with
t
h
eir
in
ter
ac
tio
n
with
th
e
I
o
T
a
n
d
th
e
clo
u
d
will
lead
to
f
u
tu
r
is
tic
C
PS
,
n
am
ely
th
e
in
ter
n
et
o
f
cy
b
er
-
p
h
y
s
ical
th
in
g
s
(
I
o
C
PT)
,
wh
ich
r
ef
e
r
s
to
an
ad
v
an
ce
d
s
y
s
tem
o
f
th
e
s
ea
m
less
in
teg
r
atio
n
o
f
co
m
p
u
tatio
n
em
p
o
wer
e
d
b
y
cl
o
u
d
c
o
m
p
u
tin
g
an
d
p
h
y
s
ical
co
m
p
o
n
en
ts
em
p
o
wer
e
d
b
y
I
o
T
[
4
]
.
T
h
is
f
u
tu
r
is
tic
tech
n
o
lo
g
y
in
ter
ests
r
esear
ch
co
m
m
u
n
ities
an
d
in
d
u
s
tr
ies
d
u
e
to
its
p
o
ten
tial
b
e
n
ef
its
to
s
o
ciety
,
t
h
e
e
n
v
ir
o
n
m
en
t,
an
d
th
e
e
co
n
o
m
y
[
5
]
,
[
6
]
.
An
o
m
a
lies
in
I
o
C
PS
d
ata
ca
n
o
cc
u
r
f
o
r
v
ar
io
u
s
r
ea
s
o
n
s
,
in
clu
d
in
g
s
y
s
tem
m
alf
u
n
ctio
n
s
,
cy
b
er
-
attac
k
s
,
o
r
h
u
m
an
er
r
o
r
.
An
o
m
alies
in
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
1
6
9
-
7
1
7
7
7170
n
etwo
r
k
r
e
f
er
to
u
n
u
s
u
al
o
r
a
b
n
o
r
m
al
b
e
h
av
io
r
th
at
d
e
v
iates
f
r
o
m
th
e
ex
p
ec
te
d
p
atter
n
o
r
b
eh
av
io
r
[
7
]
.
T
h
ese
an
o
m
alies
ca
n
h
av
e
s
er
io
u
s
co
n
s
eq
u
en
ce
s
,
s
u
ch
as
d
ec
r
ea
s
ed
ef
f
icien
cy
,
in
cr
ea
s
ed
d
o
wn
tim
e,
an
d
p
o
ten
tial
s
af
ety
r
is
k
s
[
8
]
.
Attack
er
s
m
ay
tar
g
et
th
ese
s
y
s
tem
s
to
s
teal
s
en
s
itiv
e
in
f
o
r
m
atio
n
,
alter
o
r
d
is
r
u
p
t
n
o
r
m
a
l
o
p
er
atio
n
s
,
o
r
g
ain
u
n
au
th
o
r
iz
ed
co
n
tr
o
l.
I
n
s
o
m
e
ca
s
es,
an
attac
k
er
m
ay
ex
p
l
o
it
a
v
u
ln
er
a
b
ilit
y
in
th
e
s
y
s
tem
to
ca
u
s
e
a
m
alf
u
n
cti
o
n
o
r
f
a
ilu
r
e
[
9
]
.
Similar
ly
,
an
i
n
d
u
s
tr
ial
co
n
tr
o
l
s
y
s
tem
an
o
m
aly
co
u
ld
r
esu
lt
in
a
p
r
o
d
u
ctio
n
lin
e
s
h
u
td
o
wn
,
lea
d
in
g
to
s
ig
n
if
ican
t
f
in
an
cial
lo
s
s
es
an
d
o
p
er
atio
n
al
d
is
r
u
p
tio
n
s
[
1
0
]
.
T
h
er
e
f
o
r
e,
it
is
ess
en
tia
l
to
d
etec
t
an
o
m
alies
in
th
e
d
ata
g
en
er
ate
d
b
y
in
tellig
en
t
s
en
s
o
r
s
as
q
u
ick
l
y
an
d
ac
c
u
r
ately
as
p
o
s
s
ib
le.
An
o
m
aly
d
etec
tio
n
i
d
en
tifie
s
p
atter
n
s
o
r
b
eh
av
io
r
s
in
d
ata
th
at
d
ev
iate
f
r
o
m
s
tan
d
ar
d
p
atter
n
s
in
r
ea
l
tim
e.
Var
io
u
s
liter
atu
r
e
d
is
cu
s
s
es
ap
p
r
o
ac
h
es
to
d
etec
t
in
t
r
u
s
io
n
s
an
d
an
o
m
alies
in
th
ese
s
y
s
tem
s
,
in
clu
d
in
g
r
u
le
-
b
ased
s
y
s
tem
s
,
s
ig
n
atu
r
e
-
b
ased
s
y
s
tem
s
[
1
1
]
an
d
m
ac
h
in
e
lear
n
in
g
-
b
ased
s
y
s
tem
s
[
1
2
]
.
Ma
ch
in
e
lear
n
in
g
-
b
ased
s
y
s
tem
s
ef
f
ec
tiv
ely
d
etec
t
n
ew
ty
p
es
o
f
attac
k
s
an
d
an
o
m
alies,
b
u
t
th
e
y
ca
n
b
e
co
m
p
le
x
an
d
tim
e
-
co
n
s
u
m
in
g
to
im
p
lem
e
n
t
[
1
3
]
.
T
h
e
r
elate
d
wo
r
k
in
th
is
d
ir
ec
tio
n
f
o
llo
ws:
J
in
et
a
l.
[
1
4
]
p
r
esen
ted
a
m
u
ltil
ay
er
lear
n
in
g
m
o
d
el
to
d
etec
t
an
o
m
alies
in
p
o
wer
s
y
s
tem
s
u
s
in
g
a
co
n
v
o
lu
tio
n
n
eu
r
al
n
etwo
r
k
(
C
NN)
to
le
ar
n
th
e
ty
p
ical
d
ata
p
atter
n
s
an
d
d
etec
t
an
o
m
alies
in
r
ea
l
tim
e.
T
h
e
r
esu
lt
s
u
g
g
ests
th
at
th
is
s
ch
em
e
p
e
r
f
o
r
m
s
b
etter
th
a
n
co
n
v
en
tio
n
al
m
et
h
o
d
s
,
s
u
ch
a
s
Kalm
an
f
ilter
in
g
a
n
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
.
C
h
e
n
et
a
l.
[
1
5
]
u
s
ed
a
d
ee
p
lear
n
i
n
g
-
b
ased
ap
p
r
o
ac
h
to
d
etec
t
an
o
m
alies
in
s
m
ar
t
g
r
id
d
ata.
T
h
is
s
ch
em
e
a
d
o
p
te
d
a
r
ec
u
r
r
en
t
n
eu
r
a
l
n
etwo
r
k
(
R
NN)
m
o
d
el
to
ca
p
tu
r
e
th
e
tem
p
o
r
al
r
elatio
n
s
h
ip
s
b
etwe
en
d
ata
p
o
in
ts
an
d
d
etec
t
r
ea
l
-
tim
e
an
o
m
alies.
T
h
e
o
u
tco
m
e
d
em
o
n
s
tr
ates
th
at
th
e
p
r
esen
ted
a
p
p
r
o
ac
h
is
p
r
ac
tical
o
v
er
c
o
n
v
en
tio
n
al
m
eth
o
d
s
,
s
u
ch
as
B
ay
esian
n
etwo
r
k
s
a
n
d
d
ec
is
io
n
tr
ee
s
.
Gu
et
a
l.
[
1
6
]
p
r
esen
ted
a
r
u
le
-
b
ased
s
y
s
tem
f
o
r
in
tr
u
s
io
n
d
etec
tio
n
in
C
PS
.
T
h
e
s
y
s
tem
was
b
ased
o
n
a
s
et
o
f
p
r
ed
e
f
in
ed
r
u
les
an
d
p
o
licies
th
at
w
er
e
u
s
ed
to
d
etec
t
p
o
ten
tial
in
tr
u
s
io
n
s
.
T
h
e
a
u
th
o
r
s
ev
alu
ated
th
e
s
y
s
tem
u
s
i
n
g
r
ea
l
-
wo
r
l
d
C
PS
d
ata
an
d
f
o
u
n
d
it
ef
f
ec
tiv
ely
d
etec
ted
in
tr
u
s
io
n
s
with
h
ig
h
ac
cu
r
ac
y
.
Ho
wev
e
r
,
th
is
s
y
s
tem
is
lim
i
ted
in
co
u
n
ter
in
g
n
ew
attac
k
s
an
d
an
o
m
alies.
B
ao
et
a
l.
[
1
7
]
s
u
g
g
ested
a
s
y
s
tem
b
ased
o
n
p
r
ed
ef
in
ed
p
atter
n
s
to
d
etec
t
i
n
tr
u
s
io
n
s
an
d
an
o
m
alies
in
I
o
T
d
ata.
R
ea
l
-
wo
r
ld
I
o
T
d
ata
is
u
s
ed
in
th
e
ev
alu
atio
n
,
a
n
d
r
esu
lts
in
d
icate
th
at
it
ef
f
ec
tiv
ely
d
etec
ted
o
n
l
y
k
n
o
wn
in
tr
u
s
io
n
s
an
d
an
o
m
al
ies.
I
n
g
r
e
et
a
l.
[
1
8
]
a
d
ec
is
io
n
tr
ee
-
b
ased
s
y
s
tem
was
p
r
o
p
o
s
ed
,
ef
f
ec
tiv
el
y
d
etec
tin
g
in
tr
u
s
io
n
s
a
n
d
a
n
o
m
alies
in
C
PS
d
ata.
T
h
e
s
im
u
latio
n
o
u
tco
m
e
s
h
o
ws
th
at
th
is
m
eth
o
d
o
u
tp
er
f
o
r
m
ed
o
th
er
tr
ad
itio
n
al
lear
n
in
g
alg
o
r
ith
m
s
r
eg
ar
d
in
g
ac
cu
r
ac
y
an
d
s
p
ee
d
.
L
iu
et
a
l.
[
1
9
]
em
p
lo
y
ed
a
r
an
d
o
m
f
o
r
est
f
o
r
in
tr
u
s
io
n
d
etec
tio
n
in
I
o
T
s
y
s
tem
s
.
T
h
e
r
esu
lt
s
h
o
ws
th
at
th
e
s
y
s
tem
ef
f
ec
tiv
ely
d
etec
ts
in
tr
u
s
io
n
s
an
d
an
o
m
alies
in
I
o
T
d
ata
a
n
d
o
u
t
p
er
f
o
r
m
s
o
th
e
r
t
r
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
r
eg
ar
d
i
n
g
ac
cu
r
ac
y
an
d
s
p
ee
d
.
L
i
et
a
l.
[
2
0
]
h
a
v
e
d
escr
ib
ed
th
e
ef
f
ec
ti
v
en
ess
o
f
d
ee
p
lear
n
in
g
-
b
ased
in
tr
u
s
io
n
d
etec
tio
n
C
PS
.
Ao
u
ed
i
et
a
l.
[
2
1
]
d
esig
n
ed
a
d
ee
p
b
elief
n
etwo
r
k
,
a
n
d
Der
h
a
b
et
a
l.
[
2
2
]
d
e
v
elo
p
e
d
a
m
u
ltil
ay
er
d
ee
p
n
eu
r
al
n
etwo
r
k
(
DNN)
to
d
et
ec
t
an
o
m
alies
in
I
o
T
n
etwo
r
k
d
ata
an
d
ev
al
u
ate
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
u
s
in
g
r
ea
l
-
wo
r
ld
I
o
T
n
etwo
r
k
d
ata.
Alth
o
b
aiti
et
a
l.
[
2
3
]
ad
o
p
ted
DNN
to
id
en
tif
y
in
t
r
u
s
io
n
p
at
ter
n
s
in
C
PS
d
ata.
Awo
tu
n
d
e
et
a
l.
[
2
4
]
h
av
e
d
e
v
elo
p
ed
p
r
o
to
c
o
l
-
in
d
e
p
en
d
e
n
t
in
d
ep
en
d
en
t
I
DS
u
s
in
g
d
ee
p
lear
n
in
g
to
d
etec
t
d
y
n
am
ic
attac
k
s
s
u
ch
as
b
lack
h
o
le,
d
is
tr
ib
u
ted
d
en
ial
o
f
s
er
v
ice
(
DDo
S),
o
p
p
o
r
tu
n
is
tic
s
er
v
ice
,
Sin
k
h
o
le,
a
n
d
W
o
r
m
h
o
le
attac
k
s
.
T
u
s
h
k
a
n
o
v
a
et
a
l.
[
2
5
]
e
x
p
lo
r
e
d
e
x
is
tin
g
ap
p
r
o
ac
h
es,
s
u
g
g
ested
d
ev
elo
p
in
g
th
r
ea
t
d
etec
tio
n
b
ased
o
n
th
e
b
eh
av
i
o
r
an
aly
s
es,
a
n
d
a
d
o
p
ted
an
u
n
s
u
p
er
v
is
ed
lear
n
in
g
ap
p
r
o
ac
h
.
T
an
g
et
a
l.
[
2
6
]
p
r
esen
ted
a
th
r
ea
t
d
etec
tio
n
b
ased
o
n
a
d
if
f
u
s
io
n
m
o
d
el
f
o
r
in
d
u
s
tr
ial
C
PS
.
A
d
if
f
u
s
io
n
m
o
d
el
is
ad
o
p
te
d
to
b
alan
ce
th
e
d
ataset,
an
d
th
en
bi
-
d
ir
ec
tio
n
al
lo
n
g
-
s
h
o
r
t
-
ter
m
-
m
em
o
r
y
(
B
iLST
M)
is
ad
o
p
ted
to
class
if
y
th
e
an
o
m
aly
.
Ka
n
d
h
r
o
et
a
l.
[
2
7
]
ad
o
p
ted
a
jo
in
t
ap
p
r
o
ac
h
o
f
u
n
s
u
p
er
v
is
ed
lea
r
n
in
g
an
d
g
e
n
er
ativ
e
ad
v
e
r
s
ar
ial
n
etwo
r
k
to
d
etec
t
p
o
ten
tial
cy
b
er
-
attac
k
s
in
I
o
T
-
d
r
iv
e
n
cy
b
er
in
f
r
astru
ctu
r
e
.
T
h
e
r
esu
lt
s
h
o
ws
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
p
r
esen
te
d
s
ch
em
e
i
n
th
at
it
o
u
tp
er
f
o
r
m
s
an
o
th
er
s
im
ilar
m
o
d
el
in
ter
m
s
o
f
ac
cu
r
ac
y
,
r
eliab
ilit
y
,
an
d
d
etec
tio
n
ef
f
ici
en
cy
.
T
h
e
co
r
e
r
esear
ch
p
r
o
b
lem
s
id
en
tifie
d
f
r
o
m
a
liter
atu
r
e
r
e
v
ie
w
ar
e:
i)
d
eg
r
ad
ed
s
ca
lab
ilit
y
,
ii)
h
ig
h
er
f
alse
p
o
s
itiv
e
o
u
tco
m
e
an
d
iii)
d
ata
im
b
alan
ce
f
ac
t
o
r
ass
o
ciate
d
with
th
e
n
etwo
r
k
d
ataset.
I
o
T
an
d
C
PS
s
y
s
tem
s
o
f
ten
in
v
o
lv
e
m
an
y
c
o
n
n
ec
ted
d
e
v
ices,
an
d
it
ca
n
b
e
ch
allen
g
in
g
to
a
p
p
ly
co
m
p
lex
an
d
s
p
ec
if
ically
d
esig
n
ed
d
ee
p
lear
n
in
g
tech
n
i
q
u
es
in
a
s
ca
lab
le
m
an
n
er
to
d
etec
t
an
o
m
alies
in
h
ig
h
v
o
lu
m
es
o
f
s
tr
ea
m
in
g
n
etwo
r
k
d
ata.
Ap
ar
t
f
r
o
m
th
i
s
th
ese
s
y
s
tem
s
o
f
ten
ex
p
er
ien
ce
im
b
alan
ce
d
d
ata
d
is
tr
ib
u
t
io
n
s
,
with
a
s
m
all
n
u
m
b
er
o
f
an
o
m
alies
o
r
in
tr
u
s
io
n
s
am
o
n
g
a
lar
g
e
am
o
u
n
t
o
f
s
tan
d
ar
d
d
ata.
T
h
is
ca
n
m
a
k
e
it
d
if
f
icu
lt
f
o
r
d
ee
p
lear
n
in
g
m
o
d
els to
id
en
tify
an
o
m
alies a
cc
u
r
ately
.
T
h
er
e
f
o
r
e,
th
e
r
esear
ch
wo
r
k
r
ep
o
r
ted
in
th
is
p
ap
er
s
u
g
g
ests
an
o
p
tim
al
s
ec
u
r
ity
s
y
s
tem
b
y
co
m
b
in
in
g
th
e
s
tr
en
g
th
s
o
f
m
u
ltip
le
o
p
tim
ized
class
if
ier
s
f
o
llo
wed
b
y
a
n
ef
f
ec
tiv
e
d
ata
m
o
d
ellin
g
s
ch
e
m
e
to
ac
h
iev
e
h
ig
h
ac
cu
r
ac
y
,
f
aster
r
esp
o
n
s
e
tim
e
an
d
r
o
b
u
s
tn
ess
in
d
etec
tin
g
d
y
n
am
ic
s
ec
u
r
ity
th
r
ea
ts
.
I
n
r
esp
o
n
s
e
to
th
e
s
tu
d
ies
m
e
n
tio
n
ed
ab
o
v
e,
th
is
m
an
u
s
cr
i
p
t'
s
co
n
tr
ib
u
tio
n
is
a
n
ef
f
ec
tiv
e
s
ec
u
r
ity
s
o
lu
tio
n
b
ased
o
n
an
en
s
em
b
le
lear
n
in
g
tech
n
iq
u
e
in
teg
r
ated
with
o
p
tim
al
d
ata
s
am
p
lin
g
o
p
er
atio
n
.
T
h
e
p
r
im
e
aim
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
tem
is
to
p
er
f
o
r
m
th
e
d
etec
tio
n
o
f
an
o
m
alies
an
d
class
if
icatio
n
o
f
i
n
tr
u
s
io
n
s
o
n
a
r
ea
l
-
tim
e
b
asis
.
T
h
e
v
alu
e
-
ad
d
ed
n
o
v
elties
o
f
th
is
wo
r
k
ar
e
as
f
o
llo
ws:
i)
A
n
o
v
el
an
d
s
im
p
lifie
d
ar
ch
itectu
r
e
o
f
n
etwo
r
k
c
o
n
ce
n
tr
atin
g
ed
g
e
c
o
m
p
u
tin
g
c
o
n
ce
p
t
th
at
en
a
b
les
ef
f
icien
t
ex
ec
u
tio
n
o
f
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
F
r
a
mewo
r
k
fo
r
d
etec
tin
g
a
n
d
r
esis
tin
g
cy
b
era
tta
ck
s
o
n
cy
b
e
r
-
p
h
ysica
l sys
tems
…
(
Jy
o
ti M
eta
n
)
7171
p
r
o
p
o
s
ed
lear
n
in
g
-
d
r
iv
e
n
s
ec
u
r
ity
s
y
s
tem
,
ii)
a
p
r
ac
tical
d
ata
m
o
d
ellin
g
ap
p
r
o
ac
h
is
p
r
e
s
en
ted
f
o
llo
wed
b
y
s
u
itab
le
p
r
ep
r
o
ce
s
s
in
g
o
p
er
ati
o
n
a
n
d
d
ata
s
am
p
lin
g
ap
p
r
o
a
ch
to
b
alan
ce
d
ata,
o
v
e
r
co
m
e
b
iased
p
r
ed
ictiv
e
o
u
tco
m
e,
a
n
d
e
m
p
o
wer
an
o
m
aly
d
etec
tio
n
,
iii)
A
n
en
s
em
b
l
e
lear
n
in
g
as
j
o
in
t
ap
p
r
o
ac
h
o
f
M
-
Ad
a
B
o
o
s
t
an
d
n
eu
r
al
d
ec
is
io
n
t
r
ee
(
NDT
)
h
as
b
ee
n
p
r
esen
ted
t
o
p
er
f
o
r
m
p
r
ed
ictiv
e
m
o
d
ellin
g
f
o
r
a
n
o
m
aly
an
d
i
n
tr
u
s
io
n
d
etec
tio
n
in
I
o
C
PS
.
T
h
e
f
o
llo
win
g
s
ec
tio
n
d
is
cu
s
s
es a
b
o
u
t a
d
o
p
ted
r
esear
ch
m
eth
o
d
o
lo
g
y
.
2.
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
r
esear
ch
m
eth
o
d
o
lo
g
y
aim
s
to
co
n
s
tr
u
ct
a
n
o
v
el
co
m
p
u
tatio
n
al
m
o
d
el
ca
p
ab
le
o
f
d
eter
m
in
in
g
t
h
e
leth
al
th
r
ea
ts
ass
o
ciate
d
with
an
o
m
alies in
I
o
C
PS
.
T
h
e
p
r
o
p
o
s
ed
s
tu
d
y
h
as
in
tr
o
d
u
ce
d
a
n
o
v
el
in
teg
r
ated
f
r
am
ew
o
r
k
to
c
o
u
n
ter
s
ec
u
r
ity
th
r
ea
ts
in
a
m
o
d
er
n
n
etwo
r
k
o
f
I
o
C
PS
.
Fig
u
r
e
1
illu
s
tr
ates
th
e
co
n
ce
p
tu
al
ar
ch
itectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
b
ased
o
n
t
h
e
ed
g
e
n
etwo
r
k
in
g
co
n
ce
p
t,
s
tatis
tical
m
eth
o
d
s
f
o
r
n
etwo
r
k
d
ata
m
o
d
ellin
g
,
an
d
en
s
em
b
led
lear
n
in
g
m
ec
h
an
is
m
.
T
h
e
c
o
r
e
n
o
tio
n
o
f
t
h
is
ar
ch
itectu
r
e
is
to
em
p
o
wer
p
r
ed
ictiv
e
an
al
y
tics
o
n
th
e
s
tr
ea
m
in
g
n
etwo
r
k
tr
af
f
ic
f
o
r
r
ea
l
-
tim
e
a
n
o
m
aly
d
etec
tio
n
.
Fig
u
r
e
1
.
Sch
em
atic
a
r
ch
itectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
in
te
g
r
ated
f
r
am
ewo
r
k
As
d
ep
icted
in
Fig
u
r
e
1
,
th
e
s
y
s
tem
d
esig
n
co
m
p
r
is
es
th
r
ee
ess
en
tial
m
o
d
u
les:
I
o
C
PS
,
ed
g
e
co
m
p
u
tin
g
in
f
r
astru
ct
u
r
e,
a
n
d
th
e
clo
u
d
s
y
s
tem
.
T
h
e
I
o
C
PS
m
o
d
u
le
is
a
cu
ttin
g
-
ed
g
e
s
y
s
tem
th
at
in
teg
r
ates
cy
b
er
s
y
s
tem
s
en
ab
led
b
y
clo
u
d
co
m
p
u
tin
g
a
n
d
p
h
y
s
ical
co
m
p
o
n
en
ts
em
p
o
wer
e
d
b
y
I
o
T
.
T
h
is
in
n
o
v
ativ
e
tech
n
o
lo
g
y
attr
ac
ts
s
ig
n
if
ican
t
atten
tio
n
f
r
o
m
r
esear
ch
c
o
m
m
u
n
ities
an
d
in
d
u
s
tr
ies
f
o
r
its
p
o
ten
tial
b
en
ef
its
to
s
o
ciety
,
th
e
en
v
ir
o
n
m
en
t,
an
d
th
e
ec
o
n
o
m
y
.
T
h
e
I
o
C
PS
m
o
d
u
le
en
co
m
p
ass
es
p
h
y
s
ical
co
m
p
o
n
en
ts
s
u
ch
as
in
tellig
en
t
elec
tr
o
n
ic
d
e
v
ices,
s
en
s
o
r
n
o
d
es,
an
d
c
y
b
er
co
m
p
o
n
en
ts
r
esp
o
n
s
ib
le
f
o
r
co
m
p
u
t
atio
n
,
s
to
r
ag
e,
a
n
d
n
etwo
r
k
m
an
ag
em
e
n
t
task
s
,
al
l
lev
er
ag
in
g
clo
u
d
tec
h
n
o
lo
g
y
.
T
h
e
e
d
g
e
co
m
p
u
tin
g
i
n
f
r
astru
ctu
r
e
en
c
o
m
p
ass
es
n
etwo
r
k
in
g
m
eth
o
d
s
f
o
r
d
ata
r
o
u
tin
g
a
n
d
th
e
p
r
o
p
o
s
ed
p
r
ed
i
ctiv
e
s
y
s
tem
f
o
r
an
o
m
aly
d
ete
ctio
n
.
I
t
f
ea
tu
r
es
an
I
o
T
g
atew
ay
f
o
r
r
o
u
tin
g
s
tr
ea
m
in
g
n
etwo
r
k
d
ata
(
tim
e
s
er
ies).
T
h
e
I
o
T
g
atew
ay
c
o
llects
d
ata
f
r
o
m
v
ar
io
u
s
d
ev
ices
an
d
s
en
d
s
it
to
t
h
e
m
ess
ag
in
g
lay
er
,
p
o
wer
ed
b
y
t
h
e
m
ess
ag
e
q
u
e
u
in
g
telem
etr
y
tr
an
s
p
o
r
t
(
MQ
T
T
)
p
r
o
to
co
l.
T
h
e
d
ata
s
to
r
e
a
n
d
p
r
o
ce
s
s
in
g
co
m
p
o
n
en
ts
e
x
tr
ac
t
th
e
d
ata
f
r
o
m
t
h
e
m
ess
ag
in
g
l
ay
er
,
p
r
o
ce
s
s
it
in
a
q
u
eu
e,
an
d
p
ass
it
th
r
o
u
g
h
th
e
tr
ain
ed
an
o
m
aly
d
etec
tio
n
m
o
d
el.
T
h
e
p
r
o
p
o
s
ed
an
o
m
aly
d
etec
tio
n
alg
o
r
ith
m
r
etr
iev
es
d
ata
f
r
o
m
th
e
d
esig
n
ated
q
u
e
u
es,
p
e
r
f
o
r
m
s
an
o
m
al
y
d
etec
tio
n
,
an
d
s
en
d
s
th
e
r
esu
lts
to
th
e
cl
o
u
d
f
o
r
ce
n
tr
alize
d
aler
tin
g
a
n
d
r
ep
o
r
tin
g
.
Ad
d
itio
n
ally
,
th
e
m
o
d
el
s
to
r
es
th
e
d
ata
in
a
d
atab
ase
f
o
r
p
o
ten
tial
f
u
tu
r
e
u
p
d
ates
an
d
im
p
r
o
v
em
e
n
ts
to
th
e
m
o
d
el
th
r
o
u
g
h
a
d
d
itio
n
al
o
b
s
er
v
atio
n
al
d
ata.
T
h
e
s
y
s
tem
also
in
co
r
p
o
r
ates
an
o
f
f
lin
e
tr
ain
in
g
s
ch
ed
u
lin
g
m
ec
h
an
is
m
th
at
p
e
r
io
d
ically
r
etr
iev
es
b
u
lk
d
ata
f
r
o
m
th
e
d
a
tab
ase,
co
m
p
r
ess
es
it,
an
d
s
en
d
s
it to
th
e
cl
o
u
d
f
o
r
f
u
tu
r
e
u
s
e,
s
u
ch
as a
tr
ain
in
g
m
o
d
el
with
n
ew
o
b
s
er
v
atio
n
s
.
T
h
e
in
teg
r
atio
n
o
f
th
e
ed
g
e
co
m
p
u
tin
g
c
o
n
ce
p
t
is
m
o
ti
v
ated
b
y
th
e
g
r
o
win
g
am
o
u
n
t
o
f
d
ata
p
r
o
d
u
ce
d
b
y
I
o
T
d
ev
ices
in
th
e
I
o
C
PS
s
y
s
tem
,
lead
in
g
to
in
cr
ea
s
ed
d
em
an
d
s
o
n
n
etwo
r
k
b
an
d
wid
th
,
s
to
r
ag
e
,
an
d
co
m
p
u
te
r
eso
u
r
ce
s
.
As
a
r
esu
lt,
r
ely
in
g
s
o
lely
o
n
ce
n
tr
alize
d
d
ata
p
r
o
ce
s
s
in
g
,
in
clu
d
in
g
in
th
e
clo
u
d
,
h
as
b
ec
o
m
e
in
cr
ea
s
in
g
l
y
co
s
tly
a
n
d
ca
n
r
esu
lt
in
p
r
o
lo
n
g
ed
d
e
lay
s
in
d
ata
p
r
o
ce
s
s
in
g
.
E
d
g
e
co
m
p
u
tin
g
o
f
f
e
r
s
a
m
o
r
e
ef
f
ec
tiv
e
m
ea
n
s
o
f
u
tili
zin
g
ML
-
b
ased
an
o
m
aly
d
etec
tio
n
b
y
b
r
in
g
in
g
d
ata
p
r
o
ce
s
s
in
g
clo
s
er
to
th
e
d
ata
s
o
u
r
ce
.
T
h
is
ap
p
r
o
ac
h
r
e
d
u
c
es
th
e
b
u
r
d
en
o
n
th
e
clo
u
d
,
en
s
u
r
es
im
m
ed
iate
d
ata
p
r
o
ce
s
s
in
g
,
im
p
r
o
v
es
r
esp
o
n
s
e
tim
es,
an
d
d
ec
r
ea
s
e
s
n
etwo
r
k
d
em
an
d
an
d
clo
u
d
co
s
ts
,
r
esu
ltin
g
in
a
m
o
r
e
co
s
t
-
ef
f
icien
t
an
d
ef
f
ec
tiv
e
s
o
lu
tio
n
.
T
h
e
p
r
o
p
o
s
ed
s
ch
em
e
u
s
es
a
p
r
ep
r
o
ce
s
s
in
g
m
ec
h
an
is
m
with
a
u
n
iq
u
e
o
v
er
s
am
p
lin
g
ap
p
r
o
ac
h
ad
o
p
ted
f
o
r
d
ata
m
o
d
ellin
g
an
d
to
h
an
d
le
th
e
h
ea
v
ily
im
b
alan
ce
d
n
at
u
r
e
o
f
th
e
I
o
T
d
ata
[
2
8
]
.
T
h
e
s
tu
d
y
im
p
lem
en
tatio
n
u
s
es
an
en
s
em
b
le
m
o
d
el
b
ased
o
n
M
-
Ad
aBo
o
s
t
an
d
NDT
alg
o
r
ith
m
f
o
r
an
o
m
aly
d
etec
tio
n
.
An
ex
p
l
o
r
ato
r
y
an
al
y
s
is
is
ca
r
r
ied
o
u
t
f
o
r
th
e
d
ata
s
et
wh
ile
an
o
v
er
s
am
p
lin
g
ap
p
r
o
ac
h
is
ap
p
lied
to
o
b
tain
a
b
alan
ce
d
d
ataset
s
u
itab
le
f
o
r
s
u
b
jectin
g
it
t
o
a
m
a
ch
in
e
lear
n
in
g
ap
p
r
o
ac
h
.
T
h
e
p
r
o
p
o
s
ed
s
ch
em
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
1
6
9
-
7
1
7
7
7172
u
s
es
e
n
s
em
b
le
lear
n
i
n
g
,
wh
ich
ass
o
ciate
s
m
u
ltip
le
lear
n
in
g
m
o
d
els
to
im
p
r
o
v
e
th
e
ac
c
u
r
a
cy
an
d
r
o
b
u
s
tn
ess
o
f
p
r
ed
ictio
n
s
.
T
h
e
b
asic
id
ea
b
e
h
in
d
en
s
em
b
le
lear
n
in
g
is
to
u
s
e
m
u
ltip
le
m
o
d
els
to
m
ak
e
p
r
ed
ictio
n
s
an
d
th
en
co
m
b
in
e
th
eir
p
r
ed
ictio
n
s
to
m
ak
e
a
f
in
al
p
r
ed
ictio
n
.
T
h
is
ap
p
r
o
ac
h
ca
n
lead
t
o
b
etter
p
e
r
f
o
r
m
a
n
ce
th
an
u
s
in
g
a
s
in
g
le
m
o
d
el,
as
th
e
er
r
o
r
s
m
ad
e
b
y
i
n
d
iv
id
u
al
m
o
d
els
c
an
b
e
av
e
r
ag
ed
o
u
t.
T
h
is
p
ap
er
p
r
esen
ts
a
n
o
v
el
s
y
s
tem
d
ev
elo
p
ed
b
ased
o
n
th
e
ass
em
b
lin
g
o
f
M
-
Ad
aBo
o
s
t
an
d
NDT
m
o
d
els to
p
er
f
o
r
m
a
n
o
m
aly
d
etec
tio
n
.
M
-
Ad
aBo
o
s
t
is
an
im
p
r
o
v
ed
v
er
s
io
n
o
f
th
e
ad
ap
tiv
e
b
o
o
s
tin
g
alg
o
r
ith
m
,
wid
ely
ad
o
p
ted
f
o
r
b
in
ar
y
class
if
icatio
n
p
r
o
b
lem
s
.
M
-
Ad
aBo
o
s
t
is
d
esig
n
ed
to
h
a
n
d
le
m
u
lti
-
class
class
if
icatio
n
p
r
o
b
lem
s
,
wh
ic
h
in
v
o
lv
e
class
if
y
in
g
in
s
tan
ce
s
in
to
m
u
ltip
le
ca
teg
o
r
ies
r
ath
er
th
an
ju
s
t
two
.
I
n
th
is
m
o
d
el,
th
e
b
asic
id
ea
is
to
tr
ain
m
u
ltip
le
b
in
a
r
y
class
if
ier
s
,
o
n
e
f
o
r
ea
ch
class
ag
ain
s
t
a
ll
th
e
o
th
er
s
,
an
d
th
en
co
m
b
i
n
e
th
eir
p
r
e
d
ictio
n
s
to
m
ak
e
t
h
e
f
in
al
m
u
lti
-
class
p
r
ed
ictio
n
.
T
h
e
b
i
n
ar
y
class
if
ier
s
ar
e
tr
ain
ed
in
a
s
eq
u
en
tial
m
an
n
er
,
wh
er
e
ea
c
h
class
if
ier
f
o
cu
s
es
o
n
co
r
r
ec
tin
g
th
e
m
is
class
if
icatio
n
s
m
ad
e
b
y
th
e
p
r
ev
i
o
u
s
class
if
ier
.
T
h
e
f
in
al
p
r
e
d
ictio
n
is
m
ad
e
b
y
ta
k
in
g
a
weig
h
ted
s
u
m
o
f
th
e
p
r
ed
ictio
n
s
o
f
all
b
in
ar
y
class
if
ier
s
,
wh
er
e
th
e
weig
h
ts
r
ef
lect
th
e
class
if
ier
'
s
ac
cu
r
ac
y
.
On
th
e
o
th
er
h
a
n
d
,
NDT
o
p
ti
m
ized
lear
n
in
g
class
if
ier
co
m
b
in
es
th
e
s
tr
en
g
th
s
o
f
d
ec
is
io
n
tr
ee
s
an
d
n
eu
r
al
n
etwo
r
k
s
.
I
t
u
s
es
th
e
t
r
ee
-
lik
e
s
tr
u
ctu
r
e
o
f
d
ec
is
io
n
tr
ee
s
to
m
ak
e
p
r
e
d
ictio
n
s
an
d
th
e
r
ep
r
esen
tatio
n
lear
n
in
g
ca
p
ab
ilit
ies
o
f
n
eu
r
a
l
n
etwo
r
k
s
to
lear
n
m
o
r
e
co
m
p
lex
d
ata
r
ep
r
esen
tatio
n
s
.
I
n
th
is
m
o
d
el,
ea
c
h
in
ter
n
al
n
o
d
e
o
f
th
e
tr
ee
is
r
ep
r
esen
ted
b
y
a
n
eu
r
al
n
etwo
r
k
,
wh
ich
is
tr
ain
ed
to
lear
n
a
m
o
r
e
co
m
p
lex
r
ep
r
esen
tatio
n
o
f
t
h
e
d
ata,
wh
ich
allo
ws
f
o
r
ef
f
icien
t
ca
p
tu
r
e
o
f
th
e
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
b
etwe
en
th
e
f
ea
tu
r
es
an
d
th
e
tar
g
et,
th
er
eb
y
im
p
r
o
v
in
g
ac
cu
r
ac
y
,
h
ig
h
er
in
ter
p
r
etab
ilit
y
,
an
d
r
o
b
u
s
tn
e
s
s
o
f
th
e
alg
o
r
ith
m
in
th
e
p
r
ed
ictiv
e
task
.
T
h
e
p
r
o
p
o
s
ed
en
s
em
b
led
lear
n
in
g
m
o
d
el
ca
n
b
e
m
ath
em
atica
ll
y
r
ep
r
esen
ted
as
a
weig
h
ted
s
u
m
o
f
t
h
e
class
p
r
o
b
ab
ilit
ies
p
r
ed
icted
b
y
ea
c
h
cl
ass
if
ier
.
Giv
en
two
class
if
ier
s
,
1
(M
-
Ad
aBo
o
s
t)
an
d
2
(
NDT
)
,
th
e
f
in
al
e
n
s
em
b
l
e
class
if
ier
ca
n
b
e
d
ef
in
e
d
as
(
1
)
:
(
)
=
1
1
(
)
+
2
2
(
)
(
1
)
Acc
o
r
d
in
g
to
e
x
p
r
ess
io
n
(
1
)
,
th
e
v
ar
iab
le
r
ep
r
esen
ts
th
e
in
p
u
t
s
am
p
le,
an
d
1
an
d
2
ar
e
th
e
weig
h
ts
ass
ig
n
ed
to
ea
ch
cl
ass
if
ier
.
T
h
e
weig
h
ts
w
1
an
d
w
2
d
eter
m
in
e
th
e
r
elativ
e
i
m
p
o
r
tan
ce
o
f
ea
c
h
class
if
ier
in
th
e
en
s
em
b
le,
f
o
llo
wed
b
y
th
e
v
o
tin
g
m
ec
h
an
is
m
.
T
h
e
v
o
tin
g
m
ec
h
an
is
m
co
m
b
in
es
th
e
p
r
ed
ictio
n
s
o
f
m
o
d
els
1
(
)
an
d
2
(
)
.
I
n
th
e
p
r
o
p
o
s
ed
e
n
s
em
b
le
lear
n
in
g
m
o
d
el,
a
s
o
f
t
v
o
tin
g
m
ec
h
an
is
m
is
u
s
ed
to
co
n
s
id
er
th
e
weig
h
ted
av
er
ag
e
o
f
th
e
class
p
r
o
b
ab
ilit
ies to
p
r
ed
ict
th
e
class
.
T
h
er
ef
o
r
e,
th
e
weig
h
ts
1
an
d
2
ar
e
s
et
p
r
o
p
o
r
tio
n
al
t
o
th
e
ac
cu
r
ac
y
o
f
ea
ch
class
if
ier
.
I
f
class
if
ier
1
(
)
h
as
a
h
i
g
h
er
ac
cu
r
ac
y
,
it
will
h
av
e
a
h
ig
h
er
weig
h
t
in
th
e
en
s
em
b
le,
an
d
v
ice
v
er
s
a.
T
h
e
f
in
al
en
s
em
b
le
p
r
ed
ictio
n
is
o
b
tain
ed
b
y
tak
in
g
th
e
class
with
th
e
h
ig
h
est we
ig
h
ted
s
u
m
o
f
class
p
r
o
b
ab
ilit
ies,
n
u
m
er
ically
g
iv
en
as
(
2
)
:
=
(
)
(
1
1
+
2
2
)
(
2
)
Acc
o
r
d
in
g
t
o
ex
p
r
ess
io
n
(
2
)
,
th
e
v
ar
iab
le
c
is
th
e
class
in
d
ex
,
a
n
d
1
an
d
2
ar
e
th
e
class
p
r
o
b
a
b
ilit
ies
p
r
ed
icted
b
y
clas
s
if
ier
s
1
(
)
an
d
2
(
)
f
o
r
class
c
i
.
T
h
er
e
f
o
r
e,
it
ca
n
b
e
n
o
ted
th
at
th
e
p
r
o
p
o
s
ed
s
ch
em
e
h
as
in
tr
o
d
u
ce
d
a
p
r
o
g
r
ess
iv
e
an
d
s
eq
u
en
tial
p
r
o
ce
s
s
o
f
co
n
f
ir
m
in
g
th
e
p
r
esen
c
e
o
f
an
o
m
alies
an
d
p
er
f
o
r
m
in
g
class
if
icatio
n
.
T
h
e
p
r
im
e
n
o
v
elty
o
f
th
is
im
p
lem
en
tatio
n
s
tr
ateg
y
is
ass
o
ciate
d
with
its
d
etec
tio
n
ca
p
ab
ilit
y
o
f
m
o
s
t
co
m
p
le
x
an
o
m
alies
o
r
an
y
f
o
r
m
o
f
d
y
n
am
ic
th
r
ea
ts
p
r
esen
t
with
in
th
e
I
o
C
PS
en
v
ir
o
n
m
en
t.
T
h
e
class
if
icatio
n
o
p
tim
izes
t
h
e
lear
n
in
g
p
r
o
ce
s
s
,
co
n
s
id
er
i
n
g
th
e
p
o
ten
tial
o
f
n
eu
r
al
n
etwo
r
k
s
an
d
d
ec
is
io
n
tr
ee
s
.
Hen
ce
,
th
e
p
r
o
p
o
s
ed
s
y
s
tem
h
as
n
o
ted
an
o
p
tim
al
b
ala
n
ce
b
etwe
en
co
m
p
u
tatio
n
al
ef
f
o
r
t
an
d
r
esis
tiv
ity
f
ea
tu
r
es.
T
h
e
f
o
llo
win
g
s
ec
tio
n
p
r
esen
ts
a
d
is
cu
s
s
io
n
o
f
t
h
e
ac
co
m
p
lis
h
ed
o
u
tco
m
e
o
f
th
e
s
tu
d
y
.
3.
RE
SU
L
T
S
T
h
is
s
ec
tio
n
p
r
esen
ts
an
d
ass
ess
es
th
e
o
u
tco
m
e
o
f
th
e
s
im
u
latio
n
ex
ec
u
te
d
to
v
alid
ate
t
h
e
s
co
p
e
o
f
th
e
p
r
o
p
o
s
ed
en
s
em
b
led
m
o
d
el
f
o
r
an
o
m
al
y
d
etec
tio
n
in
t
h
e
I
o
C
PS
.
T
h
e
d
esig
n
an
d
d
ev
elo
p
m
en
t
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
is
d
ev
elo
p
ed
with
a
Py
th
o
n
en
v
ir
o
n
m
e
n
t
e
x
ec
u
ted
o
n
An
ac
o
n
d
a
d
is
tr
ib
u
tio
n
.
T
h
e
an
al
y
s
is
co
n
ce
r
n
s
v
a
r
io
u
s
p
er
f
o
r
m
a
n
ce
in
d
icato
r
s
,
an
d
t
h
eir
r
esu
lts
ar
e
co
m
p
ar
e
d
in
m
u
ltip
le
s
ce
n
ar
io
s
.
T
h
e
r
esu
lts
ar
e
d
is
cu
s
s
ed
f
r
o
m
th
e
p
er
s
p
ec
tiv
e
o
f
th
e
im
p
lem
en
tatio
n
e
n
v
ir
o
n
m
en
t,
d
ata
m
o
d
ellin
g
,
an
d
ac
co
m
p
lis
h
ed
r
esu
lts
.
3
.
1
.
I
m
plem
ent
a
t
io
n
e
nv
iro
nm
en
t
T
h
e
d
ataset
u
s
ed
to
m
o
d
el
th
e
p
r
o
p
o
s
ed
s
y
s
tem
is
DS2
OS
I
o
T
,
o
b
tain
ed
f
r
o
m
th
e
Ka
g
g
l
e
p
latf
o
r
m
[
2
8
]
.
T
h
is
d
ataset
is
co
llected
f
r
o
m
a
n
I
o
T
n
etwo
r
k
an
d
co
n
tain
s
m
an
y
f
ea
t
u
r
es
r
elate
d
t
o
n
etwo
r
k
b
eh
a
v
io
r
an
d
s
y
s
tem
p
er
f
o
r
m
an
ce
.
T
h
e
d
ataset
p
r
o
v
id
es
a
u
n
iq
u
e
o
p
p
o
r
tu
n
ity
to
s
tu
d
y
an
o
m
alies
in
I
o
T
n
etwo
r
k
s
an
d
d
ev
elo
p
m
ac
h
i
n
e
-
lear
n
i
n
g
alg
o
r
ith
m
s
to
d
etec
t
th
ese
an
o
m
alies
ef
f
ec
tiv
ely
.
T
h
e
d
ataset
is
im
b
alan
ce
d
,
with
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
F
r
a
mewo
r
k
fo
r
d
etec
tin
g
a
n
d
r
esis
tin
g
cy
b
era
tta
ck
s
o
n
cy
b
e
r
-
p
h
ysica
l sys
tems
…
(
Jy
o
ti M
eta
n
)
7173
o
n
ly
a
s
m
all
p
er
ce
n
ta
g
e
o
f
th
e
d
ata
b
ein
g
a
n
o
m
alo
u
s
,
m
ak
i
n
g
it
ch
allen
g
in
g
f
o
r
m
ac
h
in
e
lear
n
in
g
m
o
d
els
to
ac
cu
r
ately
p
r
e
d
ict
th
e
ty
p
e
o
f
an
o
m
alies.
3
.
2
.
Da
t
a
m
o
dellin
g
As
a
p
r
e
-
r
eq
u
est
s
tep
,
th
e
p
r
o
p
o
s
ed
wo
r
k
p
er
f
o
r
m
s
an
ex
p
l
o
r
ato
r
y
a
n
aly
s
is
o
f
th
e
d
ataset;
th
e
in
s
ig
h
t
s
h
o
ws
th
at
th
e
d
ataset
co
n
s
is
ts
o
f
lar
g
e
s
am
p
les,
i.e
.
,
3
5
7
,
9
5
1
in
a
r
o
w
a
n
d
1
2
f
ea
t
u
r
es
in
t
h
e
co
lu
m
n
.
Fu
r
t
h
er
an
aly
s
is
is
ca
r
r
ied
o
u
t
to
war
d
s
an
aly
zin
g
th
e
m
is
s
in
g
v
alu
e
s
in
th
e
d
ataset,
wh
ich
s
h
o
ws
th
at
th
e
d
ataset
h
as
1
4
8
m
is
s
in
g
v
alu
es
ab
o
u
t
co
l
u
m
n
"a
cc
ess
ed
n
o
d
e
ty
p
e
"
a
n
d
2
,
0
5
0
m
is
s
in
g
in
s
tan
ce
s
s
u
b
jecte
d
to
co
lu
m
n
n
am
e
"v
alu
e"
.
T
h
e
m
is
s
in
g
v
alu
es
ar
e
r
em
o
v
ed
u
n
d
er
ess
en
tial
p
r
ep
r
o
ce
s
s
in
g
o
p
e
r
atio
n
.
Als
o
,
th
e
d
ataset
co
n
s
is
ts
o
f
b
o
th
n
u
m
er
ical
an
d
ca
teg
o
r
ical
v
alu
es.
T
h
e
ca
te
g
o
r
ical
v
alu
es
ar
e
tr
an
s
f
o
r
m
ed
an
d
en
co
d
ed
u
s
in
g
o
n
e
h
o
t
en
c
o
d
in
g
m
ec
h
an
is
m
.
I
n
th
e
s
u
b
s
eq
u
en
t
p
r
o
ce
s
s
,
th
e
d
ataset'
s
v
alu
es
ar
e
n
o
r
m
alize
d
u
n
d
er
th
e
m
i
n
-
m
ax
s
ca
lin
g
s
ch
em
e
an
d
m
ad
e
s
u
itab
le
f
o
r
f
u
r
th
er
task
s
.
I
t h
as b
ee
n
o
b
s
er
v
e
d
th
at
th
e
a
d
o
p
ted
d
ataset
co
n
s
is
ts
o
f
eig
h
t
class
es,
in
clu
d
in
g
o
n
e
r
eg
u
lar
an
d
s
ev
en
attac
k
s
,
wh
ich
is
r
elate
d
to
a
m
u
lti
-
class
p
r
ed
ictio
n
task
p
r
o
b
lem
.
Fu
r
t
h
er
an
aly
s
is
r
ev
ea
ls
th
at
th
e
d
ataset
h
a
s
a
s
ig
n
if
ican
t
class
im
b
alan
ce
p
r
o
b
lem
.
T
h
e
d
is
tr
ib
u
tio
n
o
f
d
ata
co
n
ce
r
n
i
n
g
ea
ch
class
is
s
h
o
wn
in
Fig
u
r
e
2
.
Fig
u
r
e
2
s
h
o
ws
th
at
th
e
d
atas
et
is
im
b
alan
ce
d
;
m
o
s
t
s
am
p
l
es
b
elo
n
g
to
in
t
r
u
s
io
n
class
7
,
wh
er
e
th
e
av
er
ag
e
class
is
en
co
d
ed
wit
h
0
,
an
d
th
e
r
est
ar
e
d
if
f
er
e
n
t
in
tr
u
s
io
n
class
es
1
to
7
.
I
m
p
lem
en
tin
g
d
ee
p
lear
n
in
g
o
r
m
ac
h
in
e
lear
n
in
g
will
alwa
y
s
g
et
b
iased
to
wa
r
d
s
p
r
e
d
ictin
g
t
h
e
m
ajo
r
ity
cl
ass
.
T
h
er
ef
o
r
e
,
th
e
s
tu
d
y
ad
o
p
ts
o
v
er
s
am
p
lin
g
o
f
th
e
m
i
n
o
r
ity
class
es
to
war
d
s
d
ata
p
r
ep
ar
atio
n
a
n
d
u
n
b
iased
s
u
p
er
v
is
ed
lear
n
in
g
.
T
h
e
o
v
er
s
am
p
lin
g
ap
p
r
o
ac
h
wo
r
k
s
b
y
s
y
n
th
e
s
izin
g
n
ew
s
am
p
les
f
o
r
th
e
m
in
o
r
ity
class
b
y
in
ter
p
o
latin
g
b
etwe
en
e
x
is
tin
g
s
am
p
les.
T
o
d
o
th
is
,
th
e
p
r
o
p
o
s
ed
o
v
er
s
am
p
lin
g
ap
p
r
o
ac
h
f
ir
s
t
s
elec
ts
a
m
in
o
r
ity
class
s
am
p
le
at
r
an
d
o
m
an
d
th
e
n
s
elec
ts
its
n
ea
r
est
n
eig
h
b
o
r
s
.
T
h
e
alg
o
r
ith
m
th
e
n
s
y
n
th
esizes
a
n
ew
s
am
p
le
b
y
r
a
n
d
o
m
ly
in
ter
p
o
l
atin
g
b
etwe
en
th
e
s
elec
ted
s
am
p
le
an
d
o
n
e
o
f
its
n
eig
h
b
o
r
s
.
T
h
is
p
r
o
ce
s
s
is
r
ep
ea
ted
u
n
til
th
e
m
i
n
o
r
ity
class
is
o
v
er
s
am
p
led
to
b
alan
c
e
th
e
d
ata.
T
h
e
im
p
lem
en
tati
o
n
p
r
o
ce
s
s
in
v
o
lv
es
s
p
litt
in
g
th
e
d
ataset
in
to
tr
ain
in
g
an
d
test
in
g
s
ets
u
s
in
g
th
e
_
_
f
u
n
ctio
n
f
r
o
m
s
cik
it
-
lear
n
.
Ne
x
t,
p
r
o
p
o
s
ed
o
v
er
s
am
p
lin
g
is
u
s
ed
to
o
v
er
s
am
p
le
th
e
m
i
n
o
r
it
y
class
.
Fin
ally
,
th
e
d
ataset
is
o
v
er
s
am
p
led
,
as
s
h
o
wn
in
Fig
u
r
e
3
.
As s
h
o
wn
in
Fig
u
r
e
3
,
th
e
d
ataset
is
o
v
er
s
am
p
led
an
d
b
ala
n
ce
d
with
ev
e
n
d
is
tr
ib
u
tio
n
,
i.e
.
,
ea
ch
class
with
2
4
3
,
5
1
3
s
am
p
les.
T
h
e
n
e
x
t
s
tep
is
to
p
er
f
o
r
m
p
r
e
d
ictiv
e
an
al
y
tics
u
s
in
g
th
e
p
r
o
p
o
s
ed
en
s
em
b
led
m
ec
h
a
n
is
m
.
Fig
u
r
e
2
.
Statis
tics
o
f
d
ata
d
is
tr
ib
u
tio
n
n
u
m
b
e
r
o
f
s
am
p
les
vs
an
o
m
aly
class
es
F
i
g
u
r
e
3
.
S
t
at
is
t
i
cs
o
f
d
a
t
a
d
is
t
r
i
b
u
t
i
o
n
a
f
t
e
r
o
v
e
r
s
a
m
p
l
i
n
g
n
u
m
b
e
r
o
f
s
a
m
p
le
s
vs
a
n
o
m
a
l
y
cl
as
s
es
T
h
e
f
ir
s
t
p
ar
t
o
f
th
e
r
esu
lt
an
aly
s
is
i
s
ca
r
r
ied
o
u
t
with
o
u
t
a
n
o
v
er
s
am
p
lin
g
ap
p
r
o
ac
h
.
T
h
e
p
r
o
p
o
s
ed
en
s
em
b
led
lear
n
in
g
m
o
d
el
is
tr
ain
ed
o
v
er
th
e
im
b
alan
ce
d
d
ataset.
T
o
p
er
f
o
r
m
a
co
m
p
a
r
ativ
e
an
aly
s
is
,
th
e
s
tu
d
y
ev
al
u
ates
M
-
Ad
aBo
o
s
t
an
d
NDT
.
T
h
e
co
n
f
u
s
io
n
p
lo
t
f
o
r
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
with
o
u
t
th
e
o
v
e
r
s
am
p
lin
g
m
eth
o
d
is
s
h
o
wn
in
Fig
u
r
e
4
(
a)
,
wh
ile
th
e
p
r
o
p
o
s
ed
m
o
d
el'
s
an
aly
s
is
with
o
v
er
s
am
p
lin
g
is
s
h
o
wn
in
Fig
u
r
e
4
(
b
)
.
Fig
u
r
e
4
(
b
)
s
h
o
ws
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
p
r
o
v
id
es
a
b
ett
er
d
etec
tio
n
r
ate
with
1
0
0
%
p
r
ec
is
io
n
,
r
ec
all
an
d
F1
-
s
co
r
e
r
esu
lts
.
T
h
e
r
ea
s
o
n
b
eh
in
d
th
is
is
th
at
th
is
ap
p
r
o
ac
h
co
m
b
in
es
th
e
o
v
er
s
am
p
lin
g
an
d
th
e
en
s
em
b
le
o
f
NDT
a
n
d
M
-
Ad
a
B
o
o
s
t
alg
o
r
ith
m
to
h
an
d
le
th
e
h
ea
v
y
im
b
ala
n
ce
d
n
atu
r
e
o
f
th
e
I
o
C
PS
d
ata
a
n
d
p
r
o
v
id
e
a
n
ef
f
ec
tiv
e
s
o
lu
tio
n
f
o
r
an
o
m
al
y
d
etec
tio
n
.
T
h
e
r
esu
lts
in
d
icate
th
at
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
p
r
o
v
id
es
g
o
o
d
p
er
f
o
r
m
a
n
ce
f
o
r
an
o
m
aly
d
etec
tio
n
an
d
ca
n
p
o
ten
tially
im
p
r
o
v
e
th
e
s
ec
u
r
ity
o
f
I
o
C
PS
b
y
id
en
tify
in
g
p
o
ten
tial th
r
ea
ts
in
r
ea
l
-
tim
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
1
6
9
-
7
1
7
7
7174
(
a)
(
b
)
Fig
u
r
e
4
.
C
o
n
f
u
s
io
n
p
l
o
t f
o
r
th
e
p
r
o
p
o
s
ed
s
y
s
tem
(
a)
m
o
d
el
with
o
u
t th
e
o
v
er
s
am
p
lin
g
m
eth
o
d
an
d
(
b
)
m
o
d
el'
s
an
aly
s
is
with
o
v
er
s
am
p
lin
g
T
h
e
n
ex
t
p
a
r
t
o
f
th
e
a
n
aly
s
is
is
ab
o
u
t
co
m
p
ar
i
n
g
th
e
o
u
tc
o
m
e
o
f
th
e
p
r
o
p
o
s
ed
s
tu
d
y
Pro
p
with
ex
is
tin
g
lear
n
in
g
-
b
ased
m
eth
o
d
s
.
Fo
r
t
h
is
p
u
r
p
o
s
e,
th
e
ex
is
tin
g
lear
n
in
g
m
eth
o
d
s
co
n
s
id
er
ed
ar
e
i)
s
u
p
er
v
is
e
d
lear
n
in
g
tec
h
n
iq
u
es,
e.
g
.
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM
)
,
r
an
d
o
m
f
o
r
est
(
R
F),
an
d
d
ec
is
io
n
tr
ee
(
DT
)
,
ii)
u
n
s
u
p
er
v
is
ed
lear
n
in
g
tec
h
n
iq
u
es,
e.
g
.
,
k
-
m
ea
n
s
c
lu
s
ter
in
g
(
k
MC),
Den
s
ity
-
b
ased
s
p
atial
clu
s
ter
in
g
o
f
ap
p
licatio
n
s
with
n
o
is
e
(
B
DS
C
AN)
,
an
d
is
o
latio
n
f
o
r
est
(
I
F),
an
d
iii)
d
ee
p
lear
n
in
g
s
ch
em
e
e.
g
.
,
r
ec
u
r
r
e
n
t
n
eu
r
al
n
etwo
r
k
(
R
NN)
,
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
,
an
d
a
u
to
en
c
o
d
er
(
AE
)
.
T
h
e
ass
ess
m
en
t
o
f
co
m
p
ar
ativ
e
an
aly
s
is
is
ca
r
r
ie
d
o
u
t
co
n
ce
r
n
in
g
th
r
ea
t
d
etec
tio
n
ac
cu
r
a
cy
a
n
d
r
esp
o
n
s
e
ti
m
e.
T
h
e
n
u
m
er
ical
o
u
tco
m
e
is
ex
h
ib
ited
i
n
T
ab
le
1
,
wh
ich
s
h
o
ws
th
at
th
e
p
r
o
p
o
s
ed
s
ch
em
e
o
f
f
er
s
ap
p
r
o
x
im
at
ely
7
.
2
%
im
p
r
o
v
e
d
th
r
ea
t d
etec
tio
n
ac
c
u
r
ac
y
a
n
d
6
8
% r
ed
u
ce
d
r
esp
o
n
s
e
tim
e
co
m
p
ar
ed
to
all
th
e
ex
is
tin
g
lear
n
in
g
s
ch
em
es.
T
ab
le
1
.
Nu
m
e
r
ical
o
u
tco
m
e
o
f
co
m
p
a
r
ativ
e
an
aly
s
is
A
p
p
r
o
a
c
h
e
s
Th
r
e
a
t
d
e
t
e
c
t
i
o
n
a
c
c
u
r
a
c
y
(
%)
R
e
s
p
o
n
se
t
i
me
(
s)
P
r
o
p
9
8
.
4
0
.
3
9
9
S
V
M
9
2
.
8
3
0
.
9
3
7
RF
8
9
.
5
5
1
.
9
9
DT
9
0
.
1
1
0
.
9
9
7
k
M
C
8
5
.
1
1
1
.
3
7
B
D
S
C
A
N
9
0
.
3
7
0
.
9
8
3
IF
9
0
.
9
9
0
.
9
5
2
R
N
N
9
2
.
1
1
0
.
8
9
8
LSTM
9
4
.
2
5
0
.
7
9
1
AE
9
4
.
9
2
0
.
8
0
3
T
h
e
g
r
a
p
h
ical
o
u
tc
o
m
e
o
f
th
e
n
u
m
er
ical
ev
al
u
atio
n
is
s
h
o
w
n
in
Fig
u
r
es
5
a
n
d
6
f
o
r
s
im
p
l
if
y
in
g
th
e
in
f
er
en
ce
o
f
th
e
o
u
tco
m
e.
A
s
ig
n
if
ican
t
tr
ad
e
-
o
f
f
is
o
b
s
er
v
e
d
f
o
r
ex
is
tin
g
lear
n
in
g
ap
p
r
o
a
ch
es
wh
er
e
th
er
e
is
m
u
ch
f
lu
ctu
atio
n
b
etwe
en
th
r
ea
t
d
etec
tio
n
ac
c
u
r
ac
y
an
d
r
es
p
o
n
s
e
tim
e.
T
h
e
c
u
m
u
lativ
e
o
u
tco
m
e
r
e
f
lects
th
e
p
r
o
p
o
s
ed
s
ch
em
e
to
e
x
ce
l in
a
b
etter
b
alan
ce
b
etwe
en
b
o
t
h
p
er
f
o
r
m
a
n
ce
m
etr
ics.
A
s
im
p
lifie
d
f
o
r
m
o
f
h
y
p
er
p
ar
am
eter
tu
n
in
g
is
ca
r
r
ied
o
u
t
in
p
r
o
p
o
s
ed
s
ch
em
e.
T
h
e
s
ch
em
e
co
n
f
ig
u
r
es
th
e
r
ate
o
f
tr
ain
in
g
at
0
.
0
1
wh
ile
in
o
r
d
e
r
to
r
esis
t
an
y
p
o
s
s
ib
ilit
y
o
f
o
v
er
f
itti
n
g
,
th
e
s
ch
em
e
f
u
r
th
er
co
n
f
ig
u
r
es
th
e
r
eg
u
lar
izatio
n
p
ar
am
eter
as
0
.
0
0
0
1
wh
ile
1
2
5
b
atch
s
ize
is
m
ain
tain
ed
.
T
h
e
ex
p
er
im
e
n
tatio
n
h
as
in
itially
co
n
s
id
er
ed
to
tal
n
u
m
b
er
o
f
esti
m
ato
r
s
as
5
0
,
1
0
0
,
1
5
0
,
2
0
0
,
2
5
0
wh
ile
b
est
esti
m
ato
r
h
as
b
ee
n
f
o
u
n
d
to
b
e
2
5
0
.
T
h
e
r
ate
o
f
lear
n
in
g
is
in
itialized
to
0
.
1
,
0
.
2
,
0
.
3
,
0
.
4
,
0
.
5
,
0
.
6
,
0
.
7
,
0
.
8
,
0
.
9
,
1
wh
ile
th
e
b
est
lear
n
in
g
r
ate
was
o
b
s
er
v
ed
at
0
.
5
.
T
h
e
s
tr
ateg
ies
to
m
itig
at
e
o
v
er
f
itti
n
g
is
as
f
o
llo
ws:
-
A
d
aBo
o
s
t
tr
ain
s
th
e
n
eu
r
al
d
ec
is
io
n
tr
ee
s
s
eq
u
en
ti
ally
.
Af
ter
ea
c
h
iter
atio
n
,
it
a
d
ju
s
ts
th
e
weig
h
ts
o
f
m
is
class
if
ied
in
s
tan
ce
s
to
p
r
io
r
itize
th
em
in
th
e
s
u
b
s
eq
u
en
t
iter
atio
n
.
T
h
is
iter
ativ
e
t
r
ain
in
g
p
r
o
ce
s
s
h
elp
s
in
g
r
ad
u
ally
im
p
r
o
v
in
g
th
e
m
o
d
el'
s
ac
cu
r
ac
y
o
n
d
if
f
icu
lt
ex
am
p
les
with
o
u
t
o
v
er
f
itti
n
g
to
th
e
en
tire
d
ataset
in
o
n
e
g
o
.
T
h
e
b
o
o
s
tin
g
tech
n
iq
u
e
em
p
lo
y
ed
b
y
M
-
Ad
aBo
o
s
t
p
lace
s
m
o
r
e
em
p
h
asis
o
n
in
s
tan
ce
s
th
at
ar
e
h
ar
d
e
r
to
class
if
y
co
r
r
ec
tly
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
F
r
a
mewo
r
k
fo
r
d
etec
tin
g
a
n
d
r
esis
tin
g
cy
b
era
tta
ck
s
o
n
cy
b
e
r
-
p
h
ysica
l sys
tems
…
(
Jy
o
ti M
eta
n
)
7175
B
y
iter
ativ
ely
f
o
cu
s
in
g
o
n
th
e
s
e
in
s
tan
ce
s
,
th
e
m
o
d
el
lear
n
s
to
g
en
er
alize
b
etter
r
ath
er
th
an
m
em
o
r
izin
g
th
e
tr
ain
in
g
d
ata,
w
h
ich
r
e
d
u
ce
s
th
e
r
is
k
o
f
o
v
er
f
itti
n
g
.
Fig
u
r
e
5
.
C
o
m
p
a
r
ativ
e
an
aly
s
i
s
o
f
th
r
ea
t d
etec
tio
n
ac
cu
r
ac
y
Fig
u
r
e
6
.
C
o
m
p
a
r
ativ
e
an
aly
s
i
s
o
f
r
esp
o
n
s
e
tim
e
T
h
e
b
etter
p
e
r
f
o
r
m
an
ce
o
f
p
r
o
p
o
s
ed
s
y
s
tem
i
n
c
o
n
tr
ast
to
ex
is
tin
g
m
ac
h
in
e
lear
n
in
g
a
p
p
r
o
ac
h
es
ca
n
b
e
attr
ib
u
ted
f
r
o
m
m
u
ltip
le
p
er
s
p
ec
tiv
e.
T
h
e
p
r
im
ar
y
r
ati
o
n
ale
is
its
r
ed
u
ce
d
s
et
o
f
iter
atio
n
with
m
o
r
e
co
n
tex
tu
al
d
ata
r
elate
d
to
tr
af
f
ic
in
f
o
r
m
atio
n
lead
in
g
to
r
e
d
u
ce
d
co
m
p
u
tatio
n
al
ef
f
o
r
t
an
d
h
ig
h
e
r
ac
cu
r
ac
y
.
M
-
Ad
aBo
o
s
t
is
a
v
ar
ian
t
o
f
Ad
aBo
o
s
t
th
at
co
m
b
in
es
m
u
ltip
le
class
if
ier
s
(
in
th
i
s
ca
s
e,
NDT
)
to
im
p
r
o
v
e
o
v
er
all
ac
cu
r
ac
y
.
B
y
ag
g
r
eg
at
in
g
th
e
p
r
e
d
ictio
n
s
o
f
m
u
ltip
le
m
o
d
els,
it
ten
d
s
to
r
ed
u
ce
v
ar
ian
ce
an
d
im
p
r
o
v
e
g
en
er
aliza
tio
n
,
t
h
u
s
in
cr
ea
s
in
g
ac
cu
r
ac
y
.
Neu
r
al
d
ec
is
io
n
t
r
ee
s
,
wh
ich
ar
e
ess
en
tially
d
ec
is
io
n
tr
ee
s
wh
er
e
ea
ch
n
o
d
e
is
a
n
eu
r
al
n
etwo
r
k
,
ca
n
ca
p
tu
r
e
co
m
p
lex
,
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
in
th
e
d
ata.
T
h
is
f
lex
ib
ilit
y
allo
ws
th
em
to
m
o
d
el
in
tr
icate
p
atter
n
s
th
at
tr
ad
itio
n
al
d
ec
is
io
n
tr
ee
s
m
ig
h
t
m
is
s
,
t
h
er
eb
y
im
p
r
o
v
i
n
g
ac
cu
r
ac
y
.
T
h
e
co
m
p
ar
ativ
e
o
u
tc
o
m
e
o
f
p
r
o
p
o
s
ed
s
ch
em
e
s
h
o
ws
b
ette
r
n
u
m
er
ical
s
co
r
es
with
ac
co
m
p
lis
h
m
en
t
o
f
7
.
2
%
o
f
in
c
r
ea
s
ed
ac
cu
r
a
cy
an
d
6
8
%
o
f
m
in
im
ized
r
esp
o
n
s
e
tim
e.
Hen
ce
,
th
e
p
r
i
m
e
s
tr
en
g
th
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
ass
o
ciate
d
with
im
p
r
o
v
in
g
class
if
icatio
n
b
y
s
eq
u
en
tially
ap
p
l
y
in
g
wea
k
lear
n
er
s
to
f
o
cu
s
o
n
in
s
tan
ce
s
th
at
ar
e
h
ar
d
er
to
class
if
y
co
r
r
ec
tly
.
T
h
is
iter
ativ
e
ap
p
r
o
ac
h
h
elp
s
in
g
r
ad
u
ally
im
p
r
o
v
in
g
ac
cu
r
ac
y
.
W
h
ile
NDT
ca
n
p
o
ten
tially
o
v
e
r
f
it,
b
u
t
b
y
co
m
b
in
in
g
th
em
with
Ad
aBo
o
s
t,
wh
ich
p
e
n
alize
s
m
is
class
if
icatio
n
s
an
d
em
p
h
asizes
d
if
f
icu
lt
ex
am
p
les,
th
e
o
v
er
all
m
o
d
el
ten
d
s
to
g
en
er
alize
b
etter
,
lead
in
g
to
h
ig
h
er
ac
c
u
r
ac
y
o
n
u
n
s
ee
n
d
at
a.
T
h
e
p
r
im
e
p
u
r
p
o
s
e
o
f
th
e
s
tu
d
y
is
to
wa
r
d
s
s
tr
en
g
t
h
en
in
g
s
y
s
tem
s
tr
en
g
th
in
p
r
esen
ce
o
f
an
o
m
alies.
T
h
e
im
p
o
r
ta
n
ce
o
f
t
h
e
s
tu
d
y
i
s
to
war
d
s
a
n
o
v
el
an
d
co
s
t
-
ef
f
ec
tiv
e
an
o
m
aly
d
etec
tio
n
s
ch
e
m
e.
T
h
e
m
o
d
el
n
o
t
o
n
ly
o
f
f
e
r
s
ef
f
ec
tiv
e
n
etwo
r
k
m
o
n
ito
r
in
g
b
u
t
also
f
ac
ilit
ate
s
p
r
ac
tical
wo
r
ld
s
ce
n
ar
io
s
b
y
co
n
s
id
er
in
g
tim
e
-
s
er
ies
ap
p
r
o
ac
h
to
war
d
s
d
ata
s
to
r
ag
e.
Ad
o
p
tio
n
o
f
th
is
m
o
d
e
l
is
b
en
ef
icial
f
o
r
all
f
u
tu
r
e
p
o
ten
tial
ap
p
licatio
n
s
th
at
d
em
an
d
s
m
ass
iv
e
n
u
m
b
e
r
o
f
in
ter
c
o
n
n
ec
te
d
m
ac
h
in
es
wo
r
k
in
g
o
n
p
u
b
lic
n
etwo
r
k
s
f
o
r
o
f
f
er
in
g
co
s
t
-
ef
f
ec
tiv
e
d
ata
s
ec
u
r
ity
.
4.
CO
NCLU
SI
O
N
An
o
m
aly
d
etec
tio
n
is
a
cr
itic
al
ch
allen
g
e
in
m
o
d
er
n
n
etwo
r
k
s
lik
e
I
o
T
an
d
C
PS
,
a
s
it
c
an
in
d
icate
ab
n
o
r
m
al
b
eh
a
v
io
r
t
h
at
p
o
ten
tially
co
m
p
r
o
m
is
es
th
e
s
y
s
tem
'
s
in
teg
r
ity
.
T
h
e
p
r
o
p
o
s
ed
wo
r
k
h
as
p
r
esen
ted
a
n
o
v
el
an
d
s
ig
n
if
ican
t
wo
r
k
-
b
a
s
ed
d
ata
b
alan
cin
g
an
d
e
n
s
em
b
le
lear
n
in
g
m
ec
h
an
is
m
.
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
co
n
s
is
ts
o
f
two
p
h
ases
.
T
h
e
f
ir
s
t
p
h
ase
is
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
wh
er
e
th
e
I
o
C
PS
d
ata
is
p
r
o
ce
s
s
ed
an
d
clea
n
ed
to
r
em
o
v
e
ir
r
elev
a
n
t
in
f
o
r
m
atio
n
.
T
h
e
d
ata
is
th
en
s
p
lit
in
to
tr
ain
in
g
an
d
test
in
g
s
ets.
T
h
e
s
ec
o
n
d
p
h
ase
is
th
e
m
o
d
ellin
g
p
h
ase,
wh
er
e
th
e
o
v
er
s
am
p
lin
g
ap
p
r
o
ac
h
is
im
p
l
em
en
ted
to
b
alan
ce
d
ata
an
d
t
r
ain
th
e
m
o
d
el.
T
h
is
m
o
d
el
co
n
s
is
ts
o
f
two
m
ajo
r
co
m
p
o
n
en
ts
:
M
-
Ad
aBo
o
s
t
an
d
NDT
alg
o
r
ith
m
,
wh
ich
ar
e
co
m
b
in
ed
b
ased
o
n
th
e
weig
h
ted
v
o
tin
g
to
m
ak
e
th
e
f
in
al
p
r
ed
ictio
n
a
n
d
ad
j
u
s
t
th
e
weig
h
ts
b
ased
o
n
th
e
ac
cu
r
ac
y
o
f
ea
c
h
class
if
ier
.
T
h
e
ex
p
er
im
e
n
t
s
h
o
ws
p
r
o
m
is
in
g
p
r
ec
is
io
n
,
r
ec
all
,
an
d
F1
-
s
co
r
e
r
esu
lts
.
T
h
e
co
n
clu
d
in
g
o
u
tc
o
m
e
o
f
th
e
co
m
p
ar
ativ
e
an
al
y
s
is
s
h
o
wca
s
es
th
at
th
e
p
r
o
p
o
s
ed
s
ch
em
e
o
f
f
er
s
a
s
ig
n
if
ican
tl
y
im
p
r
o
v
ed
th
r
ea
t
d
etec
tio
n
ac
cu
r
ac
y
an
d
f
aste
r
r
esp
o
n
s
e
tim
e
c
o
m
p
ar
e
d
t
o
s
u
p
er
v
is
ed
,
u
n
s
u
p
er
v
is
ed
,
an
d
d
ee
p
lea
r
n
in
g
s
ch
em
es f
r
eq
u
en
tly
ad
o
p
ted
to
s
ec
u
r
e
I
o
T
e
n
v
ir
o
n
m
en
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
1
6
9
-
7
1
7
7
7176
I
t
s
h
o
u
ld
b
e
n
o
ted
th
at
p
r
o
p
o
s
ed
s
tu
d
y
tar
g
ets
to
war
d
s
an
o
m
aly
d
etec
tio
n
u
s
in
g
n
o
v
e
l
m
ac
h
in
e
lean
in
g
ap
p
r
o
ac
h
;
h
o
wev
er
,
th
ey
ar
e
n
o
t
m
e
an
t
to
s
ec
u
r
e
th
e
AI
-
b
ased
c
y
b
er
th
r
e
ats.
Su
ch
f
o
r
m
o
f
cy
b
er
th
r
ea
ts
is
f
o
r
m
ed
wh
e
n
attac
k
er
its
elf
ad
o
p
ts
AI
to
in
tr
o
d
u
ce
th
e
th
r
ea
ts
an
d
th
is
is
o
n
e
lim
itatio
n
o
f
p
r
o
p
o
s
ed
m
o
d
el.
T
h
is
lim
itatio
n
ca
n
b
e
o
v
er
c
o
m
e
in
f
u
tu
r
e
wo
r
k
wh
er
e
a
n
o
v
el
d
etec
tio
n
alg
o
r
ith
m
ca
n
b
e
d
esig
n
ed
u
s
in
g
AI
t
h
at
ca
n
i
d
en
tify
th
e
a
n
o
m
alies
ass
o
ciate
d
with
AI
-
b
ased
p
r
o
ce
s
s
o
r
its
elf
o
r
th
e
d
ev
ice/
co
m
p
o
n
en
t
th
at
r
u
n
s
th
e
s
ec
u
r
ity
alg
o
r
ith
m
.
B
lo
ck
ch
ain
a
p
p
r
o
ac
h
al
o
n
g
with
b
io
in
s
p
ir
e
d
alg
o
r
ith
m
ca
n
b
e
in
teg
r
ated
to
wa
r
d
s
ac
co
m
p
lis
h
in
g
th
is
tar
g
et
in
f
u
tu
r
e
to
r
esis
t
AI
-
p
o
wer
ed
cy
b
e
r
th
r
ea
ts
.
Fu
r
th
er
wo
r
k
ca
n
b
e
ca
r
r
ied
o
u
t to
war
d
s
in
v
esti
g
ati
n
g
th
e
m
o
d
el
o
n
o
th
e
r
p
u
b
licly
av
ailab
le
d
ataset.
RE
F
E
R
E
NC
E
S
[
1
]
İ
.
K
a
h
r
a
ma
n
,
A
.
K
ö
se
,
M
.
K
o
c
a
,
a
n
d
E.
A
n
a
r
i
m
,
“
A
g
e
o
f
i
n
f
o
r
mat
i
o
n
i
n
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s:
a
s
u
r
v
e
y
,
”
I
EE
E
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
J
o
u
rn
a
l
,
v
o
l
.
1
1
,
n
o
.
6
,
p
p
.
9
8
9
6
–
9
9
1
4
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T.
2
0
2
3
.
3
3
2
4
8
7
9
.
[
2
]
P
.
M
.
C
h
a
n
a
l
a
n
d
M
.
S
.
K
a
k
k
a
sa
g
e
r
i
,
“
S
e
c
u
r
i
t
y
a
n
d
p
r
i
v
a
c
y
i
n
I
o
T:
a
s
u
r
v
e
y
,
”
Wi
r
e
l
e
ss
P
e
rs
o
n
a
l
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
1
1
5
,
n
o
.
2
,
p
p
.
1
6
6
7
–
1
6
9
3
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
7
7
-
0
2
0
-
0
7
6
4
9
-
9.
[
3
]
Y
.
Ji
a
n
g
,
S
.
W
u
,
R
.
M
a
,
M
.
Li
u
,
H
.
Lu
o
,
a
n
d
O
.
K
a
y
n
a
k
,
“
M
o
n
i
t
o
r
i
n
g
a
n
d
d
e
f
e
n
se
o
f
i
n
d
u
st
r
i
a
l
c
y
b
e
r
-
p
h
y
s
i
c
a
l
s
y
st
e
ms
u
n
d
e
r
t
y
p
i
c
a
l
a
t
t
a
c
k
s:
f
r
o
m
a
s
y
s
t
e
ms
a
n
d
c
o
n
t
r
o
l
p
e
r
sp
e
c
t
i
v
e
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
d
u
s
t
ri
a
l
C
y
b
e
r
-
Ph
y
si
c
a
l
S
y
s
t
e
m
s
,
v
o
l
.
1
,
p
p
.
1
9
2
–
2
0
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
C
P
S
.
2
0
2
3
.
3
3
1
7
2
3
7
.
[
4
]
E.
H
.
H
a
f
s
h
e
j
a
n
i
e
t
a
l
.
,
“
S
e
l
f
-
a
w
a
r
e
d
a
t
a
p
r
o
c
e
ssi
n
g
f
o
r
p
o
w
e
r
s
a
v
i
n
g
i
n
r
e
so
u
r
c
e
-
c
o
n
st
r
a
i
n
e
d
I
o
T
c
y
b
e
r
-
p
h
y
s
i
c
a
l
s
y
st
e
ms,
”
I
E
EE
S
e
n
so
rs J
o
u
rn
a
l
,
v
o
l
.
2
2
,
n
o
.
4
,
p
p
.
3
6
4
8
–
3
6
5
9
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
1
.
3
1
3
3
4
0
5
.
[
5
]
I
.
G
r
a
j
a
,
S
.
K
a
l
l
e
l
,
N
.
G
u
e
r
mo
u
c
h
e
,
S
.
C
h
e
i
k
h
r
o
u
h
o
u
,
a
n
d
A
.
H
a
d
j
K
a
c
e
m
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
s
u
r
v
e
y
o
n
mo
d
e
l
i
n
g
o
f
c
y
b
e
r
‐
p
h
y
s
i
c
a
l
sy
st
e
m
s
,
”
C
o
n
c
u
r
re
n
c
y
a
n
d
C
o
m
p
u
t
a
t
i
o
n
:
P
ra
c
t
i
c
e
a
n
d
Ex
p
e
ri
e
n
c
e
,
v
o
l
.
3
2
,
n
o
.
1
5
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
2
/
c
p
e
.
4
8
5
0
.
[
6
]
D
.
H
a
st
b
a
c
k
a
e
t
a
l
.
,
“
D
y
n
a
mi
c
e
d
g
e
a
n
d
c
l
o
u
d
s
e
r
v
i
c
e
i
n
t
e
g
r
a
t
i
o
n
f
o
r
i
n
d
u
st
r
i
a
l
I
o
T
a
n
d
p
r
o
d
u
c
t
i
o
n
mo
n
i
t
o
r
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s
o
f
i
n
d
u
st
r
i
a
l
c
y
b
e
r
-
p
h
y
s
i
c
a
l
sy
s
t
e
ms
,
”
I
EEE
T
r
a
n
sa
c
t
i
o
n
s
o
n
I
n
d
u
s
t
ri
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
8
,
n
o
.
1
,
p
p
.
4
9
8
–
5
0
8
,
Ja
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
I
.
2
0
2
1
.
3
0
7
1
5
0
9
.
[
7
]
Y
.
G
a
o
,
J
.
C
h
e
n
,
H
.
M
i
a
o
,
B
.
S
o
n
g
,
Y
.
Lu
,
a
n
d
W
.
P
a
n
,
“
S
e
l
f
-
l
e
a
r
n
i
n
g
s
p
a
t
i
a
l
d
i
s
t
r
i
b
u
t
i
o
n
-
b
a
se
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
f
o
r
i
n
d
u
s
t
r
i
a
l
c
y
b
e
r
-
p
h
y
si
c
a
l
sy
s
t
e
ms
,
”
I
EE
E
T
ra
n
sa
c
t
i
o
n
s
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
S
o
c
i
a
l
S
y
st
e
m
s
,
v
o
l
.
9
,
n
o
.
6
,
p
p
.
1
6
9
3
–
1
7
0
2
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
S
S
.
2
0
2
1
.
3
1
3
5
5
8
6
.
[
8
]
A
.
A
.
A
l
Z
u
b
i
,
M
.
A
l
-
M
a
i
t
a
h
,
a
n
d
A
.
A
l
a
r
i
f
i
,
“
C
y
b
e
r
-
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
i
n
h
e
a
l
t
h
c
a
r
e
u
si
n
g
c
y
b
e
r
-
p
h
y
s
i
c
a
l
s
y
s
t
e
m
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
5
,
n
o
.
1
8
,
p
p
.
1
2
3
1
9
–
1
2
3
3
2
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
0
0
-
0
2
1
-
0
5
9
2
6
-
8.
[
9
]
B
h
a
r
a
t
h
i
.
V
a
n
d
C
.
N
.
S
.
V
.
K
u
mar,
“
A
r
e
a
l
t
i
m
e
h
e
a
l
t
h
c
a
r
e
c
y
b
e
r
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
u
s
i
n
g
e
n
sem
b
l
e
c
l
a
ssi
f
i
e
r
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
0
1
,
Ju
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
e
l
e
c
e
n
g
.
2
0
2
2
.
1
0
8
0
4
3
.
[
1
0
]
A
.
B
h
a
r
d
w
a
j
,
F
.
A
l
-
T
u
r
j
ma
n
,
M
.
K
u
mar,
T.
S
t
e
p
h
a
n
,
a
n
d
L.
M
o
st
a
r
d
a
,
“
C
a
p
t
u
r
i
n
g
-
t
h
e
-
i
n
v
i
si
b
l
e
(
C
TI
)
:
B
e
h
a
v
i
o
r
-
b
a
se
d
a
t
t
a
c
k
s
r
e
c
o
g
n
i
t
i
o
n
i
n
I
o
T
-
o
r
i
e
n
t
e
d
i
n
d
u
st
r
i
a
l
c
o
n
t
r
o
l
s
y
st
e
ms,”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
0
4
9
5
6
–
1
0
4
9
6
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
9
8
9
8
3
.
[
1
1
]
J.
Ta
n
g
e
t
a
l
.
,
“
A
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
i
n
s
o
c
i
a
l
-
a
w
a
r
e
I
o
T
n
e
t
w
o
r
k
s,
”
I
EE
E
T
ra
n
sa
c
t
i
o
n
s
o
n
N
e
t
w
o
rk
a
n
d
S
e
rv
i
c
e
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
2
0
,
n
o
.
3
,
p
p
.
3
1
6
2
–
3
1
7
6
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
S
M
.
2
0
2
3
.
3
2
4
2
3
2
0
.
[
1
2
]
K
.
A
t
e
f
i
,
S
.
Y
a
h
y
a
,
A
.
R
e
z
a
e
i
,
a
n
d
S
.
H
.
B
i
n
t
i
M
o
h
d
H
a
s
h
i
m,
“
A
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
p
r
o
f
i
l
e
si
g
n
a
t
u
r
e
i
n
n
e
t
w
o
r
k
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
,
”
i
n
2
0
1
6
I
EEE
Re
g
i
o
n
1
0
S
y
m
p
o
si
u
m
(
T
E
N
S
Y
MP
)
,
M
a
y
2
0
1
6
,
p
p
.
7
1
–
7
6
,
d
o
i
:
1
0
.
1
1
0
9
/
TEN
C
O
N
S
p
r
i
n
g
.
2
0
1
6
.
7
5
1
9
3
8
0
.
[
1
3
]
X
.
Y
a
n
,
Y
.
X
u
,
X
.
X
i
n
g
,
B
.
C
u
i
,
Z
.
G
u
o
,
a
n
d
T
.
G
u
o
,
“
Tr
u
s
t
w
o
r
t
h
y
n
e
t
w
o
r
k
a
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
a
n
a
d
a
p
t
i
v
e
l
e
a
r
n
i
n
g
r
a
t
e
a
n
d
mo
m
e
n
t
u
m
i
n
I
I
o
T,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
d
u
st
r
i
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
6
,
n
o
.
9
,
p
p
.
6
1
8
2
–
6
1
9
2
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
I
.
2
0
2
0
.
2
9
7
5
2
2
7
.
[
1
4
]
W
.
Ji
n
,
S
.
Z
h
a
n
g
,
B
.
S
u
n
,
P
.
Ji
n
,
a
n
d
Z.
L
i
,
“
A
n
a
n
a
l
y
t
i
c
a
l
i
n
v
e
s
t
i
g
a
t
i
o
n
o
f
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
met
h
o
d
s
b
a
se
d
o
n
se
q
u
e
n
c
e
t
o
seq
u
e
n
c
e
m
o
d
e
l
i
n
s
a
t
e
l
l
i
t
e
p
o
w
e
r
s
u
b
sy
st
e
m,
”
S
e
n
so
rs
,
v
o
l
.
2
2
,
n
o
.
5
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
2
0
5
1
8
1
9
.
[
1
5
]
Y
.
C
h
e
n
,
S
.
H
u
a
n
g
,
F
.
Li
u
,
Z
.
W
a
n
g
,
a
n
d
X
.
S
u
n
,
“
Ev
a
l
u
a
t
i
o
n
o
f
r
e
i
n
f
o
r
c
e
m
e
n
t
l
e
a
r
n
i
n
g
-
b
a
s
e
d
f
a
l
se
d
a
t
a
i
n
j
e
c
t
i
o
n
a
t
t
a
c
k
t
o
a
u
t
o
m
a
t
i
c
v
o
l
t
a
g
e
c
o
n
t
r
o
l
,
”
I
E
EE
T
ra
n
sa
c
t
i
o
n
s
o
n
S
m
a
rt
G
ri
d
,
v
o
l
.
1
0
,
n
o
.
2
,
p
p
.
2
1
5
8
–
2
1
6
9
,
M
a
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
TSG
.
2
0
1
8
.
2
7
9
0
7
0
4
.
[
1
6
]
Z.
G
u
,
X
.
Zh
o
u
,
T.
Zh
a
n
g
,
F
.
Y
a
n
g
,
a
n
d
M
.
S
h
e
n
,
“
E
v
e
n
t
-
t
r
i
g
g
e
r
e
d
f
i
l
t
e
r
d
e
s
i
g
n
f
o
r
n
o
n
l
i
n
e
a
r
c
y
b
e
r
–
p
h
y
si
c
a
l
s
y
st
e
ms
s
u
b
j
e
c
t
t
o
d
e
c
e
p
t
i
o
n
a
t
t
a
c
k
s,
”
I
S
A
T
r
a
n
sa
c
t
i
o
n
s
,
v
o
l
.
1
0
4
,
p
p
.
1
3
0
–
1
3
7
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
s
a
t
r
a
.
2
0
1
9
.
0
2
.
0
3
6
.
[
1
7
]
Z.
B
a
o
,
D
.
H
e
,
M
.
K
.
K
h
a
n
,
M
.
Lu
o
,
a
n
d
Q
.
X
i
e
,
“
P
B
i
d
m
:
P
r
i
v
a
c
y
-
p
r
e
s
e
r
v
i
n
g
b
l
o
c
k
c
h
a
i
n
-
b
a
se
d
i
d
e
n
t
i
t
y
ma
n
a
g
e
men
t
s
y
st
e
m
f
o
r
i
n
d
u
st
r
i
a
l
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s,”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
d
u
st
r
i
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
9
,
n
o
.
2
,
p
p
.
1
5
2
4
–
1
5
3
4
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
I
.
2
0
2
2
.
3
2
0
6
7
9
8
.
[
1
8
]
B
.
I
n
g
r
e
,
A
.
Y
a
d
a
v
,
a
n
d
A
.
K
.
S
o
n
i
,
“
D
e
c
i
si
o
n
t
r
e
e
b
a
se
d
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m
f
o
r
N
S
L
-
K
D
D
d
a
t
a
se
t
,
”
i
n
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
f
o
r I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s (I
C
T
I
S
2
0
1
7
)
-
Vo
l
u
m
e
2
2
,
2
0
1
8
,
p
p
.
2
0
7
–
2
1
8
.
[
1
9
]
C
.
Li
u
,
Z.
G
u
,
a
n
d
J.
W
a
n
g
,
“
A
h
y
b
r
i
d
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
sca
l
a
b
l
e
K
-
me
a
n
s
+
r
a
n
d
o
m
f
o
r
e
st
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
7
5
7
2
9
–
7
5
7
4
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
8
2
1
4
7
.
[
2
0
]
B
.
L
i
,
Y
.
W
u
,
J
.
S
o
n
g
,
R
.
L
u
,
T.
Li
,
a
n
d
L
.
Z
h
a
o
,
“
D
e
e
p
F
e
d
:
f
e
d
e
r
a
t
e
d
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
i
n
i
n
d
u
st
r
i
a
l
c
y
b
er
–
p
h
y
s
i
c
a
l
sy
s
t
e
ms
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
d
u
s
t
ri
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
7
,
n
o
.
8
,
p
p
.
5
6
1
5
–
5
6
2
4
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
I
.
2
0
2
0
.
3
0
2
3
4
3
0
.
[
2
1
]
O
.
A
o
u
e
d
i
,
K
.
P
i
a
mr
a
t
,
G
.
M
u
l
l
e
r
,
a
n
d
K
.
S
i
n
g
h
,
“
F
e
d
e
r
a
t
e
d
s
e
mi
s
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
f
o
r
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
i
n
i
n
d
u
st
r
i
a
l
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s,
”
I
EE
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
d
u
st
ri
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
9
,
n
o
.
1
,
p
p
.
2
8
6
–
2
9
5
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
I
.
2
0
2
2
.
3
1
5
6
6
4
2
.
[
2
2
]
A
.
D
e
r
h
a
b
,
A
.
A
l
d
w
e
e
s
h
,
A
.
Z.
Em
a
m,
a
n
d
F
.
A
.
K
h
a
n
,
“
I
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m
f
o
r
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
b
a
se
d
o
n
t
e
m
p
o
r
a
l
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
e
f
f
i
c
i
e
n
t
f
e
a
t
u
r
e
e
n
g
i
n
e
e
r
i
n
g
,
”
Wi
r
e
l
e
ss
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
M
o
b
i
l
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
0
2
0
,
p
p
.
1
–
1
6
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
0
/
6
6
8
9
1
3
4
.
[
2
3
]
M
.
M
.
A
l
t
h
o
b
a
i
t
i
,
K
.
P
.
M
.
K
u
mar
,
D
.
G
u
p
t
a
,
S
.
K
u
mar,
a
n
d
R
.
F
.
M
a
n
so
u
r
,
“
A
n
i
n
t
e
l
l
i
g
e
n
t
c
o
g
n
i
t
i
v
e
c
o
mp
u
t
i
n
g
b
a
se
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
f
o
r
i
n
d
u
s
t
r
i
a
l
c
y
b
e
r
-
p
h
y
si
c
a
l
sy
s
t
e
ms
,
”
Me
a
s
u
reme
n
t
,
v
o
l
.
1
8
6
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
a
su
r
e
me
n
t
.
2
0
2
1
.
1
1
0
1
4
5
.
[
2
4
]
J.
B
.
A
w
o
t
u
n
d
e
,
C
.
C
h
a
k
r
a
b
o
r
t
y
,
a
n
d
A
.
E.
A
d
e
n
i
y
i
,
“
I
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
i
n
i
n
d
u
st
r
i
a
l
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
n
e
t
w
o
r
k
-
b
a
se
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
w
i
t
h
r
u
l
e
-
b
a
s
e
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
,
”
Wi
r
e
l
e
ss
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
M
o
b
i
l
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
0
2
1
,
n
o
.
1
,
J
a
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
7
1
5
4
5
8
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
F
r
a
mewo
r
k
fo
r
d
etec
tin
g
a
n
d
r
esis
tin
g
cy
b
era
tta
ck
s
o
n
cy
b
e
r
-
p
h
ysica
l sys
tems
…
(
Jy
o
ti M
eta
n
)
7177
[
2
5
]
O
.
Tu
s
h
k
a
n
o
v
a
,
D
.
Le
v
s
h
u
n
,
A
.
B
r
a
n
i
t
s
k
i
y
,
E.
F
e
d
o
r
c
h
e
n
k
o
,
E.
N
o
v
i
k
o
v
a
,
a
n
d
I
.
K
o
t
e
n
k
o
,
“
D
e
t
e
c
t
i
o
n
o
f
c
y
b
e
r
a
t
t
a
c
k
s
a
n
d
a
n
o
ma
l
i
e
s
i
n
c
y
b
e
r
-
p
h
y
si
c
a
l
s
y
s
t
e
m
s:
a
p
p
r
o
a
c
h
e
s,
d
a
t
a
s
o
u
r
c
e
s,
e
v
a
l
u
a
t
i
o
n
,
”
A
l
g
o
r
i
t
h
m
s
,
v
o
l
.
1
6
,
n
o
.
2
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
1
6
0
2
0
0
8
5
.
[
2
6
]
B
.
Ta
n
g
,
Y
.
L
u
,
Q
.
Li
,
Y
.
B
a
i
,
J.
Y
u
,
a
n
d
X
.
Y
u
,
“
A
d
i
f
f
u
s
i
o
n
mo
d
e
l
b
a
se
d
o
n
n
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
me
t
h
o
d
f
o
r
i
n
d
u
s
t
r
i
a
l
c
y
b
e
r
-
p
h
y
si
c
a
l
s
y
st
e
ms,”
S
e
n
so
rs
,
v
o
l
.
2
3
,
n
o
.
3
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
3
0
3
1
1
4
1
.
[
2
7
]
I
.
A
.
K
a
n
d
h
r
o
e
t
a
l
.
,
“
D
e
t
e
c
t
i
o
n
o
f
r
e
a
l
-
t
i
m
e
m
a
l
i
c
i
o
u
s
i
n
t
r
u
s
i
o
n
s
a
n
d
a
t
t
a
c
k
s
i
n
I
o
T
e
m
p
o
w
e
r
e
d
c
y
b
e
r
sec
u
r
i
t
y
i
n
f
r
a
s
t
r
u
c
t
u
r
e
s,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
9
1
3
6
–
9
1
4
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
3
8
6
6
4
.
[
2
8
]
J.
H
.
J
o
l
o
u
d
a
r
i
,
A
.
M
a
r
e
f
a
t
,
M
.
A
.
N
e
mat
o
l
l
a
h
i
,
S
.
S
.
O
y
e
l
e
r
e
,
a
n
d
S
.
H
u
ssa
i
n
,
“
Ef
f
e
c
t
i
v
e
c
l
a
ss
-
i
m
b
a
l
a
n
c
e
l
e
a
r
n
i
n
g
b
a
se
d
o
n
S
M
O
TE
a
n
d
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
6
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
0
6
4
0
0
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
J
y
o
ti
Met
a
n
c
u
rre
n
tl
y
wo
r
k
in
g
a
s
a
n
a
ss
o
c
iate
p
r
o
fe
ss
o
r
i
n
t
h
e
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
De
p
a
rt
m
e
n
t
,
Atria
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Ba
n
g
a
lo
re
,
I
n
d
ia.
S
h
e
h
a
s
re
c
e
iv
e
d
h
e
r
P
h
D
fro
m
VTU
Un
iv
e
rsity
,
I
n
d
ia
in
2
0
2
0
.
He
r
re
se
a
rc
h
a
re
a
in
c
lu
d
e
s
c
ry
p
to
g
ra
p
h
y
,
wire
les
s
se
n
so
r
n
e
t
wo
rk
s,
se
c
u
rit
y
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
h
a
s
m
o
re
th
a
n
1
7
y
e
a
rs o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
jy
o
ti
m
e
tan
@g
m
a
il
.
c
o
m
.
Ma
h
a
n
te
sh
Ma
t
h
a
p
a
ti
is
c
u
rre
n
tl
y
wo
rk
in
g
a
s
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
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
En
g
in
e
e
rin
g
,
Am
ru
ta
In
stit
u
te
o
f
En
g
in
e
e
ri
n
g
a
n
d
M
a
n
a
g
e
m
e
n
t
S
c
ien
c
e
,
Be
n
g
a
lu
r
u
,
a
ffil
iate
d
with
Visv
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
Un
i
v
e
rsity
,
Be
lag
a
v
i.
He
h
a
s
2
0
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
His
re
se
a
rc
h
in
tere
sts
a
re
wire
les
s
se
n
so
r
n
e
two
rk
s,
i
n
tern
e
t
o
f
th
in
g
s,
d
e
e
p
lea
rn
in
g
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
a
n
tes
h
k
rish
n
a
@g
m
a
il
.
c
o
m
.
Pra
sa
d
Ada
g
u
r
u
Y
o
g
e
g
o
wd
a
wo
rk
i
n
g
a
s
a
ss
o
c
iate
p
r
o
fe
ss
o
r,
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
ri
n
g
a
t
S
JB
In
st
it
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Ba
n
g
a
l
o
re
,
Ka
rn
a
tak
a
,
In
d
ia.
He
p
u
rs
u
e
d
a
P
h
.
D
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
e
n
g
in
e
e
ri
n
g
,
2
0
2
0
,
M
.
Tec
h
.
in
C
S
E
-
2
0
1
1
,
B.
E.
in
CS
E
-
2
0
0
9
,
a
ll
d
e
g
re
e
s
a
wa
rd
e
d
fro
m
Visv
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
Un
iv
e
rsit
y
,
Be
lag
a
v
i.
Ka
rn
a
tak
a
,
I
n
d
ia
.
He
p
u
b
li
sh
e
d
a
to
tal
o
f
3
2
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
ls
a
n
d
Co
n
fe
re
n
c
e
p
a
p
e
rs.
He
p
u
b
li
sh
e
d
5
I
n
d
ia
n
p
a
ten
ts.
He
is
a
li
fe
m
e
m
b
e
r
o
f
p
ro
fe
ss
io
n
a
l
so
c
ieties
li
k
e
IAENG
,
LM
IS
TE
,
S
DIWC,
IM
AP
a
n
d
AICTS
D.
His
re
se
a
rc
h
a
re
a
s
o
f
i
n
tere
st
a
re
wire
les
s
se
n
so
r
n
e
t
wo
rk
s,
d
a
ta
m
in
i
n
g
,
AI
,
a
n
d
b
lo
c
k
c
h
a
in
tec
h
n
o
l
o
g
y
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
y
p
ra
sa
d
2
6
@g
m
a
il
.
c
o
m
.
K
u
r
il
in
g
a
S
a
n
n
a
li
n
g
a
p
p
a
An
a
n
d
a
K
u
m
a
r
r
e
c
e
iv
e
d
P
h
D
f
ro
m
Visv
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
Un
i
v
e
rsity
,
Be
lag
a
v
i,
Ka
rn
a
tak
a
,
I
n
d
ia.
Ha
v
i
n
g
1
2
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rie
n
c
e
.
Cu
rre
n
tl
y
,
h
e
is
w
o
rk
i
n
g
a
s
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
i
n
th
e
De
p
ar
t
m
e
n
t
o
f
I
n
fo
rm
a
ti
o
n
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
a
t
Atria
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Ba
n
g
a
lo
re
,
In
d
ia
.
His
re
se
a
r
c
h
a
re
a
in
tere
sts
a
re
WS
N,
d
a
ta
m
in
in
g
,
m
a
c
h
i
n
e
l
e
a
rn
in
g
,
a
n
d
c
l
o
u
d
c
o
m
p
u
ti
n
g
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
a
n
d
g
d
k
@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.