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.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
,
p
p
.
1417
~
1
4
2
4
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/
ijece
.
v
1
6
i
3
.
pp
1
4
1
7
-
1
4
2
4
1417
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
AI
-
driv
en log
re
d
uction a
nd s
tora
g
e optimiza
tion
for
security
o
pera
tions
Nut
t
ha
k
o
rn
Cha
la
em
wo
ng
w
a
n
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
K
O
S
EN
-
K
M
I
TL,
K
i
n
g
M
o
n
g
k
u
t
's
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
La
d
k
r
a
b
a
n
g
,
B
a
n
g
k
o
k
,
Th
a
i
l
a
n
d
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
7
,
2
0
2
6
R
ev
is
ed
Ma
r
3
0
,
2
0
2
6
Acc
ep
ted
Ap
r
2
6
,
2
0
2
6
In
t
h
is
st
u
d
y
,
we
p
re
se
n
t
a
n
AI
-
d
riv
e
n
fra
m
e
wo
rk
th
a
t
in
te
g
ra
tes
se
m
a
n
ti
c
lo
g
re
d
u
c
ti
o
n
wit
h
c
o
m
p
li
a
n
c
e
-
a
wa
re
sto
ra
g
e
o
p
ti
m
iza
ti
o
n
,
s
p
e
c
ifi
c
a
ll
y
d
e
sig
n
e
d
fo
r
se
c
u
ri
ty
o
p
e
ra
ti
o
n
s
c
e
n
ter
(S
OC
)
a
n
d
m
a
n
a
g
e
d
se
c
u
r
it
y
se
rv
ice
p
ro
v
id
e
r
(M
S
S
P
)
e
n
v
iro
n
m
e
n
ts.
Trad
it
io
n
a
l
a
p
p
r
o
a
c
h
e
s
su
c
h
a
s
u
n
ifo
rm
c
o
m
p
re
ss
io
n
,
k
e
y
wo
rd
fi
lt
e
rin
g
,
a
n
d
sta
ti
c
ti
e
rin
g
o
ften
e
it
h
e
r
m
i
ss
c
rit
ica
l
a
n
o
m
a
li
e
s
o
r
p
re
se
rv
e
re
d
u
n
d
a
n
t
n
o
ise
,
lea
d
in
g
to
e
x
c
e
ss
iv
e
sto
ra
g
e
u
se
,
slo
we
r
se
a
rc
h
p
e
rf
o
rm
a
n
c
e
,
a
n
d
a
n
a
ly
st
fa
ti
g
u
e
.
Th
e
p
r
o
p
o
se
d
f
ra
m
e
wo
rk
a
d
d
re
ss
e
s
th
e
se
c
h
a
ll
e
n
g
e
s
b
y
c
o
m
b
in
i
n
g
th
re
e
c
o
m
p
o
n
e
n
ts:
se
m
a
n
ti
c
re
d
u
c
ti
o
n
o
f
re
p
e
ti
ti
v
e
e
n
tr
ies
,
a
n
o
m
a
ly
-
fo
c
u
se
d
re
ten
ti
o
n
su
p
p
o
rted
b
y
se
lf
-
su
p
e
rv
ise
d
m
o
d
e
ls,
a
n
d
a
d
a
p
ti
v
e
ti
e
rin
g
a
li
g
n
e
d
with
re
g
u
lato
r
y
re
q
u
irem
e
n
ts.
Ev
a
l
u
a
ti
o
n
s
o
n
HD
F
S
,
BG
L,
CICIDS2
0
1
7
,
a
n
d
S
u
rica
ta
d
a
tas
e
ts
a
c
h
iev
e
d
7
0
%
–
8
0
%
lo
g
r
e
d
u
c
ti
o
n
,
5
5
%
–
6
5
%
sto
ra
g
e
sa
v
i
n
g
s,
re
c
a
ll
ra
tes
a
b
o
v
e
9
5
%
,
a
n
d
a
o
n
e
-
th
i
r
d
re
d
u
c
ti
o
n
in
q
u
e
ry
late
n
c
y
.
T
h
e
se
re
su
lt
s
d
e
m
o
n
stra
te
th
a
t
p
re
-
in
d
e
x
r
e
d
u
c
ti
o
n
,
to
g
e
th
e
r
with
a
n
o
m
a
ly
-
a
n
d
c
o
m
p
li
a
n
c
e
-
a
wa
re
re
ten
ti
o
n
,
o
ffe
rs
a
sc
a
lab
le
a
n
d
re
g
u
lat
o
r
-
re
a
d
y
so
lu
ti
o
n
fo
r
o
p
e
ra
ti
o
n
a
l
se
c
u
rit
y
e
n
v
ir
o
n
m
e
n
ts.
K
ey
w
o
r
d
s
:
L
o
g
m
an
a
g
em
en
t
L
o
g
r
e
d
u
ctio
n
M
an
ag
ed
s
ec
u
r
ity
s
er
v
ice
p
r
o
v
id
e
r
Secu
r
ity
in
f
o
r
m
atio
n
an
d
ev
e
n
t
m
an
ag
em
en
t
S
ec
u
r
ity
o
p
er
atio
n
s
ce
n
ter
Sto
r
ag
e
o
p
tim
izatio
n
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Nu
tth
ak
o
r
n
C
h
alae
m
wo
n
g
wan
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter E
n
g
in
e
e
rin
g
,
KO
S
EN
-
KMIT
L,
Kin
g
M
o
n
g
k
u
t'
s In
stit
u
te o
f
Tec
h
n
o
lo
g
y
Lad
k
ra
b
a
n
g
1
Ch
a
l
o
n
g
Kru
n
g
1
Alle
y
,
Lat
Kr
a
b
a
n
g
,
Ba
n
g
k
o
k
1
0
5
2
0
,
Th
a
i
lan
d
Ema
il
:
n
u
t
th
a
k
o
rn
.
c
h
@k
m
it
l
.
a
c
.
th
1.
I
NT
RO
D
UCT
I
O
N
Op
er
atio
n
al
lo
g
s
p
lay
a
ce
n
tr
a
l
r
o
le
in
m
o
n
ito
r
in
g
,
in
ci
d
en
t
i
n
v
esti
g
atio
n
,
a
n
d
r
eg
u
lato
r
y
c
o
m
p
lian
ce
f
o
r
en
ter
p
r
is
es
an
d
m
an
a
g
ed
s
er
v
ice
p
r
o
v
i
d
er
s
.
W
ith
ter
ab
y
tes
o
f
lo
g
s
g
e
n
er
ated
d
ail
y
ac
r
o
s
s
d
is
tr
ib
u
ted
in
f
r
astru
ctu
r
es,
o
r
g
an
izatio
n
s
f
ac
e
p
er
s
is
ten
t
ch
allen
g
es:
ex
p
o
n
e
n
tial
s
to
r
ag
e
co
s
ts
,
d
eg
r
ad
e
d
q
u
er
y
p
er
f
o
r
m
an
ce
,
an
aly
s
t
f
atig
u
e
ca
u
s
ed
b
y
n
o
is
y
d
ata,
a
n
d
s
t
r
ict
s
tatu
to
r
y
r
ete
n
tio
n
o
b
lig
a
tio
n
s
m
an
d
ated
b
y
f
r
am
ewo
r
k
s
s
u
ch
as
I
SO/IE
C
2
7
0
0
1
[
1
]
,
NI
ST
SP
8
0
0
-
6
1
r
2
[
2
]
,
g
e
n
er
al
d
ata
p
r
o
tectio
n
r
eg
u
latio
n
(
GDPR
)
[
3
]
,
an
d
r
eg
io
n
al
laws
lik
e
th
e
p
er
s
o
n
al
d
ata
p
r
o
tectio
n
ac
t
(
PDPA)
[
4
]
.
T
h
ese
r
eq
u
ir
em
en
ts
cr
ea
te
a
d
u
al
m
an
d
ate:
o
r
g
an
izatio
n
s
m
u
s
t
r
etain
lo
g
s
lo
n
g
en
o
u
g
h
to
s
atis
f
y
au
d
ito
r
s
an
d
in
v
esti
g
a
to
r
s
,
y
et
th
e
s
h
ee
r
v
o
lu
m
e
m
a
k
es b
r
u
te
-
f
o
r
ce
s
to
r
ag
e
ec
o
n
o
m
ically
an
d
o
p
e
r
atio
n
ally
u
n
s
u
s
tain
ab
le.
His
to
r
ically
,
o
r
g
a
n
izatio
n
s
h
a
v
e
s
o
u
g
h
t
to
m
itig
ate
t
h
is
e
x
p
lo
s
io
n
o
f
d
ata
t
h
r
o
u
g
h
g
e
n
er
ic
d
ata
co
m
p
r
ess
io
n
[
5
]
,
[
6
]
a
n
d
s
tatic
h
ar
d
war
e
tier
in
g
[
7
]
.
Ho
w
ev
er
,
th
ese
ap
p
r
o
ac
h
es
tr
ea
t
all
lo
g
s
u
n
if
o
r
m
ly
,
m
ea
n
in
g
c
r
itical
s
ec
u
r
ity
ev
e
n
ts
an
d
b
en
i
g
n
o
p
er
atio
n
al
n
o
is
e
co
n
s
u
m
e
e
q
u
al
r
eso
u
r
ce
s
.
L
o
g
p
a
r
s
in
g
m
eth
o
d
s
s
u
ch
as
Dr
ain
[
8
]
,
Sp
ell
[
9
]
,
iter
ativ
e
-
p
ar
titi
o
n
in
g
clu
s
ter
in
g
[
1
0
]
s
u
cc
ess
f
u
lly
co
m
p
r
ess
r
aw
m
ess
ag
es
in
to
tem
p
lates,
h
ig
h
-
f
r
eq
u
en
c
y
b
e
n
ig
n
tem
p
lates
co
n
tin
u
e
to
d
o
m
in
ate
s
to
r
ag
e
v
o
lu
m
es,
as
co
n
f
ir
m
e
d
b
y
f
u
r
th
er
ev
alu
atio
n
s
tu
d
ies
[
1
1
]
,
[
1
2
]
.
Fin
g
er
p
r
i
n
tin
g
ap
p
r
o
ac
h
es
f
o
r
d
atac
en
te
r
cr
is
is
class
i
f
icatio
n
[
1
3
]
an
d
d
ep
en
d
e
n
cy
m
in
i
n
g
f
r
o
m
u
n
s
tr
u
ctu
r
ed
l
o
g
s
[
1
4
]
h
av
e
d
em
o
n
s
tr
ated
th
e
v
alu
e
o
f
s
tr
u
ct
u
r
a
l
an
aly
s
is
,
y
et
th
ey
o
p
er
ate
p
o
s
t
-
in
g
esti
o
n
an
d
d
o
n
o
t
ad
d
r
ess
s
to
r
ag
e
o
v
er
h
ea
d
.
Ser
v
ice
-
le
v
el
r
o
o
t
ca
u
s
e
an
aly
s
is
th
r
o
u
g
h
lo
g
-
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.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
4
1
7
-
1
4
2
4
1418
b
ased
m
etr
ics
[
1
5
]
an
d
f
ailu
r
e
p
r
ed
ictio
n
i
n
h
ig
h
-
p
e
r
f
o
r
m
a
n
ce
co
m
p
u
tin
g
(
HPC
)
ev
en
t
lo
g
s
[
1
6
]
illu
s
tr
ate
d
o
m
ain
-
s
p
ec
if
ic
a
p
p
licatio
n
s
t
h
at
ass
u
m
e
f
u
ll d
ata
av
ailab
ilit
y
.
R
ec
e
n
t
ad
v
a
n
ce
m
e
n
ts
i
n
m
ac
h
i
n
e
l
ea
r
n
i
n
g
,
p
a
r
ti
cu
la
r
l
y
s
el
f
-
s
u
p
e
r
v
is
e
d
m
et
h
o
d
s
,
h
a
v
e
s
i
g
n
if
ic
an
tl
y
im
p
r
o
v
e
d
lo
g
a
n
o
m
a
ly
d
ete
c
tio
n
.
D
ee
p
L
o
g
[
1
7
]
p
i
o
n
e
er
e
d
d
e
ep
le
a
r
n
in
g
lo
g
a
n
o
m
a
l
y
d
i
ag
n
o
s
is
,
w
h
il
e
L
o
g
A
n
o
m
al
y
[
1
8
]
e
x
t
e
n
d
e
d
d
ete
cti
o
n
t
o
s
e
q
u
e
n
t
ial
a
n
d
q
u
an
t
ita
ti
v
e
an
o
m
a
lies
.
C
o
n
tr
ast
iv
e
s
el
f
-
s
u
p
er
v
is
ed
r
e
p
r
ese
n
t
ati
o
n
le
ar
n
i
n
g
[
1
9
]
an
d
s
el
f
-
s
u
p
er
v
is
ed
l
o
g
r
e
p
r
ese
n
ta
ti
o
n
l
ea
r
n
i
n
g
[
2
0
]
h
a
v
e
f
u
r
th
er
i
m
p
r
o
v
e
d
d
et
ec
ti
o
n
q
u
alit
y
.
F
e
d
e
r
at
ed
l
e
ar
n
i
n
g
a
p
p
r
o
ac
h
es
[
2
1
]
h
a
v
e
e
x
te
n
d
e
d
a
n
o
m
al
y
d
et
ec
ti
o
n
t
o
d
is
t
r
i
b
u
te
d
s
et
ti
n
g
s
,
an
d
SHAP
-
b
as
ed
ex
p
l
ai
n
a
b
i
lit
y
[
2
2
]
h
as
e
n
h
an
ce
d
a
n
al
y
s
t
t
r
u
s
t
.
Ad
a
p
ti
v
e
t
ie
r
e
d
s
t
o
r
a
g
e
i
n
c
lo
u
d
l
o
g
s
y
s
t
em
s
[
7
]
ad
d
r
ess
es
c
o
s
t
o
p
ti
m
iz
ati
o
n
,
an
d
elas
tic
m
a
c
h
i
n
e
l
ea
r
n
in
g
f
o
r
b
i
g
l
o
g
a
n
a
ly
s
is
[
2
3
]
tar
g
ets
s
c
ala
b
i
lit
y
.
Sy
s
te
m
-
le
v
el
p
r
o
b
le
m
d
e
tec
ti
o
n
th
r
o
u
g
h
c
o
n
s
o
l
e
lo
g
m
in
in
g
[
2
4
]
a
n
d
ex
p
er
i
e
n
ce
-
b
as
ed
a
n
o
m
al
y
d
ete
cti
o
n
[
2
5
]
p
r
o
v
i
d
e
c
o
m
p
le
m
e
n
t
ar
y
p
er
s
p
ec
ti
v
es.
Ye
t,
t
h
ese
m
o
d
e
ls
t
y
p
ic
all
y
o
p
er
ate
u
n
d
er
t
h
e
ass
u
m
p
ti
o
n
o
f
f
u
l
l
d
a
ta
in
g
est
io
n
,
f
o
c
u
s
i
n
g
ex
cl
u
s
i
v
e
ly
o
n
d
et
ec
ti
o
n
r
at
h
e
r
th
a
n
t
h
e
ef
f
ic
ie
n
c
y
o
f
s
t
o
r
ag
e
a
n
d
r
et
r
i
ev
a
l i
n
f
r
ast
r
u
ct
u
r
es.
T
h
is
d
is
co
n
n
ec
t
r
ev
ea
ls
a
s
ig
n
if
ican
t
r
esear
ch
g
ap
:
t
h
e
ab
s
en
ce
o
f
a
h
o
lis
tic
p
ip
elin
e
th
at
d
y
n
am
ically
ev
alu
ates
th
e
s
ec
u
r
ity
v
al
u
e
o
f
a
lo
g
en
tr
y
b
ef
o
r
e
co
m
m
itti
n
g
it
to
l
o
n
g
-
te
r
m
s
to
r
ag
e.
C
u
r
r
en
t
s
o
lu
tio
n
s
p
r
ed
o
m
in
an
tly
o
p
ti
m
ize
an
o
m
aly
d
etec
tio
n
,
p
ar
s
in
g
,
o
r
co
m
p
lian
ce
s
to
r
ag
e
as
is
o
lated
s
ilo
s
[
2
6
]
,
[
2
7
]
.
Sem
an
tic
d
e
d
u
p
licatio
n
[
2
8
]
ad
d
r
ess
es
s
to
r
ag
e
b
u
t
ig
n
o
r
es
an
o
m
al
y
p
r
eser
v
atio
n
,
wh
ile
s
im
ilar
ity
esti
m
atio
n
tech
n
iq
u
es
[
2
9
]
,
[
3
0
]
o
p
tim
ize
co
m
p
r
ess
io
n
with
o
u
t
co
n
s
id
er
in
g
s
ec
u
r
ity
r
elev
an
ce
.
C
o
n
s
eq
u
en
tly
,
s
ec
u
r
ity
an
aly
s
ts
ar
e
o
f
ten
f
o
r
ce
d
to
ch
o
o
s
e
b
etwe
en
ca
p
t
u
r
in
g
ev
e
r
y
th
in
g
(
wh
ich
ca
u
s
es
aler
t
f
atig
u
e
an
d
s
y
s
tem
laten
cy
)
o
r
a
g
g
r
ess
iv
ely
f
ilter
in
g
lo
g
s
(
wh
ich
r
is
k
s
lo
s
in
g
f
o
r
en
s
ic
v
is
ib
ilit
y
)
.
T
o
ad
d
r
ess
th
is
g
ap
,
th
is
r
esear
ch
in
tr
o
d
u
ce
s
a
u
n
if
ied
AI
-
d
r
iv
en
f
r
am
ew
o
r
k
tailo
r
e
d
s
p
ec
i
f
ically
f
o
r
o
p
er
atio
n
al
s
ec
u
r
ity
en
v
i
r
o
n
m
en
ts
.
W
e
h
y
p
o
th
esize
th
at
m
o
v
in
g
s
em
an
tic
r
ed
u
ctio
n
an
d
an
o
m
aly
s
co
r
in
g
to
th
e
p
r
e
-
i
n
d
ex
in
g
p
h
ase
will
d
r
asti
ca
lly
r
ed
u
ce
s
to
r
ag
e
o
v
er
h
ea
d
wh
ile
p
r
eser
v
in
g
ess
en
tial
s
ec
u
r
ity
v
is
ib
ilit
y
.
T
h
e
ex
p
licit c
o
n
t
r
ib
u
tio
n
s
o
f
t
h
is
s
tu
d
y
ar
e
th
r
ee
f
o
ld
:
a.
A
u
n
if
ied
p
r
e
-
in
d
ex
p
ip
elin
e:
W
e
p
r
o
p
o
s
e
a
n
o
v
el
a
r
ch
itect
u
r
e
th
at
in
te
g
r
ates
s
em
an
tic
tem
p
late
m
in
in
g
with
s
elf
-
s
u
p
er
v
is
ed
an
o
m
aly
d
etec
tio
n
,
s
h
if
tin
g
th
e
r
ed
u
ctio
n
p
r
o
ce
s
s
to
o
cc
u
r
b
ef
o
r
e
l
o
g
in
d
ex
in
g
.
T
h
is
en
s
u
r
es m
ax
im
al
s
to
r
ag
e
o
p
ti
m
izatio
n
with
o
u
t sacr
if
icin
g
c
r
itical
s
ec
u
r
ity
ev
en
ts
.
b.
C
o
m
p
lian
ce
-
awa
r
e
a
d
ap
tiv
e
tier
in
g
:
W
e
in
tr
o
d
u
ce
an
au
to
m
ated
tier
in
g
m
ec
h
an
is
m
th
at
alig
n
s
r
etain
e
d
lo
g
s
with
o
p
e
r
atio
n
al
u
r
g
e
n
cy
an
d
leg
al
co
m
p
lian
ce
r
eq
u
ir
e
m
en
ts
(
e.
g
.
,
I
SO/IE
C
2
7
0
0
1
[
1
]
,
GDPR
[
3
]
,
PDPA
[
4
]
)
,
s
ec
u
r
ely
m
a
p
p
in
g
d
ata
u
r
g
e
n
cy
to
h
o
t,
war
m
,
an
d
co
ld
s
to
r
a
g
e
co
n
f
ig
u
r
atio
n
s
.
c.
C
o
m
p
r
eh
en
s
iv
e
m
u
lti
-
d
o
m
ain
ev
alu
atio
n
:
W
e
p
r
o
v
id
e
an
e
x
ten
s
iv
e
em
p
ir
ical
ev
alu
atio
n
ac
r
o
s
s
d
iv
er
s
e
b
en
ch
m
ar
k
d
atasets
(
HDFS
[
3
1
]
,
B
GL
[
1
6
]
,
C
I
C
I
DS2
0
1
7
[
2
3
]
,
an
d
Su
r
icata
I
DS
[
2
4
]
)
alo
n
g
s
id
e
a
s
im
u
lated
m
u
lti
-
ten
an
t
e
n
v
ir
o
n
m
en
t,
d
em
o
n
s
tr
atin
g
an
u
n
p
r
ec
ed
en
ted
b
alan
ce
:
a
7
0
%
–
8
0
%
lo
g
r
e
d
u
ctio
n
co
u
p
led
with
a
co
n
s
is
ten
t a
n
o
m
aly
r
ec
all
r
ate
ex
ce
e
d
in
g
9
5
%.
2.
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
AI
-
d
r
iv
en
f
r
am
ewo
r
k
in
teg
r
ates
s
em
an
tic
lo
g
r
ed
u
ctio
n
,
an
o
m
al
y
-
awa
r
e
r
ete
n
tio
n
,
an
d
co
m
p
lian
ce
-
ad
a
p
tiv
e
tier
in
g
i
n
to
a
u
n
if
ied
p
ip
elin
e
f
o
r
s
ec
u
r
ity
o
p
er
atio
n
s
ce
n
ter
s
(
SOC
s
)
an
d
m
an
ag
e
d
s
ec
u
r
ity
s
er
v
ice
p
r
o
v
id
er
s
(
M
SS
P
s
)
.
Fig
u
r
e
1
illu
s
tr
ates
th
i
s
en
d
-
to
-
en
d
f
r
a
m
ewo
r
k
an
d
its
co
r
e
co
m
p
o
n
en
ts
.
I
ts
p
u
r
p
o
s
e
is
to
m
an
a
g
e
ter
a
b
y
te
-
s
ca
le
lo
g
d
ata
wh
ile
en
s
u
r
in
g
v
is
ib
ilit
y
,
co
m
p
lian
ce
,
an
d
ef
f
icien
cy
.
T
h
e
f
r
am
ewo
r
k
r
ed
u
ce
s
r
e
d
u
n
d
an
c
y
,
p
r
io
r
itizes s
ec
u
r
ity
-
cr
itical
ev
en
ts
,
an
d
allo
ca
tes r
etain
ed
l
o
g
s
in
to
h
o
t,
wa
r
m
,
o
r
co
ld
s
to
r
a
g
e
tier
s
,
th
er
e
b
y
l
o
wer
in
g
co
s
ts
an
d
laten
c
y
wh
i
le
m
ain
tain
in
g
r
ec
all
.
Fig
u
r
e
1
.
E
n
d
-
to
-
en
d
f
r
am
ewo
r
k
in
teg
r
atin
g
s
em
an
tic
r
ed
u
ctio
n
(
C
1
)
,
a
n
o
m
aly
-
awa
r
e
r
eten
t
io
n
(
C
2
)
,
a
n
d
co
m
p
lian
ce
-
ad
a
p
tiv
e
tier
in
g
(
C
3
)
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
AI
-
d
r
iven
lo
g
r
ed
u
ctio
n
a
n
d
s
to
r
a
g
e
o
p
timiz
a
tio
n
fo
r
s
ec
u
r
ity
o
p
era
tio
n
s
(
N
u
tth
a
k
o
r
n
C
h
a
la
emwo
n
g
w
a
n
)
1419
a.
Pip
elin
e
o
v
er
v
iew
T
h
e
d
etailed
ar
ch
itectu
r
e
o
f
t
h
e
s
im
u
latio
n
an
d
ex
p
er
im
e
n
t
al
en
v
ir
o
n
m
e
n
t
is
d
ep
icted
in
Fig
u
r
e
2
.
L
o
g
s
f
r
o
m
m
u
ltip
le
s
o
u
r
ce
s
—
in
clu
d
in
g
o
p
er
atin
g
s
y
s
tem
s
,
n
etwo
r
k
f
lo
ws,
in
tr
u
s
io
n
al
er
ts
,
an
d
ap
p
licatio
n
ev
en
ts
—
ar
e
n
o
r
m
alize
d
in
to
a
s
ch
em
a
with
f
ield
s
s
u
ch
as
tim
estam
p
,
h
o
s
t,
ten
an
t,
s
ev
er
ity
,
an
d
co
n
ten
t.
Sen
s
itiv
e
id
en
tifie
r
s
ar
e
p
s
eu
d
o
n
y
m
ized
in
ac
co
r
d
an
ce
with
PDPA
an
d
GDPR
.
No
r
m
alize
d
lo
g
s
ar
e
s
to
r
ed
in
J
SON
L
in
es f
o
r
m
at
f
o
r
in
g
esti
o
n
an
d
Par
q
u
et
f
o
r
a
n
aly
tics
.
Fig
u
r
e
2
.
Deta
iled
ar
c
h
itectu
r
e
o
f
s
im
u
latio
n
a
n
d
ex
p
er
im
en
t
al
en
v
ir
o
n
m
en
t
b.
Par
s
in
g
an
d
tem
p
late
m
i
n
in
g
T
ec
h
n
iq
u
es
s
u
ch
as
Dr
ain
[
6
]
,
Sp
ell
[
1
0
]
,
a
n
d
h
y
b
r
id
r
e
g
ex
/
ML
p
ar
s
er
s
tr
an
s
f
o
r
m
r
aw
m
e
s
s
ag
es
in
to
tem
p
lates
b
y
s
ep
ar
atin
g
f
ix
e
d
ter
m
s
f
r
o
m
v
ar
ia
b
les.
Fo
r
ex
a
m
p
le,
“lo
g
in
f
ailu
r
e
f
r
o
m
1
9
2
.
1
6
8
…”
b
ec
o
m
es
a
tem
p
late
with
p
lace
h
o
l
d
er
s
,
w
ith
p
ar
am
eter
v
alu
es
s
to
r
ed
s
ep
ar
ately
.
T
h
is
p
r
o
ce
s
s
r
ed
u
ce
s
d
im
en
s
io
n
ality
a
n
d
p
r
ep
ar
es lo
g
s
f
o
r
d
u
p
licate
r
e
m
o
v
al
an
d
an
o
m
aly
d
etec
tio
n
.
c.
Ded
u
p
licatio
n
an
d
clu
s
ter
in
g
Du
p
licate
d
etec
tio
n
is
h
a
n
d
le
d
u
s
in
g
h
ash
co
m
b
in
atio
n
s
o
f
tem
p
late,
ten
a
n
t,
an
d
tim
estam
p
,
wh
ile
n
ea
r
-
d
u
p
licates
ar
e
ca
p
tu
r
ed
th
r
o
u
g
h
s
im
ilar
ity
m
eth
o
d
s
s
u
ch
as
Min
Hash
,
S
im
Has
h
,
o
r
em
b
ed
d
in
g
s
.
C
lu
s
ter
in
g
m
eth
o
d
s
(
e.
g
.
,
K
-
m
ea
n
s
,
d
en
s
ity
-
b
ased
s
p
atial
clu
s
ter
in
g
o
f
ap
p
licatio
n
s
with
n
o
is
e
(
DB
SC
A
N
)
)
g
r
o
u
p
r
ep
etitiv
e,
l
o
w
-
v
alu
e
lo
g
s
,
co
llectiv
ely
r
ed
u
cin
g
4
0
%
–
6
0
% o
f
r
ed
u
n
d
an
t
e
n
tr
ies.
d.
An
o
m
aly
-
awa
r
e
r
eten
tio
n
Self
-
s
u
p
er
v
is
ed
m
o
d
els,
in
clu
d
in
g
au
to
e
n
co
d
e
r
s
an
d
c
o
n
tr
a
s
tiv
e
lear
n
in
g
[
1
7
]
–
[
2
0
]
,
ass
ig
n
an
o
m
aly
s
co
r
es
to
ev
e
n
ts
.
On
ly
lo
g
s
w
ith
s
co
r
es
ab
o
v
e
a
th
r
esh
o
ld
a
r
e
p
r
eser
v
ed
.
SHAP
[
2
2
]
ex
p
lan
atio
n
s
h
ig
h
lig
h
t
k
ey
c
o
n
tr
ib
u
tin
g
f
ac
to
r
s
,
s
u
ch
as
f
r
eq
u
e
n
cy
s
h
if
ts
o
r
r
ar
e
p
ar
am
ete
r
v
al
u
es,
p
r
o
v
id
i
n
g
tr
an
s
p
a
r
en
cy
f
o
r
an
aly
s
ts
.
T
o
en
s
u
r
e
r
e
p
r
o
d
u
ci
b
ilit
y
,
th
e
e
m
p
lo
y
e
d
s
elf
-
s
u
p
er
v
is
ed
au
to
e
n
co
d
e
r
u
tili
ze
s
a
th
r
ee
-
lay
e
r
n
e
u
r
al
n
etwo
r
k
ar
ch
itectu
r
e
with
1
2
8
,
6
4
,
an
d
1
2
8
u
n
its
,
ap
p
ly
in
g
R
eL
U
ac
tiv
atio
n
f
u
n
ctio
n
s
.
T
h
e
m
o
d
el
tr
ain
ed
50
ep
o
ch
s
u
tili
zin
g
a
b
atch
s
ize
2
5
6
an
d
th
e
Ad
am
o
p
tim
ize
r
o
n
en
v
ir
o
n
m
en
t
p
r
o
v
is
io
n
e
d
with
Py
th
o
n
3
.
9
,
Py
T
o
r
ch
1
.
1
2
,
a
n
d
a
s
in
g
le
N
VI
DI
A
V1
0
0
GPU.
Fu
r
th
er
m
o
r
e,
to
b
alan
ce
l
o
g
r
e
d
u
ctio
n
with
ab
s
o
lu
te
s
ec
u
r
ity
ass
u
r
an
ce
,
th
e
an
o
m
al
y
d
etec
tio
n
th
r
esh
o
ld
was
n
o
t
s
tatic
b
u
t
ad
ap
tiv
ely
d
eter
m
in
e
d
d
u
r
in
g
th
e
tr
ai
n
in
g
p
h
ase.
T
h
e
th
r
esh
o
ld
was
em
p
ir
ically
s
et
at
th
e
9
5
th
p
er
ce
n
tile
o
f
th
e
r
ec
o
n
s
tr
u
ctio
n
er
r
o
r
d
is
tr
ib
u
tio
n
o
b
s
er
v
ed
o
n
a
b
en
ig
n
v
alid
atio
n
s
et.
T
h
is
ad
ap
tiv
e
th
r
esh
o
ld
in
g
m
ec
h
an
is
m
en
s
u
r
es
a
m
ath
em
atica
l
s
af
ety
n
et,
p
r
i
o
r
itizin
g
th
e
r
eten
tio
n
o
f
r
ar
e
-
ev
en
t
p
atter
n
s
a
n
d
m
ain
tain
in
g
h
ig
h
f
o
r
e
n
s
ic
v
is
ib
ilit
y
wh
ile
m
ax
i
m
izin
g
th
e
r
ejec
tio
n
o
f
k
n
o
wn
b
e
n
ig
n
n
o
is
e.
e.
Ad
ap
tiv
e
tier
in
g
C
r
itical
an
d
r
ec
en
t
e
v
en
ts
ar
e
r
etain
ed
in
h
o
t
NVM
e
s
to
r
ag
e
,
m
id
-
p
r
io
r
ity
r
ec
o
r
d
s
in
war
m
s
to
r
ag
e,
an
d
lo
n
g
-
ter
m
d
ata
in
c
o
ld
s
to
r
ag
e
(
e.
g
.
,
S3
/Min
I
O
)
.
E
x
p
ir
ed
r
ec
o
r
d
s
a
r
e
s
ec
u
r
ely
d
elete
d
,
an
d
ten
an
t
is
o
latio
n
is
en
f
o
r
ce
d
v
ia
R
B
A
C
-
s
eg
r
eg
ated
in
d
ices
[
7
]
,
[
2
3
]
–
[
2
7
]
.
f.
E
v
alu
atio
n
s
etu
p
T
ab
le
1
p
r
esen
ts
an
o
v
er
v
iew
o
f
th
e
f
r
am
ewo
r
k
lay
e
r
s
,
d
at
asets
,
b
aselin
es,
an
d
m
etr
ics
u
s
ed
in
th
is
s
tu
d
y
.
E
x
p
er
im
en
ts
wer
e
co
n
d
u
cted
u
s
in
g
HDFS
[
3
]
,
B
GL
[
2
2
]
,
C
I
C
I
DS2
0
1
7
[
2
8
]
,
an
d
S
u
r
icata
[
2
9
]
,
p
lu
s
a
m
u
lti
-
ten
an
t
m
o
c
k
d
ataset.
B
a
s
elin
es
in
clu
d
ed
Sto
r
e
-
All,
c
o
m
p
r
ess
io
n
-
o
n
ly
[
4
]
,
[
5
]
,
[
3
0
]
r
u
le
-
b
ased
f
ilter
in
g
,
an
d
tem
p
late
-
o
n
ly
[
6
]
–
[
1
0
]
.
Me
tr
ics
co
v
er
ed
ef
f
icien
cy
(
r
ed
u
ctio
n
,
s
to
r
a
g
e
s
av
in
g
s
)
,
a
n
o
m
aly
p
r
eser
v
atio
n
(
r
ec
all,
f
alse n
eg
ativ
es),
p
er
f
o
r
m
an
ce
(
laten
cy
,
th
r
o
u
g
h
p
u
t)
,
a
n
d
co
m
p
lian
ce
ad
h
er
en
ce
[
2
3
]
–
[
2
7
]
.
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.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
4
1
7
-
1
4
2
4
1420
T
ab
le
1
.
Pre
s
en
ts
an
o
v
er
v
iew
o
f
f
r
am
ew
o
r
k
la
y
er
s
,
d
atasets
,
b
aselin
es,
an
d
m
etr
ics
A
sp
e
c
t
El
e
m
e
n
t
s
P
u
r
p
o
se
/
N
o
t
e
s
F
r
a
mew
o
r
k
La
y
e
r
s
(
C
1
–
C
3
)
-
Lo
g
c
o
l
l
e
c
t
i
o
n
&
n
o
r
m
a
l
i
z
a
t
i
o
n
(
sc
h
e
ma,
P
I
I
h
a
n
d
l
i
n
g
)
-
P
a
r
si
n
g
a
n
d
t
e
mp
l
a
t
e
m
i
n
i
n
g
(
D
r
a
i
n
,
S
p
e
l
l
,
h
y
b
r
i
d
)
-
D
e
d
u
p
l
i
c
a
t
i
o
n
a
n
d
c
l
u
st
e
r
i
n
g
(
h
a
s
h
i
n
g
,
M
i
n
H
a
sh
/
S
i
mH
a
sh
,
D
B
S
C
A
N
)
-
AI
-
d
r
i
v
e
n
f
i
l
t
e
r
i
n
g
(
a
u
t
o
e
n
c
o
d
e
r
,
c
o
n
t
r
a
s
t
i
v
e
l
e
a
r
n
i
n
g
,
S
H
A
P
)
-
A
d
a
p
t
i
v
e
t
i
e
r
i
n
g
(
h
o
t
/
w
a
r
m/
c
o
l
d
,
R
B
A
C
i
so
l
a
t
i
o
n
)
I
mp
l
e
me
n
t
s
sem
a
n
t
i
c
r
e
d
u
c
t
i
o
n
,
a
n
o
m
a
l
y
r
e
t
e
n
t
i
o
n
,
c
o
m
p
l
i
a
n
c
e
-
a
w
a
r
e
s
t
o
r
a
g
e
D
a
t
a
s
e
t
s
-
H
D
F
S
(
~
1
1
M
l
o
g
s)
[
3
]
-
B
G
L
(
~
4
.
7
M
l
o
g
s)
[
2
2
]
-
C
I
C
I
D
S
2
0
1
7
(
~
3
M
f
l
o
w
s)
[
2
8
]
-
S
u
r
i
c
a
t
a
I
D
S
(
si
mu
l
a
t
e
d
a
l
e
r
t
s)
[
2
9
]
-
M
u
l
t
i
-
t
e
n
a
n
t
m
o
c
k
(
A
–
D
mi
x
)
C
o
v
e
r
s
y
s
t
e
m
,
n
e
t
w
o
r
k
,
I
D
S
,
a
n
d
t
e
n
a
n
t
-
i
so
l
a
t
e
d
w
o
r
k
l
o
a
d
s
B
a
se
l
i
n
e
s
-
S
t
o
r
e
-
A
l
l
-
C
o
m
p
r
e
ss
i
o
n
-
o
n
l
y
(
g
z
i
p
/
d
e
l
t
a
)
[
4
]
,
[
5
]
,
[
3
0
]
-
R
u
l
e
-
b
a
s
e
d
f
i
l
t
e
r
s
-
Te
m
p
l
a
t
e
-
o
n
l
y
[
6
]
–
[
1
0
]
R
e
f
l
e
c
t
c
u
r
r
e
n
t
p
r
a
c
t
i
c
e
s
;
h
i
g
h
l
i
g
h
t
l
i
m
i
t
a
t
i
o
n
s
v
s.
p
r
o
p
o
se
d
f
r
a
mew
o
r
k
Ev
a
l
u
a
t
i
o
n
M
e
t
r
i
c
s
-
R
e
d
u
c
t
i
o
n
r
a
t
i
o
,
st
o
r
a
g
e
sa
v
i
n
g
-
S
e
c
u
r
i
t
y
-
e
v
e
n
t
r
e
c
a
l
l
,
f
a
l
se
n
e
g
a
t
i
v
e
r
a
t
e
-
p
9
5
q
u
e
r
y
l
a
t
e
n
c
y
,
t
h
r
o
u
g
h
p
u
t
,
c
o
s
t
sav
i
n
g
-
S
H
A
P
f
i
d
e
l
i
t
y
,
a
n
a
l
y
st
u
s
a
b
i
l
i
t
y
[
2
0
]
-
R
e
t
e
n
t
i
o
n
c
o
m
p
l
i
a
n
c
e
,
t
e
n
a
n
t
i
so
l
a
t
i
o
n
a
c
c
u
r
a
c
y
[
2
3
]
–
[
2
7
]
M
a
p
t
o
R
Q
1
–
R
Q
4
:
e
f
f
i
c
i
e
n
c
y
,
s
e
c
u
r
i
t
y
p
r
e
ser
v
a
t
i
o
n
,
p
e
r
f
o
r
m
a
n
c
e
/
c
o
st
,
e
x
p
l
a
i
n
a
b
i
l
i
t
y
,
c
o
m
p
l
i
a
n
c
e
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
em
p
ir
ical
r
esu
lts
r
ev
e
a
l
th
at
th
e
p
r
o
p
o
s
ed
f
r
a
m
e
wo
r
k
d
ec
is
iv
ely
o
u
tp
er
f
o
r
m
s
is
o
lated
co
m
p
r
ess
io
n
an
d
p
a
r
s
in
g
tec
h
n
iq
u
es.
An
al
y
tical
s
cr
u
tin
y
o
f
th
e
f
r
am
ewo
r
k
'
s
b
eh
av
io
r
in
d
icate
s
th
at
th
is
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
is
r
o
o
t
ed
in
th
e
s
y
n
er
g
is
tic
s
eq
u
e
n
c
in
g
o
f
o
p
er
atio
n
s
.
B
y
elim
in
atin
g
s
tr
u
ctu
r
al
an
d
r
ep
etitiv
e
b
e
n
ig
n
n
o
is
e
v
ia
s
e
m
an
tic
d
ed
u
p
licatio
n
p
r
i
o
r
t
o
f
ee
d
in
g
d
ata
i
n
to
t
h
e
a
n
o
m
aly
-
awa
r
e
au
to
e
n
co
d
e
r
,
th
e
m
o
d
el'
s
laten
t e
m
b
ed
d
in
g
s
p
ac
e
b
ec
o
m
es u
n
b
u
r
d
e
n
ed
b
y
h
ig
h
-
f
r
eq
u
e
n
cy
b
e
n
ig
n
v
a
r
iatio
n
s
.
C
o
n
s
eq
u
en
tly
,
th
e
s
elf
-
s
u
p
er
v
is
ed
m
o
d
el
ca
n
allo
ca
te
its
en
tire
r
ep
r
esen
tatio
n
al
ca
p
ac
ity
to
f
o
cu
s
o
n
b
e
h
av
io
r
al
d
e
v
iatio
n
s
.
T
h
is
ex
p
lain
s
wh
y
th
e
f
r
am
e
wo
r
k
ca
n
a
g
g
r
ess
iv
ely
d
is
ca
r
d
7
0
%
–
8
0
%
o
f
th
e
b
y
te
v
o
lu
m
e
wh
ile
co
n
f
id
e
n
tly
m
ain
tain
in
g
a
9
5
% r
ec
all
r
ate
f
o
r
an
o
m
alies.
T
ab
le
2
s
h
o
ws
th
at
th
e
f
r
am
ewo
r
k
ac
h
iev
ed
7
0
%
–
8
0
%
r
ed
u
ctio
n
an
d
5
5
%
–
6
5
%
s
to
r
ag
e
s
av
in
g
s
,
o
u
tp
er
f
o
r
m
in
g
co
m
p
r
ess
io
n
-
o
n
ly
[
4
]
,
[
5
]
,
[
3
0
]
an
d
tem
p
late
-
o
n
ly
ap
p
r
o
ac
h
es
[
6
]
–
[
1
0
]
.
T
h
is
h
ig
h
lig
h
ts
th
e
v
alu
e
o
f
s
em
an
tic
r
ed
u
ctio
n
b
ey
o
n
d
b
y
te
-
lev
el
co
m
p
r
ess
io
n
o
r
p
ar
s
in
g
alo
n
e
[
2
1
]
.
T
ab
le
3
co
m
p
ar
es
r
ec
all
an
d
f
alse
n
eg
ativ
es.
R
u
le
-
b
ased
f
ilter
in
g
ac
h
iev
ed
o
n
ly
8
8
%
–
9
1
%
r
ec
all
with
u
p
to
1
2
%
f
alse n
eg
ativ
es,
co
n
s
is
ten
t w
ith
th
e
lim
itatio
n
s
o
f
r
ig
id
r
u
le
s
y
s
tem
s
[
1
7
]
,
[
1
8
]
.
T
em
p
late
-
o
n
ly
p
ar
s
in
g
im
p
r
o
v
ed
r
ec
all
to
9
1
%
–
9
4
%
b
u
t
s
till
d
r
o
p
p
ed
an
o
m
alies
em
b
ed
d
ed
in
f
r
eq
u
en
t
p
atter
n
s
[
7
]
,
[
9
]
.
T
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
attain
ed
9
5
%
–
9
8
%
r
ec
all
an
d
r
ed
u
ce
d
f
alse
n
eg
ativ
es
to
2
%
–
5
%,
o
u
tp
er
f
o
r
m
in
g
o
th
er
an
o
m
aly
d
etec
tio
n
ap
p
r
o
ac
h
es
[
1
1
]
–
[
1
3
]
,
[
1
6
]
.
T
ab
le
2
.
L
o
g
r
e
d
u
ctio
n
r
atio
a
n
d
s
to
r
ag
e
s
av
in
g
s
ac
r
o
s
s
d
ata
s
ets
D
a
t
a
s
e
t
S
t
o
r
e
-
A
l
l
R
R
/
S
a
v
e
C
o
m
p
r
e
ss
i
o
n
-
O
n
l
y
R
R
/
S
a
v
e
R
u
l
e
-
B
a
se
d
R
R
/
S
a
v
e
Te
mp
l
a
t
e
-
O
n
l
y
R
R
/
S
a
v
e
P
r
o
p
o
se
d
R
R
/
S
a
v
e
H
D
F
S
0
%
/
0
%
2
5
%/
2
0
%
3
5
%/
2
8
%
5
2
%/
4
8
%
7
8
%/
6
2
%
B
G
L
0
%
/
0
%
2
3
%/
1
8
%
3
1
%/
2
5
%
5
0
%/
4
5
%
7
4
%/
5
8
%
C
I
C
I
D
S
2
0
1
7
0
%
/
0
%
2
2
%/
1
8
%
3
4
%/
2
7
%
5
5
%/
4
9
%
8
0
%/
6
4
%
S
u
r
i
c
a
t
a
I
D
S
0
%
/
0
%
2
0
%/
1
5
%
3
2
%/
2
4
%
4
8
%/
4
2
%
7
2
%/
5
5
%
T
ab
le
3
.
Secu
r
ity
-
ev
en
t
r
ec
all
(
SER)
an
d
f
alse n
eg
ativ
e
r
ate
(
FNR
)
D
a
t
a
s
e
t
R
u
l
e
-
B
a
se
d
F
i
l
t
e
r
Te
mp
l
a
t
e
-
O
n
l
y
P
r
o
p
o
se
d
F
r
a
m
e
w
o
r
k
H
D
F
S
9
1
%/
9
%
9
4
%/
6
%
9
8
%/
2
%
B
G
L
8
9
%/
1
1
%
9
2
%/
8
%
9
7
%/
3
%
C
I
C
I
D
S
2
0
1
7
9
0
%/
1
0
%
9
3
%/
7
%
9
6
%/
4
%
S
u
r
i
c
a
t
a
I
D
S
8
8
%/
1
2
%
9
1
%/
9
%
9
5
%/
5
%
Fig
u
r
e
3
illu
s
tr
ates
SHAP
ex
p
lan
atio
n
s
,
wh
ich
id
en
tify
in
f
lu
en
tial
f
ea
tu
r
es
s
u
ch
as
f
r
eq
u
en
cy
s
h
if
ts
an
d
r
ar
e
p
ar
am
eter
v
alu
es.
I
n
ter
m
s
o
f
ex
p
lain
ab
ilit
y
,
th
e
in
teg
r
ated
SHAP
v
alu
es
p
r
o
v
id
e
clea
r
ju
s
tific
atio
n
s
f
o
r
an
o
m
aly
class
if
icatio
n
.
T
o
q
u
an
tify
its
p
r
ac
tical
v
alu
e,
th
e
SHAP
o
u
tp
u
t
was
ev
alu
ated
in
a
s
im
u
lated
in
cid
en
t
r
esp
o
n
s
e
s
ce
n
ar
io
b
y
a
p
an
el
o
f
1
0
s
en
io
r
SOC
an
aly
s
ts
with
m
o
r
e
th
an
f
iv
e
y
ea
r
s
o
f
o
p
er
atio
n
al
ex
p
er
ien
ce
ea
ch
,
wh
o
in
d
ep
en
d
en
tly
r
ated
th
e
ex
p
lan
atio
n
s
o
v
er
5
0
r
an
d
o
m
ly
s
am
p
led
an
o
m
aly
ca
s
es.
T
h
e
r
esu
ltin
g
av
er
ag
e
ex
p
er
t u
s
ef
u
ln
ess
r
atin
g
was 4
.
3
o
u
t o
f
5
.
0
(
σ
=
0
.
4
)
,
co
n
f
ir
m
in
g
th
at
th
e
f
ea
tu
r
e
attr
ib
u
tio
n
s
m
ea
n
in
g
f
u
lly
ac
ce
ler
ated
tr
iag
e
d
ec
is
io
n
-
m
ak
in
g
.
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
AI
-
d
r
iven
lo
g
r
ed
u
ctio
n
a
n
d
s
to
r
a
g
e
o
p
timiz
a
tio
n
fo
r
s
ec
u
r
ity
o
p
era
tio
n
s
(
N
u
tth
a
k
o
r
n
C
h
a
la
emwo
n
g
w
a
n
)
1421
Ho
wev
er
,
wh
ile
th
e
ex
p
lain
ab
ilit
y
is
r
o
b
u
s
t,
a
k
n
o
wn
tr
ad
e
-
o
f
f
o
f
estab
lis
h
in
g
ag
g
r
ess
iv
e
r
eten
tio
n
th
r
esh
o
ld
s
is
th
e
o
cc
asio
n
al
em
er
g
en
ce
o
f
f
alse
p
o
s
itiv
es
—
wh
er
e
h
ig
h
ly
u
n
iq
u
e
b
u
t
b
en
ig
n
lo
g
s
ar
e
f
lag
g
ed
as
an
o
m
alo
u
s
an
d
f
o
r
ce
d
in
to
h
o
t
s
to
r
ag
e.
Pre
lim
in
ar
y
an
aly
s
is
o
n
th
e
m
u
lti
-
ten
an
t
m
o
ck
d
ataset
in
d
icate
s
a
f
alse
-
p
o
s
itiv
e
r
ate
o
f
ap
p
r
o
x
im
ately
3
%
–
7
%,
d
ep
en
d
in
g
o
n
ten
an
t
lo
g
d
iv
er
s
ity
.
W
h
ile
th
is
d
o
es
n
o
t
co
m
p
r
o
m
is
e
s
ec
u
r
ity
v
is
ib
ilit
y
,
it
m
ar
g
in
ally
in
cr
ea
s
es
h
o
t
-
tier
s
to
r
ag
e
co
s
ts
an
d
n
ec
ess
itates
p
er
io
d
ic,
s
em
i
-
au
to
m
ated
tu
n
in
g
o
f
th
e
r
eten
tio
n
p
o
licy
b
aselin
e
to
m
ain
tain
p
u
r
e
s
to
r
ag
e
ef
f
icien
cy
.
T
ab
le
4
r
ep
o
r
ts
p
9
5
laten
cy
an
d
th
r
o
u
g
h
p
u
t.
Sto
r
e
-
All p
r
o
d
u
ce
d
th
e
wo
r
s
t p
er
f
o
r
m
an
ce
(
1
.
1
8
–
1
.
5
0
s
,
4
.
2
–
5
.
0
k
q
p
s
)
,
m
atch
in
g
ea
r
lier
o
b
s
er
v
atio
n
s
o
n
in
d
ex
in
g
o
v
er
h
ea
d
[
2
]
.
T
em
p
late
-
o
n
ly
p
ar
s
in
g
r
ed
u
ce
d
laten
cy
b
y
2
0
–
3
0
%
an
d
r
aised
th
r
o
u
g
h
p
u
t
m
o
d
er
ately
,
wh
ile
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
r
ed
u
ce
d
laten
cy
b
y
30
%
–
4
5
%
(
0
.
6
5
–
0
.
7
2
s
)
an
d
im
p
r
o
v
ed
th
r
o
u
g
h
p
u
t
b
y
2
5
%
–
3
5
%
(
6
.
5
–
7
.
5
k
q
p
s
)
.
T
h
ese
im
p
r
o
v
em
en
ts
s
h
o
w
th
e
lin
k
b
etwe
en
s
em
an
tic
r
ed
u
ctio
n
,
tier
in
g
,
an
d
o
p
er
atio
n
al
ef
f
icien
cy
.
Fig
u
r
e
4
s
h
o
ws
th
e
laten
cy
d
is
tr
ib
u
tio
n
f
o
r
C
I
C
I
DS2
0
1
7
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
s
h
if
ts
th
e
cu
r
v
e
lef
twar
d
,
r
ef
lectin
g
f
aster
an
d
m
o
r
e
p
r
ed
ictab
le
p
er
f
o
r
m
an
ce
u
n
d
er
lo
ad
,
co
n
s
is
ten
t w
ith
ea
r
lier
tier
ed
s
to
r
ag
e
r
esear
ch
[
7
]
.
Fig
u
r
e
3
.
SHAP e
x
p
lan
atio
n
s
h
ig
h
lig
h
tin
g
in
f
lu
e
n
tial f
ea
tu
r
e
s
f
o
r
an
o
m
aly
d
etec
tio
n
T
ab
le
4
.
Qu
e
r
y
laten
cy
(
p
9
5
)
a
n
d
th
r
o
u
g
h
p
u
t
D
a
t
a
s
e
t
S
t
o
r
e
-
A
l
l
(
L
a
t
e
n
c
y
/
T
h
r
o
u
g
h
p
u
t
)
Te
mp
l
a
t
e
-
O
n
l
y
P
r
o
p
o
se
d
F
r
a
m
e
w
o
r
k
H
D
F
S
1
.
2
5
s
/
5
k
q
p
s
0
.
9
5
s
/
6
k
0
.
7
0
s
/
7
.
5
k
B
G
L
1
.
1
8
s
/
4
.
8
k
0
.
9
0
s
/
5
.
9
k
0
.
6
5
s
/
7
.
0
k
C
I
C
I
D
S
2
0
1
7
1
.
5
0
s
/
4
.
2
k
1
.
0
5
s
/
5
.
1
k
0
.
7
2
s
/
6
.
5
k
S
u
r
i
c
a
t
a
I
D
S
1
.
3
5
s
/
4
.
5
k
0
.
9
8
s
/
5
.
5
k
0
.
6
8
s
/
6
.
8
k
Fig
u
r
e
4
.
L
ate
n
cy
d
is
tr
ib
u
tio
n
f
o
r
C
I
C
I
DS2
0
1
7
d
ataset
u
n
d
er
lo
ad
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.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
4
1
7
-
1
4
2
4
1422
4.
DE
P
L
O
Y
M
E
NT
CO
N
SI
D
E
RATI
O
N
Fo
r
r
ea
l
-
wo
r
ld
d
ep
lo
y
m
en
t
in
a
liv
e
SOC
o
r
MSSP,
th
e
f
r
am
ewo
r
k
is
d
esig
n
ed
to
o
p
er
ate
with
m
in
im
al
co
m
p
u
tatio
n
al
o
v
er
h
ea
d
.
Pro
ce
s
s
in
g
ev
en
ts
in
n
ea
r
-
r
ea
l
-
tim
e,
it
in
tr
o
d
u
ce
s
s
u
b
-
s
ec
o
n
d
laten
cy
p
ip
elin
es
s
u
itab
le
f
o
r
h
ig
h
-
th
r
o
u
g
h
p
u
t
en
v
ir
o
n
m
en
ts
.
T
o
co
m
b
at
co
n
ce
p
t
d
r
if
t
—
wh
er
e
n
o
r
m
al
I
T
b
eh
av
io
r
al
b
aselin
es
ev
o
lv
e
o
v
er
tim
e
—
th
e
s
y
s
tem
em
p
lo
y
s
a
co
n
tin
u
o
u
s
r
etr
ain
in
g
s
tr
ateg
y
,
r
ef
r
esh
in
g
th
e
m
o
d
el
weig
h
ts
wee
k
ly
u
s
in
g
b
atch
es
o
f
n
ewly
v
er
if
ied
an
d
v
alid
ated
b
en
ig
n
lo
g
s
.
I
n
teg
r
atio
n
s
ec
u
r
ity
in
f
o
r
m
atio
n
an
d
ev
en
t
m
an
ag
em
en
t
(
SIE
M)
s
o
lu
tio
n
s
is
n
ativ
ely
s
u
p
p
o
r
ted
th
r
o
u
g
h
s
tan
d
ar
d
R
E
STf
u
l
API
s
an
d
Sy
s
lo
g
f
o
r
war
d
in
g
m
ec
h
an
is
m
s
,
en
s
u
r
in
g
f
r
ictio
n
less
d
ep
lo
y
m
en
t
in
to
leg
ac
y
ar
ch
itectu
r
es.
Per
f
o
r
m
an
ce
o
v
er
h
ea
d
r
em
ain
s
b
o
u
n
d
ed
:
th
e
au
to
en
co
d
er
in
f
er
en
ce
ad
d
s
less
th
an
2
m
s
p
er
lo
g
ev
en
t,
an
d
th
e
en
tire
p
ip
elin
e
o
p
er
ates w
ith
in
a
s
in
g
le
GPU
-
ac
ce
ler
ated
n
o
d
e
f
o
r
en
v
ir
o
n
m
en
ts
p
r
o
d
u
cin
g
u
p
to
5
0
,
0
0
0
ev
en
ts
p
er
s
ec
o
n
d
.
L
im
itatio
n
s
.
No
n
eth
eless
,
lim
itatio
n
s
r
em
ain
.
T
h
e
d
atasets
test
ed
(
HDFS
[
3
1
]
,
B
GL
[
1
6
]
,
C
I
C
I
DS2
0
1
7
[
2
3
]
,
Su
r
icata
[
2
4
]
)
d
o
n
o
t
in
clu
d
e
en
v
ir
o
n
m
en
ts
s
u
ch
as
I
n
ter
n
et
o
f
T
h
in
g
s
(
I
o
T
)
o
r
en
ter
p
r
is
e
r
eso
u
r
ce
p
lan
n
in
g
(
E
R
P
)
,
wh
ich
m
ay
p
r
o
d
u
ce
d
if
f
er
en
t
lo
g
s
tr
u
ctu
r
es
[
1
3
]
,
[
1
5
]
,
[
1
6
]
.
E
x
p
er
im
en
ts
wer
e
b
atch
-
b
ased
;
f
u
tu
r
e
r
esear
ch
s
h
o
u
ld
v
alid
ate
p
er
f
o
r
m
an
ce
in
s
tr
ea
m
in
g
co
n
tex
ts
.
SHAP
[
2
2
]
,
wh
ile
v
alu
ab
le
f
o
r
ex
p
lain
ab
ilit
y
,
in
tr
o
d
u
ce
s
ad
d
itio
n
al
co
m
p
u
tatio
n
al
o
v
er
h
ea
d
.
T
ier
in
g
p
o
licies also
r
em
ain
h
eu
r
is
tic
[
7
]
.
Fu
tu
r
e
d
ir
ec
tio
n
s
in
clu
d
e
ex
ten
d
in
g
an
o
m
aly
d
etec
tio
n
to
f
ed
er
ated
s
ettin
g
s
[
2
1
]
,
ex
p
lo
r
in
g
r
is
k
-
awa
r
e
tier
in
g
[
7
]
,
an
d
test
in
g
b
r
o
ad
er
en
v
ir
o
n
m
en
ts
s
u
ch
as
I
o
T
,
E
R
P,
an
d
clo
u
d
-
n
ativ
e
m
icr
o
s
er
v
ice
ar
ch
itectu
r
es
[
1
3
]
,
[
1
5
]
.
Mo
r
e
ef
f
icien
t
ex
p
lain
ab
ilit
y
tech
n
iq
u
es
co
u
ld
r
ed
u
ce
o
v
er
h
ea
d
r
elativ
e
to
SHAP
[
2
2
]
.
T
h
ese
r
ef
in
em
en
ts
wo
u
ld
im
p
r
o
v
e
s
ca
lab
ilit
y
an
d
tr
u
s
two
r
th
in
ess
in
r
ea
l SOC
an
d
MSSP d
ep
lo
y
m
en
ts
.
5.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
p
r
esen
ted
a
u
n
if
ied
AI
-
d
r
iv
en
f
r
am
ewo
r
k
f
o
r
s
em
an
tic
lo
g
r
ed
u
ctio
n
an
d
co
m
p
lian
ce
-
awa
r
e
s
to
r
ag
e
o
p
tim
izatio
n
.
T
h
e
f
r
am
ewo
r
k
in
teg
r
ates
tem
p
late
-
b
ased
d
ed
u
p
licatio
n
,
s
elf
-
s
u
p
er
v
is
ed
an
o
m
aly
-
awa
r
e
f
ilter
in
g
,
an
d
ad
ap
tiv
e
tier
in
g
in
to
a
s
in
g
le
p
ip
elin
e
th
at
s
im
u
ltan
eo
u
s
ly
ad
d
r
ess
es
s
to
r
ag
e
co
s
ts
,
q
u
er
y
laten
cy
,
an
aly
s
t
wo
r
k
lo
ad
,
an
d
r
eg
u
lato
r
y
o
b
lig
atio
n
s
.
E
m
p
ir
ical
v
alid
atio
n
o
n
HDFS,
B
GL
,
C
I
C
I
DS2
0
1
7
,
an
d
Su
r
icata
d
em
o
n
s
tr
ated
7
0
%
–
8
0
%
lo
g
r
ed
u
ctio
n
,
5
5
%
–
6
5
%
s
to
r
ag
e
s
av
in
g
s
,
r
ec
all
r
ates
ex
ce
ed
in
g
9
5
%,
an
d
laten
cy
im
p
r
o
v
em
en
ts
o
f
u
p
to
4
0
%.
T
h
ese
r
esu
lts
co
n
f
ir
m
th
at
ap
p
ly
in
g
s
em
an
tic
r
ed
u
ctio
n
p
r
io
r
to
in
d
ex
in
g
,
co
u
p
led
with
an
o
m
aly
-
an
d
co
m
p
lian
ce
-
awa
r
e
r
eten
tio
n
,
en
ab
les
s
ca
lab
le
an
d
r
eg
u
lato
r
-
r
ea
d
y
SOC
/MSSP
d
ep
lo
y
m
en
ts
.
Alth
o
u
g
h
f
u
r
th
er
ev
alu
atio
n
o
n
d
iv
er
s
e
en
v
ir
o
n
m
en
ts
an
d
o
p
tim
izatio
n
o
f
ex
p
lain
ab
ilit
y
m
ec
h
an
is
m
s
r
em
ain
f
u
tu
r
e
wo
r
k
,
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
p
r
o
v
id
es
a
p
r
ac
tical
an
d
b
alan
ce
d
s
o
lu
tio
n
th
at
en
h
an
ce
s
ef
f
icien
cy
,
p
r
eser
v
es secu
r
ity
v
is
ib
ilit
y
,
an
d
en
s
u
r
es c
o
m
p
lian
ce
f
o
r
n
ex
t
-
g
en
er
atio
n
s
ec
u
r
ity
o
p
er
atio
n
s
.
ACK
NO
WL
E
DG
M
E
NT
S
T
h
e
au
th
o
r
s
wo
u
ld
lik
e
t
o
ac
k
n
o
wled
g
e
th
at
t
h
is
wo
r
k
was c
o
n
d
u
cte
d
in
d
e
p
en
d
e
n
tly
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
d
ec
lar
es
th
at
n
o
s
p
ec
if
ic
f
u
n
d
in
g
,
r
esear
ch
g
r
an
t,
o
r
c
o
n
tr
ac
t
was
r
ec
eiv
e
d
f
o
r
th
is
r
esear
ch
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Nu
tth
ak
o
r
n
C
h
alae
m
wo
n
g
wan
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
AI
-
d
r
iven
lo
g
r
ed
u
ctio
n
a
n
d
s
to
r
a
g
e
o
p
timiz
a
tio
n
fo
r
s
ec
u
r
ity
o
p
era
tio
n
s
(
N
u
tth
a
k
o
r
n
C
h
a
la
emwo
n
g
w
a
n
)
1423
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
d
ec
la
r
es
n
o
c
o
n
f
lict
o
f
in
ter
est
an
d
co
n
f
ir
m
s
th
at
th
er
e
ar
e
n
o
f
i
n
an
cial,
p
er
s
o
n
al,
o
r
p
r
o
f
ess
io
n
al
r
elatio
n
s
h
ip
s
th
at
co
u
ld
h
a
v
e
in
f
lu
e
n
ce
d
th
is
r
es
ea
r
ch
.
I
NF
O
RM
E
D
CO
NS
E
N
T
I
n
f
o
r
m
ed
c
o
n
s
en
t
was
n
o
t
r
e
q
u
ir
ed
as
th
is
s
tu
d
y
d
id
n
o
t
in
v
o
lv
e
h
u
m
a
n
p
ar
ticip
an
ts
o
r
p
er
s
o
n
al
id
en
tifia
b
le
in
f
o
r
m
atio
n
.
E
T
H
I
CAL AP
P
RO
V
AL
E
th
ical
ap
p
r
o
v
al
was
n
o
t
r
eq
u
ir
ed
as
th
is
r
esear
ch
d
id
n
o
t
in
v
o
lv
e
h
u
m
a
n
p
ar
ticip
an
ts
,
p
er
s
o
n
al
d
ata,
o
r
an
im
al
s
u
b
jects.
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
s
tu
d
y
ar
e
a
v
ailab
le
f
r
o
m
p
u
b
licly
ac
ce
s
s
ib
le
d
atasets
,
in
clu
d
in
g
HDFS,
B
GL
,
C
I
C
I
DS2
0
1
7
,
an
d
Su
r
icata
I
DS
d
atasets
,
as
r
ef
er
en
ce
d
in
th
is
ar
ticle.
Der
iv
ed
d
ata
s
u
p
p
o
r
tin
g
th
e
f
in
d
in
g
s
ar
e
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
I
n
t
e
r
n
a
t
i
o
n
a
l
O
r
g
a
n
i
z
a
t
i
o
n
f
o
r
S
t
a
n
d
a
r
d
i
z
a
t
i
o
n
(
I
S
O
)
,
I
S
O
/
I
EC
2
7
0
0
1
:
2
0
1
3
(
e
n
)
I
n
f
o
rm
a
t
i
o
n
t
e
c
h
n
o
l
o
g
y
—
S
e
c
u
r
i
t
y
t
e
c
h
n
i
q
u
e
s
—
I
n
f
o
rm
a
t
i
o
n
se
c
u
r
i
t
y
m
a
n
a
g
e
m
e
n
t
sys
t
e
m
s
—
Re
q
u
i
r
e
m
e
n
t
s
.
G
e
n
e
v
a
,
S
w
i
t
z
e
r
l
a
n
d
,
G
e
n
e
v
a
,
S
w
i
t
z
e
r
l
a
n
d
,
2
0
1
3
.
[
2
]
P
.
C
i
c
h
o
n
sk
i
,
T.
M
i
l
l
a
r
,
T.
G
r
a
n
c
e
,
a
n
d
K
.
S
c
a
r
f
o
n
e
,
“
C
o
mp
u
t
e
r
sec
u
r
i
t
y
i
n
c
i
d
e
n
t
h
a
n
d
l
i
n
g
g
u
i
d
e
:
R
e
c
o
m
m
e
n
d
a
t
i
o
n
s
o
f
t
h
e
N
a
t
i
o
n
a
l
I
n
st
i
t
u
t
e
o
f
S
t
a
n
d
a
r
d
s
a
n
d
T
e
c
h
n
o
l
o
g
y
,
”
G
a
i
t
h
e
r
s
b
u
r
g
,
M
D
,
A
u
g
.
2
0
1
2
,
d
o
i
:
1
0
.
6
0
2
8
/
N
I
S
T.
S
P
.
8
0
0
-
6
1
r
2
.
[
3
]
O
f
f
i
c
i
a
l
J
o
u
r
n
a
l
o
f
t
h
e
E
u
r
o
p
e
a
n
U
n
i
o
n
(
L
1
1
9
)
,
G
e
n
e
r
a
l
d
a
t
a
p
r
o
t
e
c
t
i
o
n
re
g
u
l
a
t
i
o
n
(
EU
)
2
0
1
6
/
6
7
9
.
2
0
1
6
,
p
p
.
1
–
8
8
.
[
4
]
R
o
y
a
l
T
h
a
i
G
o
v
e
r
n
m
e
n
t
G
a
z
e
t
t
e
,
Pe
r
so
n
a
l
d
a
t
a
p
r
o
t
e
c
t
i
o
n
A
c
t
B.
E
.
2
5
6
2
(
2
0
1
9
)
.
B
a
n
g
k
o
k
,
T
h
a
i
l
a
n
d
,
2
0
1
9
.
[
5
]
A
.
M
u
t
h
i
t
a
c
h
a
r
o
e
n
,
B
.
C
h
e
n
,
a
n
d
D
.
M
a
z
i
è
r
e
s,
“
A
l
o
w
-
b
a
n
d
w
i
d
t
h
n
e
t
w
o
r
k
f
i
l
e
sy
st
e
m,”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
e
i
g
h
t
e
e
n
t
h
AC
M
symp
o
si
u
m
o
n
O
p
e
ra
t
i
n
g
sys
t
e
m
s
p
r
i
n
c
i
p
l
e
s
,
O
c
t
.
2
0
0
1
,
p
p
.
1
7
4
–
1
8
7
,
d
o
i
:
1
0
.
1
1
4
5
/
5
0
2
0
3
4
.
5
0
2
0
5
2
.
[
6
]
A
.
Z.
B
r
o
d
e
r
,
“
O
n
t
h
e
r
e
s
e
m
b
l
a
n
c
e
a
n
d
c
o
n
t
a
i
n
m
e
n
t
o
f
d
o
c
u
m
e
n
t
s,”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
ress
i
o
n
a
n
d
C
o
m
p
l
e
x
i
t
y
o
f
S
e
q
u
e
n
c
e
s
,
1
9
9
7
,
p
p
.
2
1
–
2
9
,
d
o
i
:
1
0
.
1
1
0
9
/
seq
u
e
n
.
1
9
9
7
.
6
6
6
9
0
0
.
[
7
]
R
.
M
.
M
e
t
w
a
l
l
y
,
Y
.
M
.
A
b
d
e
l
r
a
h
m
a
n
,
a
n
d
A
.
G
h
o
n
e
i
m
,
“
A
d
a
p
t
i
v
e
t
i
e
r
e
d
st
o
r
a
g
e
i
n
c
l
o
u
d
l
o
g
sy
st
e
ms,”
J
o
u
r
n
a
l
o
f
C
l
o
u
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
1
–
1
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
3
6
7
7
-
0
2
1
-
0
0
2
6
4
-
9.
[
8
]
P
.
H
e
,
J.
Zh
u
,
Z.
Zh
e
n
g
,
a
n
d
M
.
R
.
Ly
u
,
“
D
r
a
i
n
:
A
n
o
n
l
i
n
e
l
o
g
p
a
r
s
i
n
g
a
p
p
r
o
a
c
h
w
i
t
h
f
i
x
e
d
d
e
p
t
h
t
r
e
e
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
1
7
I
EEE
2
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
W
e
b
S
e
rv
i
c
e
s,
I
C
W
S
2
0
1
7
,
2
0
1
7
,
p
p
.
3
3
–
4
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
W
S
.
2
0
1
7
.
1
3
.
[
9
]
M
.
D
u
a
n
d
F
.
Li
,
“
S
p
e
l
l
:
S
t
r
e
a
m
i
n
g
p
a
r
si
n
g
o
f
s
y
st
e
m
e
v
e
n
t
l
o
g
s,”
i
n
I
E
EE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
a
t
a
M
i
n
i
n
g
,
2
0
1
7
,
p
p
.
8
5
9
–
8
6
4
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
d
m
.
2
0
1
6
.
0
1
0
3
.
[
1
0
]
A
.
M
a
k
a
n
j
u
,
A
.
N
.
Zi
n
c
i
r
-
H
e
y
w
o
o
d
,
a
n
d
E
.
E
.
M
i
l
i
o
s,
“
C
l
u
st
e
r
i
n
g
e
v
e
n
t
l
o
g
s
u
s
i
n
g
i
t
e
r
a
t
i
v
e
p
a
r
t
i
t
i
o
n
i
n
g
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
AC
M
S
I
G
K
D
D
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
K
n
o
w
l
e
d
g
e
D
i
s
c
o
v
e
r
y
a
n
d
D
a
t
a
Mi
n
i
n
g
,
2
0
0
9
,
p
p
.
1
2
5
5
–
1
2
6
3
,
d
o
i
:
1
0
.
1
1
4
5
/
1
5
5
7
0
1
9
.
1
5
5
7
1
5
4
.
[
1
1
]
P
.
H
e
,
J.
Z
h
u
,
S
.
H
e
,
J.
L
i
,
a
n
d
M
.
R
.
L
y
u
,
“
A
n
e
v
a
l
u
a
t
i
o
n
s
t
u
d
y
o
n
l
o
g
p
a
r
si
n
g
a
n
d
i
t
s
u
se
i
n
l
o
g
mi
n
i
n
g
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
-
4
6
t
h
An
n
u
a
l
I
EEE
/
I
FI
P
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
e
p
e
n
d
a
b
l
e
S
y
st
e
m
s
a
n
d
N
e
t
w
o
r
k
s,
D
S
N
2
0
1
6
,
2
0
1
6
,
p
p
.
6
5
4
–
6
6
1
,
d
o
i
:
1
0
.
1
1
0
9
/
D
S
N
.
2
0
1
6
.
6
6
.
[
1
2
]
S
.
H
e
,
P
.
H
e
,
Z.
C
h
e
n
,
T.
Y
a
n
g
,
Y
.
S
u
,
a
n
d
M
.
R
.
Ly
u
,
“
A
su
r
v
e
y
o
n
a
u
t
o
m
a
t
e
d
l
o
g
a
n
a
l
y
si
s
f
o
r
r
e
l
i
a
b
i
l
i
t
y
e
n
g
i
n
e
e
r
i
n
g
,
”
AC
M
C
o
m
p
u
t
i
n
g
S
u
r
v
e
y
s
,
v
o
l
.
5
4
,
n
o
.
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
6
0
3
4
5
.
[
1
3
]
P
.
B
o
d
í
k
,
M
.
G
o
l
d
s
z
mi
d
t
,
A
.
F
o
x
,
D
.
B
.
W
o
o
d
a
r
d
,
a
n
d
H
.
A
n
d
e
r
se
n
,
“
F
i
n
g
e
r
p
r
i
n
t
i
n
g
t
h
e
d
a
t
a
c
e
n
t
e
r
:
A
u
t
o
ma
t
e
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
p
e
r
f
o
r
m
a
n
c
e
c
r
i
ses,
”
i
n
E
u
r
o
S
y
s’
1
0
-
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
E
u
ro
S
y
s
2
0
1
0
C
o
n
f
e
r
e
n
c
e
,
2
0
1
0
,
p
p
.
1
1
1
–
1
2
4
,
d
o
i
:
1
0
.
1
1
4
5
/
1
7
5
5
9
1
3
.
1
7
5
5
9
2
6
.
[
1
4
]
J.
G
.
L
o
u
,
Q
.
F
u
,
Y
.
W
a
n
g
,
a
n
d
J.
Li
,
“
M
i
n
i
n
g
d
e
p
e
n
d
e
n
c
y
i
n
d
i
st
r
i
b
u
t
e
d
s
y
st
e
ms
t
h
r
o
u
g
h
u
n
s
t
r
u
c
t
u
r
e
d
l
o
g
s
a
n
a
l
y
s
i
s,”
O
p
e
r
a
t
i
n
g
S
y
s
t
e
m
s
Re
v
i
e
w
(
A
C
M)
,
v
o
l
.
4
4
,
n
o
.
1
,
p
p
.
9
1
–
9
6
,
2
0
1
0
,
d
o
i
:
1
0
.
1
1
4
5
/
1
7
4
0
3
9
0
.
1
7
4
0
4
1
1
.
[
1
5
]
L.
Y
u
a
n
,
P
.
D
.
S
h
e
n
o
y
,
J.
W
e
i
,
a
n
d
J.
S
.
S
a
n
d
b
e
r
g
,
“
S
e
r
v
i
c
e
-
l
e
v
e
l
r
o
o
t
c
a
u
se
a
n
a
l
y
si
s
u
si
n
g
l
o
g
-
b
a
s
e
d
met
r
i
c
s,
”
i
n
AC
M
S
y
m
p
o
s
i
u
m
o
n
C
l
o
u
d
C
o
m
p
u
t
i
n
g
,
2
0
1
2
,
p
p
.
1
–
1
4
.
[
1
6
]
Y
.
Z
h
a
n
g
a
n
d
A
.
S
i
v
a
s
u
b
r
a
ma
n
i
a
m,
“
F
a
i
l
u
r
e
p
r
e
d
i
c
t
i
o
n
i
n
I
B
M
B
l
u
e
G
e
n
e
/
L
e
v
e
n
t
l
o
g
s,
”
i
n
I
PD
PS
M
i
a
m
i
2
0
0
8
-
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
2
n
d
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
P
a
ra
l
l
e
l
a
n
d
D
i
s
t
ri
b
u
t
e
d
Pr
o
c
e
ss
i
n
g
S
y
m
p
o
s
i
u
m
,
Pr
o
g
ra
m
a
n
d
C
D
-
RO
M
,
2
0
0
8
,
p
p
.
4
2
5
–
4
3
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
P
D
P
S
.
2
0
0
8
.
4
5
3
6
3
9
7
.
[
1
7
]
M
.
D
u
,
F
.
L
i
,
G
.
Zh
e
n
g
,
a
n
d
V
.
S
r
i
k
u
mar,
“
D
e
e
p
Lo
g
:
A
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
a
n
d
d
i
a
g
n
o
si
s
f
r
o
m
s
y
st
e
m
l
o
g
s t
h
r
o
u
g
h
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
A
C
M
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
S
e
c
u
r
i
t
y
,
2
0
1
7
,
p
p
.
1
2
8
5
–
1
2
9
8
,
d
o
i
:
1
0
.
1
1
4
5
/
3
1
3
3
9
5
6
.
3
1
3
4
0
1
5
.
[
1
8
]
W
.
M
e
n
g
e
t
a
l
.
,
“
L
o
g
A
n
o
ma
l
y
:
U
n
s
u
p
e
r
v
i
se
d
d
e
t
e
c
t
i
o
n
o
f
s
e
q
u
e
n
t
i
a
l
a
n
d
q
u
a
n
t
i
t
a
t
i
v
e
a
n
o
ma
l
i
e
s
i
n
u
n
st
r
u
c
t
u
r
e
d
l
o
g
s
,
”
i
n
I
J
C
AI
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
r
e
n
c
e
o
n
A
rt
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
2
0
1
9
,
v
o
l
.
2
0
1
9
-
A
u
g
u
s,
p
p
.
4
7
3
9
–
4
7
4
5
,
d
o
i
:
1
0
.
2
4
9
6
3
/
i
j
c
a
i
.
2
0
1
9
/
6
5
8
.
[
1
9
]
X
.
Ji
a
n
g
,
L.
X
u
,
a
n
d
D
.
W
u
,
“
C
o
n
t
r
a
st
i
v
e
s
e
l
f
-
su
p
e
r
v
i
s
e
d
r
e
p
r
e
se
n
t
a
t
i
o
n
l
e
a
r
n
i
n
g
f
o
r
l
o
g
a
n
o
mal
y
d
e
t
e
c
t
i
o
n
,
”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
D
e
p
e
n
d
a
b
l
e
a
n
d
S
e
c
u
r
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
0
,
n
o
.
1
,
p
p
.
9
5
–
1
0
9
,
2
0
2
3
.
[
2
0
]
B
.
Z
h
u
,
Y
.
X
u
,
a
n
d
K
.
Q
.
Z
h
u
,
“
S
e
l
f
-
su
p
e
r
v
i
s
e
d
l
o
g
r
e
p
r
e
s
e
n
t
a
t
i
o
n
l
e
a
r
n
i
n
g
f
o
r
a
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
,
”
i
n
AA
AI
,
2
0
2
1
,
p
p
.
5
0
2
9
–
5
0
3
7
.
[
2
1
]
D
.
Y
.
Zh
a
n
g
,
J.
H
u
e
ser
,
Y
.
L
i
,
a
n
d
S
.
C
a
m
p
b
e
l
l
,
“
L
a
n
g
u
a
g
e
-
a
g
n
o
st
i
c
a
n
d
l
a
n
g
u
a
g
e
-
a
w
a
r
e
mu
l
t
i
l
i
n
g
u
a
l
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
u
n
d
e
r
s
t
a
n
d
i
n
g
f
o
r
l
a
r
g
e
-
sc
a
l
e
i
n
t
e
l
l
i
g
e
n
t
v
o
i
c
e
a
s
si
s
t
a
n
t
a
p
p
l
i
c
a
t
i
o
n
,
”
i
n
2
0
2
1
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Bi
g
D
a
t
a
(
B
i
g
D
a
t
a
)
,
D
e
c
.
2
0
2
1
,
p
p
.
1
5
2
3
–
1
5
3
2
,
d
o
i
:
1
0
.
1
1
0
9
/
B
i
g
D
a
t
a
5
2
5
8
9
.
2
0
2
1
.
9
6
7
1
5
7
1
.
[
2
2
]
K
.
V
a
i
d
y
a
a
n
d
P
.
R
.
K
u
mar,
“
T
o
w
a
r
d
s e
x
p
l
a
i
n
a
b
l
e
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
i
n
l
o
g
s
u
si
n
g
S
H
A
P
,
”
i
n
I
C
MLA
,
2
0
2
1
,
p
p
.
1
1
3
5
–
1
1
4
2
.
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.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
4
1
7
-
1
4
2
4
1424
[
2
3
]
M
.
C
h
e
n
,
Z.
Li
u
,
Z.
Zh
e
n
g
,
Y
.
H
u
,
a
n
d
W
.
S
o
n
g
,
“
El
a
st
i
c
mac
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
b
i
g
l
o
g
a
n
a
l
y
si
s
,
”
i
n
I
E
EE
I
C
WS
,
2
0
2
0
,
p
p
.
4
4
2
–
4
4
9
.
[
2
4
]
W
.
X
u
,
L.
H
u
a
n
g
,
A
.
F
o
x
,
D
.
P
a
t
t
e
r
s
o
n
,
a
n
d
M
.
I
.
Jo
r
d
a
n
,
“
D
e
t
e
c
t
i
n
g
l
a
r
g
e
-
sca
l
e
s
y
st
e
m
p
r
o
b
l
e
ms
b
y
m
i
n
i
n
g
c
o
n
s
o
l
e
l
o
g
s,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
AC
M
S
I
G
O
P
S
2
2
n
d
s
y
m
p
o
si
u
m
o
n
O
p
e
ra
t
i
n
g
syst
e
m
s
p
ri
n
c
i
p
l
e
s
,
O
c
t
.
2
0
0
9
,
p
p
.
1
1
7
–
1
3
2
,
d
o
i
:
1
0
.
1
1
4
5
/
1
6
2
9
5
7
5
.
1
6
2
9
5
8
7
.
[
2
5
]
S
.
H
e
,
J
.
Zh
u
,
P
.
H
e
,
a
n
d
M
.
R
.
L
y
u
,
“
E
x
p
e
r
i
e
n
c
e
r
e
p
o
r
t
:
S
y
s
t
e
m
l
o
g
a
n
a
l
y
si
s
f
o
r
a
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
1
6
I
E
EE
2
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
S
o
f
t
w
a
r
e
Re
l
i
a
b
i
l
i
t
y
E
n
g
i
n
e
e
ri
n
g
(
I
S
S
RE)
,
O
c
t
.
2
0
1
6
,
p
p
.
2
0
7
–
2
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
S
R
E.
2
0
1
6
.
2
1
.
[
2
6
]
D
.
O
p
r
e
a
a
n
d
G
.
B
r
e
w
st
e
r
,
“
I
mp
r
o
v
i
n
g
sea
r
c
h
l
a
t
e
n
c
y
i
n
l
a
r
g
e
-
s
c
a
l
e
l
o
g
i
n
d
e
x
i
n
g
s
y
s
t
e
ms
,
”
AC
M
S
I
G
O
P
S
O
p
e
ra
t
i
n
g
S
y
st
e
m
s
Re
v
i
e
w
,
v
o
l
.
5
3
,
n
o
.
1
,
p
p
.
1
5
–
2
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
8
3
5
8
3
.
3
3
8
3
5
8
8
.
[
2
7
]
A
.
G
a
i
n
a
r
u
,
F
.
C
a
p
p
e
l
l
o
,
M
.
S
n
i
r
,
a
n
d
W
.
K
r
a
mer
,
“
F
a
u
l
t
p
r
e
d
i
c
t
i
o
n
u
n
d
e
r
t
h
e
m
i
c
r
o
sc
o
p
e
:
A
c
l
o
s
e
r
l
o
o
k
i
n
t
o
H
P
C
sy
s
t
e
m
s,”
i
n
2
0
1
2
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
f
o
r
H
i
g
h
Pe
rf
o
rm
a
n
c
e
C
o
m
p
u
t
i
n
g
,
N
e
t
w
o
r
k
i
n
g
,
S
t
o
r
a
g
e
a
n
d
A
n
a
l
y
si
s
,
N
o
v
.
2
0
1
2
,
p
p
.
1
–
1
1
,
d
o
i
:
1
0
.
1
1
0
9
/
S
C
.
2
0
1
2
.
5
7
.
[
2
8
]
S
.
M
u
k
h
e
r
j
e
e
,
A
.
S
h
a
r
ma,
a
n
d
R
.
S
.
W
a
h
b
y
,
“
O
p
t
i
m
i
z
i
n
g
l
o
g
s
t
o
r
a
g
e
t
h
r
o
u
g
h
se
ma
n
t
i
c
d
e
d
u
p
l
i
c
a
t
i
o
n
,
”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
C
l
o
u
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
1
,
n
o
.
2
,
p
p
.
3
4
0
–
3
5
2
,
2
0
2
3
.
[
2
9
]
M
.
S
.
C
h
a
r
i
k
a
r
,
“
S
i
m
i
l
a
r
i
t
y
e
st
i
ma
t
i
o
n
t
e
c
h
n
i
q
u
e
s
f
r
o
m
r
o
u
n
d
i
n
g
a
l
g
o
r
i
t
h
ms,”
i
n
C
o
n
f
e
re
n
c
e
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
An
n
u
a
l
A
C
M
S
y
m
p
o
s
i
u
m
o
n
T
h
e
o
ry
o
f
C
o
m
p
u
t
i
n
g
,
2
0
0
2
,
p
p
.
3
8
0
–
3
8
8
,
d
o
i
:
1
0
.
1
1
4
5
/
5
0
9
9
0
7
.
5
0
9
9
6
5
.
[
3
0
]
R
o
y
a
l
T
h
a
i
G
o
v
e
r
n
m
e
n
t
G
a
z
e
t
t
e
,
C
o
m
p
u
t
e
r
C
ri
m
e
Ac
t
B
.
E.
2
5
5
0
(
2
0
0
7
)
a
n
d
Am
e
n
d
m
e
n
t
B.
E.
2
5
6
0
(
2
0
1
7
)
.
B
a
n
g
k
o
k
,
Th
a
i
l
a
n
d
,
2
0
1
7
.
[
3
1
]
K
.
S
h
v
a
c
h
k
o
,
H
.
K
u
a
n
g
,
S
.
R
a
d
i
a
,
a
n
d
R
.
C
h
a
n
s
l
e
r
,
“
T
h
e
H
a
d
o
o
p
d
i
s
t
r
i
b
u
t
e
d
f
i
l
e
sy
st
e
m,”
i
n
I
EE
E
M
S
S
T
,
2
0
1
0
,
p
p
.
1
–
1
0
,
d
o
i
:
1
0
.
1
1
0
9
/
M
S
S
T.
2
0
1
0
.
5
4
9
6
9
7
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Nutth
a
k
o
r
n
Ch
a
l
a
e
m
wo
n
g
wa
n
wa
s
b
o
r
n
in
S
u
k
h
o
t
h
a
i,
Th
a
i
lan
d
,
in
1
9
8
4
.
He
re
c
e
iv
e
d
th
e
B.
En
g
.
d
e
g
re
e
in
i
n
fo
rm
a
ti
o
n
a
n
d
c
o
m
m
u
n
ica
ti
o
n
tec
h
n
o
l
o
g
y
fro
m
M
a
e
F
a
h
Lu
a
n
g
U
n
iv
e
rsit
y
,
Ch
ian
g
Ra
i,
T
h
a
il
a
n
d
,
in
2
0
0
6
,
th
e
B.
S
c
i.
d
e
g
re
e
in
in
f
o
rm
a
ti
o
n
tec
h
n
o
lo
g
y
fro
m
Kin
g
M
o
n
g
k
u
t’s
Un
iv
e
rsity
o
f
Tec
h
n
o
lo
g
y
Th
o
n
b
u
ri,
Ba
n
g
k
o
k
,
Th
a
il
a
n
d
,
in
2
0
1
1
,
a
n
d
th
e
D.B.
A.
d
e
g
re
e
i
n
in
d
u
strial
b
u
sin
e
ss
fr
o
m
Ki
n
g
M
o
n
g
k
u
t’
s
Un
i
v
e
rsity
o
f
Tec
h
n
o
l
o
g
y
No
rth
Ba
n
g
k
o
k
,
Th
a
i
lan
d
,
i
n
2
0
2
5
.
He
is
c
u
rre
n
tl
y
a
lec
tu
re
r
wit
h
th
e
KO
S
EN
In
sti
tu
te,
Kin
g
M
o
n
g
k
u
t’s
I
n
stit
u
te
o
f
Tec
h
n
o
lo
g
y
La
d
k
ra
b
a
n
g
,
Ba
n
g
k
o
k
,
Th
a
il
a
n
d
.
He
h
a
s
a
c
a
d
e
m
ic
a
n
d
in
d
u
stry
e
x
p
e
rie
n
c
e
in
c
y
b
e
rse
c
u
rit
y
,
m
a
n
a
g
e
d
se
c
u
rit
y
se
rv
i
c
e
s,
a
n
d
d
i
g
it
a
l
w
o
rk
f
o
rc
e
d
e
v
e
lo
p
m
e
n
t.
His
re
se
a
rc
h
i
n
t
e
re
sts
in
c
lu
d
e
se
c
u
rit
y
o
p
e
ra
ti
o
n
s
c
e
n
ters
,
m
u
lt
i
-
ten
a
n
t
XD
R/S
IEM
a
rc
h
it
e
c
tu
re
s,
AI
-
d
r
i
v
e
n
S
OC
a
u
t
o
m
a
ti
o
n
,
a
n
d
a
p
p
li
e
d
m
a
c
h
in
e
lea
rn
i
n
g
f
o
r
t
h
re
a
t
d
e
tec
ti
o
n
.
He
h
a
s se
rv
e
d
a
s a
re
v
i
e
we
r
fo
r
p
e
e
r
-
re
v
iew
e
d
jo
u
rn
a
ls a
n
d
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
in
i
n
fo
rm
a
ti
o
n
se
c
u
rit
y
a
n
d
c
o
m
p
u
ter
e
n
g
in
e
e
rin
g
.
Ema
il
:
n
u
tt
h
a
k
o
rn
.
c
h
@k
m
it
l.
a
c
.
th
.
Evaluation Warning : The document was created with Spire.PDF for Python.