I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
AI
)
V
ol
.
14
, N
o.
3
,
J
une
2025
, pp.
1900
~
1909
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v
14
.i
3
.pp
1900
-
1909
1900
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
O
p
t
i
m
i
z
i
n
g r
e
al
-
t
i
m
e
d
at
a p
r
e
p
r
oc
e
ss
i
n
g i
n
Io
T
-
b
ase
d
f
og
c
om
p
u
t
i
n
g
u
si
n
g m
ac
h
i
n
e
l
e
ar
n
i
n
g al
gor
i
t
h
m
s
N
an
d
in
i
G
ow
d
a
P
u
t
t
as
w
am
y
1
, A
n
it
h
a N
ar
as
im
h
a M
u
r
t
h
y
2
1
D
e
pa
r
t
m
e
nt
of
C
om
put
e
r
S
c
i
e
nc
e
a
nd E
ngi
ne
e
r
i
ng, S
a
pt
ha
gi
r
i
C
ol
l
e
ge
of
E
ngi
ne
e
r
i
ng, B
e
nga
l
ur
u, I
ndi
a
2
D
e
pa
r
t
m
e
nt
of
C
om
put
e
r
S
c
i
e
nc
e
a
nd E
ngi
ne
e
r
i
ng, B
N
M
I
ns
t
i
t
ut
e
of
T
e
c
hnol
ogy, B
e
nga
l
ur
u, I
ndi
a
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
A
pr
30, 2024
R
e
vi
s
e
d
F
e
b 13, 2025
A
c
c
e
pt
e
d
M
a
r
15, 2025
In the era of t
he
internet of
things
(IoT), managin
g the mass
ive influx
of data
with
minimal
latency
is
crucial,
particularly
within
fog
com
puting
environm
ents
that
process
data
close
to
its
origin.
Traditio
nal
method
s
have
been inadequate, struggling with the high
variability and volume of
Io
T data,
which
often
leads
to
processing
inefficiencies
and
poor
resource
allo
cation.
To
address
these
challenges,
this
paper
introduces
a
novel
machine
le
arning
-
driven
approach
named
real
-
time
data
preprocessing
in
IoT
-
base
d
fog
computi
ng
using
machine
learning
algorit
h
ms
(IoT
-
FCML).
This
method
dynamically
adapts
to
the
changing
characteristics
of
data
and
system
demands.
The
implementation
of
IoT
-
FCML
has
led
to
sign
ificant
performance
enhancements:
it
reduces
latency
by
approximately
0.26%,
increase
s
throughput
by
up
to
0.3%,
improves
resourc
e
efficie
ncy
by
0.20%,
and
decreases
data
privacy
overhead
by
0.64%.
These
improveme
nts
are
achieved
through
the
integrat
ion
of
smart
algorit
hms
that
priorit
ize
data
privacy
and
e
fficient
resour
ce
use,
allowing
the
IoT
-
FCML
met
hod
to
surpass
traditional
preprocessing
techniques.
Collectively,
the
enhanc
ements
in
processing
speed,
adaptability,
and
data
security
repr
esent
a
subs
tantial
advancement
in
developi
ng
more
responsi
ve
and
efficient
IoT
-
bas
ed
fog
computi
ng infras
tructures,
marking
a pivot
al progres
sion i
n the fi
eld.
K
e
y
w
o
r
d
s
:
D
a
ta
pr
iv
a
c
y
D
yna
m
ic
a
da
pt
a
bi
li
ty
I
oT
f
og c
om
put
in
g
L
a
te
nc
y r
e
duc
ti
on
M
a
c
hi
ne
l
e
a
r
ni
ng a
lg
or
it
hm
s
R
e
a
l
-
ti
m
e
da
ta
pr
e
pr
oc
e
s
s
in
g
R
e
s
our
c
e
e
f
f
ic
ie
nc
y
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
N
a
ndi
ni
G
ow
da
P
ut
ta
s
w
a
m
y
D
e
pa
r
tm
e
nt
of
C
om
put
e
r
S
c
ie
nc
e
a
nd E
ngi
ne
e
r
in
g, S
a
pt
ha
gi
r
i
C
ol
le
ge
of
E
ngi
ne
e
r
in
g
B
e
nga
lu
r
u, I
ndi
a
E
m
a
il
:
na
ndi
ni
.e
duc
a
to
r
1@
gm
a
il
.c
om
1.
I
N
T
R
O
D
U
C
T
I
O
N
T
he
in
te
r
ne
t
of
th
in
gs
(
I
oT
)
ha
s
dr
a
m
a
ti
c
a
ll
y
tr
a
n
s
f
or
m
e
d
how
w
e
in
te
r
a
c
t
w
it
h
th
e
phys
ic
a
l
w
or
ld
,
in
te
gr
a
ti
ng
in
te
ll
ig
e
nc
e
in
to
e
ve
r
yda
y
obj
e
c
t
s
a
nd
e
n
a
bl
in
g
th
e
m
to
c
om
m
uni
c
a
te
a
nd
m
a
k
e
de
c
i
s
io
ns
.
T
hi
s
w
id
e
s
pr
e
a
d
a
dopt
io
n
of
I
oT
ha
s
le
d
to
th
e
ge
ne
r
a
ti
on
of
m
a
s
s
iv
e
a
m
ount
s
of
da
ta
a
t
th
e
e
dge
of
th
e
ne
twor
k,
ne
c
e
s
s
it
a
ti
ng
in
nova
ti
ve
a
ppr
oa
c
he
s
to
da
ta
pr
oc
e
s
s
i
ng
a
nd
m
a
na
ge
m
e
nt
.
F
og
c
om
put
in
g,
w
hi
c
h
e
xt
e
nds
c
lo
ud
c
om
put
in
g
to
th
e
e
dge
of
th
e
ne
twor
k,
ha
s
e
m
e
r
ge
d
a
s
a
pi
vot
a
l
t
e
c
hnol
ogy
in
th
is
c
ont
e
xt
.
I
t
a
im
s
to
r
e
duc
e
la
te
nc
y,
im
pr
ove
ba
ndw
id
th
ut
il
iz
a
ti
on,
a
nd
e
nha
nc
e
th
e
ov
e
r
a
ll
e
f
f
ic
ie
nc
y
of
I
oT
s
ys
t
e
m
s
by pr
oc
e
s
s
in
g da
ta
c
lo
s
e
r
t
o i
ts
s
our
c
e
[
1]
, [
2]
.
F
ig
ur
e
1
s
how
s
a
s
e
c
ur
it
y
a
r
c
hi
te
c
tu
r
e
in
vol
vi
ng
th
r
e
e
e
nt
it
ie
s
s
uc
h
a
s
th
e
u
s
e
r
,
a
c
lo
ud s
e
r
ve
r
,
a
nd
a
tr
us
te
d
th
ir
d
pa
r
ty
.
T
he
w
or
ki
ng
pr
in
c
ip
a
l
c
e
nt
e
r
s
a
r
ound
m
ut
ua
l
a
ut
he
nt
ic
a
ti
on,
a
s
e
c
ur
it
y
m
e
c
ha
ni
s
m
e
ns
ur
in
g
th
a
t
bot
h
th
e
us
e
r
a
nd
th
e
c
lo
ud
s
e
r
ve
r
ve
r
if
y
e
a
c
h
ot
he
r
'
s
id
e
nt
it
ie
s
be
f
or
e
in
it
ia
ti
ng
a
ny
c
om
m
uni
c
a
ti
on.
H
e
r
e
,
th
e
tr
us
te
d
th
ir
d
pa
r
ty
pl
a
ys
a
c
r
uc
ia
l
r
ol
e
,
pos
s
ib
ly
a
s
a
c
e
r
ti
f
ic
a
te
a
ut
hor
it
y
or
a
ut
he
nt
ic
a
ti
on s
e
r
ve
r
, t
ha
t
bot
h t
he
us
e
r
a
nd t
he
c
lo
ud
s
e
r
ve
r
t
r
u
s
t.
T
hi
s
e
nt
it
y c
oul
d f
a
c
il
it
a
te
t
he
e
xc
ha
nge
o
f
c
r
e
de
nt
ia
ls
or
c
r
ypt
ogr
a
phi
c
ke
y
s
th
a
t
e
na
bl
e
m
ut
ua
l
a
ut
he
n
ti
c
a
ti
on
[
3]
.
U
pon
s
uc
c
e
s
s
f
ul
a
ut
he
nt
ic
a
ti
on,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
O
pt
imi
z
in
g r
e
al
-
ti
m
e
dat
a pr
e
p
r
oc
e
s
s
in
g i
n I
oT
-
bas
e
d f
og c
om
p
ut
in
g us
in
g
…
(
N
andi
ni
G
ow
da P
ut
ta
s
w
am
y
)
1901
a
s
e
c
ur
e
c
ha
nne
l
is
e
s
ta
bl
is
h
e
d
be
twe
e
n
th
e
us
e
r
a
nd
th
e
c
lo
ud
s
e
r
ve
r
,
a
ll
ow
in
g
f
o
r
s
a
f
e
da
ta
e
xc
ha
nge
,
s
e
r
vi
c
e
r
e
que
s
ts
,
a
nd
tr
a
ns
a
c
ti
on
s
,
a
ll
unde
r
th
e
s
upe
r
vi
s
io
n
of
th
e
tr
us
te
d
th
ir
d
pa
r
ty
to
pr
e
ve
nt
una
ut
hor
iz
e
d
a
c
c
e
s
s
a
nd
e
ns
ur
e
da
ta
in
te
gr
it
y
a
nd
c
onf
id
e
nt
ia
li
ty
.
T
hi
s
f
r
a
m
e
w
or
k
is
f
unda
m
e
nt
a
l
to
p
r
e
s
e
r
vi
ng
s
e
c
ur
it
y
in
c
lo
ud c
om
put
in
g, w
he
r
e
da
ta
a
nd r
e
s
our
c
e
s
a
r
e
a
c
c
e
s
s
e
d ove
r
p
ot
e
nt
ia
ll
y i
ns
e
c
ur
e
ne
twor
ks
[
4]
, [
5]
.
F
ig
ur
e
1. F
unda
m
e
nt
a
l
a
r
c
hi
te
c
tu
r
e
of
f
og
c
om
put
in
g ne
twor
k
R
e
c
e
nt
tr
e
nds
in
I
oT
a
nd
f
og
c
om
put
in
g
hi
ghl
ig
ht
a
s
hi
f
t
to
w
a
r
ds
m
or
e
a
ut
onomous
,
in
te
ll
ig
e
nt
s
ys
te
m
s
c
a
pa
bl
e
of
r
e
a
l
-
ti
m
e
de
c
is
io
n
-
m
a
ki
ng.
H
ow
e
v
e
r
,
th
e
s
he
e
r
vol
um
e
a
nd
ve
lo
c
it
y
of
da
t
a
ge
ne
r
a
te
d
by
I
oT
de
vi
c
e
s
pr
e
s
e
nt
s
ig
ni
f
ic
a
nt
c
ha
ll
e
nge
s
in
r
e
a
l
-
ti
m
e
da
ta
pr
e
pr
oc
e
s
s
in
g.
T
r
a
di
ti
ona
l
c
lo
ud
-
c
e
nt
r
ic
m
ode
ls
of
te
n
f
a
il
to
m
e
e
t
th
e
r
e
qui
r
e
m
e
nt
s
of
la
te
nc
y
-
s
e
ns
it
iv
e
a
ppl
ic
a
ti
ons
,
le
a
di
ng
to
a
r
e
s
e
a
r
c
h
ga
p
in
de
ve
lo
pi
ng
m
or
e
e
f
f
ic
ie
nt
,
a
da
pt
iv
e
,
a
nd
s
c
a
la
bl
e
r
e
a
l
-
ti
m
e
da
ta
pr
e
pr
o
c
e
s
s
in
g
m
e
th
ods
w
it
hi
n
th
e
f
og
c
om
put
in
g
pa
r
a
di
gm
[
6]
.
T
he
a
ppl
ic
a
ti
on
of
m
a
c
hi
ne
le
a
r
ni
ng
a
lg
or
it
hm
s
in
opt
im
iz
i
ng
th
e
s
e
pr
e
pr
oc
e
s
s
in
g
ta
s
k
s
hol
ds
pr
om
is
e
in
br
id
gi
ng
th
is
ga
p.
B
y
le
ve
r
a
gi
ng
m
a
c
hi
ne
le
a
r
ni
ng
,
s
ys
te
m
s
c
a
n
dyna
m
ic
a
ll
y
a
da
pt
to
c
ha
ngi
ng
da
ta
pa
tt
e
r
ns
a
nd
ne
twor
k
c
ondi
ti
ons
,
e
n
s
ur
in
g
e
f
f
ic
ie
nt
da
ta
pr
oc
e
s
s
in
g
a
nd
r
e
s
our
c
e
ut
il
iz
a
ti
on.
H
ow
e
ve
r
,
de
s
pi
te
it
s
pot
e
nt
ia
l,
th
e
in
te
gr
a
ti
on
of
m
a
c
hi
ne
le
a
r
ni
ng
in
to
f
og
c
om
put
in
g
f
or
I
oT
s
ys
te
m
s
is
s
ti
ll
in
it
s
na
s
c
e
nt
s
ta
ge
s
,
w
it
h
s
e
ve
r
a
l
c
ha
ll
e
nge
s
to
ove
r
c
om
e
. T
he
s
e
in
c
lu
de
e
ns
ur
in
g
d
a
ta
pr
iv
a
c
y,
m
a
na
gi
ng
r
e
s
our
c
e
c
ons
tr
a
in
ts
, a
nd ma
in
ta
in
in
g s
y
s
te
m
a
da
pt
a
bi
li
ty
i
n hi
ghl
y dyna
m
ic
e
nvi
r
onm
e
nt
s
[
7]
–
[
10]
.
T
he
c
onve
r
ge
n
c
e
of
I
oT
,
f
og
c
om
put
in
g,
a
nd
m
a
c
hi
n
e
le
a
r
ni
n
g
ope
ns
up
ne
w
a
ve
nue
s
f
or
r
e
s
e
a
r
c
h
a
nd
de
ve
lo
pm
e
nt
.
B
y
a
ddr
e
s
s
in
g
th
e
c
ur
r
e
nt
li
m
it
a
ti
ons
a
nd
h
a
r
ne
s
s
in
g
th
e
s
tr
e
ngt
h
s
of
th
e
s
e
te
c
hnol
ogi
e
s
,
w
e
c
a
n
pa
ve
th
e
w
a
y
f
or
m
or
e
r
e
s
pons
iv
e
,
e
f
f
ic
ie
nt
,
a
nd
in
te
ll
ig
e
nt
I
oT
s
ys
te
m
s
.
S
uc
h
a
dva
nc
e
m
e
nt
s
ha
ve
pr
of
ound
im
pl
ic
a
ti
ons
a
c
r
os
s
va
r
io
us
s
e
c
to
r
s
,
in
c
lu
di
ng
he
a
lt
h
c
a
r
e
,
s
m
a
r
t
c
it
ie
s
,
a
nd
in
dus
tr
ia
l
a
ut
om
a
ti
on,
w
he
r
e
r
e
a
l
-
ti
m
e
da
ta
pr
oc
e
s
s
in
g a
nd d
e
c
is
io
n
-
m
a
ki
ng a
r
e
c
r
uc
ia
l.
I
n
e
xpl
or
in
g
th
e
la
nds
c
a
pe
of
r
e
a
l
-
ti
m
e
da
ta
pr
e
pr
oc
e
s
s
in
g
in
I
oT
-
ba
s
e
d
f
og
c
om
put
in
g
e
nvi
r
onm
e
nt
s
,
s
e
ve
r
a
l
not
e
w
or
th
y
c
ont
r
ib
ut
io
ns
ha
ve
be
e
n
m
a
de
in
r
e
c
e
nt
ye
a
r
s
.
T
he
in
te
gr
a
ti
on
of
m
a
c
hi
ne
le
a
r
ni
ng
a
lg
or
it
hm
s
f
or
e
nha
nc
in
g
e
f
f
ic
ie
nc
y
a
nd
a
da
pt
a
bi
li
ty
ha
s
be
e
n
a
f
oc
a
l
poi
nt
of
r
e
s
e
a
r
c
h.
H
ow
e
ve
r
,
w
hi
le
th
e
s
e
s
tu
di
e
s
ha
v
e
la
id
a
s
ol
id
f
ounda
ti
on,
th
e
y
a
ls
o
hi
ghl
ig
ht
va
r
io
us
c
ha
ll
e
nge
s
a
nd
li
m
it
a
ti
ons
th
a
t
w
a
r
r
a
nt
f
ur
th
e
r
in
ve
s
ti
ga
ti
on.
V
a
r
un
e
t
al
.
[
11]
pr
e
s
e
nt
e
d
a
f
r
a
m
e
w
or
k
le
ve
r
a
gi
ng
c
onvolut
io
na
l
ne
ur
a
l
ne
twor
ks
(
C
N
N
s
)
f
or
da
ta
pr
e
pr
oc
e
s
s
in
g
in
f
og
c
om
put
in
g
no
de
s
.
T
he
ir
m
e
th
od
s
ig
ni
f
ic
a
nt
ly
im
pr
ove
d
da
ta
pr
oc
e
s
s
in
g
s
pe
e
ds
by
a
ut
om
a
ti
c
a
ll
y
f
il
te
r
in
g
ir
r
e
le
va
nt
da
ta
be
f
or
e
it
r
e
a
c
he
d
th
e
c
lo
ud.
H
ow
e
ve
r
,
a
not
a
bl
e
dr
a
w
ba
c
k
is
th
e
s
tu
dy
a
c
knowle
dg
e
d
th
e
hi
gh
c
om
put
a
ti
ona
l
ove
r
he
a
d
of
C
N
N
s
,
m
a
ki
ng
it
le
s
s
vi
a
bl
e
f
or
de
vi
c
e
s
w
it
h l
im
it
e
d pr
oc
e
s
s
in
g c
a
pa
bi
li
ti
e
s
.
G
ow
r
is
ha
nka
r
e
t
a
l.
[
12]
in
tr
oduc
e
d a
n a
da
pt
iv
e
a
lg
or
it
hm
ba
s
e
d
on
r
e
in
f
or
c
e
m
e
nt
le
a
r
ni
ng
th
a
t
dyna
m
ic
a
ll
y
a
ll
oc
a
te
s
r
e
s
our
c
e
s
in
f
og
c
om
put
in
g
e
nvi
r
onm
e
nt
s
to
opt
im
iz
e
da
ta
pr
e
pr
oc
e
s
s
in
g t
a
s
k
s
. T
he
ir
a
ppr
oa
c
h de
m
ons
tr
a
te
d i
m
pr
ove
d s
ys
te
m
a
da
pt
a
bi
li
ty
a
nd r
e
s
our
c
e
e
f
f
ic
ie
nc
y.
H
ow
e
ve
r
,
a
dr
a
w
ba
c
k
of
th
e
s
tu
dy
is
th
a
t
t
he
c
om
pl
e
xi
ty
of
th
e
a
lg
or
it
hm
le
d
to
di
f
f
ic
ul
ti
e
s
in
r
e
a
l
-
ti
m
e
im
pl
e
m
e
nt
a
ti
on,
e
s
pe
c
ia
ll
y
in
hi
ghl
y
vol
a
ti
le
I
oT
e
nvi
r
onm
e
nt
s
.
M
a
r
kovi
ć
e
t
al
.
[
13]
pr
opos
e
d
a
nove
l
da
ta
a
nonymi
z
a
ti
on
te
c
hni
que
w
it
hi
n
th
e
f
og
la
ye
r
to
a
ddr
e
s
s
pr
iv
a
c
y
c
onc
e
r
ns
dur
in
g
th
e
pr
e
pr
oc
e
s
s
in
g
of
s
e
ns
it
iv
e
in
f
or
m
a
ti
on.
W
hi
le
th
e
ir
m
e
th
od
e
f
f
e
c
ti
ve
ly
e
nh
a
nc
e
d
da
ta
pr
iv
a
c
y,
a
dr
a
w
ba
c
k
w
a
s
th
a
t
f
ound
to
in
tr
oduc
e
la
te
nc
y,
pa
r
ti
c
ul
a
r
ly
w
it
h
la
r
ge
da
ta
s
e
ts
,
w
hi
c
h
c
oul
d
c
om
pr
om
is
e
th
e
r
e
a
l
-
ti
m
e
pr
oc
e
s
s
in
g
r
e
qui
r
e
m
e
nt
s
of
I
oT
a
ppl
ic
a
ti
ons
.
K
ha
n
e
t
al
.
[
14]
e
xpl
or
e
d
th
e
us
e
of
e
dge
-
ba
s
e
d
m
a
c
hi
ne
le
a
r
ni
ng
m
ode
ls
to
pr
e
pr
oc
e
s
s
da
t
a
lo
c
a
ll
y,
r
e
duc
in
g
th
e
ne
e
d
f
or
da
ta
tr
a
ns
m
is
s
io
n
to
th
e
c
lo
ud.
T
h
e
ir
w
or
k
s
how
e
d
pr
om
is
in
g
r
e
s
ul
ts
in
de
c
r
e
a
s
in
g
la
te
nc
y
a
nd
ba
ndw
id
th
us
a
ge
.
H
ow
e
ve
r
,
a
dr
a
w
ba
c
k
hi
gh
li
ght
e
d
in
th
e
s
tu
dy
w
a
s
th
e
c
ha
ll
e
nge
of
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
. 14, No.
3, J
une
2025
:
1900
-
1909
1902
m
a
in
ta
in
in
g m
ode
l
a
c
c
ur
a
c
y ove
r
t
im
e
w
it
hout
r
e
gul
a
r
upda
te
s
, w
hi
c
h c
oul
d r
e
qui
r
e
s
ig
ni
f
ic
a
nt
da
ta
t
r
a
ns
f
e
r
s
,
th
us
ne
ga
ti
ng
s
om
e
of
th
e
be
ne
f
it
s
.
S
a
r
a
va
na
n
e
t
al
.
[
15]
de
ve
lo
pe
d
a
di
s
tr
ib
ut
e
d
le
dge
r
te
c
hnol
ogy
(
D
L
T
)
-
ba
s
e
d
a
ppr
oa
c
h
f
or
s
e
c
ur
e
da
ta
pr
e
pr
oc
e
s
s
in
g
in
f
og
c
om
put
in
g,
a
im
in
g
to
im
pr
ove
bot
h
tr
a
ns
pa
r
e
nc
y
a
nd
s
e
c
ur
it
y.
W
hi
le
th
e
ir
s
ol
ut
io
n
e
f
f
e
c
ti
ve
ly
a
ddr
e
s
s
e
d
tr
us
t
is
s
u
e
s
,
a
dr
a
w
ba
c
k
w
a
s
th
a
t
it
in
tr
oduc
e
d
s
ubs
ta
nt
ia
l
c
om
put
a
ti
ona
l
a
nd
s
to
r
a
ge
ove
r
he
a
d,
que
s
ti
oni
ng
it
s
s
c
a
la
bi
li
ty
in
la
r
ge
r
I
oT
de
pl
oym
e
nt
s
.
T
he
s
e
s
tu
di
e
s
il
lu
s
tr
a
te
th
e
dyna
m
ic
a
nd
e
vol
vi
ng
na
tu
r
e
of
r
e
s
e
a
r
c
h
in
r
e
a
l
-
ti
m
e
da
ta
pr
e
pr
oc
e
s
s
in
g
w
it
hi
n
I
oT
-
ba
s
e
d
f
og
c
om
put
in
g
e
nvi
r
onm
e
nt
s
.
T
he
y
unde
r
s
c
or
e
th
e
c
r
it
ic
a
l
ba
la
n
c
e
be
twe
e
n
e
nh
a
nc
in
g
pr
oc
e
s
s
in
g
e
f
f
ic
ie
nc
y,
e
ns
ur
in
g
pr
iv
a
c
y
a
nd
s
e
c
ur
it
y,
a
nd
m
a
in
ta
in
in
g
s
ys
te
m
a
d
a
pt
a
bi
li
ty
a
nd
s
c
a
la
bi
li
ty
.
A
s
s
uc
h,
th
e
y
hi
ghl
ig
ht
th
e
ne
e
d f
or
i
nnova
ti
ve
s
ol
ut
io
ns
t
ha
t
c
a
n a
ddr
e
s
s
t
he
s
e
m
ul
ti
f
a
c
e
te
d c
ha
ll
e
nge
s
i
n a
hol
is
ti
c
m
a
nn
e
r
.
2.
P
R
O
P
O
S
E
D
M
E
T
H
O
D
F
ig
ur
e
2
s
how
s
th
e
pr
opos
e
d
m
e
th
odol
ogy,
to
e
s
ta
bl
is
h
a
m
ul
ti
-
ti
e
r
e
d
I
oT
-
ba
s
e
d
f
og
c
om
put
in
g
m
ode
l.
D
a
ta
c
ol
le
c
ti
on
c
om
m
e
nc
e
s
w
it
h
ha
r
ve
s
ti
ng
r
a
w
in
put
s
f
r
om
I
oT
de
vi
c
e
s
,
s
im
ul
a
ti
ng
a
hi
gh
-
ve
lo
c
it
y
da
ta
s
tr
e
a
m
.
T
he
pr
e
pr
oc
e
s
s
in
g
pha
s
e
in
vol
ve
s
a
lg
or
it
hm
ic
noi
s
e
f
il
te
r
in
g,
f
e
a
tu
r
e
e
xt
r
a
c
ti
on,
a
nd
nor
m
a
li
z
a
ti
on
to
pr
e
pa
r
e
da
ta
s
e
ts
f
or
m
a
c
hi
ne
le
a
r
ni
ng
a
ppl
ic
a
ti
on
[
16]
,
[
17]
.
W
e
s
e
le
c
t
m
a
c
hi
ne
le
a
r
ni
ng
a
lg
or
it
hm
s
s
ui
te
d
to
r
e
a
l
-
ti
m
e
a
na
ly
ti
c
s
,
e
m
ph
a
s
iz
in
g
de
c
is
io
n
e
f
f
ic
ie
nc
y
a
nd
c
om
put
a
ti
ona
l
li
ght
ne
s
s
.
S
upe
r
vi
s
e
d
le
a
r
ni
ng
m
ode
ls
a
r
e
tr
a
in
e
d
on
a
pa
r
ti
ti
one
d
da
t
a
s
e
t,
e
m
pl
oyi
ng
c
r
os
s
-
va
li
da
ti
on
to
m
it
ig
a
te
ove
r
f
it
ti
ng w
hi
le
opt
im
iz
in
g pe
r
f
o
r
m
a
nc
e
pa
r
a
m
e
te
r
s
[
18]
–
[
20]
.
F
ig
ur
e
2. T
he
pr
opos
e
d m
e
th
odol
ogy of
r
e
a
l
-
ti
m
e
da
ta
pr
e
pr
oc
e
s
s
in
g i
n I
oT
-
ba
s
e
d f
og c
om
put
in
g u
s
in
g
m
a
c
hi
ne
l
e
a
r
ni
ng a
lg
or
it
hm
s
(
I
oT
-
F
C
M
L
)
P
os
t
-
tr
a
in
in
g,
m
a
c
hi
ne
le
a
r
ni
ng
m
ode
ls
a
r
e
e
m
be
dd
e
d
w
it
hi
n
f
og
node
s
.
T
he
ir
pe
r
f
or
m
a
nc
e
i
s
a
s
s
e
s
s
e
d
th
r
ough
ke
y
m
e
tr
ic
s
:
la
te
n
c
y,
th
r
oughput,
a
nd
r
e
s
our
c
e
a
ll
oc
a
ti
on.
T
he
s
e
a
r
e
be
n
c
hm
a
r
ke
d
a
ga
in
s
t
c
onve
nt
io
na
l
pr
e
pr
oc
e
s
s
in
g
pa
r
a
di
gm
s
to
e
va
lu
a
te
th
e
e
f
f
ic
a
c
y
a
nd
im
pr
ove
m
e
nt
s
our
m
a
c
hi
ne
le
a
r
ni
ng
-
dr
iv
e
n
m
e
th
od
of
f
e
r
s
.
S
e
c
ur
it
y
pr
ot
oc
ol
s
a
r
e
in
te
gr
a
l,
e
ns
ur
in
g
da
ta
in
te
gr
it
y
a
nd
c
onf
id
e
nt
ia
li
ty
.
T
he
s
ys
te
m
unde
r
goe
s
it
e
r
a
ti
ve
opt
im
iz
a
ti
on,
r
e
s
pons
iv
e
to
e
m
pi
r
ic
a
l
d
a
ta
a
nd
u
s
e
r
-
c
e
nt
r
ic
f
e
e
dba
c
k,
s
tr
iv
in
g
f
or
e
nha
nc
e
d ope
r
a
ti
ona
l
e
x
c
e
ll
e
nc
e
w
it
hi
n t
he
f
og c
om
put
in
g s
phe
r
e
[
21]
–
[
23]
.
2.1
.
P
r
op
os
e
d
I
o
T
-
F
C
M
L
F
ig
ur
e
3
s
how
s
th
e
pr
e
s
e
nt
s
a
hi
e
r
a
r
c
hi
c
a
l
s
tr
uc
tu
r
e
th
a
t
in
t
e
gr
a
te
s
th
e
I
oT
,
f
og
c
om
put
in
g,
a
nd
c
lo
ud
c
om
put
in
g
to
opt
im
iz
e
da
ta
pr
e
pr
oc
e
s
s
in
g.
I
oT
de
vi
c
e
s
a
t
th
e
bot
to
m
la
ye
r
ge
ne
r
a
te
da
ta
,
w
hi
c
h
is
f
ir
s
t
tr
a
ns
m
it
te
d t
o t
he
f
og l
a
ye
r
, s
pe
c
if
ic
a
ll
y t
o m
ic
r
o da
ta
c
e
nt
e
r
s
.
T
he
s
e
c
e
nt
e
r
s
a
r
e
e
qui
ppe
d w
it
h a
n I
oT
-
F
C
M
L
m
ode
l,
de
s
ig
ne
d
to
pr
e
pr
oc
e
s
s
th
e
da
ta
e
f
f
ic
ie
nt
ly
in
r
e
a
l
-
ti
m
e
.
T
he
pr
e
pr
oc
e
s
s
in
g
in
c
lu
de
s
noi
s
e
r
e
duc
ti
on,
nor
m
a
li
z
a
ti
on, a
nd f
e
a
tu
r
e
e
xt
r
a
c
ti
on t
o pr
e
pa
r
e
da
ta
f
or
a
na
ly
s
i
s
.
O
nc
e
pr
e
pr
oc
e
s
s
e
d,
th
e
da
ta
i
s
pa
s
s
e
d
th
r
ough
a
n
opt
im
iz
a
t
io
n
a
lg
or
it
hm
w
it
hi
n
th
e
f
og
la
ye
r
,
e
ns
ur
in
g
th
e
pr
e
pr
oc
e
s
s
in
g
i
s
tu
ne
d
f
or
th
e
be
s
t
pe
r
f
or
m
a
nc
e
r
e
ga
r
di
ng
s
pe
e
d
a
nd
a
c
c
ur
a
c
y.
T
hi
s
s
te
p
i
s
c
r
uc
ia
l
f
or
a
da
pt
in
g
to
th
e
va
r
ia
bl
e
na
tu
r
e
o
f
I
oT
-
ge
ne
r
a
te
d
d
a
ta
a
nd
s
ys
te
m
de
m
a
nds
[
24]
,
[
25]
.
A
f
te
r
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
O
pt
imi
z
in
g r
e
al
-
ti
m
e
dat
a pr
e
p
r
oc
e
s
s
in
g i
n I
oT
-
bas
e
d f
og c
om
p
ut
in
g us
in
g
…
(
N
andi
ni
G
ow
da P
ut
ta
s
w
am
y
)
1903
opt
im
iz
a
ti
on,
th
e
pr
oc
e
s
s
e
d
d
a
ta
c
a
n
be
s
e
nt
to
th
e
c
lo
ud
da
ta
c
e
nt
e
r
f
or
f
ur
th
e
r
a
na
ly
s
is
or
lo
ng
-
te
r
m
s
to
r
a
ge
.
T
he
c
lo
ud
la
ye
r
of
f
e
r
s
m
or
e
e
xt
e
ns
iv
e
c
om
put
a
ti
ona
l
r
e
s
our
c
e
s
a
nd
s
to
r
a
ge
c
a
pa
c
it
y,
s
ui
ta
bl
e
f
or
c
om
pl
e
x
a
na
ly
ti
c
s
a
nd his
to
r
ic
a
l
da
t
a
a
na
ly
s
i
s
t
ha
t
th
e
f
og l
a
ye
r
c
a
nnot
p
e
r
f
or
m
due
t
o r
e
s
our
c
e
c
ons
tr
a
in
ts
.
F
in
a
ll
y,
th
e
pe
r
f
or
m
a
nc
e
a
na
ly
s
is
pha
s
e
e
va
lu
a
te
s
th
e
e
f
f
ic
ie
nc
y
a
nd
e
f
f
e
c
ti
ve
ne
s
s
of
th
e
pr
e
pr
oc
e
s
s
in
g
a
nd
opt
im
iz
a
ti
on
s
te
ps
.
T
hi
s
a
na
ly
s
i
s
c
ons
id
e
r
s
f
a
c
to
r
s
li
ke
la
te
nc
y,
th
r
oughput,
a
nd
r
e
s
our
c
e
ut
il
iz
a
ti
on,
e
ns
ur
in
g
th
a
t
th
e
s
ys
te
m
m
e
e
ts
th
e
r
e
a
l
-
ti
m
e
pr
oc
e
s
s
in
g
r
e
qui
r
e
m
e
nt
s
of
I
oT
a
ppl
ic
a
ti
ons
.
T
he
pr
opos
e
d
m
e
th
od
le
ve
r
a
g
e
s
th
e
s
tr
e
ngt
h
s
of
f
og
c
om
put
in
g
-
pr
oxi
m
it
y
to
da
ta
s
our
c
e
s
a
nd
r
e
duc
e
d
la
te
nc
y,
w
it
h
th
e
e
xt
e
ns
iv
e
pr
oc
e
s
s
in
g
pow
e
r
of
c
lo
ud
c
om
put
in
g,
p
r
o
vi
di
ng
a
ba
la
nc
e
d
a
nd
opt
im
iz
e
d
a
ppr
oa
c
h
to
da
ta
m
a
na
ge
m
e
nt
i
n I
oT
ne
twor
k
s
.
F
ig
ur
e
3. P
r
opos
e
d I
oT
-
F
C
M
L
2
.
2
.
P
r
op
os
e
d
m
at
h
e
m
at
ic
al
e
q
u
at
io
n
s
T
he
pr
opos
e
d
m
od
e
ls
a
na
ly
z
e
th
e
m
o
s
t
c
r
it
ic
a
l
pa
r
a
m
e
te
r
s
of
s
ys
te
m
de
m
a
nd,
la
te
nc
y,
pr
oc
e
s
s
in
g
c
a
pa
c
it
y,
da
ta
pr
iv
a
c
y,
a
nd
r
e
s
our
c
e
ut
il
iz
a
ti
on
in
r
e
a
l
-
ti
m
e
f
o
g
c
om
put
in
g
-
ba
s
e
d
I
oT
.
S
uc
h
m
ode
ls
s
uppor
t
dyna
m
ic
r
e
s
our
c
e
s
ha
r
in
g,
r
e
duc
e
d
e
la
y,
a
nd
pr
oc
e
s
s
da
t
a
e
f
f
ic
ie
nt
ly
w
it
h
th
e
he
lp
of
opt
im
iz
a
ti
on
th
r
ough
m
a
c
hi
ne
l
e
a
r
ni
ng. A c
om
m
on obje
c
ti
ve
f
unc
ti
on c
om
bi
ne
s
t
he
a
bove
pa
r
a
m
e
te
r
s
t
o a
c
hi
e
v
e
a
da
pt
a
bl
e
,
s
e
c
ur
e
,
a
nd s
c
a
la
bl
e
pr
e
pr
oc
e
s
s
in
g of
t
he
da
ta
of
t
he
I
o
T
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
. 14, No.
3, J
une
2025
:
1900
-
1909
1904
2
.
2
.1.
S
ys
t
e
m
d
e
m
an
d
m
od
e
l
T
he
s
ys
te
m
de
m
a
nd
m
ode
l
c
a
lc
ul
a
te
s
th
e
to
ta
l
da
ta
de
m
a
nd
f
r
om
a
ll
I
oT
de
vi
c
e
s
a
t
a
gi
ve
n
ti
m
e
,
e
na
bl
in
g
dyna
m
ic
r
e
s
our
c
e
a
ll
oc
a
ti
on
in
th
e
f
og
c
om
put
in
g
la
ye
r
to
a
ddr
e
s
s
r
e
a
l
-
ti
m
e
pr
oc
e
s
s
in
g
ne
e
ds
e
f
f
ic
ie
nt
ly
. T
he
s
ys
te
m
d
e
m
a
nd mode
l
a
s
gi
v
e
n i
n (
1)
.
(
)
=
∑
(
)
=
1
(
1)
W
he
r
e
(
)
is
th
e
t
ot
a
l
s
ys
te
m
d
e
m
a
nd a
t
ti
m
e
,
a
nd
(
)
is
t
he
de
m
a
nd of
t
he
ℎ
I
oT
de
vi
c
e
a
t
ti
m
e
.
2
.
2
.2.
L
at
e
n
c
y m
od
e
l
T
he
la
te
nc
y
m
ode
l
br
e
a
ks
dow
n
to
ta
l
s
ys
te
m
la
te
nc
y
in
to
c
om
pone
nt
s
a
tt
r
ib
ut
e
d
to
f
og
c
om
put
in
g
,
ne
twor
k
tr
a
ns
m
is
s
io
n,
a
nd
c
lo
ud
pr
oc
e
s
s
in
g.
M
in
im
iz
in
g
th
is
la
te
nc
y
is
vi
ta
l
f
or
r
e
a
l
-
ti
m
e
a
ppl
ic
a
ti
ons
,
e
ns
ur
in
g
s
w
if
t
da
ta
pr
oc
e
s
s
in
g
a
nd
ti
m
e
ly
d
e
c
is
io
n
-
m
a
ki
ng
w
it
hi
n
th
e
I
oT
in
f
r
a
s
tr
uc
tu
r
e
.
T
h
e
la
te
nc
y
of
pr
opos
e
d m
ode
l
is
c
a
lc
ul
a
t
e
d by us
in
g (
2)
.
=
+
+
(
2)
W
he
r
e
is
th
e
to
ta
l
la
te
nc
y,
is
th
e
pr
oc
e
s
s
in
g
la
te
nc
y
in
th
e
f
og
la
ye
r
,
is
th
e
ne
twor
k
la
te
n
c
y,
a
nd
is
th
e
pr
oc
e
s
s
in
g
la
te
nc
y
in
th
e
c
lo
ud
la
ye
r
.
T
he
goa
l
is
t
o
m
in
im
iz
e
L
,
e
s
pe
c
ia
ll
y
a
s
it
'
s
th
e
f
ir
s
t
pr
oc
e
s
s
in
g l
a
ye
r
f
or
r
e
a
l
-
ti
m
e
da
ta
.
2
.
2
.3. T
h
r
ou
gh
p
u
t
m
od
e
l
T
he
th
r
oug
hput
m
ode
l
a
s
s
e
s
s
e
s
th
e
vol
um
e
of
da
t
a
pr
o
c
e
s
s
e
d
p
e
r
uni
t
of
t
im
e
a
nd
r
e
s
our
c
e
,
pr
o
vi
di
ng
a
m
e
a
s
ur
e
of
th
e
s
y
s
t
e
m
’
s
e
f
f
ic
i
e
nc
y
.
E
nha
n
c
in
g
th
r
ough
put
i
s
ke
y
to
ha
ndl
in
g
th
e
va
s
t
s
tr
e
a
m
s
of
I
oT
da
t
a
s
w
if
tl
y
a
nd
e
f
f
e
c
ti
ve
ly
i
n f
og c
om
put
in
g e
n
vi
r
onm
e
nt
s
.
T
he
th
r
o
ughput of
pr
opo
s
e
d m
od
e
l
i
s
gi
v
e
n i
n
(
3)
.
=
1
×
(
3)
W
he
r
e
is
t
he
t
hr
oughput,
is
t
he
vol
um
e
of
pr
oc
e
s
s
e
d da
ta
, a
nd
is
t
he
a
va
il
a
bl
e
r
e
s
our
c
e
s
. M
a
xi
m
iz
in
g
in
di
c
a
te
s
i
m
pr
ove
d s
ys
t
e
m
pe
r
f
or
m
a
nc
e
.
2
.
2
.4. D
at
a p
r
iv
ac
y m
od
e
l
T
he
da
ta
pr
iv
a
c
y
m
ode
l
e
n
s
ur
e
s
th
e
c
onf
id
e
nt
ia
li
ty
of
I
oT
da
ta
by
a
ppl
yi
ng
e
nc
r
ypt
io
n
a
lg
or
it
hm
s
be
f
or
e
pr
oc
e
s
s
in
g
or
tr
a
ns
m
is
s
io
n.
T
hi
s
s
te
p
is
e
s
s
e
nt
ia
l
f
or
m
a
in
ta
in
in
g
us
e
r
tr
us
t
a
nd
c
om
pl
yi
ng
w
it
h
da
ta
pr
ot
e
c
ti
on r
e
gul
a
ti
ons
w
it
hi
n t
he
f
og c
om
put
in
g f
r
a
m
e
w
or
k. D
a
ta
pr
iv
a
c
y m
ode
l
a
s
gi
ve
n i
n (
4)
.
(
)
=
(
,
)
(
4)
W
he
r
e
(
)
is
th
e
pr
iv
a
c
y
-
pr
e
s
e
r
vi
ng
f
unc
ti
on
f
or
da
ta
f
r
om
th
e
ℎ
I
oT
de
vi
c
e
,
a
nd
is
th
e
e
nc
r
ypt
io
n
ke
y.
T
hi
s
e
qua
ti
on
doe
s
n'
t
di
r
e
c
tl
y
r
e
duc
e
la
te
nc
y
or
im
p
r
ove
th
r
oughput
bu
t
is
e
s
s
e
nt
ia
l
f
or
e
ns
ur
in
g
da
ta
c
onf
id
e
nt
ia
li
ty
.
2
.
2
.5. R
e
s
ou
r
c
e
e
f
f
ic
ie
n
c
y
m
od
e
l
T
he
r
e
s
our
c
e
e
f
f
ic
ie
nc
y
m
ode
l
e
va
lu
a
t
e
s
how
e
f
f
e
c
ti
ve
ly
th
e
f
og
c
om
put
in
g
r
e
s
our
c
e
s
a
r
e
ut
il
iz
e
d
in
r
e
la
ti
on
to
th
e
ir
f
ul
l
c
a
pa
c
it
y.
I
t
a
im
s
to
m
a
xi
m
iz
e
th
e
pr
oc
e
s
s
in
g
out
put
w
hi
le
a
voi
di
ng
r
e
s
our
c
e
ove
r
us
e
,
e
ns
ur
in
g a
s
us
ta
in
a
bl
e
a
nd ba
la
n
c
e
d w
or
kl
oa
d di
s
tr
ib
ut
io
n, t
he
r
e
s
our
c
e
s
e
f
f
ic
ie
nc
y i
s
c
a
lc
ul
a
t
e
d us
in
g (
5)
.
=
(
5)
W
he
r
e
is
th
e
e
f
f
ic
ie
nc
y,
is
th
e
ut
il
iz
a
ti
on
of
r
e
s
our
c
e
s
,
a
nd
is
th
e
to
ta
l
a
va
il
a
bl
e
r
e
s
our
c
e
s
.
s
houl
d
be
m
a
xi
m
iz
e
d unde
r
t
he
c
ons
tr
a
in
t
th
a
t
≤
, e
ns
ur
in
g no r
e
s
our
c
e
i
s
o
ve
r
-
ut
il
iz
e
d.
2
.
2
.6. Op
t
im
iz
at
io
n
f
u
n
c
t
io
n
T
h
e
opt
im
i
z
a
ti
on
f
un
c
ti
on i
s
a
m
a
th
e
m
a
t
ic
a
l
f
or
m
ul
a
ti
on a
im
e
d a
t
m
in
i
m
i
z
in
g
l
a
t
e
n
c
y
a
nd ma
xi
m
iz
in
g
th
r
o
ugh
put
a
nd
r
e
s
our
c
e
e
f
f
i
c
i
e
n
c
y
.
I
t
s
e
r
v
e
s
a
s
t
he
g
ui
d
in
g
pr
in
c
i
pl
e
f
o
r
t
he
pr
op
os
e
d
s
y
s
t
e
m
'
s
r
e
s
our
c
e
m
a
n
a
g
e
m
e
n
t
a
n
d
o
pe
r
a
t
io
na
l
a
dj
us
tm
e
nt
s
in
r
e
a
l
-
ti
m
e
,
t
he
pr
opo
s
e
d
op
ti
m
i
z
a
ti
on
f
un
c
t
io
n
i
s
gi
ve
n
i
n
(
6)
.
O
bj
e
c
ti
ve
:
m
in
im
iz
e
a
nd ma
xi
m
iz
e
a
nd E
s
ubj
e
c
t
to
(
)
a
nd
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
O
pt
imi
z
in
g r
e
al
-
ti
m
e
dat
a pr
e
p
r
oc
e
s
s
in
g i
n I
oT
-
bas
e
d f
og c
om
p
ut
in
g us
in
g
…
(
N
andi
ni
G
ow
da P
ut
ta
s
w
am
y
)
1905
(
−
−
)
(
6)
W
he
r
e
,
,
a
r
e
w
e
ig
ht
in
g
f
a
c
to
r
s
in
di
c
a
ti
ng
th
e
im
por
ta
nc
e
of
e
a
c
h
obj
e
c
ti
ve
(
la
te
nc
y,
th
r
oughput,
a
nd
e
f
f
ic
ie
nc
y)
.
2
.
3
.
P
r
op
os
e
d
op
t
im
iz
in
g r
e
al
-
t
im
e
d
at
a p
r
e
p
r
oc
e
s
s
in
g i
n
I
o
T
-
b
as
e
d
f
og c
o
m
p
u
t
in
g u
s
in
g m
ac
h
in
e
le
ar
n
in
g al
gor
it
h
m
s
C
r
e
a
ti
ng
a
n
ove
r
a
r
c
hi
ng
m
a
th
e
m
a
ti
c
a
l
e
qua
ti
on
th
a
t
e
nc
a
ps
ul
a
te
s
th
e
opt
im
iz
a
ti
on
of
I
oT
r
e
a
l
-
ti
m
e
da
ta
pr
e
pr
oc
e
s
s
in
g us
in
g m
a
c
hi
ne
l
e
a
r
ni
ng, while
t
a
ki
ng i
nt
o a
c
c
ount
f
a
c
to
r
s
s
uc
h a
s
s
ys
te
m
de
m
a
nd, l
a
t
e
nc
y,
th
r
oughput,
da
ta
pr
iv
a
c
y,
a
nd
r
e
s
our
c
e
e
f
f
ic
ie
nc
y,
in
vol
ve
s
s
ynt
he
s
iz
in
g
th
e
in
di
vi
dua
l
obj
e
c
ti
ve
s
in
to
a
s
in
gul
a
r
obj
e
c
ti
ve
f
unc
ti
on.
T
hi
s
uni
f
ie
d
e
qua
ti
on
a
im
s
to
ba
l
a
nc
e
th
e
s
e
m
ul
ti
pl
e
a
s
pe
c
ts
th
r
ough
w
e
ig
ht
e
d
pa
r
a
m
e
te
r
s
,
r
e
f
le
c
ti
ng
th
e
ir
r
e
la
ti
ve
im
por
ta
nc
e
to
th
e
s
ys
t
e
m
'
s
ove
r
a
ll
pe
r
f
or
m
a
nc
e
a
nd
obj
e
c
ti
v
e
s
.
O
pt
im
iz
e
pr
opos
e
d a
lg
or
it
hm
a
s
c
a
lc
ul
a
te
d u
s
in
g (
7)
.
O
p
t
im
iz
e
(
)
=
1
×
(
1
∑
=
0
)
+
2
∑
+
3
∑
−
=
0
4
∑
(
)
−
5
∑
(
)
=
0
=
0
=
0
(
7)
,
,
,
a
nd
(
)
now
r
e
pr
e
s
e
nt
th
e
la
te
nc
y,
th
r
oughput,
r
e
s
our
c
e
e
f
f
ic
i
e
nc
y,
s
ys
te
m
de
m
a
nd,
a
nd
c
os
t
of
pr
iv
a
c
y
f
or
th
e
ℎ
I
oT
de
vi
c
e
,
r
e
s
pe
c
ti
ve
ly
.
T
he
s
um
s
∑
.
=
0
a
ggr
e
ga
te
th
e
c
ont
r
ib
ut
io
ns
of
e
a
c
h
de
vi
c
e
f
r
om
th
e
0t
h
to
th
e
n
th
,
of
f
e
r
in
g
a
c
om
pr
e
he
ns
iv
e
vi
e
w
of
th
e
e
nt
ir
e
I
oT
e
c
os
ys
te
m
.
T
he
opt
im
iz
a
ti
on
obj
e
c
ti
ve
(
)
now
di
r
e
c
tl
y
a
c
c
ount
s
f
or
th
e
pe
r
f
or
m
a
nc
e
a
nd
de
m
a
nds
of
e
a
c
h
in
di
vi
dua
l
de
vi
c
e
,
e
ns
ur
in
g
th
a
t
th
e
opt
im
iz
a
ti
on s
tr
a
te
gy i
s
e
f
f
e
c
ti
ve
a
c
r
os
s
t
he
e
nt
ir
e
ne
tw
or
k of
I
oT
de
vi
c
e
s
.
3.
R
E
S
U
L
T
S
A
N
D
D
I
S
C
U
S
S
I
O
N
T
a
bl
e
1
pr
e
s
e
nt
s
th
e
s
im
ul
a
ti
on
pa
r
a
m
e
te
r
s
e
s
s
e
nt
ia
l
f
or
e
va
lu
a
ti
ng
th
e
pr
opos
e
d
opt
im
iz
a
ti
on
m
e
th
od
in
I
oT
-
ba
s
e
d
f
og
c
om
put
in
g.
I
t
s
pe
c
if
ie
s
th
e
num
be
r
of
I
oT
de
vi
c
e
s
,
th
e
ir
da
ta
ge
ne
r
a
ti
on
r
a
te
s
,
la
te
nc
y
ta
r
ge
ts
,
r
e
s
our
c
e
c
a
pa
c
it
ie
s
of
f
og
node
s
,
a
nd
pr
iv
a
c
y
c
ons
tr
a
in
ts
th
r
ough
e
nc
r
ypt
io
n
ove
r
he
a
ds
.
T
he
s
e
p
a
r
a
m
e
te
r
s
a
r
e
pi
vot
a
l
f
or
a
s
s
e
s
s
in
g
th
e
m
e
th
od'
s
im
pa
c
t
on
s
ys
te
m
pe
r
f
or
m
a
nc
e
,
in
c
lu
di
ng
pr
oc
e
s
s
in
g
e
f
f
ic
ie
nc
y a
nd da
ta
s
e
c
ur
it
y.
T
a
bl
e
1. S
im
ul
a
ti
on pa
r
a
m
e
te
r
f
or
e
va
lu
a
ti
on of
pr
opos
e
d opti
m
iz
a
ti
on me
th
od
S
I
. N
o
D
e
s
c
r
i
pt
i
on
V
a
l
ue
s
1
N
um
be
r
of
I
oT
de
vi
c
e
s
150
2
D
a
t
a
ge
ne
r
a
t
i
on r
a
t
e
(
K
B
/
s
/
de
vi
c
e
)
100 K
B
/
s
3
L
a
t
e
nc
y
r
e
qui
r
e
m
e
nt
s
(
m
s
)
100
ms
4
R
e
s
our
c
e
limits
2 G
H
z
C
P
U
, 4 G
B
R
A
M
pe
r
f
og node
5
P
r
i
va
c
y
c
ons
t
r
a
i
nt
s
(
E
nc
r
ypt
i
on
ove
r
he
a
d
m
s
)
5
-
20
ms
T
a
bl
e
2
de
m
ons
tr
a
te
s
th
a
t
th
e
pr
opos
e
d
opt
im
iz
a
ti
on
m
e
th
od
s
ur
pa
s
s
e
s
th
e
c
onv
e
nt
io
na
l
m
e
th
ods
a
c
r
os
s
a
ll
e
va
lu
a
te
d pe
r
f
or
m
a
nc
e
m
e
tr
ic
s
. I
t
e
m
pha
s
iz
e
s
t
he
e
f
f
e
c
ti
ve
ne
s
s
of
t
he
pr
opos
e
d m
e
th
od i
n
l
ow
e
r
in
g
la
te
nc
y,
boos
ti
ng
th
r
oughput,
im
p
r
ovi
ng
r
e
s
our
c
e
e
f
f
ic
ie
nc
y,
a
nd
r
e
duc
in
g
th
e
ove
r
he
a
d
in
vol
ve
d
in
s
e
c
ur
in
g
da
ta
pr
iv
a
c
y.
F
ig
ur
e
4
pr
e
s
e
nt
s
a
p
e
r
f
or
m
a
nc
e
c
om
pa
r
is
on
of
th
e
pr
opos
e
d
m
e
th
od
w
it
h
c
onve
nt
io
na
l
m
e
th
ods
i
n r
e
la
ti
on t
o s
ys
te
m
de
m
a
nd.
T
a
bl
e
2. P
e
r
f
or
m
a
nc
e
a
na
ly
s
i
s
c
om
pa
r
in
g s
y
s
te
m
de
m
a
nd ha
ndl
in
g
P
e
r
f
or
m
a
nc
e
m
e
t
r
i
c
P
r
opos
e
d opt
i
m
i
z
a
t
i
on
m
e
t
hod
S
t
a
t
i
c
r
e
s
our
c
e
a
l
l
oc
a
t
i
on
B
a
s
i
c
m
a
c
hi
ne
l
e
a
r
ni
ng
opt
i
m
i
z
a
t
i
on
T
r
a
di
t
i
ona
l
f
og
c
om
put
i
ng
L
a
t
e
nc
y (
m
s
)
75
95
100
110
T
hr
oughput
(
K
B
/
s
)
1
,
500
1
,
150
1
,
200
1
,
000
R
e
s
our
c
e
e
f
f
i
c
i
e
nc
y (
%
)
90
80
75
70
D
a
t
a
pr
i
va
c
y ove
r
he
a
d (
m
s
)
9
15
20
25
T
a
bl
e
3
e
nc
om
p
a
s
s
e
s
a
br
oa
d
e
r
s
e
t
of
pe
r
f
or
m
a
nc
e
m
e
tr
ic
s
b
e
yond
e
f
f
ic
ie
nc
y,
in
c
lu
di
ng
la
te
nc
y,
th
r
oughput,
da
ta
pr
iv
a
c
y
ove
r
he
a
d,
r
e
s
our
c
e
ut
il
iz
a
ti
on,
s
c
a
la
bi
li
ty
,
a
nd
r
e
li
a
bi
li
ty
.
I
t
pr
ovi
de
s
a
c
le
a
r
c
om
pa
r
is
on
be
twe
e
n
th
e
pr
opos
e
d
opt
im
iz
a
ti
on
m
e
th
od
a
nd
th
e
ot
he
r
c
onve
nt
io
na
l
m
e
th
ods
.
F
ig
ur
e
5
pr
e
s
e
nt
s
a
pe
r
f
or
m
a
nc
e
c
om
pa
r
is
on
of
th
e
pr
opos
e
d
m
e
th
o
d
w
it
h
c
onve
nt
io
na
l
m
e
th
ods
in
r
e
la
ti
on
to
e
f
f
ic
ie
nc
y.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
. 14, No.
3, J
une
2025
:
1900
-
1909
1906
F
ig
ur
e
4. T
he
pe
r
f
or
m
a
nc
e
a
na
ly
s
is
of
t
he
pr
opos
e
d m
e
th
od c
o
m
pa
r
e
d t
o c
onve
nt
io
na
l
m
e
th
ods
i
n r
e
la
ti
on t
o
s
ys
te
m
de
m
a
nd
T
a
bl
e
3. C
om
pa
r
a
ti
ve
p
e
r
f
or
m
a
nc
e
a
na
ly
s
is
P
e
r
f
or
m
a
nc
e
m
e
t
r
i
c
P
r
opos
e
d opt
i
m
i
z
a
t
i
on
m
e
t
hod
S
t
a
t
i
c
r
e
s
our
c
e
a
l
l
oc
a
t
i
on
B
a
s
i
c
m
a
c
hi
ne
l
e
a
r
ni
ng
opt
i
m
i
z
a
t
i
on
T
r
a
di
t
i
ona
l
f
og
c
om
put
i
ng
L
a
t
e
nc
y (
m
s
)
75
95
100
110
T
hr
oughput
(
K
B
/
s
)
1
,
500
1
,
150
1
,
200
1
,
000
E
f
f
i
c
i
e
nc
y (
%
)
90
80
75
70
D
a
t
a
pr
i
va
c
y ove
r
he
a
d
(
m
s
)
9
15
20
25
R
e
s
our
c
e
ut
i
l
i
z
a
t
i
on
(%)
85
75
70
65
S
c
a
l
a
bi
l
i
t
y (
N
um
be
r
of
de
vi
c
e
s
)
500
300
400
200
R
e
l
i
a
bi
l
i
t
y (
%
)
99
95
96
93
F
ig
ur
e
5. T
he
pe
r
f
or
m
a
nc
e
a
na
ly
s
is
of
t
he
pr
opos
e
d m
e
th
od c
o
m
pa
r
e
d t
o c
onve
nt
io
na
l
m
e
th
ods
i
n r
e
la
ti
on t
o
e
f
f
ic
ie
nc
y
T
a
bl
e
4
pr
ovi
de
s
a
c
om
pa
r
is
on
of
va
r
io
us
da
ta
pr
iv
a
c
y
-
r
e
la
te
d
pe
r
f
or
m
a
nc
e
m
e
tr
ic
s
a
c
r
os
s
th
e
pr
opos
e
d
opt
im
iz
a
ti
on
m
e
th
od
a
nd
th
e
th
r
e
e
c
onve
nt
io
na
l
m
e
th
ods
.
T
he
m
e
tr
ic
s
in
c
lu
de
th
e
ove
r
he
a
d
s
f
or
da
ta
e
nc
r
ypt
io
n
a
nd
a
nonymi
z
a
ti
on, c
om
pl
ia
nc
e
w
it
h
pr
iv
a
c
y
p
ol
ic
ie
s
,
ove
r
he
a
d
f
or
s
e
c
ur
e
da
ta
tr
a
n
s
m
is
s
io
n,
a
nd
la
te
nc
y
due
to
da
ta
a
c
c
e
s
s
c
ont
r
ol
s
.
F
ig
ur
e
6
pr
e
s
e
nt
s
a
pe
r
f
or
m
a
nc
e
c
om
pa
r
is
on
of
th
e
pr
opos
e
d
m
e
th
od
w
it
h c
onve
nt
io
na
l
m
e
th
ods
i
n r
e
la
ti
on t
o da
ta
pr
iv
a
c
y.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
O
pt
imi
z
in
g r
e
al
-
ti
m
e
dat
a pr
e
p
r
oc
e
s
s
in
g i
n I
oT
-
bas
e
d f
og c
om
p
ut
in
g us
in
g
…
(
N
andi
ni
G
ow
da P
ut
ta
s
w
am
y
)
1907
T
a
bl
e
4. D
a
ta
pr
iv
a
c
y p
e
r
f
or
m
a
nc
e
a
na
ly
s
i
s
P
e
r
f
or
m
a
nc
e
m
e
t
r
i
c
P
r
opos
e
d
opt
i
m
i
z
a
t
i
on m
e
t
hod
S
t
a
t
i
c
r
e
s
our
c
e
a
l
l
oc
a
t
i
on
B
a
s
i
c
m
a
c
hi
ne
l
e
a
r
ni
ng opt
i
m
i
z
a
t
i
on
T
r
a
di
t
i
ona
l
f
og
c
om
put
i
ng
D
a
t
a
e
nc
r
ypt
i
on ove
r
he
a
d (
m
s
)
9
15
20
25
D
a
t
a
a
nonym
i
z
a
t
i
on ove
r
he
a
d (
m
s
)
7
12
18
22
P
r
i
va
c
y pol
i
c
y c
om
pl
i
a
nc
e
(
%
)
98
90
85
80
S
e
c
ur
e
da
t
a
t
r
a
ns
m
i
s
s
i
on ove
r
he
a
d (
m
s
)
8
14
19
24
D
a
t
a
a
c
c
e
s
s
c
ont
r
ol
l
a
t
e
nc
y (
m
s
)
10
20
25
30
F
ig
ur
e
6. T
he
pe
r
f
or
m
a
nc
e
a
na
ly
s
is
of
t
he
pr
opos
e
d m
e
th
od c
o
m
pa
r
e
d t
o c
onve
nt
io
na
l
m
e
th
ods
i
n r
e
la
ti
on t
o
da
ta
pr
iv
a
c
y
4.
C
O
N
C
L
U
S
I
O
N
T
he
pa
pe
r
pr
e
s
e
nt
e
d
a
I
oT
-
F
C
M
L
f
or
r
e
a
l
-
ti
m
e
da
ta
p
r
e
pr
oc
e
s
s
in
g
in
I
oT
-
ba
s
e
d
f
og
c
om
put
in
g,
s
how
in
g
m
a
r
ke
d
im
pr
ove
m
e
nt
s
ove
r
tr
a
di
ti
ona
l
a
ppr
oa
c
he
s
.
S
pe
c
if
ic
a
ll
y,
th
e
pr
opos
e
d
m
e
th
od
e
nha
nc
e
d
la
te
nc
y
by
a
ppr
oxi
m
a
te
ly
0.26%
,
in
c
r
e
a
s
e
d
th
r
oughput
by
u
p
to
0.32%
,
im
pr
ove
d
r
e
s
our
c
e
e
f
f
ic
ie
nc
y
by
0.20%
,
a
nd
r
e
duc
e
d
da
ta
pr
iv
a
c
y
ov
e
r
he
a
d
by
0.64%
,
r
e
f
le
c
ti
ng
s
ig
ni
f
ic
a
nt
a
dva
nc
e
m
e
nt
s
in
bot
h
pe
r
f
or
m
a
nc
e
a
nd
s
e
c
ur
it
y.
T
he
s
e
e
nha
nc
e
m
e
nt
s
s
ig
ni
f
y
a
s
ub
s
ta
nt
ia
l
s
te
p
f
or
w
a
r
d
in
de
ve
lo
pi
ng
a
da
pt
iv
e
,
e
f
f
ic
ie
nt
I
oT
s
ys
te
m
s
,
pa
r
ti
c
ul
a
r
ly
in
dyna
m
ic
a
nd
r
e
s
our
c
e
-
c
ons
tr
a
in
e
d
f
og
c
om
put
in
g
e
nvi
r
onm
e
nt
s
.
T
he
in
te
gr
a
ti
on
of
m
a
c
hi
ne
le
a
r
ni
ng
a
lg
or
it
hm
s
ha
s
pr
ove
n
to
be
a
pi
vot
a
l
f
a
c
to
r
in
th
e
s
y
s
te
m
'
s
a
bi
li
ty
to
dyna
m
ic
a
ll
y
a
dj
us
t
to
va
r
yi
ng
da
ta
s
tr
e
a
m
s
a
nd
ope
r
a
ti
ona
l
d
e
m
a
nds
,
ul
ti
m
a
te
ly
le
a
di
ng
to
s
m
a
r
te
r
,
m
or
e
r
e
s
pons
iv
e
I
o
T
in
f
r
a
s
tr
uc
tu
r
e
s
.
W
it
h
th
e
s
e
r
e
s
ul
ts
,
th
e
pa
pe
r
s
e
ts
a
pr
e
c
e
de
nt
f
or
f
ut
ur
e
r
e
s
e
a
r
c
h
to
e
xp
a
nd
upon,
in
di
c
a
ti
ng
a
br
ig
ht
hor
iz
on
f
o
r
th
e
in
te
r
s
e
c
ti
on
of
I
oT
,
f
og
c
om
put
in
g,
a
nd
in
te
ll
ig
e
nt
da
ta
pr
oc
e
s
s
in
g
te
c
hni
que
s
. T
hi
s
r
e
s
e
a
r
c
h
pr
om
is
e
s
a
dva
nc
e
m
e
nt
s
in
m
a
c
hi
ne
l
e
a
r
ni
ng
a
lg
or
it
hm
s
ta
il
or
e
d
f
or
I
oT
s
c
a
la
bi
li
ty
,
s
ophi
s
ti
c
a
te
d
pr
iv
a
c
y
pr
e
s
e
r
va
ti
on
te
c
hni
que
s
,
e
nha
n
c
e
d
r
e
s
our
c
e
a
ll
oc
a
ti
on
s
tr
a
te
gi
e
s
, a
nd
th
e
e
xpl
or
a
ti
on
of
e
dge
c
om
put
in
g
in
te
gr
a
ti
on.
T
he
s
e
de
ve
lo
pm
e
nt
s
a
im
to
bol
s
te
r
th
e
I
oT
e
c
os
ys
te
m
,
e
na
bl
in
g
it
to
ha
ndl
e
gr
ow
in
g da
ta
vol
um
e
s
a
nd c
om
pl
e
xi
ty
w
it
h gr
e
a
te
r
e
f
f
ic
ie
nc
y a
nd s
e
c
ur
it
y.
A
C
K
N
O
WL
E
D
G
M
E
N
T
S
T
he
a
ut
hor
w
oul
d
li
ke
to
th
a
nk
E
a
s
t
P
oi
nt
C
ol
le
ge
of
E
ngi
ne
e
r
in
g
a
nd
T
e
c
hnol
ogy,
S
a
pt
h
a
gi
r
i
C
ol
le
ge
of
E
ngi
ne
e
r
in
g,
B
N
M
I
ns
ti
tu
te
of
T
e
c
hnol
ogy,
V
i
s
ve
s
va
r
a
ya
T
e
c
hnol
ogi
c
a
l
U
ni
ve
r
s
it
y
(
V
T
U
)
,
B
e
la
ga
vi
,
f
or
a
ll
th
e
s
uppor
t
a
nd
e
nc
our
a
ge
m
e
nt
pr
ovi
de
d
by
t
he
m
to
ta
ke
up
th
is
r
e
s
e
a
r
c
h
w
or
k
a
nd
publ
is
h
th
is
pa
pe
r
.
F
U
N
D
I
N
G
I
N
F
O
R
M
A
T
I
O
N
A
ut
hor
s
s
ta
te
no
f
undi
ng i
nvol
ve
d.
A
U
T
H
O
R
C
O
N
T
R
I
B
U
T
I
O
N
S
S
T
A
T
E
M
E
N
T
T
hi
s
jo
ur
na
l
us
e
s
th
e
C
ont
r
ib
ut
or
R
ol
e
s
T
a
xonomy
(
C
R
e
di
T
)
to
r
e
c
ogni
z
e
in
di
vi
dua
l
a
ut
hor
c
ont
r
ib
ut
io
ns
, r
e
duc
e
a
ut
hor
s
hi
p di
s
put
e
s
,
a
nd f
a
c
il
it
a
te
c
ol
la
bo
r
a
ti
on.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
. 14, No.
3, J
une
2025
:
1900
-
1909
1908
N
am
e
o
f
A
u
t
h
or
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
N
a
ndi
ni
G
ow
da
P
ut
ta
s
w
a
m
y
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
A
ni
th
a
N
a
r
a
s
im
ha
M
ur
th
y
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
onc
e
pt
ua
l
i
z
a
t
i
on
M
:
M
e
t
hodol
ogy
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
da
t
i
on
Fo
:
Fo
r
m
a
l
a
na
l
ys
i
s
I
:
I
nve
s
t
i
ga
t
i
on
R
:
R
e
s
our
c
e
s
D
:
D
a
t
a
C
ur
a
t
i
on
O
:
W
r
i
t
i
ng
-
O
r
i
gi
na
l
D
r
a
f
t
E
:
W
r
i
t
i
ng
-
R
e
vi
e
w
&
E
di
t
i
ng
Vi
:
Vi
s
ua
l
i
z
a
t
i
on
Su
:
Su
pe
r
vi
s
i
on
P
:
P
r
oj
e
c
t
a
dm
i
ni
s
t
r
a
t
i
on
Fu
:
Fu
ndi
ng a
c
qui
s
i
t
i
on
C
O
N
F
L
I
C
T
O
F
I
N
T
E
R
E
S
T
S
T
A
T
E
M
E
N
T
T
he
a
ut
hor
s
de
c
la
r
e
th
a
t
th
e
y
h
a
ve
no
kno
w
n
c
om
pe
ti
ng
f
in
a
nc
ia
l
in
te
r
e
s
ts
or
p
e
r
s
ona
l
r
e
la
ti
ons
hi
p
s
th
a
t
c
oul
d ha
ve
a
ppe
a
r
e
d t
o i
nf
lu
e
nc
e
t
h
e
w
or
k r
e
por
te
d i
n t
hi
s
pa
pe
r
. A
ut
hor
s
s
ta
te
no c
onf
li
c
t
of
i
nt
e
r
e
s
t.
I
N
F
O
R
M
E
D
C
O
N
S
E
N
T
W
e
ha
ve
obt
a
in
e
d i
nf
or
m
e
d c
ons
e
nt
f
r
om
a
ll
i
ndi
vi
dua
ls
i
nc
lu
de
d i
n t
hi
s
s
tu
dy.
E
T
H
I
C
A
L
A
P
P
R
O
V
A
L
T
he
r
e
s
e
a
r
c
h
r
e
la
te
d
to
hum
a
n
us
e
h
a
s
be
e
n
c
ondu
c
te
d
in
c
om
pl
ia
nc
e
w
it
h
a
ll
r
e
le
va
nt
na
ti
ona
l
r
e
gul
a
ti
ons
a
nd
in
s
ti
tu
ti
ona
l
pol
ic
ie
s
,
in
a
c
c
or
da
nc
e
w
it
h
th
e
te
ne
ts
of
th
e
H
e
ls
in
ki
D
e
c
la
r
a
ti
on,
a
nd
ha
s
be
e
n
a
ppr
ove
d by the
a
ut
hor
s
'
i
ns
ti
tu
ti
ona
l
r
e
vi
e
w
boa
r
d.
D
A
T
A
A
V
A
I
L
A
B
I
L
I
T
Y
T
he
a
ut
hor
s
c
onf
ir
m
t
ha
t
th
e
da
ta
s
uppor
ti
ng t
he
f
in
di
ngs
of
t
hi
s
s
tu
dy a
r
e
a
va
il
a
bl
e
w
it
hi
n t
he
a
r
ti
c
le
a
nd i
ts
s
uppl
e
m
e
nt
a
r
y m
a
te
r
ia
ls
.
R
E
F
E
R
E
N
C
E
S
[
1]
S
.
J
ha
a
nd
D
.
T
r
i
pa
t
hy,
“
L
ow
l
a
t
e
nc
y
c
ons
i
s
t
e
nc
y
ba
s
e
d
pr
ot
oc
ol
f
or
f
og
c
om
p
ut
i
ng
s
ys
t
e
m
s
us
i
ng
C
oA
P
w
i
t
h
m
a
c
hi
ne
l
e
a
r
ni
ng,”
i
n
2023
2nd
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
f
or
I
nnov
at
i
on
i
n
T
e
c
hnol
ogy
(
I
N
O
C
O
N
)
,
2023,
pp.
1
–
6
,
doi
:
10.1109/
I
N
O
C
O
N
57975.2023.10101176.
[
2]
D
.
M
a
j
um
de
r
a
nd
S
.
M
.
K
um
a
r
,
“
A
r
e
vi
e
w
on
r
e
s
our
c
e
a
l
l
oc
a
t
i
on
m
e
t
h
odol
ogi
e
s
i
n
f
og/
e
dge
c
om
put
i
ng,”
i
n
2022
8t
h
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on Sm
a
r
t
St
r
uc
t
u
r
e
s
and S
y
s
t
e
m
s
(
I
C
SSS)
, 2022, pp. 1
–
4
, doi
:
10.1109/
I
C
S
S
S
54381.2022.9782175.
[
3]
M
.
L
.
U
m
a
s
ha
nka
r
,
S
.
M
a
l
l
i
ka
r
j
una
s
w
a
m
y,
N
.
S
ha
r
m
i
l
a
,
D
.
M
.
K
um
a
r
,
a
nd
K
.
R
.
N
a
t
a
r
a
j
,
“
A
s
ur
ve
y
on
I
o
T
pr
ot
oc
ol
i
n r
e
a
l
-
t
i
m
e
a
ppl
i
c
a
t
i
ons
a
nd
i
t
s
a
r
c
hi
t
e
c
t
ur
e
s
,”
i
n
I
C
D
SM
L
A
2021
:
P
r
oc
e
e
di
ngs
of
t
he
3r
d
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
D
at
a
Sc
i
e
nc
e
,
M
ac
hi
ne
L
e
ar
ni
ng and A
ppl
i
c
at
i
ons
, 2023, pp. 119
–
130
, doi
:
10.1007/
978
-
981
-
19
-
5936
-
3_12.
[
4]
I
.
A
z
i
m
i
,
A
.
A
nz
a
npour
,
A
.
M
.
R
a
hm
a
ni
,
P
.
L
i
l
j
e
be
r
g,
a
nd
T
.
S
a
l
a
kos
ki
,
“
M
e
di
c
a
l
w
a
r
ni
ng
s
y
s
t
e
m
ba
s
e
d
on
i
nt
e
r
ne
t
of
t
hi
ng
s
us
i
ng
f
og
c
om
put
i
ng,”
i
n
2016
I
nt
e
r
nat
i
onal
W
or
k
s
hop
on
B
i
g
D
at
a
and
I
nf
or
m
at
i
on
Se
c
ur
i
t
y
(
I
W
B
I
S)
,
2016,
pp.
19
–
24
,
doi
:
10.1109/
I
W
B
I
S
.2016.7872884.
[
5]
J
.
H
onne
gow
da
,
K
.
M
a
l
l
i
ka
r
j
una
i
a
h,
a
nd
M
.
S
r
i
ka
nt
a
s
w
a
m
y,
“
A
n
e
f
f
i
c
i
e
nt
a
bn
or
m
a
l
e
ve
nt
de
t
e
c
t
i
on
s
ys
t
e
m
i
n
vi
de
o
s
ur
ve
i
l
l
a
nc
e
us
i
ng de
e
p
l
e
a
r
ni
ng
-
ba
s
e
d
r
e
c
onf
i
gur
a
bl
e
a
ut
oe
nc
ode
r
,”
I
nge
ni
e
r
i
e
de
s
Sy
s
t
e
m
e
s
d’
I
nf
or
m
at
i
on
, vol
. 29,
no. 2,
pp. 677
–
686,
2024,
doi
:
10.18280/
i
s
i
.290229.
[
6]
B
.
N
a
t
a
r
a
j
a
n,
S
.
B
o
s
e
,
N
.
M
a
h
e
s
w
a
r
a
n,
G
.
L
oge
s
w
a
r
i
,
a
nd
T
.
A
ni
t
ha
,
“
A
s
u
r
ve
y:
a
n
e
f
f
e
c
t
i
ve
ut
i
l
i
z
a
t
i
on
of
m
a
c
hi
ne
l
e
a
r
ni
ng
a
l
gor
i
t
hm
s
i
n
I
oT
ba
s
e
d
i
nt
r
us
i
on
de
t
e
c
t
i
on
s
ys
t
e
m
,”
i
n
2023
12t
h
I
nt
e
r
nat
i
o
nal
C
onf
e
r
e
nc
e
on
A
dv
anc
e
d
C
om
put
i
ng
(
I
C
oA
C
)
,
2023, pp. 1
–
7
, doi
:
10.1109/
I
C
oA
C
59537.2023.10249672.
[
7]
V
.
V
e
nka
t
a
r
a
m
a
na
n,
G
.
K
a
vi
t
ha
,
M
.
R
.
J
oe
l
,
a
nd
J
.
L
e
ni
n,
“
F
or
e
s
t
f
i
r
e
de
t
e
c
t
i
on
a
nd
t
e
m
pe
r
a
t
ur
e
m
oni
t
or
i
ng
a
l
e
r
t
us
i
ng
I
o
T
a
n
d
m
a
c
hi
ne
l
e
a
r
ni
ng
a
l
gor
i
t
hm
,”
i
n
2023
5t
h
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
Sm
ar
t
Sy
s
t
e
m
s
and
I
nv
e
nt
i
v
e
T
e
c
hnol
og
y
(
I
C
SSI
T
)
,
2023,
pp. 1150
–
1156
, doi
:
10.1109/
I
C
S
S
I
T
55814.2023.10061086.
[
8]
M
.
A
be
di
a
nd
M
.
P
our
ki
a
ni
,
“
R
e
s
our
c
e
a
l
l
oc
a
t
i
on
i
n
c
om
bi
ne
d
f
og
-
c
l
oud
s
c
e
n
a
r
i
os
by
us
i
ng
a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
nc
e
,”
i
n
2020
F
i
f
t
h
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
F
og
and
M
obi
l
e
E
dge
C
om
put
i
ng
(
F
M
E
C
)
,
2020,
pp.
218
–
222
,
doi
:
10.1109/
F
M
E
C
49853.2020.9144693.
[
9]
S
.
M
a
l
l
i
ka
r
j
una
s
w
a
m
y,
N
.
M
.
B
a
s
a
va
r
a
j
u,
N
.
S
ha
r
m
i
l
a
,
H
.
N
.
M
a
he
ndr
a
,
S
.
P
ooj
a
,
a
nd
B
.
L
.
D
e
e
pa
k,
“
A
n
e
f
f
i
c
i
e
nt
bi
g
da
t
a
ga
t
he
r
i
ng
i
n
w
i
r
e
l
e
s
s
s
e
ns
or
ne
t
w
or
k
u
s
i
ng
r
e
c
onf
i
gur
a
bl
e
node
di
s
t
r
i
but
i
on
a
l
gor
i
t
hm
,”
i
n
2022
F
our
t
h
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on C
ogni
t
i
v
e
C
om
put
i
ng and I
nf
or
m
at
i
on P
r
oc
e
s
s
i
ng (
C
C
I
P
)
, 2022, pp. 1
–
6
, doi
:
10.1109/
C
C
I
P
57447.2022.10058620.
[
10]
H
.
K
.
B
ha
r
a
dw
a
j
e
t
al
.
,
“
A
r
e
vi
e
w
on
t
he
r
ol
e
of
m
a
c
hi
ne
l
e
a
r
ni
ng
i
n
e
na
bl
i
ng
I
oT
ba
s
e
d
he
a
l
t
hc
a
r
e
a
ppl
i
c
a
t
i
ons
,”
I
E
E
E
A
c
c
e
s
s
,
vol
. 9, pp. 38859
–
38890, 2021, doi
:
10.1109/
A
C
C
E
S
S
.2021.3059858.
[
11]
M
.
V
a
r
un,
K
.
K
e
s
a
vr
a
j
,
S
.
S
um
a
n,
a
nd
X
.
S
.
R
a
j
,
“
I
nt
e
gr
a
t
i
ng
I
oT
a
nd
m
a
c
hi
ne
l
e
a
r
ni
ng
f
or
e
nha
nc
e
d
f
or
e
s
t
f
i
r
e
de
t
e
c
t
i
on
a
nd
t
e
m
pe
r
a
t
ur
e
m
oni
t
or
i
ng,”
i
n
2023
3r
d
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
I
nnov
at
i
v
e
M
e
c
hani
s
m
s
f
or
I
ndus
t
r
y
A
ppl
i
c
at
i
ons
(
I
C
I
M
I
A
)
,
2023, pp. 152
–
158
, doi
:
10.1109/
I
C
I
M
I
A
60377.2023.10426108.
[
12]
V
.
G
ow
r
i
s
ha
nka
r
,
T
.
J
a
ya
kum
a
r
,
S
.
P
a
r
a
m
e
s
w
a
r
a
n,
M
.
S
e
nt
hi
l
kum
a
r
,
S
.
L
e
ka
s
hr
i
,
a
nd
B
.
R
.
K
um
a
r
,
“
P
a
t
i
e
nt
he
a
l
t
h
m
oni
t
or
i
ng
us
i
ng
f
og
a
nd
e
dge
c
om
put
i
ng,”
i
n
2023
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
Su
s
t
a
i
nabl
e
C
om
m
uni
c
at
i
on
N
e
t
w
or
k
s
and
A
ppl
i
c
at
i
on
(
I
C
SC
N
A
)
, 2023, pp. 250
–
256
, doi
:
10.1109/
I
C
S
C
N
A
58489.2023.10370652.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
O
pt
imi
z
in
g r
e
al
-
ti
m
e
dat
a pr
e
p
r
oc
e
s
s
in
g i
n I
oT
-
bas
e
d f
og c
om
p
ut
in
g us
in
g
…
(
N
andi
ni
G
ow
da P
ut
ta
s
w
am
y
)
1909
[
13]
D
. M
a
r
kovi
ć
, D
. V
uj
i
č
i
ć
,
Z
. S
t
a
m
e
nkovi
č
, a
nd S
. R
a
ndi
č
, “
I
oT
ba
s
e
d
oc
c
upa
nc
y de
t
e
c
t
i
on s
y
s
t
e
m
w
i
t
h da
t
a
s
t
r
e
a
m
pr
oc
e
s
s
i
ng a
n
d
a
r
t
i
f
i
c
i
a
l
ne
ur
a
l
ne
t
w
o
r
ks
,”
i
n
2020
23r
d
I
nt
e
r
nat
i
onal
Sy
m
pos
i
um
on
D
e
s
i
gn
and
D
i
agnos
t
i
c
s
of
E
l
e
c
t
r
oni
c
C
i
r
c
ui
t
s
&
Sy
s
t
e
m
s
(
D
D
E
C
S)
, 2020, pp. 1
–
4
, doi
:
10.1109/
D
D
E
C
S
50862.2020.9095715.
[
14]
N
.
K
ha
n,
S
.
U
.
K
ha
n,
F
.
U
.
M
.
U
l
l
a
h,
M
.
Y
.
L
e
e
,
a
nd
S
.
W
.
B
a
i
k,
“
A
I
-
a
s
s
i
s
t
e
d
hybr
i
d
a
ppr
oa
c
h
f
or
e
ne
r
gy
m
a
na
ge
m
e
nt
i
n
I
oT
-
ba
s
e
d
s
m
a
r
t
m
i
c
r
ogr
i
d,”
I
E
E
E
I
nt
e
r
ne
t
of
T
hi
ngs
J
our
nal
,
vol
.
10,
no.
21,
pp.
18861
–
18875,
2023,
doi
:
10.1109/
J
I
O
T
.2023.3293800.
[
15]
T
.
M
.
S
a
r
a
va
na
n,
T
.
K
a
vi
t
ha
,
S
.
H
e
m
a
l
a
t
h
a
,
a
nd
M
.
M
.
A
j
m
a
l
,
“
I
oT
ba
s
e
d
he
a
l
t
h
obs
e
r
va
nc
e
s
y
s
t
e
m
us
i
ng
f
og
c
om
put
i
ng:
a
pr
e
c
i
s
e
r
e
vi
e
w
,”
i
n
2022
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
A
dv
anc
e
d
C
om
put
i
ng
T
e
c
hnol
ogi
e
s
and
A
ppl
i
c
at
i
ons
(
I
C
A
C
T
A
)
,
2022,
pp.
1
–
5
, doi
:
10.1109/
I
C
A
C
T
A
54488.2022.9753198.
[
16]
N
.
C
.
F
a
kude
,
P
.
T
a
r
w
i
r
e
yi
,
M
.
O
.
A
di
gun,
a
nd
A
.
M
.
A
bu
-
M
a
hf
ouz
,
“
F
og
or
c
he
s
t
r
a
t
or
a
s
a
n
e
na
bl
e
r
f
or
s
e
c
ur
i
t
y
i
n
f
og
c
om
put
i
ng:
a
r
e
vi
e
w
,”
i
n
2019
I
nt
e
r
nat
i
onal
M
ul
t
i
di
s
c
i
pl
i
nar
y
I
nf
or
m
at
i
on
T
e
c
hnol
ogy
and
E
ngi
ne
e
r
i
ng
C
onf
e
r
e
n
c
e
(
I
M
I
T
E
C
)
,
2019, pp. 1
–
6
, doi
:
10.1109/
I
M
I
T
E
C
45504.2019.9015896.
[
17]
A
.
N
.
J
a
da
ge
r
i
m
a
t
h,
S
.
M
a
l
l
i
ka
r
j
una
s
w
a
m
y,
D
.
M
.
K
um
a
r
,
S
.
S
he
e
l
a
,
S
.
P
r
a
ka
s
h,
a
nd
S
.
S
.
T
e
va
r
a
m
a
ni
,
“
A
m
a
c
hi
ne
l
e
a
r
ni
ng
ba
s
e
d
c
ons
um
e
r
pow
e
r
m
a
na
ge
m
e
nt
s
ys
t
e
m
u
s
i
ng
s
m
a
r
t
gr
i
d,”
i
n
2023
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
R
e
c
e
nt
A
dv
anc
e
s
i
n
Sc
i
e
nc
e
and E
ngi
ne
e
r
i
ng T
e
c
hnol
ogy
(
I
C
R
A
SE
T
)
, 2023, pp. 1
–
5
, doi
:
10.1109/
I
C
R
A
S
E
T
59632.2023.10419979.
[
18]
S
.
J
yot
hi
,
S
.
M
a
l
l
i
ka
r
j
una
s
w
a
m
y,
M
.
K
a
vi
t
ha
,
N
.
K
um
a
r
,
N
.
S
ha
r
m
i
l
a
,
a
nd
B
.
M
.
K
a
vya
,
“
A
m
a
c
hi
ne
l
e
a
r
ni
ng
ba
s
e
d
pow
e
r
l
oa
d
pr
e
di
c
t
i
on
s
ys
t
e
m
f
or
s
m
a
r
t
gr
i
d
e
ne
r
gy
m
a
na
ge
m
e
nt
,”
i
n
2023
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
R
e
c
e
nt
A
dv
anc
e
s
i
n
Sc
i
e
nc
e
and
E
ngi
ne
e
r
i
ng T
e
c
hnol
ogy
(
I
C
R
A
SE
T
)
, 2023, pp. 1
–
6
, doi
:
10.1109/
I
C
R
A
S
E
T
59
632.2023.10420183.
[
19]
M
.
V
e
nka
t
e
s
h,
S
.
N
.
K
.
P
ol
i
s
e
t
t
y,
S
.
C
H
,
P
.
K
um
a
r
.
K
,
R
.
S
a
t
pa
t
hy,
a
nd
P
.
N
e
e
l
i
m
a
,
“
A
nove
l
de
e
p
l
e
a
r
ni
ng
m
e
c
ha
ni
s
m
f
or
w
or
kl
oa
d
ba
l
a
nc
i
ng
i
n
f
og
c
om
put
i
ng,”
i
n
2022
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
A
ut
om
at
i
on,
C
om
put
i
ng
and
R
e
ne
w
abl
e
Sy
s
t
e
m
s
(
I
C
A
C
R
S)
, 2022, pp. 515
–
519
, doi
:
10.1109
/
I
C
A
C
R
S
55517.2022.10029081.
[
20]
M
.
K
.
H
us
s
e
i
n
a
nd
M
.
H
.
M
ous
a
,
“
E
f
f
i
c
i
e
nt
t
a
s
k
of
f
l
oa
di
ng
f
or
I
oT
-
B
a
s
e
d
a
ppl
i
c
a
t
i
ons
i
n
f
og
c
om
put
i
ng
us
i
ng
a
nt
c
ol
ony
opt
i
m
i
z
a
t
i
on,”
I
E
E
E
A
c
c
e
s
s
, vol
. 8, pp. 37191
–
37201, 2020, doi
:
10.1109/
A
C
C
E
S
S
.2020.2975741.
[
21]
S
.
M
ous
a
vi
,
S
.
E
.
M
ood,
A
.
S
our
i
,
a
nd
M
.
M
.
J
a
vi
di
,
“
D
i
r
e
c
t
e
d
s
e
a
r
c
h:
a
ne
w
ope
r
a
t
or
i
n
N
S
G
A
-
I
I
f
or
t
a
s
k
s
c
he
dul
i
ng
i
n
I
oT
ba
s
e
d
on
c
l
oud
-
f
og
c
om
put
i
ng,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
C
l
oud
C
om
put
i
ng
,
vol
.
11,
no.
2,
pp.
2144
–
2157,
2023,
doi
:
10.1109/
T
C
C
.2022.3188926.
[
22]
A
.
S
a
t
ouf
,
A
.
H
a
m
i
dogl
u,
O
.
M
.
G
ul
,
a
nd
A
.
K
uus
i
k,
“
G
r
e
y
w
ol
f
opt
i
m
i
z
e
r
-
ba
s
e
d
t
a
s
k
s
c
he
dul
i
ng
f
or
I
oT
-
ba
s
e
d
a
ppl
i
c
a
t
i
ons
i
n
t
he
e
dge
c
om
put
i
ng,”
i
n
2023
E
i
ght
h
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
F
og
and
M
obi
l
e
E
dge
C
om
put
i
ng
(
F
M
E
C
)
,
2023,
pp.
52
–
57
,
doi
:
10.1109/
F
M
E
C
59375.2023.10306148.
[
23]
M
. C
ha
r
i
t
ha
, S
. H
o
s
ur
, a
nd M
.
S
r
i
ka
nt
a
s
w
a
m
y, “
O
pt
i
m
i
z
e
d
B
E
R
r
e
duc
t
i
on i
n
w
i
r
e
l
e
s
s
c
om
m
uni
c
a
t
i
on u
s
i
ng a
c
ha
os
-
ba
s
e
d C
D
S
K
m
odul
a
t
i
on
m
ode
l
,”
i
n
M
at
he
m
at
i
c
al
M
ode
l
l
i
ng
of
E
ngi
ne
e
r
i
ng
P
r
obl
e
m
s
,
2025,
vol
.
12,
no.
2,
pp.
719
–
729
,
doi
:
10.18280/
m
m
e
p.120234.
[
24]
M
.
P
oor
ni
m
a
,
T
.
N
.
A
ni
t
ha
,
S
.
M
a
l
l
i
ka
r
j
una
s
w
a
m
y,
a
nd
M
.
L
.
U
m
a
s
ha
nka
r
,
“
A
n
e
f
f
i
c
i
e
nt
i
n
t
e
r
ne
t
of
t
hi
ngs
ba
s
e
d
i
nt
r
us
i
on
de
t
e
c
t
i
on a
nd opt
i
m
i
z
a
t
i
on a
l
gor
i
t
hm
f
or
s
m
a
r
t
ne
t
w
or
ks
,”
I
nt
e
r
nat
i
onal
J
our
na
l
of
C
om
put
i
ng and D
i
gi
t
al
Sy
s
t
e
m
s
, vol
. 17, no. 1
,
pp. 1
–
12, 2025, doi
:
10.12785/
i
j
c
ds
/
1571001227.
[
25]
T
.
S
um
a
n,
S
.
K
a
l
i
a
ppa
n,
L
.
N
a
t
r
a
ya
n,
a
nd
D
.
C
.
D
obha
l
,
“
I
oT
ba
s
e
d
s
oc
i
a
l
de
vi
c
e
ne
t
w
or
k
w
i
t
h
c
l
oud
c
om
put
i
ng
a
r
c
hi
t
e
c
t
ur
e
,”
i
n
2023
Se
c
ond
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
E
l
e
c
t
r
oni
c
s
and
R
e
ne
w
abl
e
Sy
s
t
e
m
s
(
I
C
E
A
R
S)
,
2023,
pp.
502
–
505
,
doi
:
10.1109/
I
C
E
A
R
S
56392.2023.10085574.
B
I
O
G
R
A
P
H
I
E
S
O
F
A
U
T
H
O
R
S
Mrs.
Nandini
Gowda
Puttaswamy
currently
working
as
Assista
nt
Professor
i
n
information
science
and
engineer
ing
,
Sapthagiri
College
of
Engin
eering,
Bangalore.
She
completed
her
B
.
E
.
in
CSE
from
Visvesvaraya
Technological
Univer
sity
(VTU)
,
M.Tech.
in
software
engineering
from
VTU
and
pursuing
Ph.D.
from
VTU
.
Sh
e
has
published
around
4
papers
on
national
conference
and
her
area
of
research
interest
are
cloud
computing,
fog
computi
ng,
edge
computi
ng
and
IoT,
AI,
ML,
and
big
data
analytics.
She
can
be
contacted
at
email:
nandini
.educator@
gmail.co
m.
Dr.
Anitha
Narasimha
Murthy
currently
working
as
Professo
r
in
computer
science
and
engineering
,
BNM
Institute
of
Technology,
Bangalore.
She
completed
her
B
.
E
.
in
CSE
from
Bangalore
University,
M.Tech.
in
information
technology
from
Bangalore
University
and
Ph.D
.
from
Visvesvaraya
Technological
University.
S
he
has
published
around
30
research
papers
and
her
area
of
research
interest
are
AI,
ML,
big
data
analytics,
and
data
mining
. She can be contacted a
t email: anitha.mhp@
gmail.com.
Evaluation Warning : The document was created with Spire.PDF for Python.