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
.
1236
~
1
2
4
8
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
1
6
i
3
.
pp
1
2
3
6
-
1
2
4
8
1236
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
M
a
chine
lea
rning
-
driv
en ana
ly
sis
of user
ba
ndwid
th
a
llo
ca
tion
a
nd perf
o
rma
n
ce
in 5G
h
eter
o
g
ene
o
us
network
:
a
su
rv
ey
P
a
ng
Wa
i Leo
ng
1
,
Ra
y
m
o
nd
Chia
1
,
P
ha
ng
Swee
K
ing
1
,
G
o
h H
ui H
wa
ng
1
,
Cha
n K
a
h Yo
o
ng
2
,
Chun
g
G
wo
Chin
2
1
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
i
n
g
,
T
a
y
l
o
r
’
s U
n
i
v
e
r
si
t
y
,
S
e
l
a
n
g
o
r
,
M
a
l
a
y
si
a
2
F
a
c
u
l
t
y
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
En
g
i
n
e
e
r
i
n
g
,
M
u
l
t
i
me
d
i
a
U
n
i
v
e
r
si
t
y
,
S
e
l
a
n
g
o
r
,
M
a
l
a
y
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
3
1
,
2
0
2
5
R
ev
is
ed
Ma
r
2
4
,
2
0
2
6
Acc
ep
ted
Ap
r
2
7
,
2
0
2
6
A
k
e
y
fo
u
n
d
a
ti
o
n
o
f
5
G
h
e
tero
g
e
n
e
o
u
s
n
e
tw
o
rk
s
(He
tNe
ts
)
is
t
h
e
u
se
o
f
n
e
two
rk
slici
n
g
,
w
h
ich
d
iv
i
d
e
s
b
a
n
d
wid
th
i
n
to
m
u
lt
ip
le
lo
g
ica
l
n
e
two
rk
s
a
n
d
a
c
c
o
u
n
ts
fo
r
e
a
c
h
fu
n
c
ti
o
n
’s
r
e
q
u
irem
e
n
ts.
C
u
rre
n
tl
y
,
v
a
rio
u
s
m
a
c
h
in
e
lea
rn
in
g
(
M
L)
m
o
d
e
ls
a
re
b
e
in
g
imp
lem
e
n
ted
i
n
to
t
h
e
n
e
two
r
k
slicin
g
a
lg
o
rit
h
m
to
a
ll
o
c
a
te
b
a
n
d
wi
d
th
d
y
n
a
m
ica
ll
y
.
T
h
e
n
e
two
r
k
slici
n
g
a
lg
o
ri
th
m
a
n
a
ly
z
e
s
th
e
traffic
a
n
d
a
ll
o
c
a
te
s
b
a
n
d
wid
t
h
b
a
se
d
o
n
th
e
c
u
rre
n
t
se
rv
ice
s
u
sin
g
a
n
e
two
rk
-
c
e
n
t
ric
a
p
p
ro
a
c
h
.
Ho
we
v
e
r,
li
m
it
e
d
wo
r
k
is
fo
u
n
d
o
n
fu
rth
e
r
st
u
d
y
in
g
t
h
e
imp
a
c
t
o
f
u
se
r
-
c
e
n
tri
c
a
lg
o
rit
h
m
s
i
n
b
a
n
d
wi
d
t
h
a
ll
o
c
a
ti
o
n
.
Th
is
p
a
p
e
r
p
re
se
n
ts
th
e
n
e
two
rk
slici
n
g
u
se
d
in
5
G
a
n
d
th
e
li
m
it
a
ti
o
n
s
o
f
t
h
e
se
a
lg
o
r
it
h
m
s.
A
d
e
tailed
re
v
iew
o
f
u
se
r
-
c
e
n
tri
c
b
a
n
d
wid
t
h
a
ll
o
c
a
ti
o
n
a
lg
o
rit
h
m
s
is
p
re
se
n
t
e
d
,
a
l
o
n
g
wit
h
a
c
rit
ica
l
re
v
ie
w
o
f
M
L
a
lg
o
rit
h
m
s
fo
r
traffic
p
re
d
ictio
n
a
n
d
re
so
u
rc
e
a
ll
o
c
a
ti
o
n
d
e
c
isio
n
s.
F
in
a
ll
y
,
th
e
tec
h
n
o
l
o
g
y
g
a
p
s
a
n
d
o
p
p
o
rt
u
n
it
ies
o
f
th
e
e
x
isti
n
g
wo
rk
s
a
r
e
re
p
o
rted
,
a
n
d
t
h
e
d
irec
ti
o
n
f
o
r
f
u
rt
h
e
r
re
se
a
rc
h
o
f
M
L
i
n
u
se
r
-
c
e
n
tri
c
b
a
n
d
wid
t
h
a
ll
o
c
a
ti
o
n
a
lg
o
r
it
h
m
s is
ta
b
u
late
d
.
K
ey
w
o
r
d
s
:
5
G
h
eter
o
g
e
n
eo
u
s
n
etwo
r
k
Ma
ch
in
e
lear
n
in
g
Netwo
r
k
s
licin
g
R
eso
u
r
ce
allo
ca
tio
n
User
-
ce
n
tr
ic
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
:
C
h
u
n
g
Gwo
C
h
in
Facu
lty
o
f
Ar
tific
ial
I
n
tellig
en
ce
an
d
E
n
g
in
ee
r
in
g
,
Mu
ltime
d
ia
Un
iv
er
s
ity
6
3
1
0
0
C
y
b
er
jay
a
,
Selan
g
o
r
,
Ma
lay
s
ia
E
m
ail: g
cc
h
u
n
g
@
m
m
u
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
As
ce
llu
lar
tech
n
o
lo
g
y
an
d
m
o
b
ile
n
etwo
r
k
s
h
av
e
d
e
v
elo
p
ed
o
v
e
r
th
e
y
ea
r
s
,
ea
ch
g
e
n
er
atio
n
o
f
ce
llu
lar
tech
n
o
lo
g
y
h
as
aim
ed
to
im
p
r
o
v
e.
E
ac
h
g
en
er
atio
n
(
1
G,
2
G,
3
G,
an
d
4
G)
e
x
h
ib
it
ed
im
p
r
o
v
e
m
en
ts
in
ca
p
ac
ity
,
d
ata
s
p
ee
d
,
an
d
co
v
er
ag
e.
T
h
e
n
ee
d
f
o
r
d
ep
en
d
ab
le
an
d
f
ast
d
ata
tr
an
s
m
is
s
io
n
h
as
b
ee
n
in
cr
ea
s
in
g
,
an
d
d
ata
tr
an
s
m
is
s
io
n
tech
n
o
l
o
g
y
h
as
b
ee
n
ad
v
an
cin
g
to
f
u
l
f
ill
th
is
d
em
an
d
.
T
h
e
latest
g
e
n
er
atio
n
o
f
m
o
b
ile
n
etwo
r
k
s
is
th
e
5
th
g
e
n
er
atio
n
(
5
G)
,
wh
ich
b
e
g
an
d
ep
lo
y
m
e
n
t
in
2
0
1
9
a
n
d
s
ig
n
if
ican
tly
im
p
r
o
v
e
d
t
h
e
laten
cy
an
d
c
o
v
er
ag
e
o
f
d
ata
tr
an
s
m
i
s
s
io
n
co
m
p
ar
e
d
to
4
G
ce
llu
l
ar
tech
n
o
lo
g
y
[
1
]
.
T
h
e
h
eter
o
g
en
eo
u
s
n
etwo
r
k
s
(
HetNe
ts
)
ar
ch
itectu
r
e
co
m
b
in
es
m
u
ltip
le
ty
p
es
o
f
wir
eless
t
ec
h
n
o
lo
g
y
in
t
o
th
e
s
am
e
n
etw
o
r
k
,
s
u
ch
as
W
i
-
Fi,
lo
n
g
-
ter
m
ev
o
l
u
tio
n
(
L
T
E
)
,
an
d
5
G.
I
n
5
G
HetNe
ts
,
h
et
er
o
g
en
eity
also
ar
is
es
f
r
o
m
th
e
co
ex
is
ten
ce
o
f
m
u
ltip
le
ce
ll
tier
s
,
in
clu
d
in
g
Ma
cr
o
,
Mic
r
o
,
Pico
,
an
d
Fem
to
ce
lls
,
wh
ich
d
if
f
er
in
co
v
er
ag
e
r
ad
iu
s
,
tr
an
s
m
it
p
o
wer
,
an
d
d
ep
lo
y
m
en
t d
e
n
s
ity
.
HetNe
ts
im
p
r
o
v
e
th
e
co
v
e
r
a
g
e
an
d
ca
p
ac
ity
o
f
5
G
n
etwo
r
k
s
b
u
t a
ls
o
in
cr
ea
s
e
th
e
n
u
m
b
er
o
f
u
s
er
s
in
th
e
n
e
two
r
k
.
T
h
e
r
ef
o
r
e
,
m
u
ltip
le
s
t
u
d
ies
h
av
e
b
ee
n
co
n
d
u
cted
o
n
th
is
to
p
ic
[
2
]
–
[
5
]
.
W
ith
th
e
ev
er
-
g
r
o
win
g
d
e
m
an
d
o
f
u
s
er
s
,
th
e
n
u
m
b
e
r
o
f
u
s
er
s
u
s
in
g
5
G
in
2
0
2
3
h
as
r
ea
ch
e
d
1
.
4
b
illi
o
n
an
d
is
p
r
o
jecte
d
to
co
n
tin
u
e
in
cr
ea
s
in
g
u
n
til
5
.
3
b
illi
o
n
in
d
iv
id
u
al
u
s
er
s
b
y
2
0
2
9
[
2
]
.
T
h
is
d
o
es
n
o
t
i
n
cl
u
d
e
a
ll
t
h
e
ex
t
r
a
d
ev
ic
es,
s
u
c
h
as
in
te
r
n
et
o
f
th
in
g
s
(
I
o
T
)
d
ev
ices
,
w
h
e
r
e
3
0
b
i
lli
o
n
d
e
v
ic
es
a
r
e
co
n
n
e
ct
ed
t
o
a
5
G
n
etw
o
r
k
[
6
]
.
T
h
e
r
e
f
o
r
e,
t
h
e
d
em
a
n
d
f
o
r
5
G
n
etw
o
r
k
s
is
e
x
p
e
cte
d
t
o
s
i
g
n
i
f
ic
a
n
tl
y
in
cr
ea
s
e
o
v
e
r
t
h
e
n
e
x
t
f
ew
y
ea
r
s
.
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
Ma
ch
in
e
lea
r
n
in
g
-
d
r
iven
a
n
a
lysi
s
o
f u
s
er b
a
n
d
w
id
th
a
llo
ca
t
io
n
a
n
d
p
erfo
r
ma
n
ce
in
…
(
P
a
n
g
Wa
i Leo
n
g
)
1237
5
G
p
r
o
m
is
es
to
s
atis
f
y
th
e
n
ee
d
f
o
r
r
eliab
le
a
n
d
lo
w
-
late
n
cy
d
ata
tr
an
s
m
is
s
io
n
s
.
5
G
is
n
ea
r
ly
a
h
u
n
d
r
ed
tim
es
f
aster
th
an
4
G.
Ho
wev
er
,
as
t
h
er
e
is
ex
p
lo
s
iv
e
g
r
o
wth
in
t
h
e
n
u
m
b
er
o
f
u
s
er
s
,
th
e
am
o
u
n
t
o
f
b
an
d
wid
th
m
ay
b
e
in
s
u
f
f
icie
n
t
f
o
r
d
ata
tr
an
s
m
is
s
io
n
r
e
q
u
ir
em
en
ts
,
cr
ea
tin
g
a
b
ac
k
lo
g
o
f
d
ata
.
T
h
er
ef
o
r
e,
m
o
r
e
u
s
er
eq
u
ip
m
e
n
t
(
UE
)
is
co
n
n
ec
ted
to
an
ac
ce
s
s
p
o
in
t
o
r
b
ase
s
tatio
n
,
wh
ich
in
cr
ea
s
es
th
e
laten
cy
an
d
p
ac
k
et
lo
s
s
wh
en
tr
a
n
s
m
itti
n
g
d
ata.
T
h
er
ef
o
r
e,
th
e
u
s
er
’
s
q
u
ality
o
f
ex
p
er
ien
ce
(
Qo
E
)
d
eg
r
a
d
es
as
th
e
b
an
d
wid
th
m
ay
b
e
in
s
u
f
f
icie
n
t
f
o
r
th
e
u
s
er
s
’
n
ee
d
s
[
7
]
.
Nu
m
er
o
u
s
s
tu
d
ies
h
av
e
b
ee
n
co
n
d
u
cted
to
ass
ess
n
etwo
r
k
s
licin
g
an
d
r
eso
u
r
ce
allo
ca
tio
n
s
tr
ateg
ies
to
en
h
an
ce
Qo
E
[
8
]
–
[
1
2
]
,
wh
ich
d
iv
id
e
th
e
av
ailab
le
b
an
d
wid
th
to
p
e
r
f
o
r
m
s
p
ec
if
ic
task
s
b
ased
o
n
n
etwo
r
k
tr
af
f
i
c.
C
u
r
r
en
tly
,
th
e
m
o
s
t
co
m
m
o
n
d
iv
is
io
n
f
o
r
th
ese
n
etwo
r
k
s
lices
is
th
e
v
o
ice
o
v
er
in
ter
n
et
p
r
o
to
co
l
(
Vo
I
P),
o
n
e
f
o
r
v
id
eo
s
er
v
ices
an
d
a
f
in
al
s
lice
f
o
r
b
est
-
ef
f
o
r
t
s
er
v
ices
th
at
a
r
e
n
o
t
ti
m
e
-
s
en
s
itiv
e
(
f
o
r
ex
a
m
p
le,
w
eb
b
r
o
wsi
n
g
o
r
e
m
ail)
[
1
3
]
–
[
1
5
]
.
T
h
ese
s
lices
m
ain
ly
f
o
c
u
s
o
n
r
ea
l
-
tim
e
d
ata
tr
an
s
m
is
s
io
n
to
allo
ca
t
e
m
o
r
e
b
an
d
wid
t
h
f
o
r
s
er
v
i
ce
s
th
at
m
ig
h
t
b
e
u
n
s
atis
f
ac
to
r
y
to
th
e
u
s
er
e
x
p
er
ien
ce
wh
e
n
p
ac
k
ets
ar
e
lo
s
t
o
r
h
av
e
h
ig
h
laten
cy
[
1
6
]
.
T
h
er
ef
o
r
e,
v
ar
io
u
s
n
etwo
r
k
s
licin
g
m
et
h
o
d
s
ar
e
b
ein
g
d
e
v
elo
p
e
d
to
m
an
ag
e
n
etwo
r
k
tr
af
f
ic.
Nu
m
er
o
u
s
b
a
n
d
wid
th
m
an
a
g
em
en
t
m
eth
o
d
s
h
av
e
b
ee
n
d
ev
elo
p
ed
to
r
eg
u
late
n
etwo
r
k
tr
af
f
ic
o
r
p
r
ed
ict
n
etwo
r
k
tr
af
f
ic
o
u
tco
m
es
u
s
in
g
m
ac
h
in
e
lear
n
in
g
(
ML
)
to
ef
f
ec
tiv
ely
al
lo
ca
te
b
an
d
wid
th
[
1
3
]
–
[
1
8
]
.
Netwo
r
k
s
licin
g
m
eth
o
d
s
aim
to
im
p
r
o
v
e
th
e
o
v
er
all
tr
a
f
f
ic
o
f
th
e
n
etwo
r
k
b
y
s
p
litt
in
g
s
er
v
ices
b
ased
o
n
th
e
tr
af
f
ic
u
s
ed
,
en
s
u
r
in
g
th
at
ce
r
tain
s
er
v
ices
h
av
e
allo
ca
ted
b
an
d
wid
th
,
b
u
t
d
o
n
o
t
ap
p
r
o
ac
h
th
e
allo
ca
tio
n
o
f
r
eso
u
r
ce
s
b
ased
o
n
in
d
iv
id
u
al
u
s
er
s
.
As
n
ew
t
ec
h
n
o
lo
g
ies
s
u
ch
as
th
e
in
ter
n
et
o
f
v
eh
icles
(
I
o
V)
an
d
I
o
T
ar
e
b
ein
g
d
ev
elo
p
e
d
,
th
e
q
u
ality
o
f
s
er
v
ice
(
Qo
S)
r
eq
u
ir
ed
b
y
ea
ch
s
er
v
ice
will
v
ar
y
[
1
9
]
.
Ser
v
ice
-
ce
n
tr
ic
r
eso
u
r
ce
allo
ca
tio
n
m
a
y
n
o
t
ac
h
iev
e
th
e
r
eq
u
ir
e
d
f
in
e
-
g
r
ain
ed
co
n
tr
o
l
o
f
r
eso
u
r
ce
allo
ca
tio
n
.
C
u
r
r
en
t
r
eso
u
r
ce
allo
ca
tio
n
m
eth
o
d
s
d
o
n
o
t
co
n
s
id
er
th
e
Qo
S
s
atis
f
a
ctio
n
o
f
in
d
iv
id
u
al
u
s
er
s
,
an
d
s
lices
ar
e
n
o
t
m
ad
e
to
m
ee
t u
s
er
s
’
ex
p
ec
tatio
n
s
[
1
4
]
.
Alth
o
u
g
h
m
an
y
ef
f
o
r
ts
h
av
e
b
ee
n
m
ad
e
to
im
p
r
o
v
e
n
etwo
r
k
-
ce
n
tr
ic
r
eso
u
r
ce
allo
ca
tio
n
an
d
m
an
y
alg
o
r
ith
m
s
h
av
e
b
ee
n
d
esig
n
e
d
,
th
ese
alg
o
r
ith
m
s
d
o
n
o
t
co
n
s
id
er
th
e
r
eso
u
r
ce
s
th
at
ea
ch
u
s
er
n
ee
d
s
o
r
th
eir
lev
el
o
f
s
at
is
f
ac
tio
n
[
1
8
]
,
[
2
0
]
.
T
h
er
ef
o
r
e
,
th
e
p
r
o
p
o
s
ed
s
u
r
v
ey
aim
s
to
in
v
esti
g
ate
a
u
s
er
-
ce
n
tr
ic
s
o
lu
tio
n
to
allo
ca
te
b
an
d
wid
th
to
v
a
r
io
u
s
u
s
er
s
b
ased
o
n
th
eir
Qo
E
r
eq
u
ir
em
en
ts
.
T
h
e
s
u
r
v
ey
aim
s
to
a
n
aly
ze
ML
in
u
s
er
-
ce
n
tr
ic
b
a
n
d
wid
t
h
allo
ca
tio
n
in
5
G
HetNe
ts
.
ML
-
b
ased
alg
o
r
ith
m
s
allo
w
th
e
s
y
s
tem
to
lear
n
f
r
o
m
its
ex
p
er
ien
ce
with
o
u
t
th
e
h
elp
o
f
p
r
o
g
r
am
m
in
g
.
T
h
er
ef
o
r
e,
it
m
ak
es
th
e
s
y
s
tem
d
y
n
am
ic
in
n
atu
r
e,
as
it
lear
n
s
as
m
o
r
e
d
ata
is
o
b
tain
ed
an
d
ch
a
n
g
e
s
d
ep
en
d
in
g
o
n
th
e
s
ce
n
ar
io
.
T
o
d
ay
'
s
telec
o
m
m
u
n
icatio
n
s
in
d
u
s
tr
y
u
s
es
a
wid
e
v
ar
iety
o
f
ML
alg
o
r
ith
m
s
,
b
u
t
th
e
m
ajo
r
ity
f
all
in
to
s
u
p
er
v
is
ed
lear
n
in
g
(
SL)
,
u
n
s
u
p
er
v
is
ed
lea
r
n
in
g
(
UL
)
,
o
r
r
ein
f
o
r
ce
m
en
t le
ar
n
in
g
(
R
L
)
.
S
L
is
a
m
o
d
e
l
t
h
a
t
r
e
q
u
i
r
e
s
t
h
e
d
a
t
a
t
o
b
e
l
a
b
el
l
e
d
,
as
t
h
e
m
o
d
e
l
is
t
a
r
g
e
t
e
d
t
o
l
e
a
r
n
s
p
e
ci
f
i
c
in
f
o
r
m
a
t
i
o
n
f
r
o
m
t
h
e
d
a
t
a
s
e
t
.
T
h
e
r
e
f
o
r
e
,
t
h
e
M
L
m
o
d
e
l
s
t
u
d
i
e
s
p
a
t
t
e
r
n
s
f
r
o
m
a
d
a
t
a
s
e
t
t
o
d
e
t
e
r
m
i
n
e
t
h
e
r
e
l
a
t
i
o
n
s
h
i
p
b
e
t
w
e
e
n
t
h
e
i
n
p
u
t
d
at
a
a
n
d
t
h
e
d
es
i
r
e
d
o
u
t
p
u
t
[
2
1
]
.
T
h
e
r
a
w
a
n
d
u
n
l
ab
e
l
e
d
d
a
t
as
e
ts
s
u
p
p
l
y
a
n
u
n
s
u
p
e
r
v
i
s
e
d
M
L
m
o
d
e
l.
T
h
e
d
a
t
a
w
e
r
e
t
h
e
n
a
n
a
l
y
z
e
d
to
c
r
e
a
t
e
d
i
f
f
e
r
e
n
t
cl
u
s
t
e
r
s
.
T
h
e
M
L
m
o
d
e
l
l
e
a
r
n
s
g
e
n
e
r
a
l
p
at
t
e
r
n
s
a
n
d
p
a
r
a
l
l
el
s
b
e
t
w
e
e
n
d
at
a
p
o
i
n
ts
a
n
d
t
h
e
n
ca
t
e
g
o
r
i
z
e
s
t
h
e
d
a
t
a
i
n
t
o
a
g
r
o
u
p
t
h
a
t
a
l
l
o
ws
t
h
e
m
o
d
e
l t
o
d
e
c
id
e
b
a
s
e
d
o
n
t
h
e
d
at
a
t
y
p
e
[
1
3
]
,
[
2
2
]
.
R
L
t
e
ac
h
e
s
a
m
o
d
e
l
b
as
e
d
o
n
f
e
e
d
b
a
c
k
.
A
s
t
h
e
m
o
d
e
l
h
as
d
e
ci
s
i
o
n
-
m
a
k
i
n
g
c
a
p
a
b
il
i
ti
e
s
f
o
r
its
a
c
ti
o
n
s
,
w
e
u
s
e
d
a
d
a
t
a
p
o
i
n
t
/
r
e
f
e
r
e
n
c
e
f
o
r
i
t
s
d
e
c
i
s
i
o
n
.
R
L
m
o
d
e
l
i
s
e
i
t
h
e
r
r
e
wa
r
d
e
d
o
r
p
u
n
i
s
h
e
d
f
o
r
i
t
s
a
c
t
i
o
n
s
.
T
h
e
r
e
f
o
r
e
,
t
h
i
s
m
o
d
e
l
c
o
n
s
t
a
n
tl
y
l
o
o
k
s
f
o
r
a
b
al
a
n
c
e
b
et
w
e
e
n
r
e
w
a
r
d
s
a
n
d
e
x
p
l
o
r
a
t
i
o
n
i
n
i
ts
d
e
c
i
s
i
o
n
,
t
r
y
i
n
g
t
o
f
i
n
d
t
h
e
b
e
s
t
d
e
c
is
i
o
n
s
t
o
a
c
h
ie
v
e
t
h
e
h
i
g
h
e
s
t
r
e
wa
r
d
s
[
2
3
]
.
A
n
e
x
a
m
p
l
e
al
g
o
r
i
t
h
m
is
t
h
e
Q
-
l
e
a
r
n
i
n
g
a
l
g
o
r
it
h
m
,
w
h
i
c
h
g
i
v
es
m
o
d
e
l
r
e
w
a
r
d
s
b
a
s
e
d
o
n
t
h
e
“Q
”
v
a
l
u
e
f
o
r
it
s
d
e
c
is
i
o
n
.
T
h
is
“Q
”
v
al
u
e
is
d
e
t
e
r
m
i
n
e
d
b
y
t
h
e
d
e
s
i
g
n
e
r
.
T
h
e
“
Q
”
v
a
l
u
e
is
d
e
t
e
r
m
i
n
e
d
b
y
t
h
e
t
h
r
o
u
g
h
p
u
t
f
o
r
a
l
l
u
s
e
r
s
a
n
d
w
il
l
g
a
i
n
m
o
r
e
r
e
w
a
r
d
s
f
o
r
h
i
g
h
e
r
t
h
r
o
u
g
h
p
u
t
.
T
h
e
HetNe
t
ar
ch
itectu
r
e
aim
s
to
co
m
b
i
n
e
v
a
r
io
u
s
wir
eless
tech
n
o
lo
g
ies
in
to
th
e
s
am
e
n
et
wo
r
k
,
a
n
d
r
esear
ch
er
s
h
av
e
b
ee
n
in
v
e
s
tig
atin
g
m
eth
o
d
s
o
f
c
o
ex
i
s
ten
ce
with
v
ar
io
u
s
wir
ele
s
s
co
m
m
u
n
icatio
n
tech
n
o
lo
g
ies.
R
esear
ch
co
n
d
u
cted
o
n
th
e
co
ex
is
ten
ce
o
f
L
T
E
an
d
W
i
-
Fi
s
h
o
wed
p
er
f
o
r
m
an
ce
d
e
g
r
ad
atio
n
as
th
e
o
v
er
all
th
r
o
u
g
h
p
u
t
was
d
eg
r
ad
e
d
,
r
ed
u
cin
g
th
e
u
s
er
s
'
Qo
E
[
2
4
]
,
[
2
5
]
.
Var
io
u
s
s
tu
d
ies
h
av
e
b
ee
n
co
n
d
u
cte
d
to
r
ed
u
ce
th
e
d
eg
r
ad
atio
n
o
f
th
r
o
u
g
h
p
u
t
o
win
g
to
in
ter
f
er
en
ce
f
r
o
m
th
e
HetNe
t
s
y
s
tem
.
Sev
er
al
m
o
d
u
latio
n
m
eth
o
d
s
h
av
e
b
ee
n
in
v
esti
g
ated
to
f
in
d
m
o
d
u
latio
n
m
eth
o
d
s
th
at
r
ed
u
ce
th
e
ef
f
ec
ts
o
f
in
ter
f
er
en
ce
b
etwe
en
th
e
tech
n
o
lo
g
ies
[
2
4
]
.
Var
io
u
s
s
ch
ed
u
ler
s
f
o
r
r
eso
u
r
ce
allo
ca
tio
n
ar
e
b
ein
g
test
ed
to
im
p
r
o
v
e
th
r
o
u
g
h
p
u
t
an
d
s
p
ec
tr
al
ef
f
icien
cy
to
en
h
a
n
ce
Qo
S
[
2
5
]
.
T
h
ese
wo
r
k
s
aim
to
m
ee
t
Qo
S
r
eq
u
ir
em
en
t
s
f
o
r
r
ea
l
-
tim
e
s
er
v
ices
s
u
ch
as
v
id
eo
an
d
Vo
I
P,
in
a
HetNe
t
en
v
ir
o
n
m
e
n
t.
R
eso
u
r
ce
allo
ca
tio
n
m
eth
o
d
s
h
av
e
b
ee
n
p
r
o
p
o
s
ed
to
en
s
u
r
e
f
air
n
ess
an
d
h
ig
h
th
r
o
u
g
h
p
u
t
f
o
r
m
u
ltip
le
ac
ce
s
s
m
eth
o
d
s
s
u
ch
as
n
o
n
-
o
r
th
o
g
o
n
al
m
u
ltip
le
ac
ce
s
s
(
NOM
A)
[
2
6
]
.
Ov
er
all,
d
u
e
to
th
e
HetNe
t
a
r
ch
itectu
r
e
d
eg
r
ad
i
n
g
t
h
e
o
v
er
all
th
r
o
u
g
h
p
u
t
an
d
Qo
E
o
f
th
e
u
s
er
s
,
v
ar
io
u
s
s
tu
d
ies
h
av
e
b
ee
n
co
n
d
u
cted
to
i
m
p
r
o
v
e
th
r
o
u
g
h
p
u
t
wh
en
v
ar
i
o
u
s
s
ig
n
als
o
v
er
lap
an
d
in
ter
f
e
r
e
with
ea
ch
o
th
er
.
E
x
is
tin
g
r
esear
ch
an
d
s
ev
er
al
s
u
r
v
ey
s
d
is
cu
s
s
th
e
u
s
ag
e
o
f
n
etwo
r
k
s
licin
g
f
o
r
r
eso
u
r
ce
allo
ca
tio
n
an
d
its
b
en
ef
its
.
E
x
is
tin
g
r
esear
ch
also
co
n
s
id
er
s
im
p
lem
en
t
in
g
ML
f
o
r
tr
a
f
f
ic
p
r
e
d
ictio
n
f
o
r
o
p
tim
al
n
etwo
r
k
s
lices.
ML
tech
n
iq
u
es
f
o
r
n
et
wo
r
k
s
licin
g
en
h
a
n
ce
u
s
er
s
’
Qo
E
,
b
u
t
a
k
ey
is
s
u
e
with
th
e
s
e
s
tu
d
ies
is
th
e
lack
o
f
e
x
p
lo
r
atio
n
o
f
n
etwo
r
k
o
v
e
r
lo
ad
in
g
s
itu
atio
n
s
.
T
h
er
ef
o
r
e,
th
is
s
u
r
v
e
y
is
m
o
tiv
ated
to
e
x
p
lo
r
e
u
s
er
-
ce
n
t
r
ic
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
2
3
6
-
1
2
4
8
1238
b
an
d
wid
th
allo
ca
tio
n
alg
o
r
ith
m
s
th
at
ca
n
p
o
ten
tially
im
p
r
o
v
e
th
e
Q
o
E
o
f
u
s
er
s
u
n
d
er
th
e
o
v
er
lo
ad
ed
n
etwo
r
k
.
I
n
ad
d
itio
n
,
th
e
c
u
r
r
en
t
ML
al
g
o
r
ith
m
s
u
s
ed
in
r
eso
u
r
ce
allo
ca
tio
n
an
d
th
e
p
o
te
n
tial
im
p
le
m
en
tatio
n
in
u
s
er
-
ce
n
tr
ic
r
eso
u
r
ce
allo
ca
tio
n
al
g
o
r
ith
m
s
h
a
v
e
also
b
ee
n
ex
p
lo
r
ed
.
T
h
e
f
o
llo
win
g
r
esear
ch
q
u
esti
o
n
s
wer
e
in
ten
d
ed
to
b
e
ad
d
r
ess
ed
b
y
t
h
is
s
u
r
v
ey
:
a.
W
h
at
ar
e
th
e
ex
is
tin
g
alg
o
r
ith
m
s
d
ev
elo
p
ed
f
o
r
u
s
er
-
ce
n
tr
ic
r
eso
u
r
ce
allo
ca
tio
n
?
b.
W
h
ich
r
esear
ch
d
i
r
ec
tio
n
s
ar
e
em
er
g
in
g
in
th
e
s
tu
d
y
o
f
ML
-
b
ased
alg
o
r
ith
m
s
f
o
r
u
s
e
r
-
ce
n
tr
ic
r
eso
u
r
ce
allo
ca
tio
n
an
d
n
etwo
r
k
t
r
af
f
ic
p
r
ed
ictio
n
?
T
h
e
f
o
l
l
o
w
i
n
g
s
e
c
ti
o
n
r
e
v
i
e
ws
t
h
e
p
a
p
e
r
,
p
r
o
v
i
d
e
s
a
s
u
m
m
a
r
y
o
f
t
h
e
c
u
r
r
e
n
t
w
o
r
k
,
a
n
d
d
e
l
iv
e
r
s
a
n
i
n
-
d
e
p
t
h
a
n
a
l
y
s
i
s
o
f
h
i
g
h
l
y
r
e
l
at
ed
s
t
u
d
i
es
.
F
i
r
s
t
,
a
n
o
v
e
r
v
ie
w
o
f
n
e
t
w
o
r
k
s
l
i
ci
n
g
a
l
g
o
r
i
t
h
m
s
is
i
n
t
r
o
d
u
c
e
d
,
a
n
d
t
h
e
c
u
r
r
e
n
t
a
l
g
o
r
i
t
h
m
s
e
m
p
l
o
y
e
d
in
n
e
t
w
o
r
k
s
li
c
i
n
g
a
r
e
d
is
c
u
s
s
ed
.
T
h
e
s
u
r
v
e
y
t
h
e
n
a
n
a
l
y
z
e
d
th
e
p
r
o
p
o
s
e
d
u
s
e
r
-
c
e
n
t
r
i
c
a
l
g
o
r
it
h
m
s
.
Pe
r
f
o
r
m
i
n
g
a
n
i
n
-
d
e
p
t
h
a
n
a
l
y
s
is
o
f
t
h
e
t
w
o
w
o
r
k
s
,
a
s
t
h
e
r
e
i
s
a
l
a
c
k
o
f
c
u
r
r
e
n
t
r
e
s
e
a
r
c
h
b
e
i
n
g
c
o
n
d
u
c
t
e
d
o
n
u
s
e
r
-
c
e
n
t
r
ic
r
es
o
u
r
c
e
a
l
l
o
c
at
i
o
n
a
l
g
o
r
it
h
m
s
.
T
h
e
p
a
p
e
r
t
h
e
n
f
o
ll
o
w
s
w
it
h
r
e
v
ie
w
s
o
f
t
h
e
c
u
r
r
e
n
t
w
o
r
k
b
e
i
n
g
d
o
n
e
o
n
M
L
a
n
d
t
h
e
c
o
m
p
a
r
i
s
o
n
s
t
h
a
t
a
r
e
m
a
d
e
.
F
i
n
a
l
l
y
,
w
e
e
x
p
l
o
r
e
d
a
l
g
o
r
it
h
m
s
f
o
r
m
a
n
a
g
i
n
g
c
o
n
g
e
s
t
i
o
n
i
n
5
G
He
t
N
et
s
.
2.
SURVE
Y
M
E
T
H
O
DO
L
O
G
Y
W
e
f
o
llo
wed
a
lig
h
tweig
h
t
s
y
s
tem
atic
r
ev
iew
p
r
o
t
o
co
l.
D
ig
ital
lib
r
ar
ies
u
s
ed
wer
e
I
E
E
E
Xp
lo
r
e,
Sco
p
u
s
,
an
d
W
eb
o
f
Scien
ce
.
Sear
ch
s
tr
in
g
s
ap
p
lied
to
th
e
titl
e,
ab
s
tr
ac
t,
o
r
k
e
y
wo
r
d
s
wer
e
(
“u
s
er
‑
ce
n
tr
ic
”
OR
“Qo
E
‑
awa
r
e”
OR
“u
til
ity
‑
b
ased
”)
AND
(
“r
eso
u
r
ce
allo
ca
tio
n
”
OR
“b
an
d
wid
t
h
allo
ca
tio
n
”
OR
“a
d
m
is
s
io
n
co
n
tr
o
l”
)
AND
(
“
5
G”
OR
“He
tNet”
OR
“RA
N
”)
AND
(
“m
ac
h
in
e
lear
n
in
g
”
OR
“d
ee
p
lear
n
in
g
”
OR
“r
ein
f
o
r
ce
m
en
t
lear
n
i
n
g
”)
.
T
h
e
tim
ef
r
am
e
c
o
v
er
ed
is
J
an
u
ar
y
2
0
1
9
to
Dec
em
b
er
2
0
2
5
.
E
lig
ib
le
p
a
p
er
s
in
clu
d
ed
p
ee
r
‑
r
e
v
iewe
d
jo
u
r
n
al
o
r
f
lag
s
h
ip
co
n
f
er
e
n
ce
p
u
b
licatio
n
s
in
E
n
g
lis
h
with
a
p
r
im
ar
y
f
o
cu
s
o
n
u
s
er
‑
ce
n
tr
ic
r
eso
u
r
ce
allo
ca
ti
o
n
(
UC
R
A)
o
r
ML
‑
d
r
iv
en
al
lo
ca
tio
n
r
elev
an
t
to
5
G
o
r
6
G
ac
r
o
s
s
th
e
r
ad
io
ac
ce
s
s
n
etwo
r
k
(
R
AN)
,
co
r
e,
o
r
ed
g
e.
I
tem
s
wer
e
ex
clu
d
e
d
if
th
ey
f
o
cu
s
ed
s
o
lely
o
n
s
er
v
ice‑
ce
n
tr
ic
s
licin
g
with
o
u
t
a
u
s
er
p
e
r
s
p
ec
tiv
e,
w
er
e
n
o
n
‑
tech
n
ical,
o
r
wer
e
n
o
t
wr
itten
in
E
n
g
lis
h
.
Scr
ee
n
in
g
was
p
er
f
o
r
m
e
d
b
y
ev
alu
atin
g
titl
es
an
d
ab
s
tr
ac
ts
,
f
o
llo
wed
b
y
f
u
ll‑te
x
t
ass
ess
m
en
t.
T
h
e
s
tu
d
ies
th
at
p
ass
ed
s
cr
ee
n
in
g
wer
e
t
h
en
s
y
n
th
esized
th
em
atica
lly
.
T
h
is
s
u
r
v
ey
is
m
o
tiv
ated
b
y
th
e
n
ee
d
to
b
etter
u
n
d
er
s
tan
d
u
s
er
‑
ce
n
tr
ic
r
eso
u
r
ce
allo
ca
tio
n
,
wh
ic
h
r
ef
er
s
to
d
ec
is
io
n
‑
m
a
k
in
g
b
a
s
ed
o
n
in
d
iv
i
d
u
al
u
s
er
u
tili
t
y
,
p
r
io
r
ity
,
co
n
te
x
t,
o
r
ec
o
n
o
m
ic
f
ac
to
r
s
,
wh
ile
in
co
r
p
o
r
atin
g
m
ac
h
in
e
lear
n
i
n
g
to
s
u
p
p
o
r
t
p
r
e
d
ictio
n
,
cl
u
s
ter
in
g
,
an
d
clo
s
ed
‑
lo
o
p
c
o
n
tr
o
l.
T
h
e
s
tu
d
y
aim
s
to
an
s
wer
two
k
ey
r
esear
ch
q
u
esti
o
n
s
.
First,
wh
at
ty
p
es
o
f
u
s
er
‑
ce
n
tr
ic
r
eso
u
r
ce
allo
ca
tio
n
al
g
o
r
ith
m
s
h
av
e
b
ee
n
p
r
o
p
o
s
ed
f
o
r
5
G
h
eter
o
g
e
n
eo
u
s
n
etwo
r
k
s
,
an
d
h
o
w
th
ey
d
if
f
er
in
ter
m
s
o
f
ass
u
m
p
tio
n
s
,
p
e
r
f
o
r
m
a
n
ce
m
etr
ics,
an
d
o
u
tco
m
es.
Seco
n
d
,
wh
ic
h
f
am
ilies
o
f
m
ac
h
in
e
lea
r
n
i
n
g
tech
n
i
q
u
es
ar
e
m
o
s
t
s
u
itab
le
f
o
r
p
r
e
d
ictio
n
,
clu
s
ter
in
g
,
an
d
r
ea
l‑
tim
e
co
n
tr
o
l
task
s
with
in
th
ese
alg
o
r
ith
m
s
,
alo
n
g
with
th
eir
p
r
ac
tical
lim
itatio
n
s
.
T
o
ad
d
r
ess
th
ese
q
u
esti
o
n
s
,
th
e
s
u
r
v
ey
o
r
g
a
n
izes
ex
is
tin
g
r
esear
ch
in
to
a
s
tr
u
ctu
r
ed
tax
o
n
o
m
y
,
p
r
o
v
id
es
co
m
p
ar
ativ
e
tab
les,
an
d
in
clu
d
es
clar
if
y
in
g
f
ig
u
r
es.
I
t
also
s
y
n
th
esizes
th
e
av
ailab
le
ev
id
en
ce
in
to
p
r
ac
tical
g
u
id
an
ce
wh
ile
m
ain
tain
i
n
g
th
e
in
teg
r
ity
o
f
th
e
o
r
ig
in
al
d
escr
ip
tiv
e
co
n
ten
t.
Fig
u
r
e
1
s
u
m
m
ar
izes
th
e
s
elec
tio
n
f
lo
w.
Fig
u
r
e
1
.
T
h
e
s
elec
tio
n
p
r
o
ce
s
s
an
d
s
cr
ee
n
in
g
c
r
iter
ia
3.
ANALY
SI
S O
F
US
E
R
-
C
E
N
T
RIC R
E
SO
U
RCE A
L
L
O
C
AT
I
O
N
R
ec
en
t
u
s
er
-
ce
n
tr
ic
s
tu
d
ies
f
u
r
th
er
illu
s
tr
ate
p
r
ac
tical
s
ce
n
ar
io
s
in
o
v
er
lo
ad
e
d
g
NB
s
[
2
7
]
–
[
3
1
]
.
W
e
g
r
o
u
p
p
r
i
o
r
wo
r
k
s
b
y
d
ec
is
io
n
d
r
iv
e
r
s
(
Qo
E
/u
tili
ty
,
ec
o
n
o
m
ics/
m
ar
k
et)
,
b
y
ML
p
ar
a
d
ig
m
(
SL/UL
/R
L
)
,
an
d
R
e
c
o
r
ds
i
de
nt
i
f
i
e
d
t
h
r
o
u
g
h
d
at
ab
as
e
s
-
IE
E
E
Xpl
o
r
e
,
Sc
o
p
u
s
,
W
o
S
(
n=
1,
124)
A
f
t
e
r
du
pl
i
c
at
e
s
r
e
m
o
v
e
d
(
n=
942)
S
c
r
e
e
ne
d
by
t
i
t
l
e
/abs
t
r
ac
t
(
n=
942)
-
>
Excl
ud
e
d
(
n=
812)
F
ul
l
-
t
e
xt
a
c
c
e
ss
e
d
f
o
r
e
l
i
g
i
bi
l
i
t
y
(
n=
130)
-
>
E
xc
l
ud
e
d
(
n=
77)
St
u
d
i
e
s
i
n
c
l
u
d
e
d
i
n
su
r
v
e
y
(
n=
53)
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
Ma
ch
in
e
lea
r
n
in
g
-
d
r
iven
a
n
a
lysi
s
o
f u
s
er b
a
n
d
w
id
th
a
llo
ca
t
io
n
a
n
d
p
erfo
r
ma
n
ce
in
…
(
P
a
n
g
Wa
i Leo
n
g
)
1239
b
y
d
ep
lo
y
m
en
t
lo
cu
s
(
ed
g
e/D2
D)
,
to
en
ab
le
cr
o
s
s
-
co
m
p
a
r
is
o
n
wh
ile
p
r
eser
v
in
g
th
e
d
etail
s
o
f
ea
ch
s
tu
d
y
.
T
h
e
o
v
er
all
tax
o
n
o
m
y
th
at
lin
k
s
M
L
p
ar
ad
ig
m
s
,
n
etwo
r
k
lay
er
s
,
an
d
UC
R
A
th
em
es is
s
h
o
wn
in
Fig
u
r
e
2
.
R
esear
ch
co
n
d
u
cted
b
y
C
h
e
n
et
a
l.
[
3
2
]
in
v
esti
g
ated
t
h
e
im
p
o
r
tan
ce
o
f
UC
R
A
f
o
r
m
o
b
ile
co
m
m
u
n
icatio
n
an
d
ex
p
lain
e
d
th
e
im
p
o
r
tan
ce
o
f
r
esear
ch
i
n
th
is
f
ield
f
r
o
m
an
ec
o
n
o
m
i
c
p
er
s
p
ec
tiv
e.
T
h
is
d
em
o
n
s
tr
ates
th
e
v
alid
ity
o
f
a
UC
R
A
alg
o
r
ith
m
in
wh
ich
h
i
g
h
er
-
p
r
io
r
ity
u
s
er
s
ar
e
allo
ca
ted
m
o
r
e
r
eso
u
r
ce
s
,
wh
ile
lo
wer
-
p
r
io
r
ity
u
s
er
s
h
av
e
f
ewe
r
r
eso
u
r
ce
s
.
Usi
n
g
a
m
eth
o
d
ca
lled
th
e
c
u
m
u
lativ
e
d
is
tr
ib
u
tio
n
f
u
n
ctio
n
(
C
DF)
,
th
ey
d
em
o
n
s
tr
ated
th
at
u
s
in
g
a
UC
R
A
alg
o
r
ith
m
h
as
th
e
p
o
ten
tial
to
p
r
o
v
id
e
a
h
ig
h
er
o
v
er
all
th
r
o
u
g
h
p
u
t
wh
en
t
h
er
e
is
a
h
i
g
h
am
o
u
n
t
o
f
tr
a
f
f
ic.
Dem
o
n
s
tr
atin
g
th
at
wh
e
n
th
er
e
is
m
o
r
e
tr
af
f
ic,
it
m
i
g
h
t
b
e
b
en
ef
icial
to
p
r
o
v
id
e
h
ig
h
er
d
ata
r
ates
to
u
s
er
s
o
f
a
h
ig
h
e
r
p
r
io
r
ity
a
n
d
p
r
o
v
id
e
t
h
e
m
in
i
m
u
m
f
o
r
u
s
er
s
o
f
a
lo
wer
p
r
i
o
r
ity
.
T
h
is
wo
r
k
p
r
esen
ted
th
e
id
ea
o
f
UC
R
A
in
2
0
2
2
b
u
t
h
as
r
esear
ch
ed
alg
o
r
ith
m
s
th
at
s
h
o
u
l
d
b
e
u
s
ed
f
o
r
d
y
n
a
m
ic
allo
ca
tio
n
.
Fig
u
r
e
2
.
R
elatio
n
s
h
ip
s
am
o
n
g
ML
p
ar
ad
ig
m
s
,
n
etwo
r
k
lay
er
s
,
an
d
u
s
er
-
ce
n
t
r
ic
r
eso
u
r
ce
allo
ca
tio
n
th
em
es
3
.
1
.
Net
w
o
rk
s
licing
in 5
G
B
ef
o
r
e
lo
o
k
i
n
g
i
n
to
UC
R
A,
o
n
e
k
ey
f
ea
tu
r
e
o
f
5
G
is
n
etwo
r
k
s
licin
g
,
wh
ic
h
ca
n
p
r
o
v
id
e
a
r
an
g
e
o
f
s
er
v
ices
f
o
r
v
ar
io
u
s
ty
p
es
o
f
d
ev
ices.
Un
lik
e
o
th
er
g
en
e
r
atio
n
s
o
f
m
o
b
ile
co
m
m
u
n
icatio
n
,
5
G
p
r
o
v
id
es
th
r
e
e
d
is
tin
ct
s
er
v
ices,
i.e
.
,
en
h
an
ce
d
m
o
b
ile
b
r
o
ad
b
a
n
d
(
eM
B
B
)
,
m
ass
iv
e
m
ac
h
in
e
-
ty
p
e
co
m
m
u
n
icatio
n
(
m
MT
C
)
,
an
d
u
ltra
-
r
eliab
le
lo
w
-
laten
cy
co
m
m
u
n
icatio
n
(
UR
L
L
C
)
[
3
3
]
.
eM
B
B
i
s
u
s
ed
f
o
r
h
ig
h
-
b
an
d
wid
th
s
er
v
ices,
s
u
ch
as
v
id
e
o
s
tr
ea
m
in
g
.
T
h
e
m
MT
C
is
m
ain
ly
u
s
ed
f
o
r
h
i
g
h
am
o
u
n
ts
o
f
co
m
m
u
n
icatio
n
b
etwe
en
d
e
v
ices,
wh
ich
is
m
ain
ly
n
ee
d
ed
f
o
r
I
o
T
d
ev
ices.
UR
L
L
C
is
u
s
ed
f
o
r
u
ltra
-
lo
w
-
laten
c
y
c
o
m
m
u
n
icatio
n
,
s
u
ch
th
at
it
is
u
s
ed
f
o
r
a
u
to
n
o
m
o
u
s
v
eh
icles
[
3
4
]
.
T
h
e
co
m
m
o
n
n
etwo
r
k
s
licin
g
m
eth
o
d
c
o
n
s
is
ts
o
f
p
r
e
-
d
eter
m
in
ed
lay
er
s
,
i.e
.
,
th
e
s
er
v
ice
in
s
tan
ce
lay
er
,
n
etwo
r
k
s
lice
lay
er
,
an
d
r
es
o
u
r
ce
lay
er
.
T
h
e
m
ain
lay
er
t
h
at
d
eter
m
in
es
th
e
s
lices i
s
th
e
n
etwo
r
k
s
lice
lay
e
r
[
3
4
]
.
T
h
e
n
etwo
r
k
s
lice
lay
er
will h
av
e
p
r
e
-
d
eter
m
in
ed
s
lic
es tailo
r
ed
f
o
r
ea
ch
u
s
e
ca
s
e,
b
u
t th
is
is
n
o
t d
y
n
am
ic.
T
h
e
p
r
e
-
d
eter
m
in
e
d
s
lices c
an
o
n
ly
ca
teg
o
r
ize
a
g
r
o
u
p
o
f
u
s
e
ca
s
es
.
E
x
i
s
t
i
n
g
r
e
s
ea
r
c
h
[
3
4
]
–
[
3
6
]
i
n
v
e
s
t
i
g
a
te
d
n
e
t
w
o
r
k
s
l
i
c
i
n
g
o
p
t
i
m
i
z
a
ti
o
n
,
a
n
d
r
e
s
e
a
r
c
h
c
o
n
d
u
c
t
e
d
b
y
D
a
n
g
i
a
n
d
L
a
l
w
a
n
i
[
3
3
]
e
x
p
l
o
r
e
d
t
h
e
u
s
e
o
f
M
L
i
n
d
i
v
i
d
i
n
g
t
h
e
s
l
ic
e
t
o
d
y
n
a
m
i
c
a
l
l
y
p
r
e
d
i
ct
t
h
e
o
p
t
i
m
a
l
s
l
i
c
e
.
T
h
e
s
t
u
d
y
e
x
a
m
i
n
e
d
t
h
e
u
s
e
o
f
M
L
t
o
e
x
t
r
a
c
t
c
e
r
t
ai
n
f
e
a
t
u
r
es
f
r
o
m
n
e
t
w
o
r
k
t
r
a
f
f
i
c
a
n
d
s
l
i
c
e
th
e
b
a
n
d
w
i
d
t
h
b
a
s
e
d
o
n
h
i
g
h
l
y
u
s
e
d
s
e
r
v
i
c
e
s
.
M
L
t
e
c
h
n
i
q
u
e
s
i
n
c
l
u
d
e
r
a
n
d
o
m
f
o
r
e
s
t
,
k
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
(
K
N
N
)
,
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
s
(
S
V
M
)
,
a
n
d
d
e
c
is
i
o
n
t
r
e
e
.
T
h
e
n
e
t
w
o
r
k
w
as
s
p
l
i
t
i
n
t
o
t
h
r
e
e
d
i
f
f
e
r
e
n
t
o
p
ti
m
a
l
s
l
ic
e
s
b
as
e
d
o
n
t
r
a
f
f
ic
(
e
M
B
B
,
m
M
T
C
,
a
n
d
UR
L
L
C
)
u
s
i
n
g
M
L
a
l
g
o
r
i
t
h
m
s
.
T
h
is
is
a
c
o
m
m
o
n
n
e
t
w
o
r
k
s
l
i
ci
n
g
s
p
l
i
t
p
e
r
f
o
r
m
e
d
i
n
a
H
e
t
N
et
t
o
p
o
l
o
g
y
t
o
i
n
t
e
g
r
a
t
e
v
a
r
i
o
u
s
d
e
v
i
c
e
s
a
n
d
t
r
a
f
f
i
c
[
3
7
]
.
I
t
s
h
o
w
e
d
t
h
a
t
t
h
e
r
a
n
d
o
m
f
o
r
e
s
t
y
i
e
l
d
e
d
t
h
e
m
o
s
t
a
c
c
u
r
a
t
e
r
es
u
l
ts
,
b
u
t
a
l
s
o
s
h
o
w
e
d
t
h
a
t
a
l
l
a
l
g
o
r
i
t
h
m
s
i
m
p
r
o
v
e
d
t
h
e
j
it
t
e
r
,
p
a
c
k
et
l
o
s
s
a
n
d
l
a
t
e
n
c
y
w
i
t
h
o
u
t
t
h
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.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
2
3
6
-
1
2
4
8
1240
d
y
n
a
m
i
c
s
p
li
t
.
T
h
e
p
r
o
p
o
s
e
d
m
e
t
h
o
d
i
m
p
r
o
v
e
s
n
e
tw
o
r
k
e
f
f
i
c
i
e
n
c
y
a
n
d
ca
n
s
e
r
v
e
t
h
e
n
ee
d
s
o
f
t
h
e
r
e
q
u
i
r
e
d
s
e
r
v
i
c
es
f
o
r
t
h
e
u
s
e
r
.
A
n
o
t
h
e
r
s
t
u
d
y
w
as
c
o
n
d
u
c
t
e
d
to
i
n
v
e
s
t
i
g
a
te
s
p
li
t
ti
n
g
a
n
d
g
e
n
e
r
a
t
i
n
g
n
e
t
w
o
r
k
s
li
c
es
b
a
s
e
d
o
n
M
L
[
3
8
]
.
I
n
s
t
e
a
d
o
f
s
l
i
ci
n
g
t
h
e
m
i
n
t
o
t
h
r
e
e
d
i
f
f
e
r
e
n
t
s
l
ic
e
s
,
t
h
e
M
L
m
o
d
e
l
c
a
n
c
r
e
at
e
m
u
l
ti
p
l
e
n
ew
s
l
i
c
es
.
T
h
e
a
b
il
i
t
y
t
o
d
y
n
a
m
i
c
a
l
l
y
g
e
n
e
r
a
t
e
n
e
w
s
l
i
ce
s
d
e
p
e
n
d
s
o
n
t
h
e
u
s
e
r
s
’
n
e
e
d
s
,
w
h
i
l
e
e
n
s
u
r
i
n
g
p
r
e
-
d
e
f
i
n
e
d
Q
o
S
r
e
q
u
i
r
e
m
e
n
t
s
f
o
r
c
e
r
t
a
i
n
s
e
r
v
i
c
e
s
.
A
n
S
V
M
i
s
u
s
e
d
t
o
r
e
a
c
t
t
o
s
c
e
n
a
r
i
o
s
w
h
i
l
e
m
a
i
n
t
ai
n
i
n
g
c
e
r
t
a
i
n
s
p
l
it
s
b
a
s
e
d
o
n
t
r
a
i
n
i
n
g
.
I
m
p
r
o
v
e
m
e
n
t
s
i
n
l
a
t
e
n
c
y
a
n
d
c
a
p
a
c
i
t
y
w
e
r
e
r
e
p
o
r
t
e
d
wi
t
h
2
0
u
s
e
r
s
.
H
o
w
e
v
e
r
,
f
u
r
t
h
e
r
r
es
e
a
r
c
h
n
e
e
d
s
t
o
b
e
c
o
n
d
u
c
t
e
d
f
o
r
h
i
g
h
e
r
c
a
p
a
c
i
t
y
a
n
d
d
y
n
a
m
i
c
l
e
a
r
n
i
n
g
.
T
h
e
r
e
f
o
r
e
,
f
u
r
t
h
e
r
r
e
s
e
a
r
c
h
is
b
e
i
n
g
c
o
n
d
u
c
t
e
d
o
n
t
h
e
u
s
e
o
f
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
(
F
L
)
i
n
d
y
n
a
m
i
c
n
e
t
w
o
r
k
s
l
ic
i
n
g
[
3
9
]
.
FL
i
s
a
t
y
p
e
o
f
M
L
i
n
w
h
ic
h
S
L
,
s
u
c
h
as
S
V
M
,
c
a
n
b
e
c
o
n
d
u
c
t
e
d
o
n
a
n
i
n
d
i
v
i
d
u
a
l
d
e
v
i
c
e
,
a
ll
o
w
i
n
g
d
e
c
e
n
t
r
al
iz
e
d
M
L
.
T
h
e
r
e
f
o
r
e
,
n
e
t
w
o
r
k
s
l
i
ci
n
g
n
e
e
d
s
t
o
b
e
i
m
p
l
e
m
e
n
t
e
d
t
o
a
l
l
o
ca
t
e
b
a
n
d
w
i
d
t
h
f
o
r
t
h
e
t
r
a
n
s
m
is
s
i
o
n
/
u
p
d
a
t
e
o
f
t
h
e
m
o
d
e
l
.
F
L
w
as
i
m
p
le
m
e
n
t
e
d
i
n
d
y
n
a
m
i
c
b
a
n
d
w
i
d
t
h
s
l
i
ci
n
g
[
3
9
]
.
T
h
e
m
a
i
n
l
i
m
i
t
at
i
o
n
o
f
t
h
e
s
e
p
r
o
p
o
s
ed
m
e
t
h
o
d
s
i
s
t
h
e
c
o
m
p
u
t
a
t
i
o
n
al
r
e
s
o
u
r
c
e
s
r
e
q
u
i
r
e
d
f
o
r
t
h
e
m
o
d
e
l
s
,
w
h
i
c
h
h
a
v
e
h
i
g
h
i
m
p
l
e
m
e
n
t
a
t
i
o
n
d
i
f
f
i
c
u
lt
y
.
T
h
i
s
d
e
m
o
n
s
t
r
at
e
s
t
h
e
d
i
f
f
i
c
u
l
ti
e
s
o
f
i
m
p
l
e
m
e
n
ti
n
g
d
y
n
a
m
i
c
m
o
d
e
l
s
wi
t
h
n
e
t
w
o
r
k
s
l
i
ci
n
g
t
o
a
d
a
p
t
t
o
i
n
d
i
v
i
d
u
al
u
s
e
r
s
’
c
h
a
n
g
e
s
i
n
t
r
a
f
f
i
c
.
I
t
i
s
s
h
o
w
n
t
h
a
t
t
h
e
n
e
t
w
o
r
k
s
l
i
ci
n
g
m
o
d
e
l
s
c
u
r
r
e
n
tl
y
d
e
v
e
lo
p
e
d
s
h
o
w
a
n
i
m
p
r
o
v
e
m
e
n
t
in
t
e
r
m
s
o
f
o
v
e
r
a
l
l
n
e
t
w
o
r
k
e
f
f
ic
i
e
n
c
y
.
T
h
e
m
o
d
e
l
c
o
n
s
t
a
n
tl
y
p
r
o
d
u
c
e
s
a
c
c
u
r
a
te
p
r
e
d
i
c
ti
o
n
s
o
f
5
G
n
e
t
w
o
r
k
s
li
c
es
t
h
at
i
m
p
r
o
v
e
Q
o
S
a
n
d
Q
o
E
.
D
e
m
o
n
s
t
r
a
t
i
n
g
t
h
e
c
a
p
a
b
i
li
t
y
o
f
M
L
m
o
d
e
l
s
i
n
i
m
p
r
o
v
i
n
g
t
h
e
d
e
c
i
s
i
o
n
s
-
m
a
k
i
n
g
t
o
e
n
h
a
n
c
e
t
h
e
n
e
t
w
o
r
k
s
li
c
i
n
g
a
l
g
o
r
i
t
h
m
s
.
I
t
w
a
s
al
s
o
s
h
o
wn
t
h
a
t
t
h
e
s
e
t
e
s
t
s
we
r
e
c
o
n
d
u
c
t
e
d
o
n
t
h
e
o
v
e
r
a
l
l
n
e
t
w
o
r
k
t
r
a
f
f
i
c
a
f
t
e
r
f
e
at
u
r
e
ex
t
r
a
c
t
i
o
n
a
n
d
n
o
t
o
n
i
n
d
i
v
i
d
u
a
l
u
s
e
r
s
.
P
r
e
d
i
c
ti
o
n
s
we
r
e
m
ad
e
t
o
g
e
n
e
r
a
l
i
ze
a
ll
u
s
e
r
s
,
as
t
h
e
te
s
t
w
as
p
e
r
f
o
r
m
e
d
w
h
e
n
t
h
e
u
s
e
r
w
as
g
r
o
u
p
e
d
in
t
o
s
e
r
v
i
c
e
c
at
e
g
o
r
i
es
.
I
n
a
d
d
i
ti
o
n
,
t
h
e
s
e
w
o
r
k
s
d
o
n
o
t
c
o
n
s
i
d
e
r
t
h
e
e
f
f
ec
ts
w
h
e
n
t
h
e
n
e
t
w
o
r
k
is
o
v
e
r
l
o
a
d
e
d
a
n
d
o
n
l
y
c
o
n
s
i
d
e
r
t
h
e
s
i
t
u
at
i
o
n
i
n
w
h
i
c
h
t
h
e
n
e
tw
o
r
k
c
a
n
h
a
n
d
l
e
t
r
a
f
f
i
c
a
n
d
s
l
ic
e
a
c
co
r
d
i
n
g
l
y
.
T
h
i
s
is
b
e
c
a
u
s
e
n
e
t
wo
r
k
s
l
i
c
i
n
g
h
as
t
h
e
s
a
m
e
p
e
r
f
o
r
m
a
n
c
e
f
o
r
a
l
l
u
s
e
r
s
i
n
e
v
e
r
y
s
c
e
n
a
r
i
o
a
n
d
d
o
e
s
n
o
t
d
i
s
t
i
n
g
u
is
h
b
e
t
w
ee
n
i
n
d
i
v
i
d
u
a
l
u
s
e
r
s
.
3
.
2
.
User
-
ce
ntr
ic
re
s
o
urce
a
l
lo
ca
t
io
n
Utilit
y
-
weig
h
ted
p
r
i
o
r
itizatio
n
ten
d
s
t
o
r
e
d
u
ce
ch
u
r
n
an
d
late
n
cy
b
u
t m
ay
r
eq
u
ir
e
f
air
n
ess
c
o
n
s
tr
ain
ts
f
o
r
l
o
w
-
b
atter
y
d
e
v
ices.
T
h
er
ef
o
r
e,
an
o
th
e
r
a
r
ea
th
at
is
b
ei
n
g
r
esear
c
h
ed
is
u
s
er
-
ce
n
tr
ic
r
eso
u
r
ce
allo
ca
tio
n
,
wh
er
e
r
elate
d
wo
r
k
h
as
b
ee
n
co
n
d
u
cte
d
[
4
0
]
–
[
4
2
]
.
C
o
m
p
ar
ed
to
n
etwo
r
k
s
licin
g
,
wh
ich
d
iv
id
es
th
e
n
etwo
r
k
b
ased
o
n
wh
at
u
s
ag
e
is
n
ee
d
ed
th
e
m
o
s
t,
u
s
er
-
ce
n
tr
ic
r
eso
u
r
c
e
allo
ca
tio
n
f
o
cu
s
es o
n
in
d
iv
id
u
al
u
s
er
n
ee
d
s
an
d
allo
ca
tes/
s
lice
s
th
e
b
an
d
wid
th
f
o
r
v
ar
io
u
s
u
s
er
s
in
s
tead
o
f
s
er
v
ices.
T
h
er
ef
o
r
e,
u
s
er
-
ce
n
tr
ic
r
eso
u
r
ce
allo
ca
tio
n
r
esear
ch
h
as a
ls
o
b
ee
n
in
v
esti
g
ated
,
alth
o
u
g
h
f
ew
s
tu
d
ies h
av
e
b
ee
n
c
o
n
d
u
cted
.
R
es
e
a
r
c
h
w
as
c
o
n
d
u
c
t
e
d
t
o
i
m
p
l
e
m
e
n
t
a
u
s
e
r
-
c
e
n
t
r
i
c
b
a
n
d
w
id
t
h
a
l
l
o
c
a
ti
o
n
m
e
t
h
o
d
f
o
r
v
i
d
e
o
s
t
r
e
a
m
i
n
g
a
n
d
t
h
e
y
i
n
v
e
s
t
i
g
a
te
d
u
s
i
n
g
d
e
v
i
c
e
-
to
-
d
e
v
i
c
e
(
D
2
D
)
ass
is
t
ed
c
o
m
m
u
n
i
c
a
t
i
o
n
[
4
3
]
.
D
2
D
c
o
m
m
u
n
i
c
a
t
i
o
n
i
s
a
f
o
r
m
o
f
c
o
m
m
u
n
i
c
a
t
i
o
n
i
n
w
h
ic
h
d
a
t
a
a
n
d
p
a
c
k
e
t
s
a
r
e
t
r
a
n
s
f
er
r
e
d
b
e
t
w
e
e
n
U
E
s
,
a
s
e
a
c
h
p
i
e
ce
o
f
e
q
u
i
p
m
e
n
t
a
c
t
s
a
s
a
r
e
l
a
y
n
o
d
e
t
o
t
r
a
n
s
m
i
t
d
ata
t
o
t
h
e
d
es
i
r
e
d
c
e
l
l
u
la
r
d
e
v
i
c
e
(
C
D
)
.
A
n
i
s
s
u
e
w
it
h
D
2
D
c
o
m
m
u
n
i
c
a
t
i
o
n
is
t
h
e
p
o
w
e
r
e
f
f
i
c
i
e
n
c
y
o
f
t
h
e
u
s
e
r
’
s
e
q
u
i
p
m
e
n
t
,
a
s
e
a
c
h
p
i
e
ce
o
f
eq
u
i
p
m
e
n
t
w
i
ll
b
e
u
s
e
d
t
o
t
r
a
n
s
m
i
t
d
a
t
a
.
T
h
e
r
e
f
o
r
e
,
l
o
w
-
b
a
t
t
e
r
y
u
s
e
r
s
w
i
ll
s
u
f
f
e
r
.
T
h
i
s
is
e
v
e
n
m
o
r
e
p
r
o
m
i
n
e
n
t
w
i
t
h
v
i
d
e
o
s
t
r
e
a
m
i
n
g
,
a
s
m
o
r
e
p
a
c
k
e
t
s
m
u
s
t
b
e
t
r
a
n
s
m
i
tt
e
d
t
o
o
f
f
e
r
l
o
w
-
l
a
te
n
cy
,
h
i
g
h
-
q
u
a
l
i
t
y
v
i
d
e
o
s
t
r
e
a
m
i
n
g
t
o
i
m
p
r
o
v
e
Q
o
E
.
T
h
e
r
e
f
o
r
e
,
t
h
e
y
p
r
es
e
n
t
e
d
a
n
a
l
g
o
r
i
t
h
m
t
h
a
t
d
e
f
i
n
e
s
a
n
d
c
a
t
eg
o
r
i
z
e
s
t
h
e
u
s
e
r
s
i
n
t
o
“
v
i
d
e
o
s
tr
e
a
m
l
e
v
e
l
s
”
a
n
d
a
l
l
o
c
at
e
s
b
a
n
d
w
i
d
t
h
a
c
c
o
r
d
i
n
g
l
y
.
T
h
e
y
u
s
e
d
a
m
e
t
h
o
d
t
h
a
t
ca
l
cu
l
a
t
e
s
a
u
t
i
li
t
y
v
a
l
u
e
t
h
a
t
c
o
n
s
i
d
e
r
s
t
h
e
q
u
a
l
it
y
,
b
a
t
t
e
r
y
li
f
e
,
p
o
w
e
r
u
s
a
g
e
,
a
n
d
p
a
c
k
e
t
l
o
s
s
r
a
t
i
o
.
D
e
p
e
n
d
i
n
g
o
n
t
h
e
s
e
f
a
c
t
o
r
s
,
t
h
e
y
a
r
e
c
a
t
e
g
o
r
i
z
e
d
i
n
t
o
d
i
f
f
e
r
e
n
t
p
r
i
o
r
i
t
i
es
/l
ev
e
l
s
b
as
e
d
o
n
t
h
e
i
r
n
e
e
d
s
.
T
h
e
UE
w
it
h
a
l
o
w
e
r
b
at
t
e
r
y
l
i
f
e
w
il
l
t
a
k
e
h
e
l
p
f
r
o
m
o
th
e
r
D
2
D
d
e
v
i
c
es
t
h
at
a
ct
as
r
e
la
y
n
o
d
e
s
b
u
t
wi
l
l
b
e
a
l
l
o
c
a
t
e
d
wi
t
h
l
es
s
b
a
n
d
w
i
d
t
h
.
I
n
a
d
d
i
t
i
o
n
,
U
E
s
t
h
a
t
c
a
n
a
c
t
as
D
2
D
d
e
v
i
c
es
w
i
ll
h
a
v
e
a
h
i
g
h
e
r
b
a
n
d
w
i
d
t
h
.
T
h
e
a
l
g
o
r
i
t
h
m
u
s
e
s
a
u
ti
l
it
y
-
b
a
s
e
d
m
u
l
t
i
m
e
d
i
a
s
t
r
e
a
m
i
n
g
(
U
AM
S
)
m
e
t
h
o
d
t
o
c
a
t
e
g
o
r
i
z
e
t
h
e
u
s
e
r
b
a
s
e
d
o
n
t
h
e
i
r
b
a
t
t
e
r
y
l
i
f
e
s
p
a
n
a
n
d
p
a
c
k
e
t
-
l
o
s
s
r
a
ti
o
.
B
as
e
d
o
n
t
h
e
a
s
s
i
g
n
e
d
u
t
i
l
i
t
y
v
a
l
u
e
,
t
h
e
d
e
v
i
c
e
is
c
a
te
g
o
r
i
z
e
d
a
s
e
i
t
h
e
r
a
D
2
D
r
e
la
y
n
o
d
e
o
r
a
l
o
w
‑
b
at
t
er
y
u
s
e
r
.
W
h
e
n
t
h
e
K
‑
m
ea
n
s
a
lg
o
r
i
t
h
m
i
s
u
s
e
d
,
i
t
d
e
t
e
r
m
i
n
e
s
th
e
D
2
D
d
e
v
i
c
e
t
h
a
t
a
c
t
s
as
a
r
el
a
y
n
o
d
e
f
o
r
t
h
e
l
o
w
-
b
a
t
t
e
r
y
u
s
e
r
.
T
h
e
D
2
D
r
e
l
a
y
s
e
l
e
c
t
i
o
n
l
o
g
ic
i
s
i
l
l
u
s
t
r
at
e
d
i
n
Fi
g
u
r
e
3
.
O
v
e
r
a
l
l
,
t
h
e
a
l
g
o
r
i
t
h
m
d
i
v
i
d
e
s
t
h
e
b
a
n
d
w
i
d
t
h
u
s
e
d
f
o
r
v
i
d
e
o
s
t
r
e
a
m
i
n
g
b
a
s
e
d
o
n
t
h
e
U
E
s
’
a
b
i
l
i
t
y
t
o
s
e
r
v
e
as
a
r
e
la
y
n
o
d
e
f
o
r
D
2
D
.
B
e
tt
e
r
v
i
d
e
o
q
u
a
l
i
t
y
a
n
d
r
e
d
u
ce
d
l
a
t
e
n
c
y
a
r
e
a
w
a
r
d
e
d
t
o
u
s
e
r
s
w
h
o
s
e
r
v
e
a
s
D
2
D
r
e
l
a
y
n
o
d
e
s
.
T
h
e
r
es
u
l
ts
s
h
o
w
th
a
t
t
h
is
m
e
t
h
o
d
p
r
o
v
e
d
t
o
b
e
e
f
f
e
c
t
i
v
e
,
as
it
t
es
t
e
d
t
h
e
c
h
u
r
n
r
at
e
o
f
i
n
a
c
ti
v
e
u
s
e
r
s
.
I
t
w
as
s
h
o
w
n
t
h
at
t
h
e
p
r
o
p
o
s
e
d
m
e
t
h
o
d
p
r
o
v
i
d
e
s
a
1
.
0
6
%
,
1
.
5
9
%
,
a
n
d
2
%
r
e
d
u
c
t
i
o
n
i
n
t
h
e
ch
u
r
n
r
a
t
e
c
o
m
p
a
r
e
d
t
o
n
o
n
-
a
d
a
p
t
i
v
e
m
e
t
h
o
d
s
.
T
h
i
s
d
e
m
o
n
s
t
r
a
t
es
t
h
a
t
m
o
r
e
u
s
er
s
h
a
v
e
b
e
t
t
e
r
Q
o
E
w
i
t
h
t
h
is
r
e
s
o
u
r
c
e
a
l
l
o
c
at
i
o
n
m
e
t
h
o
d
.
A
l
t
h
o
u
g
h
t
h
i
s
m
e
t
h
o
d
p
r
o
v
e
d
t
o
b
e
m
o
r
e
e
f
f
e
c
t
i
v
e
t
h
a
n
t
r
a
d
i
t
i
o
n
a
l
r
e
s
o
u
r
c
e
a
l
l
o
c
ati
o
n
m
e
t
h
o
d
s
,
a
f
e
w
l
i
m
i
t
at
i
o
n
s
c
a
n
b
e
s
e
e
n
i
n
t
h
e
w
o
r
k
.
F
i
r
s
t
,
t
h
e
r
es
e
a
r
c
h
c
o
n
d
u
c
t
e
d
o
n
l
y
l
o
o
k
e
d
a
t
v
i
d
e
o
s
t
r
e
a
m
i
n
g
s
e
r
v
i
c
e
s
f
o
r
t
h
e
d
i
v
i
s
i
o
n
o
f
b
a
n
d
w
i
d
t
h
,
a
n
d
f
u
r
t
h
e
r
t
e
s
ts
c
a
n
b
e
p
e
r
f
o
r
m
e
d
f
o
r
o
t
h
e
r
s
e
r
v
i
c
e
s
,
s
u
c
h
a
s
V
o
I
P
o
r
e
m
a
i
l
.
A
n
o
t
h
e
r
p
i
e
c
e
o
f
w
o
r
k
t
h
a
t
c
a
n
b
e
d
o
n
e
i
s
t
h
e
u
s
e
o
f
M
L
i
n
t
h
e
al
g
o
r
i
th
m
.
A
s
p
r
o
v
e
n
b
y
n
e
t
w
o
r
k
s
l
i
ci
n
g
a
l
g
o
r
i
t
h
m
s
,
t
h
e
M
L
a
l
g
o
r
i
t
h
m
s
c
a
n
p
r
o
v
e
t
o
b
e
m
o
r
e
e
f
f
e
c
t
i
v
e
.
T
h
e
r
e
f
o
r
e
,
f
u
r
t
h
e
r
w
o
r
k
c
a
n
b
e
p
e
r
f
o
r
m
e
d
o
n
t
h
e
M
L
a
l
g
o
r
i
t
h
m
s
b
e
i
n
g
i
m
p
l
e
m
e
n
t
e
d
.
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
Ma
ch
in
e
lea
r
n
in
g
-
d
r
iven
a
n
a
lysi
s
o
f u
s
er b
a
n
d
w
id
th
a
llo
ca
t
io
n
a
n
d
p
erfo
r
ma
n
ce
in
…
(
P
a
n
g
Wa
i Leo
n
g
)
1241
Fig
u
r
e
3
.
D2
D
c
o
n
n
ec
tio
n
d
ec
is
io
n
b
etwe
en
th
e
p
r
io
r
ities
3
.
3
.
E
co
no
m
ic
a
nd
m
a
r
k
et
-
driv
en
UCRA
T
h
e
e
c
o
n
o
m
i
c
a
n
d
m
a
r
k
e
t
-
d
r
i
v
e
n
U
C
R
A
c
o
n
s
i
d
e
r
s
t
h
e
s
p
e
c
t
r
u
m
t
o
b
e
a
t
r
a
d
a
b
l
e
r
e
s
o
u
r
c
e
,
a
n
d
d
e
c
i
s
i
o
n
s
r
e
f
l
e
ct
t
h
e
t
e
n
a
n
t
e
c
o
n
o
m
i
c
s
o
n
t
o
p
o
f
t
h
e
u
s
e
r
-
le
v
el
Q
o
S
/Q
o
E
.
S
p
e
ct
r
u
m
a
l
l
o
c
at
i
o
n
i
s
p
r
o
c
e
s
s
e
d
b
y
a
h
i
e
r
a
r
c
h
i
c
a
l
d
ec
is
i
o
n
p
r
o
c
e
s
s
f
r
a
m
e
w
o
r
k
a
c
c
o
r
d
i
n
g
t
o
t
h
e
d
y
n
a
m
i
c
m
a
r
k
e
t
a
n
d
o
p
e
r
a
to
r
s
'
d
e
m
a
n
d
s
.
T
h
e
f
r
a
m
e
w
o
r
k
c
o
n
s
i
s
t
s
o
f
u
p
p
e
r
a
n
d
l
o
w
e
r
p
r
i
o
r
i
t
y
t
i
e
r
s
.
I
n
t
h
e
u
p
p
e
r
-
p
r
i
o
r
i
t
y
t
i
e
r
,
t
h
e
i
n
f
r
a
s
t
r
u
c
t
u
r
e
p
r
o
v
i
d
e
r
(
I
n
P
)
a
l
l
o
c
a
t
es
s
p
e
c
t
r
u
m
a
c
r
o
s
s
t
h
e
m
o
b
i
l
e
v
i
r
t
u
al
n
e
tw
o
r
k
o
p
e
r
a
t
o
r
s
(
MV
N
Os
)
.
A
t
t
h
e
l
o
w
er
-
p
r
i
o
r
i
t
y
t
i
e
r
,
e
a
ch
M
V
N
O
t
h
e
n
s
l
ic
e
s
i
ts
ass
i
g
n
e
d
s
p
e
c
t
r
u
m
t
o
i
n
d
i
v
i
d
u
a
l
u
s
e
r
s
a
c
c
o
r
d
i
n
g
t
o
t
r
a
f
f
i
c
c
o
n
d
i
t
i
o
n
s
a
n
d
Q
o
S
r
e
q
u
i
r
e
m
e
n
t
s
.
De
e
p
r
e
i
n
f
o
r
c
em
e
n
t
l
e
a
r
n
i
n
g
(
DR
L
)
w
it
h
r
e
g
u
l
a
t
e
d
b
i
d
d
i
n
g
c
a
p
s
i
s
a
p
p
li
e
d
t
o
t
h
e
u
p
p
e
r
t
i
e
r
t
o
p
r
e
v
e
n
t
s
m
a
ll
e
r
t
e
n
a
n
t
s
f
r
o
m
b
e
i
n
g
s
t
a
r
v
e
d
o
f
r
es
o
u
r
c
e
s
w
h
i
l
e
al
s
o
i
m
p
r
o
v
i
n
g
o
v
e
r
a
l
l
s
p
e
c
t
r
al
e
f
f
ic
i
e
n
c
y
.
F
i
g
u
r
e
4
s
h
o
ws
t
h
e
a
l
g
o
r
it
h
m
f
r
a
m
e
w
o
r
k
.
Fig
u
r
e
4
.
MV
NO
b
id
d
in
g
alg
o
r
ith
m
f
r
am
ewo
r
k
f
o
r
r
eso
u
r
ce
allo
ca
tio
n
A
n
o
t
h
e
r
r
e
s
e
a
r
c
h
s
p
li
t
u
s
e
r
s
i
n
t
o
p
r
i
o
r
i
t
i
e
s
b
as
e
d
o
n
t
h
e
M
V
N
O
s
[
4
4
]
.
M
V
NO
s
a
r
e
s
e
r
v
i
ce
p
r
o
v
i
d
e
r
s
t
h
a
t
d
o
n
o
t
o
w
n
t
h
e
n
e
t
w
o
r
k
i
n
f
r
a
s
t
r
u
c
t
u
r
e
t
o
w
h
i
c
h
t
h
e
u
s
e
r
is
c
o
n
n
e
c
t
e
d
.
T
h
e
r
e
f
o
r
e
,
t
h
e
s
o
lu
t
i
o
n
p
r
o
p
o
s
e
d
w
il
l
o
n
l
y
e
x
p
l
o
r
e
c
a
s
e
s
w
h
e
n
u
s
e
r
s
o
f
d
i
f
f
e
r
e
n
t
s
e
r
v
i
c
e
p
r
o
v
i
d
e
r
s
c
o
n
n
e
c
t
t
o
a
n
e
t
w
o
r
k
i
n
f
r
a
s
t
r
u
c
t
u
r
e
t
h
a
t
d
o
e
s
n
o
t
f
a
l
l
u
n
d
e
r
t
h
e
i
r
o
w
n
n
e
t
w
o
r
k
in
f
r
a
s
t
r
u
c
t
u
r
e
.
As
m
o
r
e
u
s
e
r
s
o
f
v
a
r
i
o
u
s
s
e
r
v
i
c
e
p
r
o
v
i
d
e
r
s
c
o
n
n
e
c
t
t
o
o
n
e
n
e
t
w
o
r
k
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
2
3
6
-
1
2
4
8
1242
i
n
f
r
a
s
t
r
u
c
t
u
r
e
,
t
h
e
n
et
w
o
r
k
w
i
ll b
e
o
v
e
r
l
o
a
d
e
d
.
T
h
e
r
e
f
o
r
e
,
t
h
e
u
s
e
r
s
a
r
e
s
p
l
it
i
n
t
o
p
r
i
o
r
i
t
ie
s
.
T
h
e
p
a
p
e
r
p
r
o
p
o
s
e
s
a
t
w
o
-
p
r
i
o
r
i
t
y
m
o
d
e
l
t
h
a
t
u
s
e
s
an
u
p
p
e
r
-
p
r
i
o
r
i
t
y
t
o
a
l
l
o
c
a
t
e
r
eso
u
r
c
e
s
t
o
t
h
e
M
VN
Os
a
n
d
a
lo
w
e
r
-
p
r
i
o
r
i
t
y
f
o
r
t
h
e
M
V
N
Os
t
o
s
li
c
e
t
h
e
n
e
tw
o
r
k
b
a
s
e
d
o
n
t
h
e
t
r
a
f
f
i
c
.
T
h
e
M
VN
O
s
w
il
l
b
i
d
f
o
r
t
h
e
h
i
g
h
e
s
t
am
o
u
n
t
o
f
b
a
n
d
w
i
d
t
h
f
r
o
m
t
h
e
I
n
P
,
w
h
e
r
e
t
h
e
h
i
g
h
e
s
t
b
i
d
w
il
l
o
b
ta
i
n
t
h
e
m
o
s
t
r
e
s
o
u
r
c
e
s
a
n
d
b
a
n
d
w
i
d
t
h
,
t
h
er
e
f
o
r
e
s
p
l
it
t
i
n
g
t
h
e
M
V
N
Os
i
n
t
o
v
a
r
i
o
u
s
g
r
o
u
p
s
o
f
a
c
e
r
t
a
i
n
a
m
o
u
n
t
o
f
t
o
t
a
l
b
a
n
d
w
i
d
t
h
.
T
h
e
n
t
h
e
l
o
we
r
p
r
i
o
r
i
t
y
i
s
w
h
e
r
e
t
h
e
M
V
N
O
w
i
ll
l
o
o
k
a
t
t
h
e
Q
o
S
r
e
q
u
i
r
e
d
b
y
t
h
e
i
r
u
s
e
r
a
n
d
s
l
i
c
e
t
h
e
n
e
tw
o
r
k
a
c
c
o
r
d
i
n
g
l
y
.
T
h
e
n
,
u
s
i
n
g
d
e
e
p
Q
-
n
e
t
w
o
r
k
(
DQ
N
)
,
w
h
i
c
h
is
an
a
l
g
o
r
i
t
h
m
s
u
b
s
et
o
f
DR
L
i
n
M
L
,
t
h
e
DQ
N
w
i
ll
a
n
al
y
z
e
th
e
M
V
NO
b
i
d
s
a
n
d
n
e
t
w
o
r
k
t
r
a
f
f
i
c
t
o
h
a
v
e
a
n
o
p
t
i
m
a
l
s
p
l
it
.
T
h
e
D
Q
N
wi
l
l
b
e
u
s
e
d
t
o
l
i
m
i
t
t
h
e
m
a
x
i
m
u
m
n
u
m
b
e
r
o
f
b
i
d
s
t
h
a
t
t
h
e
M
V
N
Os
ca
n
m
a
k
e
.
I
t
e
n
s
u
r
e
s
t
h
e
l
o
w
e
r
-
b
i
d
d
i
n
g
M
VN
Os
d
o
n
o
t
d
i
e
f
r
o
m
s
t
a
r
v
at
i
o
n
(
l
a
ck
o
f
r
e
s
o
u
r
c
e
s
)
a
n
d
e
n
s
u
r
e
s
a
n
o
p
t
i
m
i
z
e
d
a
ll
o
c
a
t
i
o
n
o
f
r
e
s
o
u
r
c
e
s
.
T
h
e
D
Q
N
a
n
d
b
i
d
d
i
n
g
a
l
g
o
r
i
th
m
i
n
t
h
e
u
p
p
e
r
p
r
i
o
r
i
t
y
p
r
o
v
id
e
d
a
5
.
4
%
i
n
c
r
e
as
e
i
n
r
e
v
e
n
u
e
c
o
m
p
a
r
e
d
t
o
d
o
u
b
l
e
D
Q
N
a
n
d
a
2
.
6
%
i
n
c
r
e
a
s
e
c
o
m
p
a
r
e
d
t
o
d
u
e
l
i
n
g
DQ
N
,
a
s
b
a
n
d
w
i
d
t
h
s
a
r
e
a
l
l
o
ca
te
d
m
o
r
e
e
f
f
i
c
i
e
n
t
l
y
b
a
s
e
d
o
n
b
i
d
s
.
I
n
a
d
d
i
ti
o
n
,
i
t
w
a
s
s
h
o
w
n
t
h
a
t
t
h
e
r
e
is
a
0
.
5
-
2
.
7
%
i
n
c
r
e
a
s
e
i
n
s
p
e
c
t
r
a
l
e
f
f
ic
i
e
n
c
y
i
n
t
h
e
l
o
w
e
r
p
r
i
o
r
i
t
i
es
.
O
v
e
r
al
l
,
t
h
e
p
r
o
p
o
s
ed
m
o
d
e
l
d
e
m
o
n
s
t
r
a
t
e
d
a
m
e
t
h
o
d
o
f
r
e
s
o
u
r
c
e
a
l
l
o
c
at
i
o
n
b
as
ed
o
n
g
r
o
u
p
i
n
g
u
s
e
r
s
b
a
s
e
d
o
n
t
h
e
i
r
s
e
r
v
ic
e
p
r
o
v
i
d
e
r
a
n
d
o
b
t
a
i
n
e
d
a
h
i
g
h
e
r
b
a
n
d
w
i
d
t
h
w
h
e
n
t
h
e
i
r
s
e
r
v
i
c
e
p
r
o
v
i
d
e
r
b
i
d
s
m
o
r
e
.
A
l
t
h
o
u
g
h
t
h
e
m
et
h
o
d
i
m
p
r
o
v
e
d
s
p
e
c
t
r
u
m
e
f
f
i
c
i
e
n
c
y
a
n
d
Q
o
E
,
t
h
e
al
l
o
c
at
i
o
n
o
f
r
es
o
u
r
c
e
s
c
o
u
l
d
b
e
m
o
r
e
i
n
d
i
v
i
d
u
a
l
is
t
i
c
.
A
s
M
VN
Os
a
r
e
u
s
e
d
t
o
s
p
l
it
u
p
u
s
e
r
s
,
o
t
h
e
r
m
e
t
h
o
d
s
c
a
n
b
e
t
e
s
t
e
d
t
o
s
p
l
it
u
s
e
r
s
i
n
t
o
v
a
r
i
o
u
s
g
r
o
u
p
s
.
I
n
a
d
d
i
t
i
o
n
,
f
u
r
t
h
e
r
r
e
s
e
a
r
c
h
c
a
n
b
e
c
o
n
d
u
c
t
e
d
t
o
c
o
m
p
a
r
e
v
a
r
i
o
u
s
M
L
a
l
g
o
r
i
t
h
m
s
,
a
s
t
h
i
s
w
o
r
k
o
n
l
y
c
o
n
s
i
d
e
r
s
DQ
N
as
a
n
a
l
g
o
r
i
t
h
m
f
o
r
t
h
e
o
p
t
i
m
i
z
a
t
i
o
n
a
n
d
p
r
e
v
e
n
t
i
o
n
o
f
s
t
a
r
v
a
t
i
o
n
.
T
h
e
r
e
f
o
r
e
,
m
o
r
e
r
e
s
e
a
r
c
h
c
a
n
b
e
c
o
n
d
u
c
t
e
d
t
o
c
o
m
p
a
r
e
t
h
e
v
a
r
i
o
u
s
t
y
p
e
s
o
f
ML
a
l
g
o
r
i
t
h
m
s
.
3
.
4
.
M
a
chine
lea
rning
pa
ra
dig
m
s
f
o
r
UCRA
5
G
n
etwo
r
k
s
u
s
e
a
v
a
r
iety
o
f
ML
m
eth
o
d
s
in
r
eso
u
r
ce
allo
ca
tio
n
,
b
u
t
ea
c
h
ML
alg
o
r
ith
m
lear
n
s
in
d
if
f
er
en
t
way
s
.
T
h
e
p
e
r
f
o
r
m
a
n
ce
o
f
SL
(
p
r
ed
ictio
n
)
,
UL
(
p
r
o
f
ilin
g
/clu
s
ter
in
g
)
,
an
d
R
L
(
c
lo
s
ed
-
lo
o
p
co
n
tr
o
l)
ar
e
co
m
p
ar
e
d
.
C
o
m
p
u
tatio
n
a
l
co
m
p
lex
ity
,
s
ca
lab
ilit
y
,
ad
a
p
tab
ilit
y
,
an
d
d
ep
lo
y
ab
ilit
y
ar
e
co
n
s
id
er
ed
as
p
r
ac
tical
ev
alu
atio
n
cr
iter
ia.
Netwo
r
k
an
aly
s
is
ML
alg
o
r
ith
m
s
ca
n
f
o
r
ec
ast
n
etwo
r
k
p
er
f
o
r
m
an
ce
an
d
tr
af
f
i
c
an
d
m
ak
e
d
ec
is
io
n
s
b
ased
o
n
s
u
ch
f
o
r
ec
asts
.
T
h
e
m
o
d
el
s
u
s
ed
in
clu
d
ed
r
e
g
r
ess
io
n
tr
ee
,
r
an
d
o
m
f
o
r
est,
k
-
Me
an
s
,
KNN,
Q
-
lear
n
in
g
,
d
ee
p
n
eu
r
al
n
etwo
r
k
an
d
DQNs
.
N
e
t
w
o
r
k
s
l
i
c
i
n
g
a
n
d
R
e
g
r
ess
io
n
T
r
e
e
s
w
e
r
e
u
s
e
d
t
o
p
r
e
d
i
c
t
t
h
e
o
u
t
c
o
m
e
b
y
a
s
s
i
g
n
i
n
g
v
a
lu
e
s
t
o
t
h
e
s
l
i
ce
s
[
1
7
]
.
T
h
e
r
e
g
r
e
s
s
i
o
n
t
r
ee
m
o
d
e
l
d
e
m
o
n
s
t
r
a
t
e
d
i
s
a
S
L
m
o
d
e
l
,
a
s
t
h
e
m
o
d
e
l
w
a
s
c
r
e
a
t
e
d
w
i
t
h
t
h
e
h
e
l
p
o
f
p
r
e
v
i
o
u
s
t
r
ai
n
i
n
g
.
T
h
is
m
o
d
e
l is
d
e
v
e
l
o
p
e
d
i
n
w
h
i
c
h
d
a
ta
a
r
e
in
i
t
i
a
ll
y
f
e
d
i
n
t
o
t
h
e
m
o
d
e
l
,
w
h
e
r
e
t
h
e
m
o
d
el
is
f
e
d
d
a
t
a
o
f
t
h
e
o
p
t
i
m
a
l
r
e
s
p
o
n
s
e
t
o
a
c
e
r
t
a
i
n
d
a
t
a
t
r
a
f
f
i
c
s
c
e
n
a
r
i
o
.
T
h
e
n
,
t
h
e
s
e
d
a
t
a
a
r
e
s
p
l
i
t
i
n
t
o
tw
o
b
r
a
n
c
h
e
s
b
a
s
e
d
o
n
c
e
r
t
a
i
n
f
e
at
u
r
e
s
t
h
a
t
t
h
e
m
o
d
e
l
i
d
e
n
t
i
f
i
e
s
,
a
n
d
t
h
is
p
r
o
c
es
s
i
s
r
e
p
e
a
te
d
a
s
t
h
e
b
r
a
n
c
h
es
c
o
n
s
t
a
n
tl
y
s
p
l
i
t
a
n
d
i
d
e
n
t
i
f
y
f
e
a
t
u
r
es
t
h
a
t
w
i
ll
b
e
ca
t
e
g
o
r
i
z
e
d
i
n
t
o
a
t
y
p
e
o
f
d
a
t
a
t
r
a
f
f
i
c
.
Us
i
n
g
t
h
is
,
t
h
e
M
L
a
l
g
o
r
i
t
h
m
c
a
n
f
o
r
e
c
a
s
t
t
r
a
f
f
i
c
b
a
s
e
d
o
n
t
h
e
d
a
t
a
i
t
is
s
e
e
i
n
g
a
n
d
p
r
o
v
i
d
e
s
m
o
r
e
e
f
f
i
cie
n
t
s
p
l
it
s
a
s
t
h
e
t
h
r
o
u
g
h
p
u
t
i
s
in
c
r
e
a
s
e
d
b
y
3
0
%
.
I
t
w
a
s
al
s
o
s
h
o
w
n
t
h
at
t
h
e
r
e
g
r
ess
i
o
n
t
r
e
e
m
o
d
el
w
as
b
e
tt
e
r
t
h
an
t
h
e
o
t
h
e
r
S
L
m
o
d
el
s
,
as
i
t
h
ad
a
p
p
r
o
x
i
m
a
t
e
l
y
t
h
e
s
a
m
e
a
c
c
u
r
a
c
y
b
u
t
r
e
d
u
c
e
d
t
r
a
i
n
i
n
g
t
i
m
e
.
A
l
t
h
o
u
g
h
t
h
e
r
e
g
r
e
s
s
i
o
n
t
r
e
e
m
o
d
e
l
p
r
o
v
e
d
t
o
h
a
v
e
o
v
e
r
9
0
%
a
c
c
u
r
a
c
y
i
n
p
r
e
d
i
c
ti
o
n
,
n
o
t
e
t
h
a
t
S
L
h
a
s
a
s
l
i
g
h
t
f
a
i
l
u
r
e
,
a
s
i
t
c
an
o
v
e
r
f
i
t
t
h
e
d
a
t
a
.
As
d
at
a
c
h
a
n
g
e
s
,
t
h
e
m
o
d
el
d
e
m
o
n
s
t
r
a
t
e
d
m
i
g
h
t
n
o
t
p
r
o
v
e
to
b
e
a
s
e
f
f
e
c
ti
v
e
.
A
n
o
t
h
e
r
t
y
p
e
o
f
M
L
a
l
g
o
r
i
t
h
m
t
h
a
t
i
n
v
e
s
t
i
g
a
t
e
d
k
-
m
e
a
n
s
f
o
r
n
e
t
w
o
r
k
t
r
a
f
f
i
c
m
a
n
a
g
e
m
e
n
t
d
em
o
n
s
t
r
a
t
e
d
t
h
e
u
s
e
o
f
U
L
[
4
5
]
.
K
-
m
e
a
n
s
t
a
k
e
s
u
n
la
b
e
l
e
d
d
a
ta
a
n
d
s
p
l
it
s
it
i
n
t
o
c
l
u
s
t
e
r
s
.
E
a
c
h
c
l
u
s
t
er
i
s
c
r
ea
t
e
d
b
y
t
h
e
s
i
m
il
a
r
i
t
y
a
n
d
d
is
p
a
r
i
t
y
b
et
w
e
en
t
h
e
d
a
t
a
p
a
tt
e
r
n
s
.
E
ac
h
c
l
u
s
t
er
o
f
d
a
t
a
i
s
c
r
e
a
t
e
d
t
h
r
o
u
g
h
a
n
i
t
e
r
a
t
i
v
e
m
et
h
o
d
.
As
d
a
t
a
p
o
i
n
t
s
m
o
v
e
b
et
w
e
e
n
cl
u
s
t
e
r
s
a
f
t
e
r
ea
c
h
i
t
e
r
at
i
o
n
t
o
a
ch
i
e
v
e
t
h
e
d
e
s
i
r
e
d
s
p
li
t
.
T
h
e
s
tu
d
y
u
s
e
d
k
-
m
e
a
n
s
to
g
r
o
u
p
u
s
e
r
s
i
n
t
o
g
r
o
u
p
s
b
a
s
e
d
o
n
t
h
e
u
s
a
g
e
o
f
s
e
r
v
i
c
es
a
n
d
i
d
e
n
t
i
f
i
e
d
a
n
e
v
e
n
s
p
l
i
t
f
o
r
r
es
o
u
r
c
e
a
l
l
o
c
a
ti
o
n
o
f
t
h
e
c
l
u
s
t
e
r
t
o
e
f
f
ic
i
e
n
tl
y
u
s
e
e
a
ch
s
l
ic
e
.
T
h
is
w
o
r
k
s
h
o
w
e
d
th
a
t
u
s
i
n
g
t
h
e
k
-
m
e
a
n
s
a
l
g
o
r
it
h
m
p
r
o
v
i
d
e
s
b
e
tt
e
r
p
e
r
f
o
r
m
a
n
c
e
c
o
m
p
a
r
e
d
t
o
t
h
e
s
t
a
n
d
a
r
d
n
e
t
w
o
r
k
s
li
c
i
n
g
a
l
g
o
r
i
t
h
m
.
A
s
t
h
e
n
e
tw
o
r
k
d
y
n
a
m
i
c
a
l
l
y
s
e
a
r
c
h
e
s
f
o
r
s
i
m
il
a
r
p
a
t
t
e
r
n
s
b
e
t
w
e
e
n
u
s
e
r
s
a
n
d
p
r
o
f
i
l
e
s
t
h
e
m
i
n
t
o
c
l
u
s
t
e
r
s
.
I
t
i
m
p
r
o
v
e
s
n
e
t
w
o
r
k
t
r
a
f
f
i
c
m
a
n
a
g
e
m
e
n
t
.
T
h
i
s
s
t
u
d
y
e
v
a
l
u
a
te
d
d
i
f
f
e
r
e
n
t
M
L
a
l
g
o
r
i
t
h
m
s
,
i
n
c
l
u
d
i
n
g
d
e
n
s
i
t
y
-
b
a
s
e
d
s
p
at
i
al
c
l
u
s
t
e
r
i
n
g
o
f
a
p
p
l
i
c
a
ti
o
n
s
wi
t
h
n
o
is
e
(
D
B
S
C
A
N
)
,
Na
ï
v
e
B
a
y
e
s
,
SV
M
,
K
NN
,
a
n
d
k
-
m
e
a
n
s
.
K
-
m
e
a
n
s
o
f
f
e
r
s
m
o
r
e
d
y
n
a
m
i
c
r
e
s
o
u
r
c
e
a
l
l
o
ca
t
i
o
n
.
H
o
w
e
v
e
r
,
t
h
is
s
t
u
d
y
d
i
d
n
o
t
i
n
c
l
u
d
e
R
L
a
l
g
o
r
it
h
m
s
a
n
d
e
v
a
l
u
at
e
d
o
n
l
y
t
h
e
e
v
e
n
-
s
p
l
it
c
o
n
f
i
g
u
r
a
t
i
o
n
s
.
Q
-
l
e
a
r
n
i
n
g
f
o
r
u
s
e
r
-
c
e
n
t
r
i
c
R
AN
o
p
t
i
m
i
za
t
i
o
n
w
a
s
a
ls
o
p
r
o
p
o
s
e
d
[
3
8
]
.
Q
-
le
a
r
n
i
n
g
is
a
n
R
L
a
l
g
o
r
i
t
h
m
t
h
a
t
s
t
o
r
e
s
Q
-
v
a
l
u
es
f
o
r
d
i
f
f
e
r
e
n
t
a
c
ti
o
n
s
i
n
a
Q
-
t
a
b
le
.
T
h
e
o
u
t
c
o
m
e
s
ta
t
es
/
d
e
c
is
i
o
n
s
wi
l
l
b
e
c
a
t
e
g
o
r
i
z
e
d
i
n
t
o
Q
-
v
a
l
u
e
s
.
S
u
b
s
e
q
u
e
n
t
l
y
,
t
h
e
ML
m
o
d
e
l
w
i
ll
b
e
r
e
w
a
r
d
e
d
i
f
it
m
a
k
e
s
d
e
ci
s
i
o
n
s
t
h
a
t
o
b
t
a
i
n
h
ig
h
e
r
Q
-
v
a
l
u
e
s
.
T
h
e
Q
-
v
a
l
u
e
s
w
il
l
u
p
d
a
te
o
v
e
r
t
i
m
e
b
a
s
e
d
o
n
t
h
e
n
e
t
w
o
r
k
c
o
n
d
it
i
o
n
s
a
t t
h
at
ti
m
e
.
T
h
i
s
r
e
s
ea
r
c
h
in
t
r
o
d
u
c
e
s
t
h
e
u
s
e
o
f
S
-
z
o
n
e
s
t
o
d
e
t
e
r
m
i
n
e
h
o
w
t
o
b
o
o
s
t
s
i
g
n
a
ls
t
o
c
e
r
t
a
i
n
z
o
n
e
s
a
r
o
u
n
d
t
h
e
b
a
s
e
s
t
a
t
i
o
n
d
e
p
e
n
d
i
n
g
o
n
t
h
e
s
e
r
v
i
c
e
s
u
s
e
d
.
T
h
e
M
L
m
o
d
e
l
is
t
as
k
e
d
w
i
t
h
d
e
t
e
r
m
i
n
i
n
g
S
-
z
o
n
es
b
ase
d
o
n
t
h
e
u
s
a
g
e
o
f
s
e
r
v
i
ce
s
.
T
h
i
s
w
o
r
k
s
h
o
ws
t
h
at
t
h
e
s
t
a
n
d
a
r
d
Q
-
l
e
a
r
n
i
n
g
a
l
g
o
r
i
th
m
d
o
e
s
n
o
t
s
i
g
n
i
f
i
c
a
n
t
l
y
i
n
c
r
ea
s
e
p
e
r
f
o
r
m
a
n
c
e
,
b
u
t
i
t
s
m
a
i
n
b
e
n
e
f
i
t
i
s
t
h
a
t
it
h
a
s
l
o
w
e
r
c
o
m
p
l
e
x
it
y
a
n
d
c
a
n
d
y
n
a
m
i
c
a
l
l
y
u
p
d
a
te
c
h
a
n
g
e
s
.
A
c
o
m
p
a
r
a
t
i
v
e
s
u
m
m
a
r
y
o
f
t
h
e
SL
,
U
L
,
a
n
d
R
L
m
o
d
e
l
s
a
p
p
l
i
e
d
i
n
UC
R
A
t
as
k
s
i
s
p
r
es
en
t
e
d
i
n
T
a
b
l
e
1
.
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
Ma
ch
in
e
lea
r
n
in
g
-
d
r
iven
a
n
a
lysi
s
o
f u
s
er b
a
n
d
w
id
th
a
llo
ca
t
io
n
a
n
d
p
erfo
r
ma
n
ce
in
…
(
P
a
n
g
Wa
i Leo
n
g
)
1243
T
h
e
r
e
f
o
r
e
,
b
a
s
e
d
o
n
t
h
e
r
es
ea
r
c
h
t
h
a
t
h
as
b
e
e
n
c
o
n
d
u
c
t
e
d
,
M
L
s
h
o
ws
it
s
m
e
r
i
ts
,
as
i
t
h
a
s
b
e
e
n
p
r
e
s
e
n
t
e
d
i
n
p
r
i
o
r
r
e
s
e
a
r
c
h
.
I
t
o
u
t
p
e
r
f
o
r
m
s
i
n
e
f
f
i
c
i
e
n
t
u
s
a
g
e
o
f
t
h
e
b
a
n
d
w
i
d
t
h
a
n
d
c
a
n
d
y
n
a
m
i
c
a
l
l
y
c
h
a
n
g
e
b
a
s
e
d
o
n
t
h
e
c
u
r
r
e
n
t
d
a
t
a
.
H
o
w
e
v
e
r
,
a
k
e
y
l
i
m
i
t
i
n
g
f
a
c
t
o
r
i
n
t
h
e
r
e
s
e
a
r
c
h
is
t
h
e
l
a
c
k
o
f
c
o
m
p
ar
i
s
o
n
b
e
t
w
e
e
n
M
L
a
l
g
o
r
i
t
h
m
s
.
T
h
e
a
l
g
o
r
it
h
m
s
a
r
e
m
o
s
t
l
y
c
o
m
p
a
r
e
d
w
it
h
n
o
n
‑
ML
m
e
t
h
o
d
s
o
r
w
i
t
h
o
t
h
e
r
s
i
m
i
lar
M
L
m
o
d
e
ls
.
M
o
r
e
e
f
f
o
r
t
i
s
n
e
e
d
e
d
t
o
e
v
a
l
u
a
t
e
d
i
f
f
e
r
e
n
t
M
L
al
g
o
r
i
t
h
m
s
f
o
r
t
h
e
i
r
s
t
r
e
n
g
t
h
s
a
n
d
w
ea
k
n
e
s
s
e
s
i
n
n
et
w
o
r
k
p
e
r
f
o
r
m
a
n
c
e
a
n
d
b
a
n
d
w
i
d
t
h
a
l
l
o
c
a
ti
o
n
.
T
a
b
l
e
1
.
C
o
m
p
a
r
is
o
n
o
f
M
L
p
ar
a
d
i
g
m
s
m
a
p
p
e
d
t
o
u
s
e
r
‑
c
e
n
t
r
ic
r
e
s
o
u
r
c
e
a
ll
o
c
a
t
i
o
n
(
UC
R
A
)
ta
s
k
s
,
e
v
al
u
a
t
i
o
n
m
e
t
r
i
c
s
,
s
t
r
e
n
g
t
h
s
,
a
n
d
l
i
m
i
t
a
tio
n
s
A
l
g
o
r
i
t
h
m
/
P
a
r
a
d
i
g
m
Ta
sk
i
n
U
C
R
A
K
e
y
M
e
t
r
i
c
s
S
t
r
e
n
g
t
h
s
Li
mi
t
a
t
i
o
n
s
R
e
g
r
e
ssi
o
n
t
r
e
e
/
r
a
n
d
o
m
f
o
r
e
s
t
(
S
L)
Tr
a
f
f
i
c
/
Q
o
E
p
r
e
d
i
c
t
i
o
n
A
c
c
u
r
a
c
y
,
l
a
t
e
n
c
y
F
a
st
t
r
a
i
n
i
n
g
;
i
n
t
e
r
p
r
e
t
a
b
l
e
N
e
e
d
s
l
a
b
e
l
s
;
d
r
i
f
t
-
se
n
s
i
t
i
v
e
S
V
M
(
S
L)
S
l
i
c
e
d
e
c
i
s
i
o
n
s
u
p
p
o
r
t
F1
-
sc
o
r
e
,
d
e
l
a
y
R
o
b
u
st
t
o
sma
l
l
d
a
t
a
se
t
s
K
e
r
n
e
l
t
u
n
i
n
g
;
l
i
m
i
t
e
d
sca
l
a
b
i
l
i
t
y
K
-
me
a
n
s
(
U
L)
U
ser/
ser
v
i
c
e
c
l
u
st
e
r
i
n
g
Th
r
o
u
g
h
p
u
t
,
c
l
u
st
e
r
q
u
a
l
i
t
y
La
b
e
l
-
f
r
e
e
;
s
i
m
p
l
e
K
s
e
l
e
c
t
i
o
n
;
c
l
u
st
e
r
d
r
i
f
t
Q
-
l
e
a
r
n
i
n
g
(
R
L)
A
d
mi
ss
i
o
n
/
c
o
n
t
r
o
l
a
t
R
A
N
Q
o
E,
f
a
i
r
n
e
ss
Lo
w
c
o
m
p
l
e
x
i
t
y
;
o
n
l
i
n
e
l
e
a
r
n
i
n
g
C
o
n
v
e
r
g
e
n
c
e
;
r
e
w
a
r
d
sh
a
p
i
n
g
D
Q
N
/
D
R
L
(
R
L)
S
l
i
c
e
a
d
m
i
ssi
o
n
a
n
d
l
o
a
d
b
a
l
a
n
c
i
n
g
Q
o
E,
sp
e
c
t
r
a
l
e
f
f
i
c
i
e
n
c
y
H
a
n
d
l
e
s
h
i
g
h
-
d
i
m
e
n
s
i
o
n
a
l
s
t
a
t
e
s
S
a
mp
l
e
c
o
mp
l
e
x
i
t
y
;
st
a
b
i
l
i
t
y
3
.
5
.
E
dg
e
-
a
s
s
is
t
ed
a
nd
D2
D
UCRA
W
e
d
is
cu
s
s
co
n
g
esti
o
n
m
an
a
g
em
en
t
an
d
th
e
r
o
le
o
f
e
d
g
e
co
m
p
u
tin
g
,
m
u
lti
-
co
n
n
ec
tiv
ity
,
an
d
D
2
D
ass
is
tan
ce
u
n
d
e
r
o
v
er
lo
a
d
co
n
d
itio
n
s
.
Natu
r
ally
,
s
o
m
e
s
tu
d
ies
in
v
esti
g
ate
co
n
g
esti
o
n
co
n
t
r
o
l
f
o
r
h
ig
h
tr
af
f
ic
lo
ad
s
in
n
etwo
r
k
s
.
As
co
n
g
e
s
tio
n
co
n
tr
o
l
is
an
im
p
o
r
tan
t
asp
ec
t
o
f
5
G,
HetNe
ts
allo
w
v
ar
io
u
s
n
etwo
r
k
in
s
tan
ce
s
in
a
s
in
g
le
in
f
r
astru
ctu
r
e
to
im
p
r
o
v
e
Qo
E
[
4
6
]
.
T
h
e
u
s
e
o
f
n
etwo
r
k
s
licin
g
alg
o
r
ith
m
s
in
h
ig
h
co
n
g
esti
o
n
/o
v
e
r
lo
ad
e
d
s
ce
n
ar
i
o
s
was
ev
alu
ated
with
an
8
9
%
r
ed
u
ctio
n
in
th
e
o
v
er
all
Q
o
E
[
4
7
]
.
E
v
e
n
wh
en
in
tr
o
d
u
cin
g
DQN
in
to
th
e
r
eso
u
r
ce
allo
ca
tio
n
,
o
n
ly
a
2
0
%
in
cr
ea
s
e
in
Q
o
E
ca
n
b
e
o
b
s
er
v
ed
,
s
h
o
win
g
t
h
e
s
ev
er
ity
o
f
th
e
o
v
er
lo
a
d
ed
n
et
wo
r
k
o
n
u
s
er
Qo
E
.
I
t
is
also
f
u
r
th
er
d
em
o
n
s
tr
ated
th
at
n
etwo
r
k
s
licin
g
m
ay
n
o
t
b
e
an
o
p
tio
n
al
m
et
h
o
d
f
o
r
s
o
l
v
in
g
th
ese
is
s
u
es.
T
h
e
p
r
o
p
o
s
ed
n
etwo
r
k
s
licin
g
m
o
d
els
f
r
o
m
th
ese
s
tu
d
ies
d
o
n
o
t
in
d
icate
an
im
p
r
o
v
em
en
t
in
Qo
E
o
r
Q
o
S
[
4
8
]
–
[
5
0
]
.
As
th
ese
m
o
d
els
d
em
o
n
s
tr
ated
th
e
ca
p
ab
ilit
ies
to
p
r
ed
ict
h
ig
h
-
co
n
g
esti
o
n
s
ce
n
a
r
io
s
with
an
ac
cu
r
ac
y
o
f
ap
p
r
o
x
im
ately
9
0
%
u
s
in
g
b
o
th
r
ei
n
f
o
r
ce
m
e
n
t
an
d
SL.
T
h
is
co
n
f
ir
m
s
th
e
r
eliab
ilit
y
o
f
th
e
im
p
le
m
en
tatio
n
o
f
ML
.
Alth
o
u
g
h
th
ese
m
eth
o
d
s
ac
h
i
ev
e
h
ig
h
p
r
e
d
ictio
n
ac
cu
r
ac
y
,
n
etwo
r
k
s
licin
g
alg
o
r
ith
m
s
ar
e
s
till
u
n
ab
le
to
s
ig
n
if
ican
tly
in
cr
ea
s
e
u
s
er
s
'
Qo
E
.
T
h
e
r
e
f
o
r
e
,
s
o
m
e
r
e
s
e
a
r
c
h
c
o
n
s
id
e
r
s
i
m
p
r
o
v
i
n
g
c
o
n
g
e
s
t
i
o
n
m
an
a
g
e
m
e
n
t
b
y
a
p
p
l
y
i
n
g
a
l
g
o
r
i
t
h
m
s
c
h
e
m
es
w
i
t
h
m
u
l
t
i
-
c
o
n
n
e
c
ti
v
i
t
y
[
5
1
]
,
[
5
2
]
.
A
s
i
n
g
l
e
d
e
v
i
c
e
c
a
n
b
e
c
o
n
n
e
c
t
e
d
t
o
s
e
v
e
r
a
l
c
e
l
ls
u
s
i
n
g
m
u
l
t
i
-
c
o
n
n
e
c
t
i
v
i
t
y
a
l
g
o
r
i
t
h
m
s
,
w
h
i
c
h
d
i
v
i
d
e
h
e
a
v
y
t
r
a
f
f
i
c
a
m
o
n
g
ce
l
ls
.
O
t
h
e
r
w
o
r
k
s
p
r
o
p
o
s
e
d
e
p
l
o
y
i
n
g
a
d
d
it
i
o
n
a
l
s
m
a
ll
c
el
l
s
t
o
s
u
p
p
o
r
t
h
i
g
h
c
o
n
g
e
s
t
i
o
n
.
T
h
e
u
s
e
o
f
a
u
s
e
r
-
c
e
n
t
r
i
c
a
s
s
o
c
i
at
i
o
n
b
e
t
w
e
e
n
v
a
r
i
o
u
s
s
m
al
l
b
a
s
e
s
t
at
i
o
n
s
w
as
p
r
o
p
o
s
e
d
[
5
3
]
.
T
h
e
D
Q
N
m
o
d
e
l
w
as
u
s
e
d
t
o
a
s
s
o
c
i
at
e
i
n
d
i
v
i
d
u
al
U
E
w
i
t
h
a
n
o
t
h
e
r
b
as
e
s
t
at
i
o
n
t
h
at
o
f
f
e
r
s
t
h
e
h
i
g
h
e
s
t
r
e
s
o
u
r
c
e
s
.
T
h
e
m
e
t
h
o
d
s
d
e
m
o
n
s
t
r
a
t
e
d
a
n
8
0
%
i
m
p
r
o
v
e
m
e
n
t
i
n
t
h
e
o
v
e
r
a
l
l
t
h
r
o
u
g
h
p
u
t
u
n
d
e
r
o
v
e
r
l
o
a
d
e
d
s
i
t
u
at
i
o
n
s
wi
t
h
5
0
U
E
s
,
a
s
t
h
e
n
e
t
w
o
r
k
t
r
a
f
f
i
c
w
as
b
a
l
a
n
c
e
d
b
e
t
w
e
e
n
n
o
d
e
s
.
H
o
we
v
e
r
,
t
h
es
e
m
e
t
h
o
d
s
h
a
v
e
a
m
a
i
n
l
i
m
i
t
a
ti
o
n
.
T
h
e
y
a
r
e
d
i
f
f
ic
u
l
t
t
o
i
m
p
l
e
m
e
n
t
i
n
r
e
a
l
-
w
o
r
l
d
s
it
u
a
t
i
o
n
s
,
as
h
i
g
h
r
es
o
u
r
c
es
a
r
e
r
e
q
u
i
r
e
d
t
o
c
r
e
a
te
m
u
l
t
i
p
l
e
n
o
d
es
i
n
a
d
e
n
s
e
a
r
e
a.
T
h
e
r
e
f
o
r
e
,
i
t
w
as
p
r
o
p
o
s
e
d
b
y
r
e
s
e
a
r
c
h
e
r
s
[
4
3
]
,
[
4
4
]
,
a
n
d
[
5
3
]
t
o
s
t
u
d
y
a
u
s
e
r
-
c
e
n
t
r
i
c
r
es
o
u
r
c
e
a
l
l
o
c
at
i
o
n
m
e
t
h
o
d
f
o
r
c
o
n
g
e
s
t
i
o
n
c
o
n
t
r
o
l
,
a
s
u
s
e
r
-
ce
n
t
r
i
c
al
g
o
r
i
t
h
m
s
p
e
r
f
o
r
m
b
e
t
t
e
r
t
h
a
n
n
e
t
w
o
r
k
-
c
e
n
t
r
i
c
a
l
g
o
r
it
h
m
s
.
T
h
e
d
i
f
f
e
r
e
n
c
e
s
b
e
tw
e
e
n
Q
o
E
‑
b
a
s
e
d
,
e
c
o
n
o
m
i
c
,
DR
L
‑
b
as
e
d
,
an
d
c
l
u
s
t
e
r
i
n
g
‑
b
a
s
e
d
U
C
R
A
s
c
h
e
m
es
a
r
e
s
u
m
m
a
r
i
z
ed
i
n
T
a
b
l
e
2
.
T
a
b
l
e
2
.
T
h
e
m
a
t
i
c
c
o
m
p
a
r
i
s
o
n
o
f
u
s
e
r
‑
c
e
n
t
r
i
c
r
es
o
u
r
c
e
a
l
l
o
ca
ti
o
n
s
c
h
e
m
e
s
,
r
e
p
r
e
s
e
n
ta
t
i
v
e
s
t
u
d
i
e
s
,
n
e
tw
o
r
k
s
e
t
ti
n
g
s
,
r
e
p
o
r
t
e
d
o
u
t
c
o
m
es
,
a
n
d
k
e
y
o
b
s
e
r
v
a
t
i
o
n
s
Th
e
m
e
R
e
p
r
e
se
n
t
a
t
i
v
e
S
t
u
d
y
S
e
t
t
i
n
g
R
e
p
o
r
t
e
d
O
u
t
c
o
m
e
Li
mi
t
a
t
i
o
n
s
Q
o
E/
U
t
i
l
i
t
y
-
b
a
se
d
a
l
l
o
c
a
t
i
o
n
D
2
D
-
a
ssi
s
t
e
d
v
i
d
e
o
U
A
M
S
H
e
t
N
e
t
v
i
d
e
o
st
r
e
a
m
i
n
g
↓
c
h
u
r
n
1
–
2
%,
↓
l
a
t
e
n
c
y
R
e
l
a
y
i
n
c
e
n
t
i
v
e
v
s
b
a
t
t
e
r
y
f
a
i
r
n
e
ss
Ec
o
n
o
mi
c
/
M
a
r
k
e
t
-
b
a
s
e
d
a
l
l
o
c
a
t
i
o
n
Tw
o
-
p
r
i
o
r
i
t
y
D
R
L
+
b
i
d
d
i
n
g
M
V
N
O
o
v
e
r
sh
a
r
e
d
R
A
N
↑
r
e
v
e
n
u
e
2
.
6
–
5
.
4
%,
↑
S
p
e
c
t
r
a
l
Ef
f
i
c
i
e
n
c
y
0
.
5
–
2
.
7
%
S
t
a
r
v
a
t
i
o
n
a
v
o
i
d
a
n
c
e
v
i
a
b
i
d
c
a
p
s
RL
-
b
a
se
d
c
o
n
t
r
o
l
U
ser
-
c
e
n
t
r
i
c
a
ss
o
c
i
a
t
i
o
n
(
D
R
L)
U
l
t
r
a
-
d
e
n
se
mi
l
l
i
m
e
t
e
r
w
a
v
e
(
mm
W
a
v
e
)
↑
t
h
r
o
u
g
h
p
u
t
(
si
m
u
l
a
t
i
o
n
)
H
i
g
h
d
e
p
l
o
y
me
n
t
c
o
m
p
l
e
x
i
t
y
;
c
o
o
r
d
i
n
a
t
i
o
n
o
v
e
r
h
e
a
d
UL
-
b
a
se
d
c
l
u
s
t
e
r
i
n
g
A
d
a
p
t
i
v
e
sl
i
c
i
n
g
v
i
a
k
-
mea
n
s
M
i
x
e
d
t
r
a
f
f
i
c
↑
Q
o
S
/
Q
o
E
c
o
m
p
a
r
e
d
t
o
st
a
t
i
c
sl
i
c
i
n
g
C
l
u
st
e
r
r
o
b
u
st
n
e
ss
r
e
q
u
i
r
e
d
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
2
3
6
-
1
2
4
8
1244
4.
DIS
CU
SS
I
O
N
AND
CR
I
T
I
CAL SY
NT
H
E
SI
S
T
h
e
s
u
r
v
e
y
h
ig
h
lig
h
ts
s
ev
e
r
a
l
s
ig
n
if
ican
t
in
s
ig
h
ts
r
eg
ar
d
i
n
g
th
e
u
s
e
o
f
ML
‑
b
ased
UC
R
A
in
5
G
h
eter
o
g
en
e
o
u
s
n
etwo
r
k
s
.
E
a
ch
ML
p
ar
ad
ig
m
co
n
tr
ib
u
te
s
d
if
f
er
en
tly
to
p
r
ed
ictio
n
,
class
if
icatio
n
,
an
d
r
ea
l‑
tim
e
co
n
tr
o
l
task
s
.
SL
m
eth
o
d
s
d
em
o
n
s
tr
ate
s
tr
o
n
g
ca
p
ab
ilit
y
in
f
o
r
ec
asti
n
g
tr
a
f
f
ic
lev
els
an
d
s
lice
r
eq
u
ir
em
e
n
ts
.
T
h
ese
m
ak
e
th
e
m
s
u
itab
le
f
o
r
p
r
o
ac
tiv
e
ad
m
is
s
io
n
co
n
tr
o
l
an
d
r
eso
u
r
ce
p
la
n
n
in
g
.
UL
m
eth
o
d
s
p
r
o
v
id
e
a
d
v
an
ta
g
es
wh
en
g
r
o
u
p
in
g
u
s
er
s
o
r
s
er
v
ices
b
ased
o
n
p
atter
n
s
in
tr
af
f
ic
b
eh
av
io
r
o
r
Qo
E
r
eq
u
ir
em
e
n
ts
.
R
L
tech
n
iq
u
es
ar
e
p
a
r
ticu
lar
ly
ef
f
ec
tiv
e
f
o
r
co
n
tin
u
o
u
s
a
n
d
a
d
ap
tiv
e
d
ec
is
io
n
‑
m
ak
in
g
in
en
v
ir
o
n
m
en
ts
wh
er
e
n
etwo
r
k
co
n
d
itio
n
s
an
d
u
s
er
d
e
m
an
d
s
c
h
an
g
e
r
a
p
id
ly
.
A
co
n
s
is
ten
t
f
in
d
i
n
g
is
t
h
at
s
er
v
ice
-
ce
n
tr
ic
s
licin
g
s
tr
at
eg
ies
p
er
f
o
r
m
p
o
o
r
ly
u
n
d
e
r
co
n
g
ested
n
etwo
r
k
co
n
d
itio
n
s
wh
en
co
m
p
ar
ed
with
UC
R
A
ap
p
r
o
ac
h
es.
Ser
v
ice
-
ce
n
tr
ic
allo
ca
tio
n
tr
e
ats
all
u
s
er
s
w
ith
in
a
s
lice
as
a
s
in
g
le
g
r
o
u
p
,
wh
ic
h
r
esu
lts
in
in
s
u
f
f
icien
t
d
if
f
er
e
n
tiatio
n
am
o
n
g
u
s
er
s
with
d
is
tin
ct
Qo
E
n
ee
d
s
.
I
n
co
n
tr
ast,
UC
R
A
m
eth
o
d
s
th
at
in
co
r
p
o
r
ate
u
s
er
u
tili
ty
,
co
n
tex
tu
al
in
f
o
r
m
atio
n
,
an
d
p
r
io
r
i
ty
attr
ib
u
tes.
T
h
ese
d
em
o
n
s
tr
ate
b
etter
p
e
r
f
o
r
m
a
n
ce
in
ter
m
s
o
f
f
air
n
ess
,
th
r
o
u
g
h
p
u
t,
a
n
d
r
esil
ien
ce
d
u
r
in
g
o
v
er
l
o
ad
.
T
h
is
o
b
s
er
v
atio
n
is
s
u
p
p
o
r
ted
b
y
s
ev
er
al
R
L
-
b
ased
UC
R
A
s
tu
d
ies
th
at
ad
j
u
s
t
ad
m
is
s
io
n
o
r
r
eso
u
r
ce
-
allo
ca
tio
n
d
ec
is
io
n
s
in
r
ea
l
tim
e.
T
h
ese
s
tu
d
ies
r
ep
o
r
t
im
p
r
o
v
em
e
n
ts
in
s
p
ec
tr
al
ef
f
icien
cy
,
th
r
o
u
g
h
p
u
t,
an
d
u
s
er
Qo
E
,
p
ar
ticu
lar
ly
wh
e
n
th
e
n
etwo
r
k
is
s
u
b
ject
to
h
ea
v
y
tr
a
f
f
ic.
T
h
e
p
r
ac
tical
d
ep
lo
y
m
e
n
t
o
f
ML
with
in
UC
R
A
p
r
esen
ts
s
ev
er
al
im
p
o
r
tan
t
ch
allen
g
es.
Ma
n
y
ML
m
o
d
els
h
av
e
h
ig
h
c
o
m
p
u
tatio
n
al
d
em
an
d
s
,
an
d
th
is
co
m
p
le
x
ity
ca
n
lim
it
d
ep
lo
y
m
en
t
at
th
e
b
ase
s
tatio
n
o
r
u
s
er
-
eq
u
ip
m
e
n
t
lev
el.
Op
e
r
ato
r
s
also
r
eq
u
ir
e
s
o
m
e
lev
el
o
f
i
n
ter
p
r
etab
ilit
y
in
d
ec
is
io
n
-
m
a
k
in
g
to
en
s
u
r
e
tr
u
s
t
in
r
eso
u
r
ce
m
an
a
g
em
en
t.
Fair
n
ess
is
an
im
p
o
r
tan
t
co
n
s
id
er
atio
n
b
ec
au
s
e
ce
r
tain
ap
p
r
o
ac
h
es
n
atu
r
ally
ass
ig
n
h
ig
h
er
p
r
io
r
ity
t
o
s
p
ec
if
ic
u
s
er
g
r
o
u
p
s
.
L
o
w
-
p
r
io
r
ity
o
r
lo
w
-
b
atter
y
u
s
er
s
m
ay
ex
p
e
r
ien
ce
s
tar
v
atio
n
o
r
d
eg
r
ad
e
d
s
er
v
ice
q
u
ality
with
o
u
t saf
eg
u
ar
d
s
.
T
h
e
r
ev
iew
also
r
ev
ea
ls
s
ev
er
al
r
esear
ch
g
ap
s
th
at
ar
e
co
m
m
o
n
ac
r
o
s
s
s
tu
d
ies.
C
u
r
r
en
t
ML
-
b
ased
m
eth
o
d
s
ar
e
n
o
t
s
u
f
f
icien
tly
r
o
b
u
s
t
ag
ain
s
t
d
is
tu
r
b
an
ce
s
in
tr
ain
in
g
d
ata,
s
u
ch
as
n
o
is
e,
an
o
m
alies,
o
r
ad
v
er
s
ar
ial
m
a
n
ip
u
latio
n
.
Mo
s
t
r
eso
u
r
ce
-
allo
ca
tio
n
m
o
d
els
f
o
c
u
s
p
r
im
a
r
ily
o
n
th
e
r
ad
i
o
-
ac
ce
s
s
n
etwo
r
k
.
Pra
ctica
l
im
p
lem
en
tatio
n
r
eq
u
ir
es
co
n
s
is
ten
t
co
o
r
d
in
atio
n
ac
r
o
s
s
th
e
r
ad
i
o
-
ac
ce
s
s
n
etwo
r
k
,
th
e
c
o
r
e
n
etwo
r
k
,
an
d
ed
g
e
-
c
o
m
p
u
ti
n
g
en
v
ir
o
n
m
en
ts
.
An
o
th
er
em
er
g
in
g
d
ir
ec
tio
n
is
th
e
p
o
ten
tial
s
h
if
t
t
o
war
d
s
em
an
tic
o
r
g
o
al
-
o
r
ie
n
ted
co
m
m
u
n
icatio
n
,
wh
ich
r
e
d
ef
in
es
r
eso
u
r
ce
all
o
ca
tio
n
ar
o
u
n
d
u
s
er
i
n
ten
t
r
at
h
er
th
an
r
aw
tr
af
f
ic
ch
ar
ac
ter
is
tics
.
L
ig
h
tweig
h
t
a
n
d
in
ter
p
r
etab
le
ML
m
o
d
els
ar
e
also
n
ee
d
ed
to
s
u
p
p
o
r
t d
ep
lo
y
m
en
t
clo
s
er
to
th
e
n
etwo
r
k
ed
g
e,
wh
er
e
h
a
r
d
wa
r
e
r
eso
u
r
ce
s
ar
e
m
o
r
e
lim
ite
d
.
Ov
e
r
all,
th
e
s
y
n
th
esis
s
h
o
ws
th
at
ML
-
b
ased
UC
R
A
p
r
o
v
id
es
a
s
tr
o
n
g
p
o
ten
tial
f
o
r
im
p
r
o
v
in
g
u
s
er
-
le
v
el
Qo
E
in
th
e
o
v
er
lo
a
d
ed
5
G
h
eter
o
g
en
e
o
u
s
n
etwo
r
k
s
.
At
t
h
e
s
am
e
tim
e,
s
ev
er
al
tech
n
ical
an
d
o
p
er
at
io
n
al
ch
allen
g
es
m
u
s
t
b
e
a
d
d
r
ess
ed
to
ac
h
iev
e
r
eliab
le,
ef
f
icien
t,
a
n
d
f
air
d
ep
lo
y
m
en
t in
t
h
e
r
ea
l sy
s
tem
s
.
5.
CO
NCLU
SI
O
N
A
r
ev
iew
o
f
ex
is
tin
g
w
o
r
k
s
d
e
m
o
n
s
tr
ates
a
f
ew
r
esear
ch
g
a
p
s
an
d
th
e
f
u
t
u
r
e
d
i
r
ec
tio
n
o
f
r
esear
ch
to
d
ev
elo
p
n
ew
al
g
o
r
ith
m
s
.
Mo
s
t
o
f
th
e
ex
is
tin
g
wo
r
k
s
f
o
cu
s
ed
o
n
n
etwo
r
k
s
licin
g
to
im
p
r
o
v
e
th
e
n
etwo
r
k
p
er
f
o
r
m
an
ce
b
y
allo
ca
tin
g
b
a
n
d
wid
th
b
ased
o
n
wh
ich
s
er
v
ices
ar
e
b
ein
g
u
s
ed
.
Ho
wev
er
,
th
e
o
v
e
r
lo
ad
e
d
n
etwo
r
k
co
n
d
itio
n
is
n
o
t
ev
a
lu
ated
in
th
ese
wo
r
k
s
.
C
o
n
g
esti
o
n
co
n
tr
o
l
is
an
im
p
o
r
ta
n
t
asp
ec
t
o
f
th
e
5
G
HetNe
ts
b
ec
au
s
e
v
ar
io
u
s
d
ev
ices
ar
e
b
ein
g
co
n
n
ec
te
d
to
o
n
e
in
f
r
astru
ctu
r
e.
T
h
er
ef
o
r
e,
u
s
er
-
ce
n
tr
ic
m
eth
o
d
s
ar
e
cu
r
r
en
tly
b
ei
n
g
d
ev
elo
p
e
d
to
allo
ca
te
r
eso
u
r
ce
s
to
th
e
u
s
er
.
ML
m
o
d
els
ar
e
a
p
r
o
m
is
in
g
m
eth
o
d
to
b
e
im
p
lem
en
ted
i
n
alg
o
r
ith
m
p
r
ed
ictio
n
a
n
d
d
ec
is
io
n
-
m
ak
i
n
g
.
T
h
e
y
im
p
r
o
v
e
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
5
G
n
etwo
r
k
,
b
u
t
it
is
d
if
f
icu
lt
to
i
d
en
tify
th
e
o
p
tim
al
ML
m
o
d
el
f
o
r
u
s
er
-
ce
n
tr
ic
alg
o
r
ith
m
s
.
E
x
i
s
t
i
n
g
w
o
r
k
s
h
a
v
e
n
o
t
c
o
n
d
u
c
t
e
d
a
h
o
l
i
s
ti
c
a
p
p
r
o
ac
h
i
n
e
v
a
l
u
a
t
i
n
g
v
a
r
i
o
u
s
M
L
a
lg
o
r
i
t
h
m
s
,
e
s
p
ec
i
a
ll
y
c
o
m
p
a
r
i
n
g
S
L
,
U
L
a
n
d
RL
.
6.
F
UT
UR
E
DIR
E
C
T
I
O
N
T
h
er
ef
o
r
e,
f
u
r
th
e
r
r
esear
c
h
ca
n
b
e
co
n
d
u
cted
to
f
ill
th
e
g
a
p
s
in
t
h
e
c
u
r
r
en
t
r
esear
ch
.
T
h
e
u
s
er
-
ce
n
tr
ic
r
eso
u
r
ce
allo
ca
tio
n
alg
o
r
ith
m
th
at
u
s
es
u
s
er
p
r
io
r
ities
wit
h
lo
w
r
eso
u
r
c
e
r
eq
u
ir
em
en
ts
ca
n
b
e
d
esig
n
ed
to
im
p
r
o
v
e
c
o
n
g
esti
o
n
co
n
tr
o
l.
I
n
ad
d
itio
n
,
v
ar
io
u
s
ML
alg
o
r
ith
m
s
ca
n
also
b
e
ex
p
lo
r
e
d
in
a
u
s
er
-
ce
n
tr
ic
r
eso
u
r
ce
allo
ca
tio
n
alg
o
r
ith
m
to
id
en
tify
th
e
b
est
ML
alg
o
r
ith
m
th
at
p
r
o
v
id
es
th
e
b
est
d
ec
is
io
n
to
im
p
r
o
v
e
Qo
E
an
d
Qo
S.
O
v
er
all,
f
u
r
th
er
r
esear
ch
ca
n
b
e
c
o
n
d
u
cted
o
n
a
ML
-
b
ased
u
s
er
-
ce
n
tr
ic
r
eso
u
r
ce
allo
ca
tio
n
alg
o
r
ith
m
to
im
p
r
o
v
e
co
n
g
esti
o
n
co
n
t
r
o
l in
th
e
5
G
HetNe
t in
f
r
astru
ctu
r
e.
ACK
NO
WL
E
DG
E
M
E
NT
W
e
wo
u
ld
lik
e
to
ex
p
r
ess
o
u
r
g
r
atitu
d
e
to
th
e
Min
is
tr
y
o
f
Hig
h
er
E
d
u
ca
tio
n
(
MO
HE
)
f
o
r
p
r
o
v
id
in
g
f
u
n
d
in
g
f
o
r
th
is
p
r
o
ject.
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
Ma
ch
in
e
lea
r
n
in
g
-
d
r
iven
a
n
a
lysi
s
o
f u
s
er b
a
n
d
w
id
th
a
llo
ca
t
io
n
a
n
d
p
erfo
r
ma
n
ce
in
…
(
P
a
n
g
Wa
i Leo
n
g
)
1245
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
s
u
p
p
o
r
ted
b
y
t
h
e
Min
is
tr
y
o
f
Hig
h
er
E
d
u
ca
tio
n
(
MO
HE
)
th
r
o
u
g
h
th
e
Fu
n
d
am
en
tal
R
esear
ch
Gr
an
t
Sch
em
e
(
FR
GS/1
/2
0
2
4
/I
C
T
0
6
/TA
YL
OR
/0
2
/1
)
.
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
Pan
g
W
ai
L
eo
n
g
✓
✓
✓
✓
✓
✓
✓
R
ay
m
o
n
d
C
h
ia
✓
✓
✓
✓
✓
Ph
an
g
Swee
Kin
g
✓
✓
✓
✓
✓
Go
h
Hu
i H
wan
g
✓
✓
✓
✓
C
h
an
Kah
Yo
o
n
g
✓
✓
✓
C
h
u
n
g
Gwo
C
h
in
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
Sin
ce
th
is
is
a
r
ev
iew
a
r
ticle,
th
e
au
th
o
r
s
co
n
f
ir
m
t
h
at
th
e
d
ata
s
u
p
p
o
r
tin
g
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
cited
with
in
th
e
ar
ticle.
No
n
ew
d
ata
wer
e
cr
ea
te
d
o
r
a
n
al
y
ze
d
in
th
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
R
.
I
.
R
o
n
y
,
E.
L
o
p
e
z
-
A
g
u
i
l
e
r
a
,
a
n
d
E.
G
a
r
c
i
a
-
V
i
l
l
e
g
a
s
,
“
D
y
n
a
m
i
c
s
p
e
c
t
r
u
m
a
l
l
o
c
a
t
i
o
n
f
o
l
l
o
w
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
s
i
n
5
G
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
4
3
4
5
8
–
1
4
3
4
7
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
2
2
3
3
1
.
[
2
]
E.
G
u
r
e
s,
I
.
S
h
a
y
e
a
,
M
.
S
h
e
i
k
h
,
M
.
E
r
g
e
n
,
a
n
d
A
.
A
.
El
-
S
a
l
e
h
,
“
A
d
a
p
t
i
v
e
c
e
l
l
s
e
l
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
b
a
l
a
n
c
i
n
g
c
e
l
l
l
o
a
d
s
i
n
5
G
h
e
t
e
r
o
g
e
n
e
o
u
s
n
e
t
w
o
r
k
s,
”
A
l
e
x
a
n
d
ri
a
En
g
i
n
e
e
ri
n
g
J
o
u
rn
a
l
,
v
o
l
.
7
2
,
n
o
.
7
2
,
p
p
.
6
2
1
–
6
3
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
3
.
0
4
.
0
1
2
.
[
3
]
S
.
A
.
K
h
a
n
,
I
.
S
h
a
y
e
a
,
M
.
Er
g
e
n
,
A
.
A
.
El
-
S
a
l
e
h
,
a
n
d
M
.
R
o
s
l
e
e
,
“
A
n
i
mp
r
o
v
e
d
h
a
n
d
o
v
e
r
d
e
c
i
s
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
5
G
h
e
t
e
r
o
g
e
n
e
o
u
s
n
e
t
w
o
r
k
s,”
i
n
1
5
t
h
I
E
EE
M
a
l
a
y
si
a
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
s:
Em
e
r
g
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
i
n
I
o
T
a
n
d
5
G
,
MIC
C
2
0
2
1
-
Pro
c
e
e
d
i
n
g
s
,
2
0
2
1
,
p
p
.
2
5
–
3
0
,
d
o
i
:
1
0
.
1
1
0
9
/
M
I
C
C
5
3
4
8
4
.
2
0
2
1
.
9
6
4
2
0
7
6
.
[
4
]
R
.
G
a
t
t
i
,
G
.
B
.
A
r
j
u
n
K
u
mar,
K
.
N
.
S
u
n
i
l
K
u
m
a
r
,
S
.
P
a
l
l
e
,
a
n
d
T.
R
.
G
a
d
e
k
a
l
l
u
,
“
O
p
t
i
m
a
l
r
e
s
o
u
r
c
e
s
c
h
e
d
u
l
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
c
e
l
l
b
o
u
n
d
a
r
i
e
s
u
sers
i
n
h
e
t
e
r
o
g
e
n
o
u
s
5
G
n
e
t
w
o
r
k
s,”
P
h
y
s
i
c
a
l
C
o
m
m
u
n
i
c
a
t
i
o
n
,
v
o
l
.
5
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
h
y
c
o
m
.
2
0
2
2
.
1
0
1
9
1
5
.
[
5
]
M
.
U
.
I
q
b
a
l
,
E.
A
.
A
n
sar
i
,
S
.
A
k
h
t
a
r
,
M
.
F
a
r
o
o
q
-
I
-
A
z
a
m,
S
.
R
.
H
a
ss
a
n
,
a
n
d
R
.
A
si
f
,
“
O
p
t
i
ma
l
l
e
a
r
n
i
n
g
p
a
r
a
d
i
g
m
a
n
d
c
l
u
s
t
e
r
i
n
g
f
o
r
e
f
f
e
c
t
i
v
e
r
a
d
i
o
r
e
so
u
r
c
e
ma
n
a
g
e
me
n
t
i
n
5
G
H
e
t
N
e
t
s,”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
4
1
2
6
4
–
4
1
2
8
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
6
8
5
4
3
.
[
6
]
I
.
C
h
a
k
o
u
r
,
C
.
D
a
o
u
i
,
M
.
B
a
sl
a
m,
B
.
S
a
i
n
z
-
De
-
A
b
a
j
o
,
a
n
d
B
.
G
a
r
c
i
a
-
Za
p
i
r
a
i
n
,
“
S
t
r
a
t
e
g
i
c
b
a
n
d
w
i
d
t
h
a
l
l
o
c
a
t
i
o
n
f
o
r
Q
o
S
i
n
I
o
T
g
a
t
e
w
a
y
:
p
r
e
d
i
c
t
i
n
g
f
u
t
u
r
e
n
e
e
d
s
b
a
s
e
d
o
n
I
o
T
d
e
v
i
c
e
h
a
b
i
t
s
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
6
5
9
0
–
6
6
0
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
a
c
c
e
s
s.
2
0
2
4
.
3
3
5
1
1
1
1
.
[
7
]
J.
S
.
P
e
r
e
z
,
S
.
K
.
J
a
y
a
w
e
e
r
a
,
a
n
d
S
.
La
n
e
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
i
d
e
d
c
o
g
n
i
t
i
v
e
R
A
T
s
e
l
e
c
t
i
o
n
f
o
r
5
G
h
e
t
e
r
o
g
e
n
e
o
u
s
n
e
t
w
o
r
k
s,
”
i
n
2
0
1
7
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
B
l
a
c
k
S
e
a
C
o
n
f
e
re
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
N
e
t
w
o
r
k
i
n
g
,
Bl
a
c
k
S
e
a
C
o
m
2
0
1
7
,
2
0
1
8
,
v
o
l
.
2
0
1
8
-
Jan
u
a
r
y
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
B
l
a
c
k
S
e
a
C
o
m.
2
0
1
7
.
8
2
7
7
6
7
5
.
[
8
]
F
.
O
.
O
k
e
l
l
o
,
V
.
O
d
u
o
l
,
C
.
M
a
i
n
a
,
a
n
d
A
.
A
p
i
y
o
,
“
I
mp
r
o
v
e
me
n
t
o
f
5
G
c
o
r
e
n
e
t
w
o
r
k
p
e
r
f
o
r
m
a
n
c
e
u
si
n
g
n
e
t
w
o
r
k
sl
i
c
i
n
g
a
n
d
d
e
e
p
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
E
l
e
c
t
r
o
n
i
c
s
Re
s
e
a
rc
h
,
v
o
l
.
1
2
,
n
o
.
2
,
p
p
.
4
9
3
–
5
0
2
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
3
7
3
9
1
/
i
j
e
e
r
.
1
2
0
2
2
2
.
[
9
]
I
.
U
l
l
a
h
,
H
.
E
l
S
a
y
e
d
,
S
.
M
a
l
i
k
,
a
n
d
A
.
M
a
n
z
o
o
r
A
h
m
e
d
K
h
a
n
,
“
P
e
r
f
o
r
m
a
n
c
e
e
v
a
l
u
a
t
i
o
n
o
f
q
u
a
l
i
t
y
o
f
e
x
p
e
r
i
e
n
c
e
a
w
a
r
e
m
o
b
i
l
i
t
y
man
a
g
e
me
n
t
i
n
h
e
t
e
r
o
g
e
n
e
o
u
s
c
e
l
l
u
l
a
r
n
e
t
w
o
r
k
s,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
9
7
9
9
4
–
9
8
0
0
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
4
2
6
9
9
1
.
[
1
0
]
A
.
A
.
S
i
mi
s
c
u
k
a
,
A
.
Y
a
q
o
o
b
,
a
n
d
G
.
M
.
M
u
n
t
e
a
n
,
“
F
R
A
D
I
S
:
A
mac
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
mu
l
t
i
p
a
t
h
s
o
l
u
t
i
o
n
f
o
r
d
i
f
f
e
r
e
n
t
i
a
t
e
d
serv
i
c
e
s
i
n
a
n
e
t
w
o
r
k
s
l
i
c
i
n
g
-
e
n
h
a
n
c
e
d
d
e
l
i
v
e
r
y
e
n
v
i
r
o
n
m
e
n
t
,
”
i
n
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
Br
o
a
d
b
a
n
d
M
u
l
t
i
m
e
d
i
a
S
y
s
t
e
m
s
a
n
d
Br
o
a
d
c
a
st
i
n
g
,
B
MS
B
,
2
0
2
4
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
B
M
S
B
6
2
8
8
8
.
2
0
2
4
.
1
0
6
0
8
2
3
7
.
[
1
1
]
D
.
Y
a
n
,
B
.
K
.
N
g
,
W
.
K
e
,
a
n
d
C
.
T.
La
m
,
“
D
e
e
p
r
e
i
n
f
o
r
c
e
m
e
n
t
l
e
a
r
n
i
n
g
b
a
s
e
d
r
e
s
o
u
r
c
e
a
l
l
o
c
a
t
i
o
n
f
o
r
n
e
t
w
o
r
k
sl
i
c
i
n
g
w
i
t
h
massi
v
e
M
I
M
O
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
7
5
8
9
9
–
7
5
9
1
1
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
9
6
8
5
1
.
[
1
2
]
K
.
B
.
A
j
e
y
p
r
a
s
a
a
t
h
a
n
d
P
.
V
e
t
r
i
v
e
l
a
n
,
“
A
h
y
b
r
i
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
i
m
p
r
o
v
i
s
e
d
Q
o
E
i
n
v
i
d
e
o
s
e
r
v
i
c
e
s
o
v
e
r
5
G
w
i
r
e
l
e
s
s
n
e
t
w
o
r
k
s
,
”
C
o
m
p
u
t
e
rs,
M
a
t
e
ri
a
l
s
a
n
d
C
o
n
t
i
n
u
a
,
v
o
l
.
7
8
,
n
o
.
3
,
p
p
.
3
1
9
5
–
3
2
1
3
,
2
0
2
4
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
mc.
2
0
2
3
.
0
4
6
9
1
1
.
[
1
3
]
O
.
A
o
u
e
d
i
,
K
.
P
i
a
mr
a
t
,
S
.
H
a
mm
a
,
a
n
d
J.
K
.
M
.
P
e
r
e
r
a
,
“
N
e
t
w
o
r
k
t
r
a
f
f
i
c
a
n
a
l
y
s
i
s
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
:
a
n
u
n
s
u
p
e
r
v
i
se
d
Evaluation Warning : The document was created with Spire.PDF for Python.