I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
14
,
No
.
4
,
Dec
em
b
er
20
25
,
p
p
.
1
4
3
3
~
1
4
4
3
I
SS
N:
2252
-
8
8
1
4
,
DOI
:
1
0
.
1
1
5
9
1
/ijaas
.
v
14
.
i
4
.
pp
1
4
3
3
-
1
4
4
3
1433
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
Foreca
sting
int
er
net
t
ra
ff
ic
patt
ern
s for th
e camp
us
M
etro
-
E
network
using
a h
y
brid ma
chine l
ea
rning
mo
del
No
ra
km
a
r
Arba
in
1
,
M
uriza
h K
a
s
s
im
1,
2
,
Da
rma
wa
t
y
M
o
hd
Ali
1
,
Sh
uria
Sa
a
idi
n
1
1
F
a
c
u
l
t
y
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
i
T
e
k
n
o
l
o
g
i
M
A
R
A
,
S
h
a
h
A
l
a
m,
S
e
l
a
n
g
o
r
,
M
a
l
a
y
s
i
a
2
I
n
st
i
t
u
t
e
f
o
r
B
i
g
D
a
t
a
A
n
a
l
y
t
i
c
s a
n
d
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
I
B
D
A
A
I
)
,
U
n
i
v
e
r
si
t
i
Te
k
n
o
l
o
g
i
M
A
R
A
,
S
h
a
h
A
l
a
m
,
S
e
l
a
n
g
o
r
,
M
a
l
a
y
s
ia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
24
,
2
0
2
5
R
ev
is
ed
Oct
30
,
2
0
2
5
Acc
ep
ted
No
v
4
,
2
0
2
5
C
o
m
p
lex
traffic
p
a
tt
e
rn
s
lea
d
to
c
ru
c
ial
c
a
m
p
u
s
M
e
tro
-
E
n
e
two
r
k
m
a
n
a
g
e
m
e
n
t
a
n
d
re
so
u
rc
e
a
ll
o
c
a
t
io
n
.
T
h
is
p
a
p
e
r
p
re
se
n
ts
a
n
in
ter
n
e
t
traffic
fo
re
c
a
stin
g
b
y
p
re
-
p
r
o
c
e
ss
in
g
d
a
ta
to
o
ffe
r
b
e
tt
e
r
b
a
n
d
wi
d
th
q
u
a
li
t
y
o
f
se
rv
ice
(
Qo
S
)
.
Ei
g
h
t
(
8
)
c
a
m
p
u
s
es
'
traffic
d
a
ta
we
re
a
n
a
ly
se
d
fo
r
m
o
d
e
ll
in
g
p
re
d
ictio
n
s
u
si
n
g
sta
ti
stica
l
a
n
a
l
y
sis
.
A
M
e
tro
-
E
c
a
m
p
u
s
n
e
two
r
k
p
re
se
n
ts
fo
u
r
(
4
)
l
o
c
a
ti
o
n
s
:
A,
E,
F
,
a
n
d
H
h
a
v
e
is
a
stro
n
g
c
o
rre
latio
n
b
e
twe
e
n
in
b
o
u
n
d
a
n
d
o
u
tb
o
u
n
d
traffic,
w
it
h
c
o
rre
latio
n
v
a
lu
e
s
b
e
twe
e
n
0
.
4
5
4
7
a
n
d
0
.
5
2
0
4
.
As
t
h
e
in
b
o
u
n
d
traffic
i
n
c
re
a
se
s,
o
u
tb
o
u
n
d
traffic
ten
d
s
to
rise
a
s
we
ll
.
Co
n
v
e
rse
ly
,
lo
c
a
ti
o
n
s
B,
C,
a
n
d
G
h
a
v
e
we
a
k
c
o
rre
latio
n
s
,
i
n
d
ica
ti
n
g
m
o
re
in
d
e
p
e
n
d
e
n
t
traffic
p
a
tt
e
r
n
s.
Da
ta
o
u
tl
iers
we
re
fo
u
n
d
fo
r
l
o
c
a
ti
o
n
s
C
a
n
d
F
,
wh
e
re
u
n
u
su
a
l
traffic
sp
ik
e
s
re
q
u
ire
fu
rt
h
e
r
n
e
two
r
k
e
x
p
lo
r
a
ti
o
n
a
n
d
sh
o
w
k
e
y
tre
n
d
s
i
n
traffic
d
a
ta.
De
sc
rip
ti
v
e
sta
ti
stics
re
v
e
a
l
n
o
ta
b
le
d
iffere
n
c
e
s
,
wit
h
H
h
a
s
th
e
h
i
g
h
e
s
t
a
v
e
ra
g
e
traffic
a
t
a
b
o
u
t
7
5
M
b
p
s
,
wh
i
le
C
h
a
s
th
e
lo
we
st
a
t
a
ro
u
n
d
3
0
M
b
p
s.
L
o
c
a
ti
o
n
F
s
h
o
ws
th
e
g
re
a
tes
t
traffic
flu
c
tu
a
ti
o
n
wit
h
a
sta
n
d
a
rd
d
e
v
i
a
ti
o
n
o
f
0
.
4
0
7
6
,
w
h
e
re
a
s
Lo
c
a
ti
o
n
G
h
a
s
v
e
ry
li
tt
le
fl
u
c
tu
a
ti
o
n
wit
h
a
sta
n
d
a
rd
d
e
v
iatio
n
o
f
0
.
0
2
4
0
.
O
v
e
ra
ll
,
th
is
p
re
-
p
ro
c
e
ss
d
a
ta
is
u
se
t
o
c
o
m
b
in
e
m
a
c
h
in
e
lea
rn
i
n
g
(M
L)
to
imp
r
o
v
e
p
re
d
ictio
n
a
b
il
it
ies
f
o
r
b
e
tt
e
r
b
a
n
d
wi
d
th
m
a
n
a
g
e
m
e
n
t
a
n
d
re
a
l
-
ti
m
e
h
a
n
d
li
n
g
in
d
i
g
it
a
l
c
a
m
p
u
s e
n
v
ir
o
n
m
e
n
ts.
K
ey
w
o
r
d
s
:
C
am
p
u
s
Me
tr
o
-
E
n
etwo
r
k
Hy
b
r
id
m
ac
h
in
e
lear
n
i
n
g
I
n
ter
n
et
tr
af
f
ic
f
o
r
ec
asti
n
g
Netwo
r
k
ef
f
icien
cy
T
r
af
f
ic
m
an
a
g
em
en
t stra
teg
ies
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
:
Mu
r
izah
Kass
im
I
n
s
titu
te
f
o
r
B
ig
Data
An
aly
tic
s
an
d
Ar
tific
ial
I
n
tellig
en
ce
,
U
n
iv
er
s
iti T
ek
n
o
lo
g
i M
AR
A
4
0
4
5
0
Sh
ah
Alam
,
Selan
g
o
r
,
Ma
lay
s
ia
E
m
ail:
m
u
r
izah
@
u
itm
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
e
c
o
n
tex
t
o
f
to
d
ay
'
s
d
ig
ital
lan
d
s
ca
p
e
r
esear
ch
,
p
r
e
d
ictin
g
in
ter
n
et
tr
af
f
ic
h
as
b
ec
o
m
e
a
cr
u
cial
asp
ec
t.
T
h
is
in
v
o
lv
es
esti
m
atin
g
d
ata
v
o
lu
m
e
o
n
a
n
etwo
r
k
o
v
e
r
a
s
p
ec
if
ic
tim
ef
r
am
e,
wh
ich
is
ess
en
tial
f
o
r
m
ain
tain
in
g
s
m
o
o
th
o
p
e
r
atio
n
s
.
Acc
u
r
ate
f
o
r
ec
asti
n
g
aid
s
in
m
an
ag
i
n
g
n
etwo
r
k
s
,
co
n
t
r
o
llin
g
c
o
n
g
esti
o
n
,
an
d
ef
f
icien
tly
allo
ca
tin
g
r
eso
u
r
ce
s
,
esp
ec
ially
in
ca
m
p
u
s
Me
tr
o
-
E
n
etwo
r
k
s
[
1
]
.
T
h
e
r
a
p
id
ex
p
an
s
io
n
o
f
d
ig
ital
p
latf
o
r
m
s
h
ig
h
lig
h
ts
th
e
n
ec
ess
ity
f
o
r
ac
cu
r
ate
in
ter
n
et
tr
af
f
ic
f
o
r
ec
asti
n
g
,
p
a
r
ticu
lar
ly
as
ed
u
ca
tio
n
al
in
s
titu
tio
n
s
in
cr
ea
s
in
g
ly
r
ely
o
n
o
n
lin
e
r
eso
u
r
ce
s
an
d
s
er
v
i
ce
s
[
2
]
.
As
m
o
r
e
u
s
er
s
ac
ce
s
s
ed
u
ca
tio
n
al
co
n
ten
t
s
im
u
ltan
eo
u
s
ly
,
n
etwo
r
k
s
f
r
e
q
u
en
tly
ex
p
er
ie
n
ce
u
n
p
r
ed
ictab
le
tr
af
f
ic
s
p
ik
es,
r
esu
ltin
g
in
co
n
g
esti
o
n
,
laten
cy
,
an
d
a
d
im
in
is
h
ed
u
s
er
ex
p
er
i
en
ce
[
3
]
,
[
4
]
.
C
o
n
s
eq
u
en
tly
,
ef
f
ec
tiv
e
tr
af
f
ic
f
o
r
ec
asti
n
g
i
s
ess
en
tial
f
o
r
th
e
p
r
o
ac
tiv
e
m
an
ag
em
e
n
t
o
f
n
et
wo
r
k
r
eso
u
r
ce
s
[
5
]
.
Pre
d
ictin
g
tr
af
f
ic
f
l
o
w
p
atter
n
s
ca
n
en
h
a
n
ce
u
s
er
s
atis
f
ac
tio
n
b
y
m
an
a
g
in
g
b
a
n
d
wid
th
d
u
r
i
n
g
s
u
r
g
es.
T
h
is
r
ev
iew
ass
ess
ed
ex
is
tin
g
in
ter
n
et
tr
af
f
ic
p
r
ed
ictio
n
m
o
d
els,
h
ig
h
lig
h
tin
g
th
eir
lim
itatio
n
s
an
d
id
e
n
tify
in
g
ar
ea
s
f
o
r
f
u
tu
r
e
r
esear
ch
.
A
cr
u
cial
asp
ec
t
o
f
d
e
v
elo
p
in
g
th
ese
m
o
d
els
is
s
ca
lab
ilit
y
an
d
c
o
m
p
u
tatio
n
al
e
f
f
icien
cy
,
as
ac
c
u
r
ac
y
r
elies
o
n
t
h
e
r
eso
u
r
ce
s
r
e
q
u
ir
ed
f
o
r
an
aly
zi
n
g
lar
g
e
d
atasets
u
s
ed
b
y
m
a
n
y
in
s
titu
tio
n
s
an
d
u
s
er
s
[
6
]
,
[
7
]
.
Scalab
ilit
y
r
ef
er
s
to
t
h
e
m
o
d
el
’
s
ca
p
ac
ity
to
h
an
d
le
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
4
,
Dec
em
b
er
20
25
:
1
4
3
3
-
1
4
4
3
1434
in
cr
ea
s
in
g
am
o
u
n
ts
o
f
d
ata
an
d
its
ab
ilit
y
to
ad
ap
t
to
an
y
n
etwo
r
k
g
r
o
wth
with
o
u
t
a
co
r
r
esp
o
n
d
in
g
d
eg
r
ad
atio
n
in
p
er
f
o
r
m
a
n
ce
[
8
]
,
[
9
]
.
A
k
e
y
c
h
allen
g
e
f
ac
e
d
b
y
m
a
n
y
t
r
ad
itio
n
al
m
o
d
els
is
th
at
th
e
y
o
f
ten
ex
h
ib
it
a
tr
a
d
e
-
o
f
f
b
etwe
en
ac
cu
r
ac
y
an
d
co
m
p
u
tatio
n
a
l
r
eso
u
r
ce
s
.
W
h
ile
m
o
r
e
co
m
p
lex
alg
o
r
ith
m
s
,
p
ar
ticu
lar
ly
th
o
s
e
b
ased
o
n
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es,
h
av
e
s
h
o
wn
im
p
r
o
v
ed
ac
cu
r
ac
y
i
n
f
o
r
ec
asti
n
g
,
th
ey
o
f
ten
r
eq
u
ir
e
s
u
b
s
tan
tial
co
m
p
u
tatio
n
al
p
o
wer
,
wh
ich
m
a
y
n
o
t
b
e
r
ea
d
ily
av
ailab
le
in
all
in
s
titu
tio
n
al
s
ettin
g
s
.
C
h
allen
g
es in
p
er
f
o
r
m
an
ce
m
a
n
ag
em
en
t a
r
is
e
d
u
e
to
in
cr
ea
s
e
d
u
s
er
d
en
s
ity
,
h
ig
h
-
b
an
d
wid
t
h
ap
p
licatio
n
s
,
an
d
f
lu
ctu
atin
g
d
em
a
n
d
,
o
f
ten
r
es
u
ltin
g
in
n
etwo
r
k
co
n
g
esti
o
n
th
at
ca
n
d
eg
r
a
d
e
q
u
ality
o
f
s
er
v
ice
(
Qo
S)
th
r
o
u
g
h
laten
cy
,
p
ac
k
et
lo
s
s
,
an
d
r
ed
u
ce
d
th
r
o
u
g
h
p
u
t
[
8
]
,
[
1
0
]
.
Ma
n
y
in
s
titu
tio
n
s
u
s
e
r
ea
ctiv
e
n
et
wo
r
k
m
a
n
ag
em
e
n
t,
wh
ich
ad
d
r
ess
es
p
er
f
o
r
m
an
ce
is
s
u
es
o
n
ly
af
ter
th
ey
ar
is
e.
T
h
is
lim
its
th
e
ab
ilit
y
to
an
ti
cip
ate
d
em
a
n
d
a
n
d
allo
ca
te
r
eso
u
r
ce
s
ef
f
ec
tiv
ely
.
W
h
ile
d
escr
ip
tiv
e
an
aly
tics
ca
n
an
aly
ze
h
is
to
r
ical
d
ata,
it
ca
n
n
o
t
p
r
ed
ict
f
u
tu
r
e
tr
af
f
ic
ch
a
n
g
es.
Pre
d
ictiv
e
a
n
aly
tics
with
m
ac
h
in
e
lear
n
in
g
(
ML
)
p
r
o
v
id
es
a
b
etter
s
o
l
u
tio
n
.
M
o
d
els
lik
e
s
ea
s
o
n
al
au
to
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
i
n
g
a
v
er
ag
e
(
SAR
I
MA
)
id
en
tify
l
o
n
g
-
ter
m
p
atter
n
s
,
wh
ile
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
n
etw
o
r
k
s
m
an
ag
e
n
o
n
lin
ea
r
d
ep
e
n
d
en
cies.
C
o
m
b
in
in
g
t
h
ese
m
eth
o
d
s
in
a
h
y
b
r
id
ap
p
r
o
ac
h
ca
n
e
n
h
an
ce
f
o
r
ec
ast
in
g
ac
cu
r
ac
y
[
1
1
]
–
[
1
3
]
.
Pre
d
ictiv
e
an
aly
tics
in
ca
m
p
u
s
Me
tr
o
-
E
n
etwo
r
k
s
o
f
f
er
s
b
en
ef
its
d
u
e
to
u
n
iq
u
e
tr
a
f
f
i
c
p
atter
n
s
s
h
ap
ed
b
y
ac
ad
em
ic
ca
len
d
ar
s
,
ex
am
s
,
ev
en
ts
,
an
d
ir
r
eg
u
la
r
u
s
er
b
eh
av
io
r
s
.
Ho
wev
e
r
,
r
e
s
ea
r
ch
h
as
lar
g
ely
f
o
cu
s
ed
o
n
s
in
g
le
-
m
o
d
el
f
r
am
ewo
r
k
s
,
h
ig
h
lig
h
tin
g
a
g
ap
in
th
e
d
ev
elo
p
m
en
t
o
f
h
y
b
r
id
p
r
e
d
ictiv
e
f
r
am
ewo
r
k
s
f
o
r
ca
m
p
u
s
o
r
m
u
lti
-
ca
m
p
u
s
n
etwo
r
k
s
[
1
4
]
,
[
1
5
]
.
Pre
d
ictiv
e
m
o
d
elin
g
o
f
in
ter
n
et
tr
af
f
ic
in
ac
ad
em
ic
n
etwo
r
k
s
o
f
ten
r
elies
o
n
s
in
g
le
m
eth
o
d
s
lik
e
SAR
I
MA
,
wh
ich
h
an
d
les
s
ea
s
o
n
ality
an
d
tr
en
d
s
b
u
t
s
tr
u
g
g
les
with
s
u
d
d
e
n
n
o
n
lin
ea
r
ch
a
n
g
es.
L
STM
n
et
wo
r
k
s
ca
p
tu
r
e
c
o
m
p
lex
p
atter
n
s
b
u
t
m
ay
o
v
e
r
lo
o
k
r
ec
u
r
r
in
g
cy
cles
ty
p
ical
in
ac
ad
em
ic
s
ettin
g
s
,
s
u
ch
as
s
em
ester
s
ch
ed
u
les.
Few
s
tu
d
ie
s
h
av
e
d
ev
elo
p
ed
h
y
b
r
id
f
r
a
m
ewo
r
k
s
f
o
r
m
u
lti
-
ca
m
p
u
s
h
ig
h
er
e
d
u
ca
tio
n
,
le
ad
in
g
to
less
ac
cu
r
ate
tr
af
f
ic
p
r
ed
ictio
n
s
.
A
h
y
b
r
i
d
ap
p
r
o
ac
h
co
u
ld
im
p
r
o
v
e
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
b
y
ad
d
r
ess
in
g
b
o
th
s
ea
s
o
n
al
r
eg
u
lar
ities
an
d
n
o
n
lin
e
ar
b
u
r
s
ts
[
1
6
]
,
[
1
7
]
.
A
p
o
p
u
lar
ar
ea
o
f
r
esear
ch
i
n
v
o
lv
es
d
ev
el
o
p
in
g
h
y
b
r
id
ML
m
o
d
els
th
at
co
m
b
in
e
th
e
s
tr
en
g
th
s
o
f
v
a
r
io
u
s
alg
o
r
ith
m
s
[
1
8
]
–
[
2
0
]
.
Hy
b
r
id
m
o
d
els
co
m
b
in
e
tim
e
-
s
er
ies
f
o
r
ec
asti
n
g
with
ML
alg
o
r
ith
m
s
,
s
u
ch
as
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
an
d
n
e
u
r
al
n
etwo
r
k
s
,
to
ac
h
iev
e
h
ig
h
ac
cu
r
ac
y
an
d
ef
f
icien
cy
in
p
r
ed
ict
in
g
in
ter
n
et
tr
af
f
ic
.
C
o
m
b
in
in
g
a
u
to
r
e
g
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
a
v
er
ag
e
(
AR
I
MA
)
with
n
eu
r
al
n
et
wo
r
k
s
ca
n
en
h
a
n
ce
p
r
ed
ictio
n
s
d
u
r
in
g
p
ea
k
u
s
ag
e
p
er
io
d
s
.
I
n
e
d
u
ca
tio
n
,
u
s
er
b
e
h
av
io
r
h
as c
y
clica
l p
atter
n
s
,
h
i
g
h
lig
h
tin
g
th
e
n
ee
d
f
o
r
ef
f
icien
t
alg
o
r
ith
m
s
to
o
p
ti
m
ize
r
eso
u
r
ce
s
.
T
ec
h
n
iq
u
es
lik
e
f
ea
tu
r
e
s
elec
tio
n
an
d
d
im
e
n
s
io
n
ality
r
ed
u
ctio
n
ca
n
im
p
r
o
v
e
co
m
p
u
tatio
n
s
p
e
ed
with
m
in
im
al
p
er
f
o
r
m
an
ce
lo
s
s
,
wh
ich
is
ess
en
tia
l
f
o
r
a
ca
m
p
u
s
Me
tr
o
-
E
n
etwo
r
k
r
e
q
u
ir
in
g
f
ast r
esp
o
n
s
e
tim
es
[
2
1
]
–
[
2
3
]
.
I
n
ter
n
et
tr
af
f
ic
p
r
e
d
ictio
n
wit
h
a
h
y
b
r
id
ML
m
o
d
el
en
co
m
p
ass
es
a
v
ar
iety
o
f
alg
o
r
ith
m
s
,
r
an
g
in
g
f
r
o
m
s
tatis
tical
lin
ea
r
m
o
d
els
to
n
o
n
lin
ea
r
ML
m
eth
o
d
s
.
T
r
ad
itio
n
ally
,
m
an
y
r
esear
ch
er
s
h
av
e
r
elied
o
n
s
tatis
t
ical
tech
n
iq
u
es,
s
u
ch
as
tim
e
s
er
ies
an
aly
s
is
an
d
r
eg
r
ess
io
n
m
o
d
els,
to
f
o
r
ec
ast
tr
af
f
ic
f
lo
w,
s
tr
iv
in
g
f
o
r
o
p
tim
al
ac
cu
r
ac
y
i
n
th
ei
r
r
es
u
lts
[
2
4
]
.
Ho
wev
e
r
,
t
h
e
ad
v
e
n
t
o
f
ML
h
as
s
ig
n
if
ican
tly
t
r
an
s
f
o
r
m
ed
tr
af
f
ic
p
r
ed
ictio
n
ca
p
ab
ilit
ies,
as
th
ese
ad
v
an
ce
d
alg
o
r
ith
m
s
ca
n
ef
f
ec
tiv
ely
m
o
d
el
an
d
lea
r
n
f
r
o
m
co
m
p
lex
,
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
with
in
th
e
d
ata
[
2
5
]
,
[
2
6
]
.
R
esear
ch
e
r
s
in
[
2
7
]
h
av
e
d
em
o
n
s
tr
ated
t
h
e
ef
f
ec
tiv
e
n
ess
o
f
v
ar
io
u
s
ML
ap
p
r
o
ac
h
es
in
ac
h
iev
in
g
h
ig
h
ac
c
u
r
ac
y
lev
els
i
n
p
r
ed
ictin
g
tr
af
f
ic
f
lo
ws,
t
h
e
r
eb
y
en
h
a
n
cin
g
th
e
o
v
er
all
ef
f
icien
cy
o
f
tr
af
f
ic
m
an
ag
em
en
t
s
y
s
tem
s
an
d
co
n
tr
ib
u
tin
g
to
b
etter
u
r
b
an
p
l
an
n
in
g
.
T
r
ad
itio
n
al
s
tatis
t
ical
m
o
d
els,
p
ar
ticu
lar
ly
tim
e
-
s
er
ies
m
o
d
els,
ar
e
co
m
m
o
n
ly
u
s
ed
f
o
r
tr
af
f
ic
f
o
r
e
ca
s
tin
g
b
y
an
aly
zin
g
h
is
to
r
ical
d
ata
f
o
r
p
atter
n
s
.
T
o
ad
d
r
ess
th
eir
lim
itatio
n
s
,
r
esear
ch
er
s
ar
e
d
ev
elo
p
in
g
h
y
b
r
id
m
o
d
els
th
at
co
m
b
in
e
s
tatis
tical
tech
n
iq
u
es
with
ad
v
an
ce
d
ML
alg
o
r
ith
m
s
[
2
8
]
,
[
2
9
]
.
T
h
e
AR
I
MA
-
L
STM
m
o
d
el
co
m
b
in
es
AR
I
MA
'
s
tim
e
s
er
ie
s
f
o
r
ec
ast
in
g
s
tr
en
g
th
s
with
L
STM
'
s
ab
ilit
y
to
lear
n
f
r
o
m
s
eq
u
en
ce
s
an
d
m
an
ag
e
lo
n
g
-
ter
m
d
ep
e
n
d
en
cies,
e
n
h
an
cin
g
th
e
ca
p
tu
r
e
o
f
b
o
t
h
lin
ea
r
an
d
n
o
n
-
lin
ea
r
p
atter
n
s
in
tr
a
f
f
ic
d
ata.
Similar
ly
,
th
e
AR
I
MA
-
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
etwo
r
k
(
C
NN
)
h
y
b
r
id
in
teg
r
ates
AR
I
MA
's
lin
ea
r
tr
en
d
an
d
s
ea
s
o
n
al
an
aly
s
is
with
C
NN
's
f
ea
tu
r
e
ex
tr
ac
tio
n
,
r
esu
ltin
g
in
im
p
r
o
v
ed
ac
c
u
r
ac
y
an
d
in
s
ig
h
ts
co
m
p
ar
ed
to
tr
ad
itio
n
al
m
o
d
els
[
3
0
]
.
T
im
e
-
s
er
ies
m
o
d
els
ar
e
s
tatis
t
ical
tech
n
iq
u
es
th
at
an
aly
ze
d
ata
p
o
in
ts
co
llected
o
r
r
ec
o
r
d
ed
at
s
p
ec
if
ic
tim
e
in
ter
v
als.
Nu
m
er
o
u
s
s
tu
d
ies
h
av
e
ap
p
lied
AR
I
MA
m
o
d
els
to
p
r
ed
ict
in
ter
n
et
tr
af
f
ic.
Fo
r
in
s
tan
ce
,
r
esear
ch
h
as
s
h
o
wn
th
at
AR
I
MA
ca
n
ef
f
ec
tiv
ely
f
o
r
ec
ast
tr
af
f
ic
in
b
o
th
lo
ca
l
ar
ea
n
etwo
r
k
s
(
L
ANs)
an
d
wid
e
ar
ea
n
etwo
r
k
s
(
W
ANs).
I
n
s
t
u
d
ies
co
n
d
u
cted
b
y
Sah
a
et
a
l.
[
3
1
]
,
[
3
2
]
,
AR
I
MA
was
u
s
ed
to
p
r
ed
ict
tr
af
f
ic
p
atter
n
s
b
ased
o
n
r
ea
l
tr
af
f
ic
d
atasets
f
r
o
m
v
a
r
io
u
s
h
ig
h
-
s
p
ee
d
tr
af
f
ic
d
ata.
Similar
ly
,
an
o
th
e
r
s
tu
d
y
b
y
W
an
g
et
a
l
.
[
3
3
]
u
s
ed
an
en
h
an
ce
d
SAR
I
MA
m
o
d
el
to
an
a
ly
ze
tr
af
f
ic
in
ce
llu
lar
zo
n
es
with
in
a
r
esid
en
tial
co
m
m
u
n
ity
.
SAR
I
MA
ad
d
s
s
ea
s
o
n
al
co
m
p
o
n
en
ts
to
th
e
tr
a
d
itio
n
al
AR
I
MA
to
h
an
d
le
p
er
i
o
d
ic
f
lu
ctu
atio
n
s
in
tr
af
f
ic,
m
ak
i
n
g
it
p
ar
ticu
lar
ly
u
s
ef
u
l
f
o
r
p
r
e
d
ictin
g
in
ter
n
et
t
r
af
f
ic
in
e
n
v
ir
o
n
m
en
ts
with
cl
ea
r
s
ea
s
o
n
al
tr
en
d
s
[
3
4
]
.
SAR
I
MA
en
h
an
ce
s
f
o
r
ec
asts
b
y
in
co
r
p
o
r
atin
g
s
ea
s
o
n
al
f
ac
to
r
s
,
o
f
f
er
in
g
g
r
ea
te
r
ac
cu
r
ac
y
d
u
r
in
g
v
ar
iatio
n
s
.
Ho
wev
e
r
,
it
c
o
m
p
licates
p
ar
am
eter
esti
m
atio
n
with
ad
d
ed
s
ea
s
o
n
al
p
a
r
am
et
er
s
an
d
s
till
f
ac
es
lim
itatio
n
s
,
s
u
ch
as
r
elian
ce
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
,
m
ak
i
n
g
it
ch
allen
g
in
g
to
ad
ap
t
to
s
u
d
d
en
ch
an
g
es
in
tr
af
f
ic
p
atter
n
s
[
3
5
]
,
[
3
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
F
o
r
ec
a
s
tin
g
in
tern
et
tr
a
ffic p
a
tter
n
s
fo
r
th
e
ca
mp
u
s
Metr
o
-
E
n
etw
o
r
k
u
s
in
g
a
h
y
b
r
id
…
(
N
o
r
a
kma
r
A
r
b
a
in
)
1435
R
esear
ch
er
s
in
[
3
7
]
in
d
icate
th
at
L
STM
s
o
f
ten
o
u
tp
er
f
o
r
m
tr
ad
itio
n
al
m
o
d
els,
s
u
ch
as
A
R
I
MA
an
d
ex
p
o
n
e
n
tial
s
m
o
o
th
in
g
,
in
ter
m
s
o
f
p
r
ed
ictiv
e
ac
cu
r
ac
y
.
H
y
b
r
id
m
o
d
els
o
f
f
er
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
b
u
t
r
eq
u
ir
e
ex
te
n
s
iv
e
p
r
ep
ar
atio
n
an
d
tr
ain
in
g
tim
e.
M
o
s
t
r
esear
ch
f
o
cu
s
es
o
n
in
ter
n
et
tr
af
f
ic
p
r
ed
ictio
n
in
wir
ed
L
AN
an
d
m
o
b
ile
n
etwo
r
k
s
,
wi
th
a
g
ap
i
n
s
tu
d
ies o
n
ca
m
p
u
s
Me
tr
o
-
E
n
etwo
r
k
tr
af
f
ic
as sh
o
wn
in
T
ab
le
1
.
T
ab
le
1
.
R
esear
ch
g
a
p
s
in
h
y
b
r
id
ML
m
o
d
els f
o
r
in
ter
n
et
tr
a
f
f
ic
p
r
ed
ictio
n
R
e
f
e
r
e
n
c
e
s
(
a
u
t
h
o
r
s,
y
e
a
r
)
H
y
b
r
i
d
m
o
d
e
l
T
r
a
f
f
i
c
t
y
p
e
/
c
o
n
t
e
x
t
A
d
v
a
n
t
a
g
e
s
Li
mi
t
a
t
i
o
n
s/
r
e
s
e
a
r
c
h
g
a
p
s
S
a
h
a
a
n
d
H
a
q
u
e
[
1
8
]
(
2
0
2
3
)
W
a
v
e
l
e
t
+
e
n
sem
b
l
e
ML
I
n
t
e
r
n
e
t
t
r
a
f
f
i
c
u
n
d
e
r
d
i
s
t
r
i
b
u
t
i
o
n
s
h
i
f
t
s
D
e
c
o
m
p
o
ses
si
g
n
a
l
;
h
y
b
r
i
d
mo
d
e
l
i
m
p
r
o
v
e
s
o
u
t
-
of
-
d
i
s
t
r
i
b
u
t
i
o
n
g
e
n
e
r
a
l
i
z
a
t
i
o
n
o
v
e
r
st
a
n
d
a
l
o
n
e
m
o
d
e
l
s
S
t
i
l
l
p
e
r
f
o
r
ma
n
c
e
d
r
o
p
u
n
d
e
r
sh
i
f
t
;
l
i
m
i
t
e
d
g
e
n
e
r
a
l
i
z
a
t
i
o
n
a
c
r
o
ss
d
i
f
f
e
r
e
n
t
t
y
p
e
s
o
f
d
i
s
t
r
i
b
u
t
i
o
n
c
h
a
n
g
e
s.
S
h
i
e
t
a
l
.
[
3
8
]
(
2
0
2
1
)
NN
-
A
R
I
M
A
(
M
LP/NN
f
o
l
l
o
w
e
d
b
y
A
R
I
M
A
)
N
e
t
w
o
r
k
-
w
i
d
e
t
r
a
f
f
i
c
(
f
l
o
w
,
sp
e
e
d
,
o
c
c
u
p
a
n
c
y
)
C
a
p
t
u
r
e
s
n
o
n
l
i
n
e
a
r
p
a
t
t
e
r
n
s
v
i
a
N
N
;
mo
d
e
l
s
r
e
s
i
d
u
a
l
s
w
i
t
h
A
R
I
M
A
t
o
r
e
f
i
n
e
a
c
c
u
r
a
c
y
R
e
si
d
u
a
l
s
m
a
y
st
i
l
l
c
o
n
t
a
i
n
st
r
u
c
t
u
r
e
;
c
h
o
i
c
e
o
f
N
N
a
n
d
A
R
I
M
A
t
u
n
i
n
g
r
e
ma
i
n
s a
d
h
o
c
.
S
a
h
a
e
t
a
l
.
[
3
9
]
(
2
0
2
4
)
C
o
n
v
LST
M
T
r
a
n
s
N
e
t
(
C
N
N
+
LST
M
+
T
r
a
n
sf
o
r
m
e
r
)
H
i
g
h
-
sp
e
e
d
p
o
r
t
i
n
t
e
r
n
e
t
t
e
l
e
met
r
y
(
t
i
me
-
s
e
r
i
e
s)
C
a
p
t
u
r
e
s
s
p
a
t
i
a
l
a
n
d
t
e
m
p
o
r
a
l
d
e
p
e
n
d
e
n
c
i
e
s;
~
1
0
%
b
e
t
t
e
r
a
c
c
u
r
a
c
y
v
s.
R
N
N
/
LST
M
/
G
R
U
b
a
se
l
i
n
e
N
o
t
t
e
st
e
d
o
n
m
u
l
t
i
v
a
r
i
a
t
e
sce
n
a
r
i
o
s
o
r
u
n
d
e
r
o
n
l
i
n
e
/
a
d
v
e
r
sar
i
a
l
se
t
t
i
n
g
s.
S
h
a
o
e
t
a
l
.
[
4
0
]
(
2
0
2
2
)
C
EE
M
D
A
N
+
P
S
O
-
LSTM
(
d
e
c
o
m
p
o
s
i
t
i
o
n
+
P
S
O
o
p
t
i
mi
z
e
d
LSTM
)
N
e
t
w
o
r
k
t
r
a
f
f
i
c
t
i
me
seri
e
s
D
e
c
o
m
p
o
ses
a
n
d
d
e
n
o
i
ses
si
g
n
a
l
s;
P
S
O
o
p
t
i
mi
z
e
s
mo
d
e
l
t
r
a
i
n
i
n
g
,
y
i
e
l
d
i
n
g
i
mp
r
o
v
e
d
p
r
e
d
i
c
t
i
o
n
C
o
m
p
l
e
x
s
e
t
u
p
;
P
S
O
ma
y
o
v
e
r
f
i
t
;
l
a
c
k
s
v
a
l
i
d
a
t
i
o
n
a
c
r
o
ss
v
a
r
y
i
n
g
n
e
t
w
o
r
k
e
n
v
i
r
o
n
me
n
t
s.
S
u
e
t
a
l
.
[
4
1
]
(
2
0
2
4
)
Li
g
h
t
w
e
i
g
h
t
h
y
b
r
i
d
a
t
t
e
n
t
i
o
n
+
C
N
N
5
G
n
e
t
w
o
r
k
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
Ef
f
i
c
i
e
n
t
f
e
a
t
u
r
e
l
e
a
r
n
i
n
g
v
i
a
a
t
t
e
n
t
i
o
n
;
c
o
mp
u
t
a
t
i
o
n
a
l
l
y
l
i
g
h
t
w
e
i
g
h
t
v
i
a
d
e
p
t
h
w
i
se
sep
a
r
a
b
l
e
c
o
n
v
s.
G
e
n
e
r
a
l
i
z
a
t
i
o
n
t
o
o
t
h
e
r
n
e
t
w
o
r
k
t
y
p
e
s
o
r
sc
a
l
e
s
n
o
t
v
a
l
i
d
a
t
e
d
;
c
o
m
p
l
e
x
i
t
y
st
i
l
l
e
x
i
s
t
s
,
a
l
b
e
i
t
r
e
d
u
c
e
d
.
N
o
r
a
k
mar
(
2
0
2
5
)
S
A
R
I
M
A
+
LS
TM
C
a
m
p
u
s
M
e
t
r
o
-
E
n
e
t
w
o
r
k
D
e
scri
p
t
i
v
e
a
n
a
l
y
si
s
a
n
d
st
a
t
i
st
i
c
a
l
mo
d
e
l
s
w
i
t
h
h
y
b
r
i
d
p
r
e
d
i
c
t
i
v
e
a
l
g
o
r
i
t
h
ms
f
o
r
c
a
m
p
u
s
M
e
t
r
o
-
E
n
e
t
w
o
r
k
s.
-
2.
M
E
T
H
O
D
2
.
1
.
I
nte
rnet
t
ra
f
f
ic
pa
t
t
er
n
a
na
ly
s
is
f
o
r
ca
m
pu
s
M
et
ro
-
E
net
wo
rk
T
h
is
s
tu
d
y
p
r
ep
r
o
ce
s
s
es
Me
tr
o
-
E
in
te
r
n
et
tr
a
f
f
ic
d
ata
to
im
p
r
o
v
e
f
o
r
ec
asti
n
g
ac
c
u
r
ac
y
an
d
r
eso
u
r
ce
allo
ca
tio
n
.
B
y
in
teg
r
atin
g
h
y
b
r
id
ML
m
o
d
els,
it
en
h
a
n
ce
s
n
etwo
r
k
r
esp
o
n
s
iv
e
n
ess
an
d
ef
f
ec
tiv
e
n
ess
.
As
r
esear
ch
p
r
o
g
r
ess
es,
d
ev
el
o
p
in
g
ef
f
icien
t
m
o
d
els
will
b
e
ess
en
tial
f
o
r
m
an
ag
in
g
ca
m
p
u
s
Me
tr
o
-
E
n
etwo
r
k
tr
af
f
ic
an
d
en
s
u
r
in
g
h
ig
h
-
q
u
al
ity
u
s
er
s
er
v
ice.
T
h
e
an
aly
tical
p
r
o
ce
s
s
in
Fig
u
r
e
1
s
tar
t
s
wi
th
co
llectin
g
tr
af
f
ic
f
lo
w
d
ata,
f
o
llo
wed
b
y
p
r
e
p
r
o
ce
s
s
in
g
f
o
r
co
n
s
is
ten
cy
,
an
d
d
escr
ip
tiv
e
s
tatis
tical
an
aly
s
i
s
to
r
ev
ea
l
in
s
ig
h
ts
lik
e
co
r
r
elatio
n
a
n
d
s
ea
s
o
n
ality
.
Pre
d
ictiv
e
m
o
d
elin
g
with
S
AR
I
MA
an
d
L
STM
tec
h
n
iq
u
es
f
o
r
ec
asts
tr
af
f
ic
d
em
an
d
,
wh
ile
d
is
tr
ib
u
tio
n
a
n
aly
s
is
ass
es
s
es
u
n
d
er
ly
in
g
p
atter
n
s
.
T
h
e
f
o
r
ec
asti
n
g
r
es
u
lts
h
elp
o
p
tim
ize
b
an
d
wid
th
a
n
d
e
n
h
an
ce
Q
o
S o
n
th
e
ca
m
p
u
s
n
etwo
r
k
.
2
.
2
.
I
nte
rnet
t
ra
f
f
ic
a
t
ca
m
pu
s
M
et
ro
-
E
net
wo
rk
E
th
er
n
et
tech
n
o
lo
g
y
b
eg
an
with
L
ANs
b
u
t
h
as
ev
o
lv
e
d
in
to
a
t
o
p
c
h
o
ice
f
o
r
m
etr
o
p
o
litan
ar
ea
n
etwo
r
k
s
(
MA
Ns).
I
t
o
f
f
er
s
g
o
o
d
p
r
ices,
ea
s
y
m
an
a
g
em
en
t
,
v
ar
io
u
s
s
er
v
ices,
a
n
d
lo
w
c
o
s
ts
.
I
n
ca
m
p
u
s
es,
m
etr
o
eth
er
n
et
n
etwo
r
k
s
(
ME
Ns)
co
n
n
ec
t
d
if
f
e
r
en
t
en
te
r
p
r
i
s
e
L
ANs
ac
r
o
s
s
u
r
b
an
ar
ea
s
an
d
wo
r
k
well
with
W
ANs
f
r
o
m
telec
o
m
p
r
o
v
id
er
s
.
ME
Ns
u
s
e
a
s
tr
o
n
g
f
ib
er
-
o
p
tic
in
f
r
astru
ctu
r
e
an
d
E
th
er
n
et
f
o
r
co
m
m
u
n
icatio
n
,
allo
win
g
f
o
r
f
ast
d
ata
tr
a
n
s
f
er
an
d
r
eliab
l
e
p
er
f
o
r
m
an
ce
f
o
r
h
i
g
h
-
b
a
n
d
wid
th
ap
p
licatio
n
s
.
Un
d
er
s
tan
d
in
g
t
r
af
f
ic
p
atter
n
s
h
elp
s
in
s
titu
tio
n
s
u
s
e
r
eso
u
r
ce
s
wis
ely
,
m
an
ag
e
co
n
g
e
s
tio
n
,
an
d
ad
d
r
ess
m
ain
ten
an
ce
n
ee
d
s
,
en
s
u
r
in
g
ef
f
icien
t
n
etwo
r
k
o
p
er
atio
n
s
f
o
r
th
e
f
u
tu
r
e.
As
d
e
p
icted
in
F
ig
u
r
e
2
,
th
e
ca
m
p
u
s
Me
tr
o
-
E
n
etwo
r
k
p
r
o
v
is
io
n
s
b
an
d
wid
th
at
an
im
p
r
ess
iv
e
r
ate
o
f
1
0
Gb
p
s
f
o
r
wir
ed
c
o
n
n
ec
tio
n
s
,
wh
ile
wir
eless
co
n
n
ec
tio
n
s
th
r
o
u
g
h
Un
if
i
ac
h
iev
ed
2
Gb
p
s
.
Ad
d
itio
n
ally
,
th
e
ev
alu
ated
tr
af
f
ic
f
lo
w
th
r
o
u
g
h
p
u
t
r
ea
ch
es
7
0
0
M
b
p
s
,
co
m
p
r
is
in
g
5
0
0
Mb
p
s
o
f
in
b
o
u
n
d
tr
a
f
f
ic
an
d
2
0
0
Mb
p
s
o
f
o
u
tb
o
u
n
d
tr
af
f
ic,
th
er
eb
y
p
r
o
v
id
i
n
g
a
clea
r
r
ep
r
esen
tatio
n
o
f
th
e
n
etwo
r
k
'
s
o
p
er
atio
n
al
ca
p
ab
ilit
ies an
d
p
er
f
o
r
m
an
ce
m
etr
ics.
2
.
3
.
Da
t
a
c
o
llect
io
n a
nd
s
co
pe
I
n
ter
n
et
tr
af
f
ic
f
lo
w
h
as
b
ee
n
m
o
n
ito
r
e
d
ac
r
o
s
s
v
ar
io
u
s
c
am
p
u
s
Me
tr
o
-
E
n
etwo
r
k
en
v
ir
o
n
m
en
ts
,
with
in
b
o
u
n
d
a
n
d
o
u
tb
o
u
n
d
th
r
o
u
g
h
p
u
t
d
ata
co
llecte
d
in
Mb
p
s
.
T
h
e
d
ataset
u
n
d
er
wen
t
th
o
r
o
u
g
h
p
r
ep
r
o
ce
s
s
in
g
to
e
n
h
an
ce
q
u
al
ity
,
in
clu
d
i
n
g
clea
n
i
n
g
m
is
s
in
g
v
alu
es,
h
an
d
li
n
g
o
u
tlier
s
,
an
d
n
o
r
m
alizin
g
d
ata
f
o
r
co
n
s
is
ten
cy
.
T
ab
le
2
s
u
m
m
ar
izes v
ar
iab
le
p
ar
am
eter
s
f
o
r
ea
ch
lo
ca
tio
n
,
o
f
f
er
i
n
g
a
co
m
p
r
eh
en
s
iv
e
an
al
y
s
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
4
,
Dec
em
b
er
20
25
:
1
4
3
3
-
1
4
4
3
1436
o
f
in
ter
n
et
tr
af
f
ic
c
h
ar
ac
ter
is
tics
.
T
h
is
s
tu
d
y
an
aly
ze
s
d
at
a
f
r
o
m
eig
h
t
ca
m
p
u
s
es
(
A
t
o
H)
.
I
t
i
n
v
o
lv
ed
p
r
ep
r
o
ce
s
s
in
g
to
clea
n
m
is
s
in
g
v
alu
es
an
d
n
o
r
m
alize
d
ata.
Key
m
etr
ics
as
s
es
s
ed
n
etwo
r
k
tr
af
f
ic,
in
clu
d
in
g
co
r
r
elatio
n
o
f
f
l
o
ws,
m
ea
n
tr
af
f
ic
v
o
lu
m
e
,
an
d
m
ea
s
u
r
es
o
f
ce
n
tr
al
ten
d
en
cy
an
d
d
i
s
p
er
s
io
n
,
r
ev
ea
lin
g
v
ar
iab
ilit
y
ac
r
o
s
s
lo
ca
tio
n
s
.
Fig
u
r
e
1
.
An
al
y
tical
p
r
o
ce
s
s
f
o
r
in
ter
n
et
tr
a
f
f
ic
f
o
r
ec
asti
n
g
i
n
ca
m
p
u
s
Me
tr
o
-
E
Netwo
r
k
Fig
u
r
e
2
.
I
ll
u
s
tr
atio
n
o
f
Me
tr
o
-
E
n
etwo
r
k
ca
m
p
u
s
T
ab
le
2
.
Su
m
m
a
r
y
o
f
v
a
r
iab
le
p
ar
am
eter
P
a
r
a
me
t
e
r
S
y
mb
o
l
V
a
l
u
e
s
Ti
me
-
b
a
s
e
d
t
r
a
f
f
i
c
X
0
:
0
0
<
X
<
1
1
.
5
9
pm
N
u
mb
e
r
o
f
d
a
y
s
D
90
I
n
t
e
r
-
a
r
r
i
v
a
l
t
i
m
e
Ta
5
m
i
n
u
t
e
s
Ti
me
f
r
a
me
mi
n
i
m
u
m
Tmi
n
0
:
0
0
am
Ti
me
f
r
a
me
ma
x
i
m
u
m
Tmax
1
1
.
5
0
pm
n
u
m
b
e
r
o
f
d
a
t
a
mi
n
i
mu
m
α
2
.
3
3
a
n
d
1
.
9
9
0
9
n
u
m
b
e
r
o
f
d
a
t
a
ma
x
i
mu
m
β
1
0
5
8
.
5
2
3
a
n
d
3
7
9
.
8
9
5
4
P
o
l
i
c
i
n
g
i
n
b
o
u
n
d
t
h
r
e
s
h
o
l
d
c
a
m
p
u
s
A
Th
t
A
5
0
0
M
b
p
s
P
o
l
i
c
i
n
g
o
u
t
b
o
u
n
d
t
h
r
e
s
h
o
l
d
c
a
mp
u
s
B
-
H
Th
t
X
2
0
0
M
b
p
s
A
c
c
e
ss
r
a
t
e
c
a
m
p
u
s
A
Ca
10
G
b
p
s
A
c
c
e
ss
r
a
t
e
c
a
m
p
u
s
B
-
H
Cx
2
G
b
p
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
F
o
r
ec
a
s
tin
g
in
tern
et
tr
a
ffic p
a
tter
n
s
fo
r
th
e
ca
mp
u
s
Metr
o
-
E
n
etw
o
r
k
u
s
in
g
a
h
y
b
r
id
…
(
N
o
r
a
kma
r
A
r
b
a
in
)
1437
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
I
nb
o
un
d a
nd
o
utbo
un
d
da
t
a
co
rr
ela
t
io
n a
na
ly
s
is
Fig
u
r
e
3
s
h
o
ws
th
at
th
e
v
ar
iab
les
f
o
r
in
b
o
u
n
d
an
d
o
u
tb
o
u
n
d
d
ata
ar
e
v
is
u
alize
d
u
s
in
g
co
lo
r
s
h
ad
es
th
at
in
d
icate
th
e
s
tr
en
g
th
an
d
d
ir
ec
tio
n
o
f
th
eir
c
o
r
r
elatio
n
s
.
I
n
an
aly
zin
g
in
b
o
u
n
d
d
ata,
s
ev
er
al
s
u
m
m
ar
y
s
tatis
t
ics
r
ev
ea
l
r
elatio
n
s
h
ip
s
b
etwe
en
v
ar
iab
les
ac
r
o
s
s
lo
ca
tio
n
s
A
th
r
o
u
g
h
H.
T
h
e
av
er
a
g
e
co
r
r
elatio
n
v
alu
es
ar
e
as
f
o
llo
ws:
A
(
0
.
4
9
6
7
)
,
B
(
0
.
2
4
4
2
)
,
C
(
0
.
2
4
0
8
)
,
D
(
0
.
3
9
7
1
)
,
E
(
0
.
4
9
5
8
)
,
F
(
0
.
4
5
4
7
)
,
G
(
0
.
2
3
1
4
)
,
an
d
H
(
0
.
5
2
0
4
)
,
with
lo
ca
tio
n
H
s
h
o
win
g
th
e
h
ig
h
est
m
ea
n
co
r
r
elatio
n
.
T
h
is
s
u
g
g
ests
H
s
ig
n
i
f
ican
tly
in
f
lu
en
ce
s
o
th
er
v
ar
ia
b
les.
C
o
n
v
er
s
ely
,
lo
ca
tio
n
F h
as th
e
h
ig
h
est s
tan
d
a
r
d
d
ev
iatio
n
at
0
.
4
0
7
6
,
in
d
icati
n
g
m
o
r
e
v
o
latilit
y
in
its
co
r
r
elatio
n
s
.
L
o
ca
tio
n
s
G
an
d
C
d
is
p
lay
th
e
lo
we
s
t
co
r
r
elatio
n
at
0
.
0
2
4
0
,
im
p
ly
in
g
a
n
e
g
lig
ib
le
r
elatio
n
s
h
ip
b
etwe
en
th
em
.
Fi
g
u
r
e
4
p
r
esen
ts
th
e
an
aly
s
is
o
f
o
u
tb
o
u
n
d
d
ata
r
ev
ea
ls
an
u
n
d
er
s
tan
d
in
g
o
f
th
e
r
elatio
n
s
h
ip
s
am
o
n
g
lo
ca
tio
n
s
,
with
m
ea
n
co
r
r
elatio
n
s
r
an
g
in
g
f
r
o
m
0
.
1
5
3
7
to
0
.
4
7
5
7
.
L
o
ca
tio
n
A
e
x
h
ib
its
th
e
h
ig
h
est
m
ea
n
co
r
r
elatio
n
at
0
.
4
7
5
7
,
wh
ile
lo
ca
tio
n
C
h
as
th
e
lo
west
at
0
.
1
5
3
7
,
in
d
icatin
g
m
o
d
e
r
ate
in
ter
co
n
n
ec
ted
n
ess
,
th
o
u
g
h
s
lig
h
tly
less
th
an
in
b
o
u
n
d
d
ata.
L
o
ca
tio
n
F
s
h
o
ws
th
e
h
ig
h
est
s
tan
d
ar
d
d
ev
iatio
n
o
f
0
.
4
3
9
5
,
h
ig
h
lig
h
tin
g
v
ar
y
in
g
co
r
r
elatio
n
s
ac
r
o
s
s
lo
ca
tio
n
s
.
W
ea
k
n
eg
ativ
e
co
r
r
elatio
n
s
e
x
is
t
b
etwe
en
p
air
s
B
an
d
E
,
a
n
d
C
an
d
F,
b
u
t
th
ey
d
o
n
o
t
s
ig
n
if
ican
tly
im
p
ac
t
o
v
er
all
tr
en
d
s
.
Un
d
er
s
tan
d
in
g
in
ter
n
et
tr
af
f
ic
p
atter
n
s
is
cr
u
cial
f
o
r
o
p
tim
izin
g
n
et
wo
r
k
p
er
f
o
r
m
a
n
ce
.
L
o
ca
tio
n
s
A,
E
,
F,
an
d
H
ar
e
m
ajo
r
h
u
b
s
with
s
tr
o
n
g
c
o
n
n
e
ctiv
ity
,
wh
ile
G,
C
,
a
n
d
B
s
h
o
w
wea
k
c
o
r
r
elatio
n
s
,
in
d
icatin
g
th
ey
f
u
n
ctio
n
as
is
o
lated
n
o
d
es
o
r
b
ac
k
u
p
s
er
v
er
s
.
I
n
b
o
u
n
d
tr
a
f
f
ic
co
r
r
elate
s
s
tr
o
n
g
ly
am
o
n
g
A,
E
,
F,
an
d
H,
r
ef
lectin
g
h
ig
h
u
s
er
en
g
ag
e
m
en
t,
w
h
ile
G
s
h
o
ws
wea
k
in
b
o
u
n
d
tr
a
f
f
ic.
O
u
tb
o
u
n
d
t
r
af
f
ic
is
m
o
r
e
co
m
p
lex
,
f
ea
tu
r
in
g
lo
wer
an
d
n
eg
ativ
e
co
r
r
elatio
n
s
,
wh
ich
m
ay
in
d
icate
is
s
u
es lik
e
tr
af
f
ic
co
n
g
esti
o
n
.
T
ab
le
3
s
u
m
m
a
r
izes
th
e
m
ea
n
s
,
co
r
r
elatio
n
,
an
d
s
tan
d
ar
d
d
ev
iatio
n
o
f
in
b
o
u
n
d
an
d
o
u
t
b
o
u
n
d
d
ata
f
o
r
all
ca
m
p
u
s
es
in
th
e
Me
tr
o
-
E
n
etwo
r
k
.
T
h
e
a
n
aly
s
is
r
ev
ea
ls
s
tr
o
n
g
co
r
r
elatio
n
s
in
lo
ca
ti
o
n
s
A,
E
,
F,
an
d
H,
with
H
s
er
v
in
g
as
a
co
r
e
h
u
b
.
I
n
co
n
t
r
ast,
B
,
C
,
an
d
G
s
h
o
w
wea
k
c
o
r
r
elatio
n
s
,
in
d
icat
in
g
is
o
lated
r
o
les.
L
o
ca
tio
n
F
h
as
th
e
h
ig
h
est
s
tan
d
ar
d
d
ev
iatio
n
(
0
.
4
0
7
6
)
,
h
ig
h
lig
h
tin
g
u
n
p
r
e
d
ictab
ilit
y
in
its
tr
a
f
f
ic
.
Neg
ativ
e
co
r
r
elatio
n
p
air
s
,
lik
e
B
an
d
E
,
an
d
C
an
d
F,
s
u
g
g
est
p
o
ten
tial
co
n
g
esti
o
n
is
s
u
es
,
in
d
icatin
g
a
n
ee
d
f
o
r
s
tr
ateg
ic
tr
a
f
f
ic
m
a
n
ag
em
en
t.
Ov
er
all,
t
h
ese
f
in
d
i
n
g
s
il
lu
s
tr
ate
th
e
co
m
p
lex
ity
o
f
tr
a
f
f
ic
d
y
n
am
ics
an
d
v
ar
y
in
g
in
ter
d
e
p
en
d
e
n
cies a
m
o
n
g
lo
ca
tio
n
s
.
Fig
u
r
e
3
.
C
o
r
r
elatio
n
an
aly
s
is
o
f
in
b
o
u
n
d
d
ata
Fig
u
r
e
4
.
C
o
r
r
elatio
n
an
aly
s
is
o
f
o
u
t
b
o
u
n
d
d
ata
T
ab
le
3
.
C
o
r
r
elatio
n
an
aly
s
is
o
f
in
b
o
u
n
d
an
d
o
u
tb
o
u
n
d
d
ata
tr
af
f
ic
Lo
c
a
t
i
o
n
M
e
a
n
c
o
r
r
e
l
a
t
i
o
n
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
K
e
y
o
b
ser
v
a
t
i
o
n
s
A
0
.
4
9
6
7
0
.
3
0
2
1
S
t
r
o
n
g
c
o
r
r
e
l
a
t
i
o
n
,
h
i
g
h
t
r
a
f
f
i
c
a
c
t
i
v
i
t
y
.
B
0
.
2
4
4
2
0
.
1
9
8
4
W
e
a
k
c
o
r
r
e
l
a
t
i
o
n
,
i
n
d
e
p
e
n
d
e
n
t
f
l
u
c
t
u
a
t
i
o
n
s
.
C
0
.
2
4
0
8
0
.
1
9
5
0
W
e
a
k
c
o
r
r
e
l
a
t
i
o
n
,
c
o
n
t
a
i
n
s
o
u
t
l
i
e
r
s
.
D
0
.
3
9
7
1
0
.
2
7
8
3
M
o
d
e
r
a
t
e
c
o
r
r
e
l
a
t
i
o
n
,
so
me
i
r
r
e
g
u
l
a
r
sp
i
k
e
s
.
E
0
.
4
9
5
8
0
.
3
0
1
5
S
t
r
o
n
g
c
o
r
r
e
l
a
t
i
o
n
,
s
t
a
b
l
e
t
r
a
f
f
i
c
b
e
h
a
v
i
o
r
.
F
0
.
4
5
4
7
0
.
4
0
7
6
H
i
g
h
v
a
r
i
a
b
i
l
i
t
y
,
f
r
e
q
u
e
n
t
f
l
u
c
t
u
a
t
i
o
n
s
.
G
0
.
2
3
1
4
0
.
0
2
4
0
V
e
r
y
w
e
a
k
c
o
r
r
e
l
a
t
i
o
n
,
s
p
o
r
a
d
i
c
t
r
a
f
f
i
c
u
s
a
g
e
.
H
0
.
5
2
0
4
0
.
3
1
2
7
S
t
r
o
n
g
e
st
c
o
r
r
e
l
a
t
i
o
n
a
c
t
s
a
s
a
c
o
r
e
n
e
t
w
o
r
k
h
u
b
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
4
,
Dec
em
b
er
20
25
:
1
4
3
3
-
1
4
4
3
1438
3
.
2
.
Descript
iv
e
a
na
ly
s
is
o
f
i
nb
o
un
d a
n
d o
utbo
un
d da
t
a
f
o
r
a
ll lo
ca
t
i
o
ns
o
n sp
ec
if
ied
da
t
es
Fig
u
r
es
5
to
9
a
n
aly
ze
in
b
o
u
n
d
an
d
o
u
tb
o
u
n
d
I
n
ter
n
et
t
r
af
f
ic
o
v
e
r
s
p
ec
if
ic
d
ates,
h
i
g
h
lig
h
tin
g
f
lu
ctu
atio
n
s
in
v
o
l
u
m
e
a
n
d
im
p
o
r
tan
t
tr
en
d
s
.
T
h
ese
v
is
u
aliza
tio
n
s
clar
if
y
tr
af
f
ic
b
eh
a
v
io
r
,
a
id
in
g
s
tak
eh
o
ld
er
s
in
m
ak
in
g
in
f
o
r
m
ed
d
ec
is
io
n
s
ab
o
u
t
r
eso
u
r
ce
allo
ca
tio
n
an
d
n
etwo
r
k
m
an
a
g
em
en
t.
Fig
u
r
e
1
0
s
h
o
ws
s
tab
le
in
ter
n
et
tr
af
f
ic
with
m
in
o
r
an
o
m
alies,
in
d
icatin
g
a
co
n
s
is
ten
t
f
lo
w.
T
h
is
an
aly
s
is
is
cr
u
cial
f
o
r
ef
f
ec
tiv
e
t
r
af
f
ic
m
an
ag
em
en
t.
I
n
co
n
tr
ast,
Fig
u
r
es
1
1
an
d
1
2
r
ev
ea
l
s
k
ewe
d
tr
af
f
ic
d
is
tr
ib
u
tio
n
,
h
i
g
h
lig
h
tin
g
co
n
g
esti
o
n
at
two
lo
ca
tio
n
s
,
lead
in
g
to
p
o
ten
tial
d
elay
s
d
u
r
in
g
p
ea
k
tim
es.
Fig
u
r
e
5
.
C
am
p
u
s
A
in
/
o
u
t
d
at
a
tr
af
f
ic
Fig
u
r
e
6
.
C
am
p
u
s
B
in
/o
u
t
d
at
a
tr
af
f
ic
Fig
u
r
e
7
.
C
am
p
u
s
C
in
/o
u
t
d
at
a
tr
af
f
ic
Fig
u
r
e
8
.
C
am
p
u
s
D
in
/
o
u
t
d
at
a
tr
af
f
ic
Fig
u
r
e
9
.
C
am
p
u
s
F
in
/o
u
t
d
at
a
tr
af
f
i
c
Fig
u
r
e
10
.
C
am
p
u
s
E
in
/o
u
t
d
a
ta
tr
af
f
ic
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
F
o
r
ec
a
s
tin
g
in
tern
et
tr
a
ffic p
a
tter
n
s
fo
r
th
e
ca
mp
u
s
Metr
o
-
E
n
etw
o
r
k
u
s
in
g
a
h
y
b
r
id
…
(
N
o
r
a
kma
r
A
r
b
a
in
)
1439
Fig
u
r
e
11
.
C
am
p
u
s
G
in
/o
u
t
d
ata
tr
af
f
ic
Fig
u
r
e
12
.
C
am
p
u
s
H
in
/o
u
t
d
ata
tr
af
f
ic
Fig
u
r
es
1
3
to
1
8
r
ev
ea
l
a
s
tr
o
n
g
c
o
r
r
elatio
n
b
etwe
en
in
b
o
u
n
d
a
n
d
o
u
tb
o
u
n
d
in
ter
n
et
tr
a
f
f
ic
with
in
th
e
an
aly
ze
d
d
ate
r
an
g
e.
T
h
is
r
elatio
n
s
h
ip
is
v
ital
f
o
r
u
n
d
e
r
s
tan
d
in
g
tr
a
f
f
ic
p
atter
n
s
an
d
en
h
an
cin
g
n
etwo
r
k
p
er
f
o
r
m
an
ce
.
C
am
p
u
s
A
e
x
h
i
b
its
a
h
ig
h
co
r
r
elatio
n
c
o
ef
f
i
cien
t
o
f
0
.
9
8
7
,
wh
ile
C
am
p
u
s
es
B
an
d
H
s
h
o
w
m
o
d
er
ate
c
o
r
r
elatio
n
s
o
f
0
.
9
5
4
an
d
0
.
9
3
2
,
r
esp
ec
tiv
ely
.
C
am
p
u
s
E
'
s
co
r
r
elatio
n
is
lo
wer
at
0
.
6
6
2
,
an
d
C
am
p
u
s
D
h
as
th
e
wea
k
est
c
o
r
r
elatio
n
at
0
.
3
4
8
,
in
d
icatin
g
a
wea
k
er
co
n
n
ec
ti
o
n
b
etwe
e
n
its
in
co
m
in
g
an
d
o
u
tg
o
in
g
tr
af
f
ic
p
atter
n
s
.
Fig
u
r
es 1
9
an
d
2
0
s
h
o
w
a
s
tr
o
n
g
c
o
r
r
elatio
n
b
etwe
en
in
b
o
u
n
d
an
d
o
u
tb
o
u
n
d
in
ter
n
et
d
ata
tr
af
f
ic,
b
u
t
o
u
tlier
s
in
d
icate
p
o
ten
tial
n
etwo
r
k
is
s
u
es.
An
aly
zin
g
th
ese
an
o
m
alies,
s
u
ch
as
n
etwo
r
k
f
ailu
r
es a
n
d
u
n
u
s
u
al
u
s
er
b
eh
a
v
io
r
,
ca
n
im
p
r
o
v
e
n
etwo
r
k
o
p
t
im
izatio
n
.
Fig
u
r
e
1
3
.
C
o
r
r
elatio
n
a
n
aly
s
is
o
n
ca
m
p
u
s
A
Fig
u
r
e
1
4
.
C
o
r
r
elatio
n
a
n
aly
s
is
o
n
ca
m
p
u
s
B
Fig
u
r
e
1
5
.
C
o
r
r
elatio
n
a
n
aly
s
is
o
n
ca
m
p
u
s
H
Fig
u
r
e
1
6
.
C
o
r
r
elatio
n
a
n
aly
s
is
o
n
cam
p
u
s
G
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
4
,
Dec
em
b
er
20
25
:
1
4
3
3
-
1
4
4
3
1440
Fig
u
r
e
1
7
.
C
o
r
r
elatio
n
a
n
aly
s
is
o
n
cam
p
u
s
E
Fig
u
r
e
1
8
.
C
o
r
r
elatio
n
a
n
aly
s
is
o
n
ca
m
p
u
s
D
Fig
u
r
e
1
9
.
C
am
p
u
s
C
in
/o
u
t
d
ata
h
ig
h
ly
c
o
r
r
elate
d
Fig
u
r
e
2
0
.
C
am
p
u
s
F f
o
r
m
a
c
lu
s
ter
with
1
o
u
tlier
3
.
3
.
P
o
s
s
ibl
e
net
wo
rk
beha
v
io
rs
a
nd
is
s
ues
T
h
e
an
aly
s
is
r
ev
ea
ls
cr
itical
i
n
s
ig
h
ts
f
o
r
n
etwo
r
k
m
a
n
ag
em
en
t.
L
o
ca
tio
n
s
A,
B
,
C
,
F,
an
d
H
h
av
e
s
tr
o
n
g
c
o
r
r
elatio
n
s
th
at
m
a
y
le
ad
to
tr
af
f
ic
co
n
g
esti
o
n
,
n
ec
es
s
itatin
g
ef
f
icien
t
tr
a
f
f
ic
m
an
ag
em
en
t.
I
n
c
o
n
tr
ast,
lo
ca
tio
n
s
D,
E
,
a
n
d
G
s
h
o
w
wea
k
co
r
r
elatio
n
s
,
in
d
icatin
g
u
n
d
er
u
tili
za
tio
n
,
p
o
te
n
tially
c
au
s
in
g
b
o
ttlen
ec
k
s
.
L
o
ca
tio
n
F
r
eq
u
ir
es
s
tr
ateg
ic
lo
ad
-
b
alan
cin
g
to
m
an
ag
e
f
l
u
ctu
atin
g
tr
af
f
ic.
ML
tech
n
iq
u
es
lik
e
AR
I
MA
,
L
STM
,
an
d
C
NN
ca
n
a
n
aly
z
e
tr
af
f
ic
p
atter
n
s
;
wh
ile
AR
I
MA
o
f
f
er
s
m
o
d
e
r
ate
s
h
o
r
t
-
ter
m
f
o
r
ec
asts
,
L
STM
an
d
C
NN
ar
e
m
o
r
e
e
f
f
ec
tiv
e
f
o
r
id
e
n
tify
in
g
p
atter
n
s
.
Seaso
n
al
tr
af
f
ic
v
a
r
iatio
n
s
ca
n
im
p
ac
t
f
o
r
ec
ast
ac
cu
r
ac
y
.
T
o
en
h
an
ce
n
etwo
r
k
p
er
f
o
r
m
an
ce
,
it's
ad
v
is
ab
le
to
im
p
lem
en
t
d
y
n
am
ic
b
an
d
wid
th
allo
c
atio
n
,
u
s
e
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
f
o
r
an
o
m
aly
d
etec
t
io
n
,
an
d
im
p
r
o
v
e
lo
a
d
b
alan
ci
n
g
in
h
i
g
h
-
tr
a
f
f
ic
ar
ea
s
.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
h
ig
h
lig
h
ts
t
h
e
ef
f
e
ctiv
en
ess
o
f
h
y
b
r
i
d
ML
m
o
d
e
ls
,
s
u
ch
as
AR
I
MA
-
L
STM
an
d
AR
I
MA
-
C
NN,
f
o
r
in
ter
n
et
tr
af
f
ic
f
o
r
ec
asti
n
g
in
Me
tr
o
-
E
ca
m
p
u
s
n
etwo
r
k
s
.
B
y
co
m
b
in
in
g
s
tatis
tical
tim
e
-
s
er
ie
s
m
eth
o
d
s
with
d
ee
p
lear
n
i
n
g
t
ec
h
n
iq
u
es,
th
ese
m
o
d
els
o
v
e
r
co
m
e
th
e
lim
itatio
n
s
o
f
tr
ad
iti
o
n
al
ap
p
r
o
ac
h
es
in
h
an
d
lin
g
co
m
p
lex
tr
af
f
ic
p
a
tter
n
s
.
An
aly
s
is
o
f
d
ata
f
r
o
m
eig
h
t
ca
m
p
u
s
lo
ca
tio
n
s
s
h
o
wed
s
ig
n
i
f
ican
t
v
ar
iatio
n
s
,
with
s
tr
o
n
g
co
r
r
e
latio
n
s
in
L
o
ca
tio
n
s
A,
E
,
F,
an
d
H,
wh
ile
B
,
C
,
an
d
G
ex
h
ib
ited
m
o
r
e
in
d
ep
en
d
en
t
b
eh
av
i
o
r
s
.
Ou
tlier
s
in
C
an
d
F
p
o
in
ted
to
p
o
ten
tial
n
etwo
r
k
an
o
m
alies.
No
tab
ly
,
L
o
ca
tio
n
H
h
ad
th
e
h
ig
h
est
av
er
a
g
e
tr
af
f
ic
(
7
5
Mb
p
s
)
,
an
d
L
o
ca
tio
n
F
s
h
o
w
ed
th
e
m
o
s
t
v
ar
ia
b
ilit
y
.
T
h
e
i
m
p
r
o
v
e
d
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
o
f
h
y
b
r
id
m
o
d
els
allo
ws
f
o
r
b
etter
b
an
d
wid
th
m
an
ag
em
en
t
an
d
u
s
er
ex
p
er
ien
ce
.
Ho
wev
er
,
ch
allen
g
es
s
u
ch
as
th
e
n
ee
d
f
o
r
ef
f
icien
t
co
m
p
u
tatio
n
al
r
es
o
u
r
ce
s
an
d
r
ea
l
-
tim
e
ad
a
p
tatio
n
s
r
em
ain
.
Fu
tu
r
e
r
esear
ch
s
h
o
u
ld
f
o
cu
s
o
n
en
h
an
cin
g
m
o
d
el
s
ca
lab
ilit
y
an
d
in
teg
r
atin
g
ex
ter
n
al
f
ac
to
r
s
f
o
r
im
p
r
o
v
ed
tr
af
f
ic
f
o
r
ec
asti
n
g
an
d
b
an
d
wid
th
all
o
ca
tio
n
,
u
ltima
tely
o
p
tim
izin
g
n
etwo
r
k
p
er
f
o
r
m
an
ce
i
n
ed
u
c
atio
n
al
s
ettin
g
s
.
ACK
NO
WL
E
DG
M
E
N
T
S
Au
th
o
r
s
ac
k
n
o
wled
g
e
th
e
I
n
s
titu
t
Pen
g
ajian
Sis
waz
ah
(
I
PS
I
S),
Un
iv
er
s
iti
T
ek
n
o
lo
g
i
MA
R
A
(
UiT
M)
f
o
r
th
e
J
o
u
r
n
al
Su
p
p
o
r
t Fu
n
d
(
J
SF
)
in
f
u
n
d
in
g
th
is
p
u
b
licatio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
F
o
r
ec
a
s
tin
g
in
tern
et
tr
a
ffic p
a
tter
n
s
fo
r
th
e
ca
mp
u
s
Metr
o
-
E
n
etw
o
r
k
u
s
in
g
a
h
y
b
r
id
…
(
N
o
r
a
kma
r
A
r
b
a
in
)
1441
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
th
er
e
is
n
o
f
u
n
d
i
n
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
No
r
ak
m
ar
Ar
b
ain
✓
✓
✓
✓
✓
✓
✓
✓
✓
Mu
r
izah
Kass
im
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Dar
m
awa
ty
Mo
h
d
Ali
✓
✓
✓
✓
Sh
u
r
ia
Saaid
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.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
all
in
d
iv
id
u
als in
c
lu
d
ed
in
t
h
is
s
tu
d
y
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
er
e
ar
e
n
o
eth
ical
is
s
u
es r
elate
d
to
th
is
r
esear
ch
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
ailab
l
e
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
a
u
t
h
o
r
,
[
MK
]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
G
.
O
.
F
e
r
r
e
i
r
a
e
t
a
l
.
,
“
F
o
r
e
c
a
st
i
n
g
n
e
t
w
o
r
k
t
r
a
f
f
i
c
:
a
s
u
r
v
e
y
a
n
d
t
u
t
o
r
i
a
l
w
i
t
h
o
p
e
n
-
s
o
u
r
c
e
c
o
mp
a
r
a
t
i
v
e
e
v
a
l
u
a
t
i
o
n
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
7
0
,
n
o
.
N
o
v
e
m
b
e
r
2
0
2
2
,
p
p
.
1
9
–
4
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mc
o
m.
2
0
2
1
.
0
1
.
0
2
1
.
[
2
]
N
.
P
.
A
b
d
u
l
l
a
h
,
S
.
M
.
D
e
n
i
,
a
n
d
M
.
K
a
ss
i
m,
“
W
A
N
i
n
t
e
r
n
e
t
t
r
a
f
f
i
c
p
a
r
a
met
e
r
a
n
a
l
y
s
i
s
o
n
M
e
t
r
o
-
E
c
a
m
p
u
s
n
e
t
w
o
r
k
,
”
i
n
2
0
2
3
I
EEE
1
4
t
h
C
o
n
t
ro
l
a
n
d
S
y
st
e
m
G
r
a
d
u
a
t
e
Re
s
e
a
rc
h
C
o
l
l
o
q
u
i
u
m
(
I
C
S
G
RC
)
,
2
0
2
3
,
p
p
.
1
8
0
–
1
8
5
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
G
R
C
5
7
7
4
4
.
2
0
2
3
.
1
0
2
1
5
4
8
7
.
[
3
]
R
.
A
l
v
a
r
a
d
o
a
n
d
A
.
S
u
á
r
e
z
,
“
A
n
o
v
e
l
e
n
e
r
g
y
-
sa
v
i
n
g
m
e
t
h
o
d
f
o
r
c
a
mp
u
s
w
i
r
e
d
a
n
d
d
e
n
s
e
W
i
F
i
n
e
t
w
o
r
k
a
p
p
l
y
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
i
d
l
e
c
y
c
l
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
FAC
ETS
,
v
o
l
.
9
,
p
p
.
1
–
1
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
3
9
/
f
a
c
e
t
s
-
2
0
2
3
-
0
1
6
4
.
[
4
]
H
.
M
l
i
k
i
,
L.
C
h
a
a
r
i
,
a
n
d
L
.
K
a
m
o
u
n
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
s
u
r
v
e
y
o
n
c
a
r
r
i
e
r
e
t
h
e
r
n
e
t
c
o
n
g
e
s
t
i
o
n
ma
n
a
g
e
me
n
t
m
e
c
h
a
n
i
sm
,
”
J
o
u
r
n
a
l
o
f
N
e
t
w
o
r
k
a
n
d
C
o
m
p
u
t
e
r A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
4
7
,
p
p
.
1
0
7
–
1
3
0
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
n
c
a
.
2
0
1
4
.
0
9
.
0
0
3
.
[
5
]
J.
Z
h
e
n
g
a
n
d
M
.
H
u
a
n
g
,
“
Tr
a
f
f
i
c
f
l
o
w
f
o
r
e
c
a
st
t
h
r
o
u
g
h
t
i
me
seri
e
s
a
n
a
l
y
s
i
s
b
a
s
e
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
8
2
5
6
2
–
8
2
5
7
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
9
0
7
3
8
.
[
6
]
S
.
T.
A
u
n
g
a
n
d
T.
T
h
e
i
n
,
“
I
n
t
e
r
n
e
t
t
r
a
f
f
i
c
c
a
t
e
g
o
r
i
e
s
d
e
ma
n
d
p
r
e
d
i
c
t
i
o
n
t
o
su
p
p
o
r
t
d
y
n
a
m
i
c
Q
o
S
,
”
i
n
2
0
2
0
5
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
st
e
m
s (I
C
C
C
S
)
,
2
0
2
0
,
p
p
.
6
5
0
–
6
5
4
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
C
S
4
9
0
7
8
.
2
0
2
0
.
9
1
1
8
4
3
1
.
[
7
]
N
.
P
.
A
b
d
u
l
l
a
h
,
M
.
K
a
ssi
m
,
S
.
M
.
D
e
n
i
,
a
n
d
Y
.
M
.
Y
u
ss
o
f
f
,
“
D
e
scr
i
p
t
i
v
e
a
n
a
l
y
s
i
s
o
f
w
i
d
e
a
r
e
a
n
e
t
w
o
r
k
f
l
o
w
c
o
n
t
r
o
l
i
n
t
e
r
n
e
t
t
r
a
f
f
i
c
o
n
M
e
t
r
o
-
E
1
0
0
M
b
p
s c
a
m
p
u
s n
e
t
w
o
r
k
,
”
B
u
l
l
e
t
i
n
o
f
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
4
,
p
p
.
2
7
3
8
–
2
7
4
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
e
e
i
.
v
1
3
i
4
.
7
0
4
4
.
[
8
]
A
.
D
.
S
.
A
.
S
h
a
msu
d
d
i
n
,
M
.
K
a
ss
i
m,
a
n
d
N
.
P
.
A
b
d
u
l
l
a
h
,
“
B
a
n
d
w
i
d
t
h
p
e
r
f
o
r
man
c
e
a
n
a
l
y
s
i
s
a
n
d
sh
a
p
i
n
g
a
l
g
o
r
i
t
h
m
o
n
M
e
t
r
o
-
E
c
a
m
p
u
s
n
e
t
w
o
r
k
,
”
i
n
2
0
2
3
I
E
E
E
C
o
n
g
r
e
ss
o
n
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
(
C
i
S
t
)
,
2
0
2
3
,
p
p
.
7
–
1
2
.
d
o
i
:
1
0
.
1
1
0
9
/
C
i
S
t
5
6
0
8
4
.
2
0
2
3
.
1
0
4
0
9
9
6
1
.
[
9
]
R
.
A
.
R
a
h
ma
n
,
M
.
K
a
ssi
m
,
Y
.
C
.
K
.
H
.
C
.
K
u
,
a
n
d
M
.
I
smai
l
,
“
P
e
r
f
o
r
m
a
n
c
e
a
n
a
l
y
s
i
s o
f
r
o
u
t
i
n
g
p
r
o
t
o
c
o
l
i
n
W
i
M
A
X
n
e
t
w
o
r
k
,
”
i
n
2
0
1
1
I
E
EE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
y
st
e
m
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(
I
C
S
ET)
,
2
0
1
1
,
p
p
.
1
5
3
–
1
5
7
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
E
n
g
T.
2
0
1
1
.
5
9
9
3
4
4
0
.
[
1
0
]
N
.
A
.
S
a
l
i
m,
V
.
N
.
S
u
l
i
st
y
a
w
a
n
,
a
n
d
F
.
T.
I
n
t
a
n
,
“
A
n
a
l
y
si
s
a
n
d
s
o
l
u
t
i
o
n
s
o
f
t
r
a
f
f
i
c
s
h
i
f
t
o
n
4
G
n
e
t
w
o
r
k
s
i
n
t
h
e
c
a
m
p
u
s
e
n
v
i
r
o
n
m
e
n
t
d
u
r
i
n
g
t
h
e
C
O
V
I
D
-
1
9
p
a
n
d
e
mi
c
,
”
I
O
P
C
o
n
f
e
re
n
c
e
S
e
ri
e
s:
Ea
r
t
h
a
n
d
E
n
v
i
r
o
n
m
e
n
t
a
l
S
c
i
e
n
c
e
,
v
o
l
.
9
6
9
,
n
o
.
1
,
p
.
1
2
0
2
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
5
-
1
3
1
5
/
9
6
9
/
1
/
0
1
2
0
2
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
4
,
Dec
em
b
er
20
25
:
1
4
3
3
-
1
4
4
3
1442
[
1
1
]
S
.
A
h
m
a
d
,
B
.
S
c
o
t
n
e
y
,
D
.
G
l
a
ss,
a
n
d
S
.
Zh
a
n
g
,
“
E
n
h
a
n
c
i
n
g
n
e
t
w
o
r
k
p
e
r
f
o
r
man
c
e
m
o
n
i
t
o
r
i
n
g
t
h
r
o
u
g
h
s
c
a
l
a
b
l
e
m
u
l
t
i
-
d
i
m
e
n
s
i
o
n
a
l
met
r
i
c
a
n
a
l
y
si
s
a
n
d
p
a
t
t
e
r
n
-
b
a
s
e
d
a
n
o
mal
y
d
e
t
e
c
t
i
o
n
.
”
2
0
2
4
.
d
o
i
:
1
0
.
2
1
2
0
3
/
r
s.3
.
r
s
-
4
9
1
4
5
1
7
/
v
1
.
[
1
2
]
Y
.
G
e
n
g
a
n
d
S
.
Li
,
“
A
LST
M
b
a
se
d
c
a
m
p
u
s
n
e
t
w
o
r
k
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
sy
s
t
e
m,
”
i
n
2
0
1
9
I
E
EE
1
0
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
o
f
t
w
a
re
En
g
i
n
e
e
ri
n
g
a
n
d
S
e
r
v
i
c
e
S
c
i
e
n
c
e
(
I
C
S
E
S
S
)
,
2
0
1
9
,
p
p
.
3
2
7
–
3
3
0
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
ESS
4
7
2
0
5
.
2
0
1
9
.
9
0
4
0
7
3
5
.
[
1
3
]
K
.
P
.
N
.
R
a
o
,
S
.
A
.
K
u
m
a
r
,
a
n
d
K
.
K
e
e
r
t
h
i
k
a
,
“
A
d
a
p
t
i
v
e
Q
o
S
p
r
o
t
o
c
o
l
i
n
s
y
st
e
mi
z
e
d
n
e
t
w
o
r
k
s
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
4
S
e
c
o
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
N
e
t
w
o
r
k
s,
M
u
l
t
i
m
e
d
i
a
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
N
MIT
C
O
N
)
,
2
0
2
4
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
N
M
I
TC
O
N
6
2
0
7
5
.
2
0
2
4
.
1
0
6
9
8
8
8
8
.
[
1
4
]
M
.
K
u
s
h
w
a
h
a
,
A
.
S
a
n
g
w
a
n
,
a
n
d
K
.
G
u
p
t
a
,
“
R
e
a
l
t
i
me
w
e
b
t
r
a
f
f
i
c
f
o
r
e
c
a
st
i
n
g
u
s
i
n
g
LS
TM
a
n
d
C
N
N
,
”
i
n
2
0
2
5
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
S
t
u
d
e
n
t
s’
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
ri
c
a
l
,
E
l
e
c
t
r
o
n
i
c
s
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
S
C
EE
C
S
)
,
2
0
2
5
,
p
p
.
1
–
7
.
d
o
i
:
1
0
.
1
1
0
9
/
S
C
EE
C
S
6
4
0
5
9
.
2
0
2
5
.
1
0
9
4
0
8
4
5
.
[
1
5
]
H
.
G
.
A
.
El
r
a
h
i
m,
N
.
N
.
N
.
A
.
M
a
l
i
k
,
a
n
d
K
.
B
.
M
.
Y
u
s
o
f
,
“
Ef
f
i
c
i
e
n
t
n
e
t
w
o
r
k
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
:
H
a
r
n
e
ss
i
n
g
h
y
b
r
i
d
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
i
n
2
0
2
4
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
d
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
N
e
t
w
o
r
k
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
(
AT
N
T
)
,
2
0
2
4
.
[
1
6
]
A
.
R
.
S
a
t
t
a
r
z
a
d
e
h
,
R
.
J.
K
u
t
a
d
i
n
a
t
a
,
P
.
N
.
P
a
t
h
i
r
a
n
a
,
a
n
d
V
.
T.
H
u
y
n
h
,
“
A
n
o
v
e
l
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
w
i
t
h
A
R
I
M
A
C
o
n
v
-
LSTM
n
e
t
w
o
r
k
s
a
n
d
s
h
u
f
f
l
e
a
t
t
e
n
t
i
o
n
l
a
y
e
r
f
o
r
sh
o
r
t
-
t
e
r
m
t
r
a
f
f
i
c
f
l
o
w
p
r
e
d
i
c
t
i
o
n
,
”
T
r
a
n
s
p
o
rt
m
e
t
r
i
c
a
A:
T
ra
n
s
p
o
rt
S
c
i
e
n
c
e
,
v
o
l
.
2
1
,
n
o
.
1
,
p
.
2
2
3
6
7
2
4
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
8
0
/
2
3
2
4
9
9
3
5
.
2
0
2
3
.
2
2
3
6
7
2
4
.
[
1
7
]
J.
W
u
,
T.
Q
i
u
,
H
.
T
a
n
g
,
a
n
d
X
.
L
i
u
,
“
N
e
t
w
o
r
k
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
b
a
s
e
d
o
n
a
C
N
N
-
LST
M
w
i
t
h
a
t
t
e
n
t
i
o
n
mec
h
a
n
i
s
m,”
i
n
2
0
2
2
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s (I
C
C
I
A)
,
2
0
2
2
.
[
1
8
]
S
.
S
a
h
a
a
n
d
A
.
H
a
q
u
e
,
“
W
a
v
e
l
e
t
-
b
a
sed
h
y
b
r
i
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
o
u
t
-
of
-
d
i
s
t
r
i
b
u
t
i
o
n
i
n
t
e
r
n
e
t
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
I
E
EE/
I
FI
P
N
e
t
w
o
rk
O
p
e
r
a
t
i
o
n
s
a
n
d
Ma
n
a
g
e
m
e
n
t
S
y
m
p
o
si
u
m
2
0
2
3
(
N
O
M
S
)
,
2
0
2
3
,
p
p
.
1
–
8
.
d
o
i
:
1
0
.
1
1
0
9
/
N
O
M
S
5
6
9
2
8
.
2
0
2
3
.
1
0
1
5
4
3
3
7
.
[
1
9
]
M
.
G
.
A
.
P
a
z
o
u
e
t
a
l
.
,
“
N
e
t
w
o
r
k
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
b
y
l
e
a
r
n
i
n
g
t
i
m
e
s
e
r
i
e
s
a
s
i
ma
g
e
s,
”
E
n
g
i
n
e
e
ri
n
g
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
a
n
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
,
v
o
l
.
5
5
,
n
o
.
F
e
b
r
u
a
r
y
,
p
.
1
0
1
7
5
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
e
s
t
c
h
.
2
0
2
4
.
1
0
1
7
5
4
.
[
2
0
]
N
.
M
.
B
a
l
a
m
u
r
u
g
a
n
,
M
.
A
d
i
m
o
o
l
a
m,
M
.
H
.
A
l
s
h
a
r
i
f
,
a
n
d
P
.
U
t
h
a
n
s
a
k
u
l
,
“
A
n
o
v
e
l
me
t
h
o
d
f
o
r
i
mp
r
o
v
e
d
n
e
t
w
o
r
k
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
u
si
n
g
e
n
h
a
n
c
e
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
a
l
g
o
r
i
t
h
m
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
1
3
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
2
1
3
5
0
0
6
.
[
2
1
]
T.
H
.
H
.
A
l
d
h
y
a
n
i
,
M
.
A
l
r
a
sh
e
e
d
i
,
A
.
A
.
A
l
q
a
r
n
i
,
M
.
Y
.
A
l
z
a
h
r
a
n
i
,
a
n
d
A
.
M
.
B
a
m
h
d
i
,
“
I
n
t
e
l
l
i
g
e
n
t
h
y
b
r
i
d
mo
d
e
l
t
o
e
n
h
a
n
c
e
t
i
m
e
seri
e
s
m
o
d
e
l
s
f
o
r
p
r
e
d
i
c
t
i
n
g
n
e
t
w
o
r
k
t
r
a
f
f
i
c
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
3
0
4
3
1
–
1
3
0
4
5
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
0
9
1
6
9
.
[
2
2
]
K
.
A
l
b
e
l
a
d
i
,
B
.
Za
f
a
r
,
a
n
d
A
.
M
u
e
e
n
,
“
Ti
m
e
seri
e
s
f
o
r
e
c
a
s
t
i
n
g
u
s
i
n
g
LS
TM
a
n
d
A
R
I
M
A
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
4
,
n
o
.
1
,
p
p
.
3
1
3
–
3
2
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
3
.
0
1
4
0
1
3
3
.
[
2
3
]
W
.
W
a
n
g
e
t
a
l
.
,
“
A
n
e
t
w
o
r
k
t
r
a
f
f
i
c
f
l
o
w
p
r
e
d
i
c
t
i
o
n
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
l
a
r
g
e
-
sc
a
l
e
m
e
t
r
o
p
o
l
i
t
a
n
a
r
e
a
n
e
t
w
o
r
k
,
”
i
n
I
EEE/
I
FI
P
N
e
t
w
o
r
k
O
p
e
ra
t
i
o
n
s
a
n
d
Ma
n
a
g
e
m
e
n
t
S
y
m
p
o
s
i
u
m
:
C
o
g
n
i
t
i
v
e
Ma
n
a
g
e
m
e
n
t
i
n
a
C
y
b
e
r
W
o
r
l
d
(
N
O
MS
)
,
2
0
1
8
,
p
p
.
1
–
9
.
d
o
i
:
1
0
.
1
1
0
9
/
N
O
M
S
.
2
0
1
8
.
8
4
0
6
2
5
2
.
[
2
4
]
M
.
K
a
ss
i
m,
M
.
I
smai
l
,
a
n
d
M
.
I
.
Y
u
so
f
,
“
S
t
a
t
i
st
i
c
a
l
a
n
a
l
y
si
s
a
n
d
mo
d
e
l
i
n
g
o
f
i
n
t
e
r
n
e
t
t
r
a
f
f
i
c
I
P
-
b
a
se
d
n
e
t
w
o
r
k
f
o
r
t
e
l
e
-
t
r
a
f
f
i
c
e
n
g
i
n
e
e
r
i
n
g
,
”
ARP
N
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
ri
n
g
a
n
d
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
0
,
n
o
.
3
,
p
p
.
1
5
0
5
–
1
5
1
2
,
2
0
1
5
.
[
2
5
]
M
.
U
sam
a
e
t
a
l
.
,
“
U
n
s
u
p
e
r
v
i
se
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
n
e
t
w
o
r
k
i
n
g
:
t
e
c
h
n
i
q
u
e
s
,
a
p
p
l
i
c
a
t
i
o
n
s
a
n
d
r
e
s
e
a
r
c
h
c
h
a
l
l
e
n
g
e
s
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
6
5
5
7
9
–
6
5
6
1
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
1
6
6
4
8
.
[
2
6
]
M
.
A
b
b
a
si
,
A
.
S
h
a
h
r
a
k
i
,
a
n
d
A
.
Ta
h
e
r
k
o
r
d
i
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
n
e
t
w
o
r
k
t
r
a
f
f
i
c
m
o
n
i
t
o
r
i
n
g
a
n
d
a
n
a
l
y
s
i
s
(
N
T
M
A
)
:
a
s
u
r
v
e
y
,
”
C
o
m
p
u
t
e
r
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
1
7
0
,
n
o
.
D
e
c
e
m
b
e
r
2
0
2
0
,
p
p
.
1
9
–
4
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mc
o
m.
2
0
2
1
.
0
1
.
0
2
1
.
[
2
7
]
Y
.
X
u
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
a
n
d
c
o
n
g
e
st
i
o
n
c
o
n
t
r
o
l
a
l
g
o
r
i
t
h
ms
i
n
s
o
f
t
w
a
r
e
d
e
f
i
n
e
d
n
e
t
w
o
r
k
s,”
i
n
2
0
2
4
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
T
e
c
h
n
o
l
o
g
i
e
s
(
I
I
S
T
)
,
2
0
2
4
,
p
p
.
2
8
5
–
2
8
9
.
d
o
i
:
1
0
.
1
1
0
9
/
I
I
S
T6
2
5
2
6
.
2
0
2
4
.
0
0
0
3
5
.
[
2
8
]
H
.
Y
a
n
g
,
X
.
Li
,
W
.
Q
i
a
n
g
,
Y
.
Zh
a
o
,
W
.
Zh
a
n
g
,
a
n
d
C
.
T
a
n
g
,
“
A
n
e
t
w
o
r
k
t
r
a
f
f
i
c
f
o
r
e
c
a
s
t
i
n
g
me
t
h
o
d
b
a
se
d
o
n
S
A
o
p
t
i
mi
z
e
d
A
R
I
M
A
–
B
P
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
C
o
m
p
u
t
e
r
N
e
t
w
o
rks
,
v
o
l
.
1
9
3
,
n
o
.
F
e
b
r
u
a
r
y
,
p
.
1
0
8
1
0
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mn
e
t
.
2
0
2
1
.
1
0
8
1
0
2
.
[
2
9
]
S
.
K
h
o
r
sa
n
d
r
o
o
,
A
.
G
.
S
á
n
c
h
e
z
,
A
.
S
.
T
o
s
u
n
,
J
.
M
.
A
r
c
o
,
a
n
d
R
.
D
.
-
C
o
r
i
n
,
“
H
y
b
r
i
d
S
D
N
e
v
o
l
u
t
i
o
n
:
a
c
o
m
p
r
e
h
e
n
s
i
v
e
s
u
r
v
e
y
o
f
t
h
e
st
a
t
e
-
of
-
t
h
e
-
a
r
t
,
”
C
o
m
p
u
t
e
r
N
e
t
w
o
rks
,
v
o
l
.
1
9
2
,
p
.
1
0
7
9
8
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
n
e
t
.
2
0
2
1
.
1
0
7
9
8
1
.
[
3
0
]
D
.
A
l
o
r
a
i
f
a
n
,
I
.
A
h
m
a
d
,
a
n
d
E.
A
l
r
a
sh
e
d
,
“
D
e
e
p
l
e
a
r
n
i
n
g
b
a
s
e
d
n
e
t
w
o
r
k
t
r
a
f
f
i
c
m
a
t
r
i
x
p
r
e
d
i
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
N
e
t
w
o
rks
,
v
o
l
.
2
,
n
o
.
M
a
y
,
p
p
.
4
6
–
5
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
i
n
.
2
0
2
1
.
0
6
.
0
0
2
.
[
3
1
]
S
.
S
a
h
a
,
A
.
H
a
q
u
e
,
a
n
d
G
.
S
i
d
e
b
o
t
t
o
m
,
“
Tr
a
n
sf
e
r
l
e
a
r
n
i
n
g
b
a
se
d
e
f
f
i
c
i
e
n
t
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
w
i
t
h
l
i
m
i
t
e
d
t
r
a
i
n
i
n
g
d
a
t
a
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
I
EE
E
C
o
n
su
m
e
r
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
N
e
t
w
o
rk
i
n
g
C
o
n
f
e
re
n
c
e
(
C
C
N
C
)
,
2
0
2
3
,
v
o
l
.
2
0
2
3
-
Ja
n
u
a
,
p
p
.
4
7
7
–
4
8
0
.
d
o
i
:
1
0
.
1
1
0
9
/
C
C
N
C
5
1
6
4
4
.
2
0
2
3
.
1
0
0
6
0
7
4
5
.
[
3
2
]
S
.
S
a
h
a
,
A
.
H
a
q
u
e
,
a
n
d
G
.
S
i
d
e
b
o
t
t
o
m,
“
A
n
a
l
y
z
i
n
g
t
h
e
i
mp
a
c
t
o
f
o
u
t
l
i
e
r
d
a
t
a
p
o
i
n
t
s
o
n
m
u
l
t
i
-
s
t
e
p
i
n
t
e
r
n
e
t
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
u
si
n
g
d
e
e
p
s
e
q
u
e
n
c
e
m
o
d
e
l
s,
”
I
EEE
T
r
a
n
sa
c
t
i
o
n
s
o
n
N
e
t
w
o
r
k
a
n
d
S
e
rv
i
c
e
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
2
0
,
n
o
.
2
,
p
p
.
1
3
4
5
–
1
3
6
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
S
M
.
2
0
2
3
.
3
2
6
2
4
0
6
.
[
3
3
]
L.
W
a
n
g
,
L.
C
h
e
,
K
.
Y
.
La
m,
W
.
L
i
u
,
a
n
d
F
.
Li
,
“
M
o
b
i
l
e
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
w
i
t
h
a
t
t
e
n
t
i
o
n
-
b
a
se
d
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Ph
y
si
c
a
l
C
o
m
m
u
n
i
c
a
t
i
o
n
,
v
o
l
.
6
6
,
n
o
.
F
e
b
r
u
a
r
y
,
p
.
1
0
2
4
2
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
h
y
c
o
m.
2
0
2
4
.
1
0
2
4
2
0
.
[
3
4
]
S
.
F
i
sc
h
e
r
,
K
.
K
a
t
sar
o
u
,
a
n
d
O
.
H
o
l
sc
h
k
e
,
“
D
e
e
p
F
l
o
w
:
t
o
w
a
r
d
s
n
e
t
w
o
r
k
-
w
i
d
e
i
n
g
r
e
ss
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
t
l
a
r
g
e
s
c
a
l
e
,
”
i
n
2
0
2
0
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
N
e
t
w
o
r
k
s,
C
o
m
p
u
t
e
rs
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
(
I
S
N
C
C
)
,
2
0
2
0
.
d
o
i
:
1
0
.
1
1
0
9
/
I
S
N
C
C
4
9
2
2
1
.
2
0
2
0
.
9
2
9
7
3
0
1
.
[
3
5
]
A
.
A
z
a
r
i
,
P
.
P
a
p
a
p
e
t
r
o
u
,
S
.
D
e
n
i
c
,
a
n
d
G
.
P
e
t
e
r
s,
“
C
e
l
l
u
l
a
r
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
:
a
c
o
m
p
a
r
a
t
i
v
e
e
v
a
l
u
a
t
i
o
n
o
f
LST
M
a
n
d
A
R
I
M
A
,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
s
u
b
s
e
ri
e
s
L
e
c
t
u
re
N
o
t
e
s
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
r
e
N
o
t
e
s
i
n
B
i
o
i
n
f
o
rm
a
t
i
c
s)
,
v
o
l
.
1
1
8
2
8
LN
A
I
,
2
0
1
9
,
p
p
.
1
2
9
–
1
4
4
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
3
3
7
7
8
-
0
_
1
1
.
[
3
6
]
Y
.
M
i
a
o
e
t
a
l
.
,
“
A
n
o
v
e
l
s
h
o
r
t
-
t
e
r
m
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
b
a
s
e
d
o
n
S
V
D
a
n
d
A
R
I
M
A
w
i
t
h
b
l
o
c
k
c
h
a
i
n
i
n
i
n
d
u
st
r
i
a
l
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s,
”
I
EE
E
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
J
o
u
r
n
a
l
,
v
o
l
.
1
0
,
n
o
.
2
4
,
p
p
.
2
1
2
1
7
–
2
1
2
2
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T.
2
0
2
3
.
3
2
8
3
6
1
1
.
[
3
7
]
C
.
H
a
j
a
j
,
P
.
A
h
a
r
o
n
,
R
.
D
u
b
i
n
,
a
n
d
A
.
D
v
i
r
,
“
Th
e
a
r
t
o
f
t
i
me
-
b
e
n
d
i
n
g
:
D
a
t
a
a
u
g
me
n
t
a
t
i
o
n
a
n
d
e
a
r
l
y
p
r
e
d
i
c
t
i
o
n
f
o
r
e
f
f
i
c
i
e
n
t
t
r
a
f
f
i
c
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
5
2
,
n
o
.
A
p
r
i
l
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
4
.
1
2
4
1
6
6
.
[
3
8
]
J.
S
h
i
,
Y
.
B
.
Le
a
u
,
K
.
L
i
,
a
n
d
J.
H
.
O
b
i
t
,
“
A
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
n
h
y
b
r
i
d
n
e
t
w
o
r
k
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
mo
d
e
l
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
1
,
n
o
.
2
,
p
p
.
1
4
5
0
–
1
4
5
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
1
i
2
.
p
p
1
4
5
0
-
1
4
5
9
.
[
3
9
]
S
.
S
a
h
a
,
S
.
D
a
s,
a
n
d
G
.
H
.
C
a
r
v
a
l
h
o
,
“
C
o
n
v
LST
M
Tr
a
n
sN
e
t
:
a
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
i
n
t
e
r
n
e
t
t
r
a
f
f
i
c
t
e
l
e
m
e
t
r
y
,
”
i
n
2
0
2
4
I
EE
E
V
i
rt
u
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
s (V
C
C
)
,
2
0
2
4
,
p
p
.
1
–
6.
[
4
0
]
B
.
S
h
a
o
,
D
.
S
o
n
g
,
G
.
B
i
a
n
,
a
n
d
Y
.
Z
h
a
o
,
“
A
h
y
b
r
i
d
a
p
p
r
o
a
c
h
b
y
C
EE
M
D
A
N
-
i
mp
r
o
v
e
d
P
S
O
-
LSTM
mo
d
e
l
f
o
r
n
e
t
w
o
r
k
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
,
”
S
e
c
u
ri
t
y
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
N
e
t
w
o
r
k
s
,
v
o
l
.
2
0
2
2
,
n
o
.
1
,
p
.
4
9
7
5
2
8
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
4
9
7
5
2
8
8
.
[
4
1
]
J.
S
u
,
H
.
C
a
i
,
Z.
S
h
e
n
g
,
A
.
X
.
L
i
u
,
a
n
d
A
.
B
a
z
,
“
Tr
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
f
o
r
5
G
:
a
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
b
a
se
d
o
n
l
i
g
h
t
w
e
i
g
h
t
h
y
b
r
i
d
a
t
t
e
n
t
i
o
n
n
e
t
w
o
r
k
s,”
D
i
g
i
t
a
l
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
,
v
o
l
.
1
4
6
,
p
.
1
0
4
3
5
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
s
p
.
2
0
2
3
.
1
0
4
3
5
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.