T
E
L
K
O
M
N
I
K
A
T
elec
o
m
m
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
18
,
No
.
5
,
Octo
b
er
2
0
2
0
,
p
p
.
2
4
5
4
~
2
4
6
2
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Kem
en
r
is
tek
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/TE
L
KOM
NI
K
A.
v
1
8
i5
.
1
6
7
1
2
2454
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
M
o
bile learning
architec
ture
using
fog
com
puting
a
nd ad
a
ptive da
ta
streamin
g
Sh
y
m
a
a
M
o
ha
mm
ed
J
a
m
ee
l
1
,
M
ua
y
a
d Sa
dik
Cro
o
ck
2
1
In
stit
u
te
o
f
I
n
fo
rm
a
ti
c
s fo
r
P
o
st
g
ra
d
u
a
te S
tu
d
ies
c
Ira
q
i
C
o
m
m
issio
n
fo
r
Co
m
p
u
ters
a
n
d
In
f
o
rm
a
ti
c
s,
Ira
q
2
Co
m
p
u
ter E
n
g
in
e
e
rin
g
De
p
a
rtm
e
n
t,
Un
i
v
e
rsity
o
f
Tec
h
n
o
l
o
g
y
,
I
r
a
q
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
1
7
,
2
0
2
0
R
ev
is
ed
Ma
y
2
8
,
2
0
2
0
Acc
ep
ted
J
u
n
1
1
,
2
0
2
0
Wi
th
t
h
e
h
u
g
e
d
e
v
e
lo
p
m
e
n
t
in
m
o
b
il
e
a
n
d
n
e
two
r
k
field
s,
se
n
so
r
tec
h
n
o
l
o
g
ies
a
n
d
fo
g
c
o
m
p
u
ti
n
g
h
e
lp
th
e
stu
d
e
n
ts f
o
r
m
o
re
e
ffe
c
ti
v
e
lea
rn
in
g
,
flex
ib
le an
d
in
a
n
d
e
ffe
c
ti
v
e
m
a
n
n
e
r
fro
m
a
n
y
wh
e
re
.
Us
in
g
th
e
m
o
b
il
e
d
e
v
ice
fo
r
lea
rn
e
n
c
o
u
ra
g
e
t
h
e
tra
n
siti
o
n
to
m
o
b
il
e
c
o
m
p
u
ti
n
g
(c
lo
u
d
a
n
d
f
o
g
c
o
m
p
u
ti
n
g
)
w
h
ich
is
led
t
o
th
e
a
b
il
it
y
to
d
e
sig
n
c
u
st
o
m
ize
d
sy
ste
m
th
a
t
h
e
lp
stu
d
e
n
t
to
lea
rn
v
ia
c
o
n
tex
t
a
wa
re
lea
rn
in
g
wh
ich
c
a
n
b
e
d
o
n
e
b
y
s
e
t
th
e
u
se
r
p
re
fe
re
n
c
e
a
n
d
u
se
p
ro
p
e
r
m
e
th
o
d
s
t
o
sh
o
w
o
n
l
y
re
late
d
m
a
n
n
e
r
su
b
jec
t.
Th
e
p
re
se
n
ted
stu
d
y
w
o
rk
s
o
n
d
e
v
e
lo
p
i
n
g
a
sy
ste
m
o
f
e
-
lea
rn
i
n
g
wh
ich
h
a
s
b
e
e
n
o
n
t
h
e
b
a
sis
o
f
fo
g
c
o
m
p
u
ti
n
g
c
o
n
c
e
p
ts
with
d
e
e
p
lea
rn
in
g
a
p
p
r
o
a
c
h
e
s
u
ti
li
z
e
d
fo
r
c
las
sifica
ti
o
n
to
t
h
e
d
a
ta
c
o
n
ten
t
f
o
r
a
c
c
o
m
p
li
sh
i
n
g
t
h
e
c
o
n
tex
t
a
wa
re
lea
rn
in
g
a
n
d
u
se
t
h
e
a
d
a
p
t
a
ti
o
n
o
f
v
id
e
o
q
u
a
li
ty
u
si
n
g
s
p
e
c
ial
e
q
u
a
ti
o
n
a
n
d
th
e
d
a
ta
e
n
c
ry
p
ted
a
n
d
d
e
c
ry
p
ted
u
sin
g
3
DES
a
l
g
o
ri
th
m
to
e
n
su
re
th
e
se
c
u
rit
y
si
d
e
o
f
th
e
o
p
e
ra
ti
o
n
.
K
ey
w
o
r
d
s
:
C
NN
Data
s
tr
ea
m
in
g
Dee
p
lear
n
in
g
Mo
b
ile
lear
n
in
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r
th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Sh
y
m
aa
Mo
h
am
m
ed
J
am
ee
l,
I
n
s
titu
te
o
f
I
n
f
o
r
m
atics f
o
r
Po
s
tg
r
ad
u
ate
Stu
d
iesc I
r
aq
i
,
C
o
m
m
is
s
io
n
f
o
r
C
o
m
p
u
ter
s
a
n
d
I
n
f
o
r
m
atics,
B
ag
h
d
ad
,
I
r
aq
.
E
m
ail:
s
h
y
m
aa
7
9
2
0
0
3
@
y
ah
o
o
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
er
e
h
as
b
e
e
n
a
c
o
n
t
i
n
u
o
u
s
d
e
v
e
l
o
p
m
e
n
t
i
n
m
o
b
i
l
e
t
e
c
h
n
o
l
o
g
i
e
s
a
s
w
e
ll
a
s
p
e
r
v
as
i
v
e
I
n
t
e
r
n
e
t
c
o
n
n
e
c
t
i
v
i
t
y
w
h
i
c
h
is
a
l
l
o
w
i
n
g
u
s
e
r
s
i
n
a
c
c
es
s
i
n
g
i
n
f
o
r
m
a
t
io
n
a
n
y
t
i
m
e
a
n
d
a
n
y
w
h
e
r
e
,
s
u
c
h
f
e
a
t
u
r
e
m
i
g
h
t
b
e
a
p
p
l
i
e
d
f
o
r
i
n
s
t
r
u
m
e
n
t
at
i
o
n
r
e
g
a
r
d
i
n
g
v
a
r
i
o
u
s
a
p
p
l
i
c
a
ti
o
n
s
s
u
ch
a
s
e
d
u
c
a
t
i
o
n
.
T
h
e
u
s
e
o
f
m
o
b
i
l
e
d
e
v
i
c
es
s
u
c
h
as
l
a
p
t
o
p
s
,
t
a
b
le
t
s
,
a
n
d
s
m
a
r
t
-
p
h
o
n
e
s
,
a
r
e
m
a
k
i
n
g
t
h
e
p
r
o
c
e
s
s
o
f
l
e
a
r
n
i
n
g
m
o
r
e
e
f
f
e
c
t
i
v
e
,
s
i
m
p
l
e
a
n
d
p
e
r
s
o
n
a
l
.
M
o
b
i
l
e
l
e
a
r
n
i
n
g
is
t
h
e
t
e
r
m
p
r
o
v
i
d
e
d
f
o
r
s
u
c
h
l
e
a
r
n
i
n
g
t
y
p
e
[
1
]
.
T
h
e
m
o
b
i
l
e
l
e
a
r
n
i
n
g
m
i
g
h
t
b
e
u
t
i
l
i
z
e
d
al
o
n
g
w
i
t
h
t
h
e
e
-
l
e
a
r
n
i
n
g
a
n
d
u
b
i
q
u
i
to
u
s
l
e
a
r
n
i
n
g
,
a
ls
o
i
t
m
i
g
h
t
b
e
s
p
e
c
i
f
i
e
d
a
s
a
s
u
b
-
s
e
t
r
e
g
a
r
d
i
n
g
e
l
e
c
t
r
o
n
i
c
-
le
a
r
n
i
n
g
w
h
i
c
h
i
n
v
o
l
v
e
s
u
s
i
n
g
m
o
b
i
l
e
d
e
v
i
c
e
s
f
o
r
a
ll
o
w
i
n
g
t
h
e
p
r
o
c
ess
o
f
l
e
a
r
n
i
n
g
a
n
y
t
i
m
e
a
n
d
a
n
y
w
h
e
r
e
.
A
t
t
h
e
s
a
m
e
t
i
m
e
,
t
h
e
u
b
i
q
u
i
t
o
u
s
l
e
a
r
n
i
n
g
i
s
n
’
t
e
s
s
e
n
t
i
al
l
y
u
s
i
n
g
t
h
e
m
o
b
i
l
e
d
e
v
i
c
e
s
.
B
a
s
e
d
o
n
a
s
t
u
d
y
c
o
n
d
u
c
t
e
d
b
y
K
l
o
p
f
e
r
e
t
al
.
[
2
]
,
t
h
e
r
e
h
a
v
e
b
e
e
n
s
o
m
e
p
r
o
p
e
r
t
i
es
r
e
la
t
e
d
to
m
o
b
i
l
e
d
e
v
i
c
es
w
h
ic
h
m
a
k
in
g
t
h
e
m
s
u
i
ta
b
l
e
f
o
r
e
d
u
c
a
t
i
o
n
a
l
i
n
te
n
t
s
–
i
n
d
i
v
i
d
u
a
li
t
y
,
c
o
n
t
e
x
t
s
e
n
s
it
i
v
it
y
,
s
o
c
i
al
in
t
e
r
a
c
t
i
v
it
y
,
p
o
r
t
a
b
i
l
it
y
,
a
n
d
c
o
n
n
e
c
t
i
v
i
t
y
.
So
m
e
o
f
th
e
f
ea
tu
r
es
in
clu
d
e
d
in
m
o
b
ile
lear
n
in
g
a
r
e
as
f
o
llo
ws
–
p
er
s
o
n
alize
d
in
f
o
r
m
atio
n
,
lear
n
in
g
th
r
o
u
g
h
o
u
t
s
p
ac
e
-
tim
e,
o
n
-
th
e
-
f
ly
lear
n
i
n
g
[
3
]
.
A
s
tu
d
y
co
n
d
u
cted
b
y
W
an
g
[
4
]
in
v
esti
g
a
ted
th
e
s
ig
n
if
ican
ce
o
f
co
n
tex
t
s
en
s
itiv
ity
as
well
as
in
d
icatin
g
th
at
th
e
m
ain
u
n
i
q
u
e
f
ea
tu
r
e
th
at
th
e
m
o
b
ile
lear
n
in
g
en
v
i
r
o
n
m
e
n
ts
m
u
s
t
in
v
o
lv
e.
Fu
r
th
e
r
m
o
r
e
,
th
e
co
n
tex
t
-
awa
r
e
m
o
b
ile
lear
n
in
g
m
ig
h
t
b
e
h
elp
in
g
th
e
le
ar
n
er
f
o
r
ef
f
ec
tiv
ely
u
s
in
g
th
e
p
r
o
v
id
ed
i
n
f
o
r
m
atio
n
.
T
h
er
e
h
av
e
b
ee
n
s
o
m
e
p
r
o
b
lem
s
f
ac
ed
wh
en
im
p
lem
e
n
tin
g
m
o
b
ile
lear
n
in
g
,
th
e
m
ater
ials
o
f
lear
n
in
g
m
ig
h
t
in
v
o
lv
e
p
r
esen
tatio
n
s
,
im
a
g
es,
an
d
v
id
e
o
s
.
I
n
ad
d
itio
n
,
s
u
p
p
o
r
ted
f
ile
ty
p
es,
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
Mo
b
ile
lea
r
n
in
g
a
r
ch
itectu
r
e
u
s
in
g
fo
g
c
o
mp
u
tin
g
a
n
d
a
d
a
p
tive
…
(
S
h
yma
a
Mo
h
a
mme
d
Ja
mee
l
)
2455
s
to
r
ag
e
ca
p
ac
ity
,
s
cr
ee
n
s
ize,
r
eso
lu
tio
n
,
I
n
ter
n
et
ac
ce
s
s
,
an
d
p
r
o
ce
s
s
in
g
tim
e
ar
e
m
aj
o
r
is
s
u
es
wh
ich
m
u
s
t
b
e
d
ea
lt
with
.
T
h
e
ap
p
r
o
ac
h
es o
f
co
n
ten
t
ad
a
p
tatio
n
m
u
s
t
b
e
a
p
p
lied
f
o
r
th
e
p
u
r
p
o
s
e
o
f
ad
d
r
e
s
s
in
g
s
u
ch
d
iv
er
s
ity
is
s
u
e
[
5
]
.
Ma
n
y
s
tu
d
ies
ar
e
wo
r
k
in
g
o
n
s
u
c
h
co
n
ce
p
t
o
f
elec
tr
o
n
ic
-
lear
n
in
g
o
n
th
e
b
a
s
is
o
f
f
o
g
o
r
clo
u
d
tech
n
o
lo
g
ies in
th
e
f
o
llo
win
g
way
.
A
s
tu
d
y
co
n
d
u
cted
b
y
[
6
]
d
esig
n
ed
co
m
p
u
ter
-
aid
ed
ed
u
c
atio
n
p
latf
o
r
m
o
n
th
e
b
asis
o
f
clo
u
d
co
m
p
u
tin
g
tech
n
o
lo
g
ies
an
d
m
o
b
ile
co
m
m
u
n
icatio
n
.
W
ith
r
eg
ar
d
to
clien
ts
,
th
ey
ar
e
d
ev
elo
p
in
g
s
m
ar
t
-
p
h
o
n
e
s
o
f
twar
e
o
n
th
e
b
asis
o
f
o
p
e
n
-
s
o
u
r
ce
J
av
aM
E
UI
f
r
am
ew
o
r
k
(
k
u
ix
)
in
ad
d
itio
n
to
J
ab
er
t
h
at
is
s
p
ec
if
ied
f
o
r
b
ein
g
o
n
e
o
f
th
e
o
p
en
s
o
u
r
ce
in
s
tan
t
m
ess
ag
e
p
r
o
to
co
l
s
.
Fo
r
th
e
p
u
r
p
o
s
e
o
f
h
elp
i
n
g
th
e
teac
h
er
s
in
co
n
v
en
ie
n
tly
u
s
in
g
th
e
s
y
s
tem
,
th
e
s
tu
d
y
d
ev
el
o
p
ed
a
web
s
ite
o
n
th
e
b
asis
o
f
Go
o
g
le
Ap
p
E
n
g
i
n
e
,
also
with
th
e
u
s
e
o
f
co
m
m
u
n
icatio
n
p
l
atf
o
r
m
,
a
s
tu
d
e
n
t
h
as
th
e
ab
i
lity
o
f
co
m
m
u
n
icatin
g
with
t
h
e
teac
h
er
at
an
y
p
o
s
s
ib
le
tim
e,
th
u
s
th
e
teac
h
er
will
k
n
o
w
th
e
teac
h
in
g
’
s
s
itu
atio
n
an
d
th
e
k
n
o
wled
g
e
lev
el
o
f
th
e
s
tu
d
en
t,
also
th
e
teac
h
er
s
will
h
av
e
th
e
ab
i
lity
f
o
r
an
s
wer
in
g
q
u
esti
o
n
s
o
r
s
en
d
in
g
m
ess
ag
es
to
s
tu
d
en
ts
f
r
ee
ly
v
ia
s
u
ch
co
m
m
u
n
icatio
n
p
latf
o
r
m
.
Pra
ctica
lly
,
th
r
o
u
g
h
s
u
c
h
tech
n
ical
m
ea
n
s
,
it
is
n
a
r
r
o
win
g
th
e
g
a
p
s
b
etwe
e
n
teac
h
er
s
an
d
s
tu
d
en
ts
an
d
p
r
o
d
u
cin
g
ad
eq
u
ate
r
esu
lts
.
A
s
tu
d
y
co
n
d
u
cte
d
b
y
[
7
]
s
u
g
g
ested
elec
tr
o
n
ic
-
lear
n
in
g
s
y
s
tem
wh
ich
is
b
ased
o
n
clo
u
d
c
o
m
p
u
tin
g
at
E
d
u
ca
tio
n
4
.
0
.
T
h
e
m
ajo
r
g
o
al
is
p
r
o
d
u
ci
n
g
a
s
y
s
tem
wh
ich
m
ig
h
t
b
e
ap
p
lied
as
a
co
n
ce
p
t
to
d
ev
elo
p
e
-
lear
n
in
g
s
y
s
tem
b
ased
o
n
clo
u
d
co
m
p
u
tin
g
wh
ich
is
an
s
wer
in
g
th
e
r
eq
u
ir
em
en
ts
o
f
E
d
u
ca
tio
n
4
.
0
.
T
h
u
s
,
t
h
is
s
tu
d
y
is
r
e
v
iewin
g
th
e
wo
r
k
s
r
elate
d
to
e
-
lear
n
in
g
s
y
s
tem
s
wh
ich
ar
e
b
ased
o
n
clo
u
d
s
.
A
s
tu
d
y
co
n
d
u
cted
b
y
[
8
]
s
u
g
g
esti
n
g
u
s
in
g
L
o
R
aWAN
f
o
g
co
m
p
u
tin
g
-
b
ased
s
y
s
tem
t
o
p
r
o
v
id
e
co
n
n
ec
tiv
ity
to
th
e
n
o
d
es
o
f
I
o
T
u
s
ed
i
n
th
e
ca
m
p
u
s
o
f
U
n
iv
er
s
ity
o
f
a
C
o
r
u
ñ
a
(
UDC),
Sp
a
in
.
Fo
r
th
e
p
u
r
p
o
s
e
o
f
v
alid
atin
g
th
e
s
u
g
g
ested
s
y
s
tem
,
s
m
ar
t
ca
m
p
u
s
was
r
ea
lis
tically
r
e
-
cr
ea
ted
v
ia
in
-
h
o
u
s
e
cr
ea
te
d
3
-
D
R
ay
-
l
au
n
ch
in
g
r
a
d
io
-
p
la
n
n
in
g
s
im
u
lato
r
wh
ich
h
as
th
e
ab
ilit
y
to
co
n
s
id
er
m
in
o
r
d
etails,
lik
e
v
eg
etat
io
n
,
b
u
ild
in
g
s
,
v
eh
icles,
tr
af
f
ic
-
lig
h
ts
,
in
d
iv
id
u
als,
an
d
u
r
b
an
f
u
r
n
itu
r
e.
T
h
e
d
esig
n
ed
to
o
l
m
ig
h
t
b
e
p
r
o
v
id
in
g
s
u
itab
le
r
ad
io
p
r
o
p
ag
atio
n
esti
m
atio
n
in
th
e
s
m
ar
t
ca
m
p
u
s
s
y
s
tem
with
r
eg
a
r
d
t
o
en
e
r
g
y
e
f
f
icien
cy
,
ca
p
ac
ity
,
an
d
co
v
er
ag
e
o
f
th
e
n
etwo
r
k
.
T
h
e
r
esu
lts
wh
ich
ar
e
ac
q
u
ir
ed
with
p
lan
n
in
g
s
im
u
lato
r
m
ig
h
t
b
e
p
u
t
to
co
m
p
ar
is
o
n
with
em
p
ir
ical
m
ea
s
u
r
em
en
ts
f
o
r
ass
ess
in
g
th
e
s
y
s
tem
’
s
ac
cu
r
ac
y
a
n
d
o
p
er
atin
g
co
n
d
itio
n
s
.
T
h
e
wo
r
k
is
p
r
esen
tin
g
e
x
p
er
im
en
ts
s
h
o
win
g
th
e
ad
e
q
u
ate
r
esu
lts
ac
q
u
ir
ed
th
r
o
u
g
h
p
lan
n
in
g
s
im
u
lato
r
i
n
m
o
s
t
s
ig
n
if
ican
t
d
ev
el
o
p
ed
s
ce
n
ar
io
,
th
at
h
av
e
b
ee
n
co
r
r
o
b
o
r
atin
g
with
e
m
p
ir
ical
m
ea
s
u
r
em
en
ts
.
Af
ter
th
at
,
th
er
e
will
b
e
ex
p
lan
atio
n
o
n
t
h
e
way
th
at
th
e
to
o
l
m
ig
h
t
b
e
u
tili
ze
d
f
o
r
d
esig
n
in
g
L
o
R
a
W
AN
in
f
r
astru
ctu
r
e
with
r
eg
ar
d
t
o
3
s
m
ar
t c
am
p
u
s
o
u
td
o
o
r
ap
p
licatio
n
s
.
2.
F
O
G
CO
M
P
UT
I
NG
T
h
is
is
co
n
s
id
er
ed
as
o
n
e
o
f
t
h
e
d
is
tr
ib
u
ted
p
latf
o
r
m
s
wh
ic
h
m
ig
h
t
b
e
p
r
o
v
id
in
g
s
to
r
ag
e,
co
m
p
u
tin
g
,
as
well
as
n
etwo
r
k
in
g
s
er
v
ice
s
b
etwe
en
tr
ad
itio
n
al
clo
u
d
c
o
m
p
u
tin
g
an
d
I
o
T
d
e
v
ices.
T
h
e
d
ata
ce
n
ter
s
th
at
m
ig
h
t
b
e
r
esid
in
g
at
th
e
n
etw
o
r
k
’
s
ed
g
e
o
r
as
in
ter
n
al
n
o
d
es
r
elate
d
to
d
is
tr
ib
u
ted
en
v
ir
o
n
m
en
ts
[
9
]
.
Als
o
,
th
e
f
o
g
co
m
p
u
tin
g
m
ig
h
t
b
e
s
p
ec
if
ied
as
th
e
s
ce
n
ar
io
in
w
h
ich
s
o
m
e
u
b
iq
u
ito
u
s
an
d
d
e
-
ce
n
tr
alize
d
d
ev
ices
h
av
e
th
e
ab
ilit
y
o
f
p
e
r
f
o
r
m
in
g
m
a
n
y
task
s
in
wir
ele
s
s
an
d
o
f
ten
au
to
n
o
m
o
u
s
a
p
p
r
o
ac
h
m
ig
h
t
b
e
co
m
m
u
n
icatin
g
an
d
c
o
o
p
e
r
atin
g
v
ia
th
e
n
etwo
r
k
s
f
o
r
th
e
p
u
r
p
o
s
e
o
f
p
er
f
o
r
m
i
n
g
t
h
e
p
r
o
ce
s
s
in
g
task
s
an
d
s
to
r
e
th
e
d
ate
with
n
o
th
i
r
d
p
ar
ty
’
s
in
ter
v
en
tio
n
[
1
0
]
.
Su
ch
task
s
m
ig
h
t
b
e
s
u
p
p
o
r
tin
g
th
e
ess
en
tial
f
u
n
ctio
n
s
o
f
th
e
n
etwo
r
k
o
r
a
f
ew
n
ew
ap
p
licatio
n
s
an
d
s
er
v
ice
r
u
n
in
its
v
ir
tu
al
en
v
ir
o
n
m
e
n
t.
Fu
r
th
er
m
o
r
e,
th
e
f
o
g
co
m
p
u
tin
g
m
ig
h
t
b
e
s
p
ec
if
ied
as
o
n
e
o
f
th
e
p
latf
o
r
m
s
r
elate
d
to
d
is
tr
ib
u
ted
co
m
p
u
tin
g
ex
te
n
d
in
g
th
e
s
er
v
ices
p
r
o
v
id
e
d
v
ia
clo
u
d
d
atac
en
ter
s
at
n
etwo
r
k
’
s
I
o
T
d
ev
ices
[
1
1
]
.
T
h
e
f
o
g
co
m
p
u
tin
g
m
i
g
h
t
b
e
p
r
o
v
id
i
n
g
f
ac
ilit
y
s
u
ch
as
co
m
p
u
tin
g
’
s
au
to
m
ati
n
g
m
an
a
g
em
en
t,
in
a
d
d
itio
n
t
o
n
etwo
r
k
in
g
an
d
s
to
r
e
d
ate
b
etwe
en
I
o
T
d
ev
ices
an
d
clo
u
d
d
atac
en
ter
s
.
T
h
e
f
o
g
co
m
p
u
tin
g
in
clu
d
es
m
a
n
y
c
o
m
p
o
n
en
ts
r
elate
d
to
th
ese
ap
p
licatio
n
s
th
at
m
i
g
h
t
r
u
n
o
n
th
e
clo
u
d
in
a
d
d
itio
n
to
th
e
ed
g
e
d
e
v
ices
b
etwe
en
t
h
e
clo
u
d
an
d
s
en
s
o
r
,
also
it
is
p
r
o
v
id
in
g
f
ea
tu
r
es
s
u
ch
as
co
n
n
ec
tiv
ity
,
co
m
m
u
n
icatio
n
a
n
d
n
etwo
r
k
p
r
o
t
o
co
ls
,
co
m
p
u
tatio
n
al
r
eso
u
r
c
es,
m
o
b
ilit
y
,
also
in
ter
f
ac
e
h
eter
o
g
en
eity
to
th
e
clo
u
d
in
ad
d
itio
n
to
th
e
d
ata
an
aly
tics
r
elate
d
to
d
is
tr
ib
u
te
d
n
etwo
r
k
th
at
d
ea
l
with
a
lo
t
o
f
n
ec
ess
itie
s
o
f
v
ar
io
u
s
ap
p
licatio
n
s
with
s
o
m
e
r
eq
u
ir
em
e
n
ts
s
u
ch
as
lo
w
late
n
cy
in
ad
d
itio
n
to
d
en
s
e
an
d
wid
e
d
en
s
e
g
eo
g
r
ap
h
ical
d
is
tr
ib
u
tio
n
s
[
1
2
]
.
3.
DE
E
P
L
E
A
RNING
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
(
A
I
)
,
n
e
u
r
a
l
n
e
t
w
o
r
k
s
(
N
N
s
)
,
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
a
r
e
s
u
b
j
e
c
t
s
w
h
i
c
h
m
i
g
h
t
b
e
a
s
s
o
c
i
a
t
e
d
t
o
a
c
h
i
e
v
e
c
e
r
t
a
i
n
a
i
m
s
i
n
s
o
m
e
a
p
p
l
i
c
a
t
i
o
n
s
.
O
n
e
o
f
t
h
e
e
x
a
m
p
l
e
p
u
r
p
o
s
e
s
i
s
c
l
a
s
s
i
f
i
c
a
t
i
o
n
.
T
h
e
d
e
e
p
l
e
a
r
n
i
n
g
m
i
g
h
t
b
e
s
p
e
c
i
f
i
e
d
a
s
a
m
o
d
e
r
n
s
u
b
j
e
c
t
.
R
e
c
e
n
t
l
y
,
i
t
h
a
s
b
e
e
n
o
f
h
i
g
h
i
m
p
o
r
t
a
n
c
e
i
n
m
a
n
y
a
p
p
l
i
c
a
t
i
o
n
s
,
l
i
k
e
N
L
P
a
n
d
c
o
m
p
u
t
e
r
v
i
s
i
o
n
.
I
n
c
o
m
p
a
r
i
s
o
n
t
o
c
o
n
v
e
n
t
i
o
n
a
l
a
p
p
r
o
a
c
h
e
s
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
t
h
e
d
e
e
p
l
e
a
r
n
i
n
g
c
o
m
e
s
w
i
t
h
s
o
l
i
d
l
e
a
r
n
i
n
g
a
b
i
l
i
t
y
a
n
d
m
i
g
h
t
e
f
f
e
c
t
i
v
e
l
y
u
t
i
l
i
z
e
t
h
e
d
a
t
a
-
s
e
t
s
f
o
r
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
[
1
3
]
.
T
h
e
a
p
p
r
o
a
c
h
e
s
o
f
d
e
e
p
l
e
a
r
n
i
n
g
u
s
i
n
g
a
l
g
o
r
i
t
h
m
s
r
e
f
e
r
r
e
d
to
a
s
N
Ns
,
t
h
a
t
h
a
v
e
b
e
e
n
o
n
th
e
b
a
s
i
s
o
f
i
n
f
o
r
m
a
t
i
o
n
p
r
o
c
e
s
s
i
n
g
a
p
p
r
o
ac
h
e
s
r
e
l
a
te
d
t
o
b
i
o
l
o
g
i
c
a
l
n
e
r
v
o
u
s
s
y
s
te
m
l
i
k
e
b
r
a
i
n
a
n
d
s
u
ch
a
p
p
r
o
a
c
h
e
s
e
n
a
b
l
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
4
5
4
-
2462
2456
t
h
e
c
o
m
p
u
t
e
r
f
o
r
l
e
a
r
n
i
n
g
t
h
at
i
s
r
e
p
r
e
s
e
n
t
e
d
b
y
e
ac
h
d
a
t
a
an
d
w
h
a
t
is
m
e
a
n
t
v
ia
e
a
c
h
o
f
t
h
e
c
o
r
r
es
p
o
n
d
i
n
g
m
o
d
e
l
s
[
1
4
]
.
R
e
ce
n
t
l
y
,
t
h
e
d
ee
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
(
DN
Ns
)
s
h
o
w
e
d
s
i
g
n
i
f
i
c
a
n
t
p
e
r
f
o
r
m
a
n
c
e
i
n
t
h
e
t
as
k
s
o
f
i
m
a
g
e
c
l
a
s
s
i
f
ic
a
t
i
o
n
,
al
s
o
i
t
h
as
b
e
e
n
s
p
e
c
i
f
i
e
d
as
a
m
a
c
h
i
n
e
le
a
r
n
i
n
g
m
o
d
e
l
o
f
h
i
g
h
i
m
p
o
r
t
a
n
c
e
[
1
5
]
.
S
i
n
c
e
2
0
0
6
,
t
h
e
d
e
e
p
l
e
a
r
n
i
n
g
w
a
s
g
e
n
e
r
al
ly
u
t
i
l
i
z
e
d
w
it
h
t
h
e
a
d
v
a
n
c
e
m
en
t
s
i
n
s
p
e
e
c
h
r
e
c
o
g
n
it
i
o
n
.
D
e
ep
l
e
a
r
n
i
n
g
’
s
r
e
c
o
v
e
r
y
m
i
g
h
t
b
e
d
u
e
t
o
t
h
e
n
e
x
t
a
s
p
e
c
t
s
.
T
h
e
d
e
v
e
l
o
p
m
e
n
t
o
f
l
a
r
g
e
-
s
c
a
l
e
a
n
n
o
t
a
t
e
d
t
r
a
i
n
i
n
g
d
a
t
a
,
i
n
c
l
u
d
i
n
g
I
m
a
g
e
N
e
t
,
f
o
r
t
o
t
a
l
l
y
s
h
o
w
i
n
g
i
ts
e
x
t
r
em
e
l
y
l
a
r
g
e
c
a
p
a
ci
t
y
o
f
l
e
a
r
n
in
g
;
t
h
e
r
a
p
i
d
d
e
v
e
l
o
p
m
e
n
ts
o
f
h
i
g
h
-
p
e
r
f
o
r
m
a
n
c
e
p
a
r
a
l
l
e
l
c
o
m
p
u
t
i
n
g
s
y
s
t
e
m
s
,
i
n
c
l
u
d
i
n
g
t
h
e
G
P
U
c
l
u
s
t
e
r
s
;
m
a
jo
r
d
e
v
e
l
o
p
m
e
n
t
s
i
n
d
e
s
i
g
n
i
n
g
th
e
t
r
a
i
n
i
n
g
s
t
r
a
t
e
g
i
e
s
a
n
d
n
e
t
w
o
r
k
s
t
r
u
c
t
u
r
e
s
[
1
6
]
.
T
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
d
e
e
p
e
a
r
n
i
n
g
i
n
o
b
j
e
c
t
r
e
c
o
g
n
i
t
i
o
n
a
n
d
i
m
a
g
e
c
l
ass
i
f
i
c
at
i
o
n
p
r
e
s
e
n
t
e
d
m
a
j
o
r
a
d
v
a
n
c
e
m
e
n
ts
d
u
e
t
o
t
h
e
m
a
j
o
r
d
e
v
e
l
o
p
m
e
n
t
s
r
e
l
a
t
e
d
t
o
d
e
e
p
l
ea
r
n
i
n
g
.
4.
CO
NVO
L
U
T
I
O
NA
L
NE
UR
A
L
NE
T
WO
RK
S (
CN
N)
AI
,
NNs,
an
d
d
ee
p
lear
n
in
g
h
av
e
b
ee
n
s
u
b
jecte
d
wh
ic
h
m
i
g
h
t
b
e
ass
o
ciate
d
to
ac
h
iev
e
s
o
m
e
aim
s
in
s
o
m
e
ap
p
licatio
n
.
A
m
ajo
r
a
p
p
r
o
ac
h
f
o
r
estab
lis
h
in
g
m
o
d
e
r
n
d
ee
p
C
NNs
h
as
b
ee
n
v
ia
f
o
r
m
in
g
th
em
i
n
2
NN
lay
er
s
,
th
e
f
ir
s
t
o
n
e
h
as
b
ee
n
alter
n
atin
g
co
n
v
o
lu
tio
n
al,
wh
i
le
th
e
o
th
er
o
n
e
h
as
b
ee
n
m
ax
-
p
o
o
lin
g
,
th
ey
h
a
v
e
b
ee
n
f
o
llo
wed
v
ia
a
f
ew
lay
er
s
wh
ich
ar
e
d
ese,
also
b
ein
g
f
u
lly
-
co
n
n
ec
ted
[
1
7
]
.
An
y
o
n
e
o
f
th
e
3
D
v
o
lu
m
es
r
ep
r
esen
tin
g
lay
er
i
n
p
u
t
as
w
ell
as
b
ein
g
co
n
v
er
ted
i
n
to
o
th
er
3
D
v
o
l
u
m
e
f
o
r
f
ee
d
in
g
to
th
e
n
e
x
t
lay
e
r
.
I
n
th
e
co
n
s
id
er
e
d
e
x
am
p
le,
th
er
e
ar
e
5
c
o
n
v
o
lu
tio
n
al
lay
er
s
,
t
h
er
e
ar
e
3
lay
er
s
o
f
m
ax
-
p
o
o
li
n
g
ty
p
e,
also
th
er
e
ar
e
3
lay
er
s
wh
ich
ar
e
f
u
lly
-
c
o
n
n
ec
ted
[
1
7
]
.
Star
tin
g
f
r
o
m
th
e
ad
v
an
ce
m
e
n
t
in
th
e
y
ea
r
2
0
1
2
,
th
e
I
m
a
g
eNe
t
co
m
p
etitio
n
th
at
h
as
b
ee
n
ac
h
iev
ed
th
r
o
u
g
h
Alex
Net
r
ep
r
es
en
tin
g
th
e
f
ir
s
t
en
tr
y
wh
ich
u
tili
ze
d
d
ee
p
n
eu
r
al
n
etwo
r
k
(
DNN)
,
m
a
n
y
o
th
er
DNNs
with
m
o
r
e
c
o
m
p
lex
ity
wer
e
s
u
b
m
itted
t
o
th
e
ch
allen
g
e
f
o
r
th
e
p
u
r
p
o
s
e
o
f
ac
h
iev
in
g
g
o
o
d
p
er
f
o
r
m
a
n
ce
[
1
8
]
.
-
C
NN
l
ay
er
s
:
T
h
r
o
u
g
h
s
tack
in
g
d
if
f
er
en
t
an
d
m
u
ltip
le
lay
er
s
in
C
NN,
th
e
co
m
p
lex
ar
ch
itectu
r
es
h
av
e
b
ee
n
d
ev
elo
p
e
d
f
o
r
class
if
icatio
n
p
r
o
b
lem
s
[
1
9
]
.
-
C
o
n
v
o
lu
tio
n
la
y
er
s
:
T
h
is
is
th
e
in
itial
lay
er
u
tili
ze
d
f
o
r
ab
s
tr
ac
tin
g
th
e
f
ea
tu
r
es
f
r
o
m
in
p
u
t
im
ag
e
[
2
0
]
.
T
h
e
o
p
er
atio
n
o
f
co
n
v
o
lu
tio
n
is
ex
tr
ac
tin
g
v
ar
io
u
s
in
p
u
t
f
ea
tu
r
es.
Als
o
,
th
e
f
ir
s
t
co
n
v
o
lu
tio
n
lay
er
is
ex
tr
ac
tin
g
lo
w
-
lev
el
f
ea
tu
r
es
s
u
ch
as
c
o
r
n
er
s
,
lin
es,
an
d
ed
g
es.
L
ay
e
r
s
o
f
h
ig
h
er
-
lev
e
l
ar
e
ex
t
r
ac
tin
g
f
ea
tu
r
es o
f
h
ig
h
er
-
lev
el
[
2
1
]
.
-
Strid
es
lay
er
s
:
W
ith
r
eg
ar
d
t
o
C
NN,
a
s
tr
id
e
is
r
e
p
r
esen
tin
g
th
e
n
u
m
b
er
o
f
p
ix
el’
s
s
h
if
t
in
in
p
u
t
m
atr
ix
.
I
n
th
e
ca
s
e
wh
e
n
th
e
v
al
u
e
o
f
s
tr
id
e
is
o
n
e,
th
e
at
a
tim
e
,
a
f
ilter
m
ig
h
t
b
e
m
o
v
e
d
s
in
g
le
p
i
x
el.
I
n
t
h
e
ca
s
e
wh
en
th
e
v
alu
e
o
f
s
tr
id
e
is
2
,
th
en
at
a
tim
e,
f
ilter
s
h
av
e
b
e
en
m
o
v
ed
2
p
ix
els.
Als
o
,
o
th
e
r
s
tr
id
e’
s
v
alu
es
ar
e
co
m
p
a
r
ab
ly
c
o
n
s
id
er
ed
[
2
2
]
.
-
Pad
d
in
g
lay
er
s
:
I
n
ce
r
tain
ca
s
es,
th
e
f
ilter
s
ar
e
n
o
t
ad
eq
u
ately
f
it
f
o
r
th
e
s
p
ec
if
ied
in
p
u
t
im
ag
e.
I
n
s
u
ch
co
n
d
itio
n
s
,
th
e
r
e
ar
e
2
o
p
tio
n
s
:
a)
Valid
: in
d
icate
s
n
o
p
ad
d
in
g
b)
Z
er
o
-
p
a
d
d
in
g
: Sim
p
l
y
,
p
a
d
ze
r
o
s
in
th
e
p
ictu
r
e
to
g
et
a
f
it [
2
3
]
.
-
R
ec
tifie
d
lin
ea
r
u
n
i
t
(
R
eL
U)
l
ay
er
s
:
R
eL
U
is
co
n
s
id
er
ed
as o
n
e
o
f
th
e
n
o
n
-
li
n
ea
r
o
p
er
atio
n
s
,
also
it
in
s
er
ts
non
-
lin
ea
r
ity
in
C
NN
an
d
allo
win
g
ef
f
icien
t
an
d
r
a
p
id
tr
ain
i
n
g
v
ia
m
a
p
p
in
g
n
eg
ativ
e
v
alu
es
ze
r
o
as
well
as
to
m
ain
tain
p
o
s
itiv
e
v
alu
e
s
.
Fu
r
th
er
m
o
r
e,
t
h
er
e
ar
e
o
th
er
n
o
n
-
lin
ea
r
ities
s
u
ch
as
(
s
ig
m
o
id
)
o
r
(
tan
h
)
wh
ich
m
ig
h
t
b
e
r
ep
lacin
g
R
eL
U.
T
h
e
m
ajo
r
ity
o
f
d
esig
n
e
r
s
o
r
au
th
o
r
s
ar
e
u
s
in
g
R
eL
U
f
o
r
en
h
an
ce
d
p
er
f
o
r
m
an
ce
in
it
[
2
4
]
.
-
Po
o
lin
g
lay
er
:
T
h
e
p
r
esen
ted
s
ec
tio
n
is
co
n
tr
ib
u
tin
g
to
th
e
p
ar
am
eter
s
’
n
u
m
b
er
r
e
d
u
ctio
n
wh
en
th
ey
ar
e
lar
g
e
im
ag
e
s
.
T
h
e
s
p
atial
ty
p
e
p
o
o
lin
g
,
also
r
e
f
er
r
ed
to
as
d
o
wn
s
am
p
lin
g
,
o
r
s
u
b
-
s
am
p
lin
g
,
r
esu
lt
in
d
im
en
s
io
n
ality
r
e
d
u
ctio
n
r
elat
ed
to
ea
c
h
o
n
e
o
f
th
e
m
ap
s
an
d
k
ee
p
i
n
g
th
e
s
ig
n
if
ican
t
in
f
o
r
m
atio
n
.
A
f
ew
o
f
th
e
ty
p
es
r
elate
d
to
s
p
atial
ty
p
e
p
o
o
lin
g
h
a
v
e
b
ee
n
a
v
er
ag
e
p
o
o
lin
g
,
m
ax
-
p
o
o
lin
g
,
a
n
d
s
u
m
p
o
o
lin
g
.
T
h
e
m
a
x
p
o
o
lin
g
is
ass
u
m
in
g
th
e
b
ig
g
est
elem
en
t
in
m
o
d
if
ied
f
ea
tu
r
e
m
ap
.
Su
g
g
esti
n
g
th
e
b
i
g
g
est
elem
en
t
m
ig
h
t
b
e
ass
u
m
in
g
th
e
av
er
ag
e
p
o
o
lin
g
.
T
h
e
s
u
m
p
o
o
lin
g
is
p
r
o
d
u
ce
d
v
ia
s
u
m
m
i
n
g
all
elem
en
ts
o
f
f
ea
tu
r
e
m
ap
[
2
5
]
.
-
Fu
lly
co
n
n
ec
ted
la
y
er
s
(
FC
)
:
W
ith
r
eg
ar
d
to
s
u
ch
t
y
p
e,
th
e
m
atr
ix
o
f
in
te
r
est
h
as
b
ee
n
f
latten
ed
to
a
v
ec
to
r
f
o
r
m
as
well
as
in
p
u
t,
s
u
ch
as
NN.
T
h
er
e
ar
e
2
f
ea
t
u
r
es
r
elate
d
to
L
ay
er
(
L
-
1
)
,
ea
ch
o
n
e
o
f
th
em
h
as
b
ee
n
(
2
x
2
)
,
f
o
r
in
s
tan
ce
,
h
as
4
ele
m
en
ts
.
T
h
er
e
a
r
e
2
f
ea
tu
r
es
o
f
L
ay
er
(
L
)
,
ea
c
h
o
n
e
with
s
in
g
le
elem
en
t
[
2
6
]
.
I
n
s
u
ch
s
y
s
tem
,
th
e
m
atr
ix
r
eg
ar
d
in
g
th
e
f
ea
tu
r
e
m
ap
is
g
o
in
g
to
b
e
tu
r
n
ed
to
v
ec
t
o
r
s
(
x
1
,
x
2
,
x
3
…)
.
Mo
d
el’
s
cr
ea
tin
g
will
b
e
ac
h
iev
ed
v
ia
c
o
m
b
in
atio
n
o
f
f
ea
tu
r
es
with
th
e
u
s
e
o
f
FC
lay
er
s
.
L
astl
y
,
o
n
e
ac
tiv
atio
n
f
u
n
ctio
n
,
s
u
ch
as
“sig
m
o
id
”
o
r
“so
f
t
-
m
ax
”,
h
as
b
e
en
ap
p
lie
d
f
o
r
o
u
tp
u
t
class
if
ied
to
c
ateg
o
r
ies,
f
o
r
in
s
tan
ce
,
b
o
at,
h
o
u
s
e,
ca
t,
t
r
ee
,
etc.
[
2
7
]
.
5.
P
RO
P
O
SE
D
SYS
T
E
M
Usi
n
g
th
e
f
o
g
co
m
p
u
tin
g
s
tr
at
eg
ies an
d
tech
n
iq
u
es with
in
th
e
e
-
lea
r
n
in
g
en
v
ir
o
n
m
en
t is p
r
etty
u
s
ef
u
l
b
u
t
s
till
ch
allen
g
ea
b
le
f
iled
i
n
g
en
e
r
al
,
ch
allen
g
es
r
elate
d
to
th
is
to
p
ic
is
th
e
s
ec
u
r
ity
in
th
e
f
ir
s
t
p
lace
,
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
Mo
b
ile
lea
r
n
in
g
a
r
ch
itectu
r
e
u
s
in
g
fo
g
c
o
mp
u
tin
g
a
n
d
a
d
a
p
tive
…
(
S
h
yma
a
Mo
h
a
mme
d
Ja
mee
l
)
2457
th
e
ch
an
n
el
o
cc
u
p
an
cy
a
n
d
th
e
d
ata
s
tr
ea
m
in
g
o
f
th
e
c
o
n
ten
t
(
au
d
i
o
o
r
v
id
e
o
)
,
th
e
p
r
esen
ted
wo
r
k
is
s
u
g
g
esti
n
g
e
-
lear
n
in
g
s
y
s
tem
is
p
r
o
p
o
s
ed
th
at
tr
y
t
o
co
v
e
r
th
e
m
ain
is
s
u
es r
elate
d
to
th
e
g
en
er
al
co
n
ce
p
ts
u
s
ed
with
in
th
is
f
ield
,
th
e
d
ata
i
s
c
o
llected
an
d
p
r
ep
ar
e
d
f
r
o
m
d
if
f
er
en
t
ed
u
ca
tio
n
al
an
d
k
n
o
wn
au
d
io
/v
id
e
o
s
ites
th
an
it
co
n
te
n
t
ca
n
b
e
u
s
ed
a
s
an
e
-
lear
n
in
g
an
d
ac
co
r
d
in
g
to
th
e
p
r
ef
er
e
n
ce
s
o
f
t
h
e
u
s
er
th
e
d
ata
will
b
e
class
if
y
to
m
ee
t
th
at
p
r
ef
er
e
n
ce
an
d
to
p
r
o
v
id
e
th
e
c
o
r
r
elat
ed
d
ata
o
n
l
y
th
is
is
d
o
n
e
v
ia
u
s
in
g
th
e
p
o
wer
f
u
l
class
if
icatio
n
tech
n
iq
u
e
d
ee
p
lear
n
in
g
(
C
NN)
,
af
ter
th
at
th
e
ad
ap
tatio
n
o
f
t
h
e
a
u
d
io
/v
id
e
o
q
u
ality
is
d
o
n
e
t
o
en
s
u
r
e
th
e
q
u
ality
o
f
s
er
v
ice
(
QOS)
ac
co
r
d
in
g
to
th
e
av
ail
ab
le
lin
k
q
u
ality
,
th
e
r
esu
lt
o
f
th
is
is
an
ad
ap
tiv
e
q
u
ality
au
d
io
/v
i
d
eo
an
d
d
ata
is
r
ea
d
y
f
o
r
tr
an
s
m
it
an
d
in
o
r
d
er
to
p
r
o
tect
th
e
d
ata
s
ec
r
et
k
ey
en
cr
y
p
tio
n
alg
o
r
ith
m
u
s
ed
to
e
n
cr
y
p
t
th
e
d
ata
wh
ile
th
e
d
ata
is
s
tr
ea
m
ed
f
r
o
m
s
er
v
e
r
to
clien
t,
th
e
clien
t
th
en
r
ec
eiv
e
th
e
en
cr
y
p
ted
d
ata
a
n
d
i
n
h
i
s
d
ev
ice
th
e
d
ata
d
ec
r
y
p
ted
an
d
th
e
f
in
al
d
ata
f
o
r
m
e
d
a
n
d
v
iewe
d
to
h
im
.
Fig
u
r
e
1
s
h
o
win
g
th
e
g
e
n
er
al
ar
ch
itectu
r
e
r
elate
d
t
o
th
e
s
u
g
g
ested
s
y
s
tem
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
f
o
r
e
-
lear
n
in
g
e
n
v
ir
o
n
m
en
t
u
s
in
g
f
o
g
c
o
m
p
u
tin
g
tech
n
iq
u
es
tr
y
to
b
u
ild
ac
cu
r
ate
a
n
d
u
s
ab
le
p
latf
o
r
m
t
h
at
ca
n
h
o
ld
th
e
m
ain
is
s
u
es r
elate
d
to
s
u
ch
s
y
s
tem
,
th
is
s
y
s
tem
is
s
p
lit u
p
to
f
iv
e
m
ain
p
h
ases
ea
ch
p
h
ase
h
av
e
it o
wn
alg
o
r
ith
m
s
an
d
r
elate
d
in
ter
n
al
s
tep
s
,
th
e
p
h
ase
s
o
f
th
e
s
y
s
tem
ca
n
b
e
s
u
m
m
ar
ized
as
f
o
llo
w
as
s
h
o
wn
in
F
ig
u
r
e
1
an
d
A
lg
o
r
ith
m
1
.
Fig
u
r
e
1
.
G
en
e
r
al
ar
ch
itectu
r
e
o
f
th
e
s
u
g
g
ested
s
y
s
tem
1)
C
las
s
if
icatio
n
p
h
ase
I
n
th
is
p
h
ase
th
e
class
if
icatio
n
m
eth
o
d
u
s
ed
to
ch
ec
k
th
e
ac
tiv
ity
o
f
th
e
class
if
icatio
n
p
r
o
ce
s
s
is
th
e
d
ee
p
lear
n
in
g
c
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
,
th
is
p
h
ase
in
clu
d
es so
m
e
in
ter
n
al
s
tep
s
as f
o
llo
w:
−
Step
1
:
T
h
e
f
ir
s
t
s
tep
with
in
th
is
p
h
ase
wh
er
e
th
e
co
llected
d
ataset
id
e
n
ter
ed
to
t
h
e
s
y
s
tem
with
s
p
ec
ial
s
p
ec
if
icatio
n
(
ea
ch
d
ataset
m
e
m
b
er
co
n
s
is
t
o
f
3
co
lu
m
n
s
with
n
u
m
er
ic
d
ata
wh
ich
is
r
e
p
r
e
s
en
t
th
e
r
elate
d
in
f
o
r
m
atio
n
o
f
t
h
e
v
id
e
o
d
ata
f
iles
,
th
e
n
u
m
er
ic
d
ata
u
s
ed
as
m
etr
ic
f
o
r
th
e
d
ata
an
d
s
p
ec
ial
in
d
ex
in
g
o
f
it.
−
Step
2
:
T
h
e
co
llected
d
ata
n
ee
d
to
p
r
e
-
p
r
o
ce
s
s
b
ef
o
r
e
u
s
in
g
it
with
th
e
tr
ain
in
g
in
s
id
e
th
e
class
if
icatio
n
alg
o
r
ith
m
a
n
d
th
e
class
if
icati
o
n
p
r
o
ce
s
s
its
elf
,
th
e
f
ea
t
u
r
e
n
u
m
er
ic
n
u
m
b
er
s
r
elate
d
to
th
e
co
lu
m
n
s
in
s
tep
1
is
co
n
v
er
ted
t
o
r
ea
l n
u
m
b
er
to
u
s
e
it a
s
weig
h
t w
ith
in
t
h
e
s
y
s
tem
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
4
5
4
-
2462
2458
−
Step
3
:
T
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
s
t
e
p
i
s
d
o
n
e
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
(
C
N
N
)
,
t
h
e
r
e
s
u
l
t
o
f
s
u
c
h
s
t
e
p
i
s
t
h
e
u
s
e
r
p
r
e
f
e
r
e
n
c
e
.
T
h
e
c
l
a
s
s
i
f
i
ca
t
i
o
n
a
n
d
i
d
e
n
t
i
f
i
ca
t
i
o
n
s
t
e
p
a
r
e
d
o
n
e
u
s
i
n
g
t
w
o
m
a
i
n
m
e
t
h
o
d
s
(
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
(
C
N
N
)
a
n
d
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
al
g
o
r
i
th
m
s
)
w
h
i
c
h
m
e
e
t
t
h
e
c
o
n
t
e
x
t
a
w
a
r
e
l
ea
r
n
i
n
g
w
h
e
r
e
t
h
e
s
u
g
g
e
s
t
e
d
v
i
d
e
o
s
t
o
t
h
e
u
s
e
r
w
il
l
o
n
l
y
r
e
la
t
e
d
t
o
t
h
e
c
l
a
s
s
i
f
ic
a
t
i
o
n
r
e
s
u
l
ts
w
h
i
c
h
i
s
b
a
s
e
d
o
n
h
i
s
c
h
o
i
c
es
.
−
S
tep
4
: th
e
r
elate
d
s
u
b
ject
co
n
n
ec
ted
to
th
e
s
elec
ted
s
u
b
ject
o
f
th
e
u
s
er
is
s
h
o
ws with
in
th
e
s
y
s
tem
.
Fig
u
r
e
2
s
h
o
win
g
th
e
m
ajo
r
s
tep
s
o
f
class
if
icatio
n
p
h
ase
.
Alg
o
r
ith
m
1
.
Pro
p
o
s
ed
s
y
s
tem
I
n
p
u
t
:
A
c
q
u
i
r
e
d
a
t
a
b
a
se
e
l
e
me
n
t
s (v
i
d
e
o
a
n
d
a
u
d
i
o
)
(
s
e
r
v
e
r
si
d
e
)
O
u
t
p
u
t
:
a
u
d
i
o
/
v
i
d
e
o
v
i
e
w
(
c
l
i
e
n
t
si
d
e
)
Start
Phase 1 classification phase
step1: data (audio / video) Pre
-
processing.
Step2: apply the CNN classification algorithm
•
Run input layer.
•
Run hidden layers.
•
Run
output layer.
•
Output the classified data.
Phase 2 Adaptation phase
Step3: Check the bandwidth amount (link quality)
Step4: Check number of users request same video at same time (N)
Step5: Adaptively control according to link quality (A)
Step6: Check the effected quality
Step7: Calculate the new quality
Step8: Adaptive spatial resolution control
Phase 3 Security phase
Step9: Request user password
Step10: Encrypt using 3DES
Step11: Encrypted video data
Phase 4: Data streaming
phase
Step: data streamed inside channel
Phase 5: User interface phase
Step: Receive encrypted data
Step: Call user key
Step: Decrypt using 3DES
Step: Video, audio creation
Step: show to user
End
Fig
u
r
e
2
.
F
lo
wch
ar
t
o
f
class
if
icatio
n
u
s
in
g
C
NN
Ph
ase
1
Ph
ase
2
Ph
ase
3
Ph
ase
5
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
Mo
b
ile
lea
r
n
in
g
a
r
ch
itectu
r
e
u
s
in
g
fo
g
c
o
mp
u
tin
g
a
n
d
a
d
a
p
tive
…
(
S
h
yma
a
Mo
h
a
mme
d
Ja
mee
l
)
2459
2)
Ad
ap
tatio
n
p
h
ase
I
n
th
is
p
h
ase
th
e
p
r
o
b
lem
o
f
ch
an
n
el
ca
p
ac
ity
a
n
d
b
a
n
d
wid
th
av
ailab
ilit
y
s
o
lv
ed
b
y
ad
ju
s
tin
g
th
e
q
u
ality
o
f
th
e
au
d
io
/v
i
d
eo
u
s
in
g
p
r
o
p
er
tech
n
iq
u
e
s
an
d
eq
u
atio
n
s
to
r
ed
u
ce
th
e
r
eso
lu
tio
n
o
f
th
e
au
d
i
o
/v
id
eo
in
th
e
ca
s
e
wh
en
th
e
n
u
m
b
er
o
f
u
s
er
s
r
eq
u
ests
th
e
s
am
e
v
id
e
o
at
th
e
s
a
m
e
tim
e
is
h
u
g
e
an
d
th
e
d
ata
n
ee
d
to
b
e
s
en
t
to
u
s
er
s
at
th
e
s
am
e
tim
e
a
n
d
th
e
ch
an
n
el
b
an
d
wid
th
will
n
o
t
b
e
av
ailab
le
an
d
th
e
g
en
er
al
co
n
ce
p
t
o
f
f
o
g
c
o
m
p
u
tin
g
was
u
s
ed
with
in
t
h
e
p
r
o
p
o
s
ed
s
y
s
tem
.
Fig
u
r
e
3
an
d
A
lg
o
r
ith
m
2
s
u
m
m
ar
ize
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
y
r
elate
d
to
m
o
b
ile
v
id
eo
s
tr
ea
m
in
g
s
y
s
tem
u
s
in
g
ad
ap
tiv
e
s
p
atial
r
eso
lu
tio
n
co
n
tr
o
l;
th
is
m
et
h
o
d
will
b
e
ass
ig
n
ed
to
th
e
s
er
v
er
s
id
e
to
t
h
e
s
y
s
tem
as
s
h
o
w
n
in
F
ig
u
r
e
1
wh
er
e
th
e
clien
t
s
id
e
will
ac
ce
p
t
th
e
o
u
tp
u
t
r
eso
lu
tio
n
v
id
e
o
s
tr
ea
m
in
g
with
o
u
t
h
av
in
g
a
n
y
d
ec
is
io
n
to
th
e
r
e
-
s
izin
g
o
f
th
e
r
eso
lu
tio
n
.
T
h
e
s
y
s
tem
o
wn
er
(
ad
m
in
)
will
s
etu
p
th
e
b
est
r
eso
lu
tio
n
o
f
th
e
v
id
eo
wh
en
m
an
y
n
u
m
b
er
s
o
f
u
s
er
s
ar
e
with
in
th
e
s
y
s
tem
r
eq
u
esti
n
g
th
e
s
am
e
v
id
eo
f
o
r
d
ata
s
tr
ea
m
in
g
ac
co
r
d
i
n
g
to
en
er
g
y
c
o
n
s
u
m
p
tio
n
a
n
d
b
est
av
ailab
le
p
ictu
r
e
q
u
ality
p
r
o
v
i
d
in
g
th
e
a
v
ailab
le
b
it
-
r
ate
an
d
in
p
u
t v
id
e
o
ac
co
r
d
in
g
to
n
u
m
b
er
o
f
s
y
s
tem
u
s
er
s
.
T
h
e
n
ew
r
eso
lu
tio
n
o
f
th
e
c
h
o
s
en
v
i
d
eo
is
p
r
ep
ar
ed
a
n
d
d
o
wn
s
am
p
led
to
th
e
ca
lcu
l
ated
r
eso
lu
tio
n
an
d
en
co
d
ed
v
ia
th
e
en
co
d
er
.
T
h
e
d
ec
o
d
er
o
n
th
e
u
s
er
d
ev
ice
(
m
o
b
ile
ap
p
licatio
n
)
wh
en
r
ec
eiv
e
th
e
b
itra
te
an
d
th
e
u
p
-
s
am
p
les it will d
ec
o
d
e
t
h
e
v
id
eo
an
d
d
is
p
lay
it o
n
s
cr
e
en
(
af
ter
e
n
cr
y
p
tio
n
/d
ec
r
y
p
tio
n
p
r
o
ce
s
s
is
d
o
n
e
)
.
Fig
u
r
e
3
.
Ar
c
h
itectu
r
e
o
f
p
r
o
p
o
s
ed
ad
ap
tiv
e
v
id
eo
s
tr
ea
m
in
g
s
y
s
tem
Alg
o
r
ith
m
2
.
Ad
ap
tiv
e
v
id
eo
s
tr
ea
m
in
g
I
n
p
u
t
:
v
i
d
e
o
r
e
so
l
u
t
i
o
n
,
n
u
m
b
e
r
o
f
a
c
c
e
p
t
e
d
r
e
d
u
c
t
i
o
n
o
f
q
u
a
l
i
t
y
(
M
)
,
n
u
m
b
e
r
o
f
u
sers
a
t
t
h
e
sam
e
t
i
m
e
(
N
)
,
A
=
a
d
a
p
t
i
v
e
l
y
c
o
n
t
r
o
l
o
f
t
h
i
s
v
i
d
e
o
O
u
t
p
u
t
:
n
e
w
o
u
t
p
u
t
r
e
s
o
l
u
t
i
o
n
Start
Step1: if N > A the goto step 3
Step2: if N<=A then F=1 AND find new resolution
New resolution =
ℎ
∗
ℎ
ℎ
Goto step 5
Step3: calculate F
F=
Step4: find new resolution
New resolution =
ℎ
∗
ℎ
ℎ
∗
Step5: reduce the resolution and send the new video to all channels
End
T
h
e
ad
ap
tiv
ely
is
co
n
tr
o
lled
b
y
th
e
s
er
v
er
ad
m
in
o
r
alg
o
r
i
th
m
,
s
in
ce
th
e
r
eso
lu
tio
n
o
f
t
h
e
v
id
eo
is
ca
n
n
o
t
r
ed
u
ce
d
to
u
n
lim
ited
n
u
m
b
er
o
f
tim
es,
wh
er
e
th
e
v
id
eo
co
n
te
n
t
will
d
is
ap
p
ea
r
an
d
ca
n
n
o
t
b
e
u
n
d
er
s
tan
d
a
b
le,
th
e
s
y
s
tem
ad
m
in
(
s
er
v
e
r
o
wn
e
r
)
will
i
n
d
ic
ate
th
e
n
u
m
b
er
o
f
tim
es
th
at
th
e
m
ax
q
u
ality
o
f
t
h
e
v
id
eo
r
ed
u
ce
d
,
if
th
e
n
u
m
b
er
o
f
u
s
er
will
r
ef
lect
th
e
r
eq
u
ested
n
u
m
b
er
t
h
en
th
e
n
ew
v
i
d
eo
r
eso
lu
tio
n
will
b
e
f
o
u
n
d
ed
an
d
s
en
d
to
all
u
s
e
r
s
o
f
th
e
s
y
s
tem
if
n
o
t th
en
t
h
e
f
o
llo
win
g
e
q
u
atio
n
will b
e
a
p
p
lied
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
4
5
4
-
2462
2460
=
ℎ
∗
ℎ
ℎ
∗
w
h
er
e
len
g
th
a
n
d
h
eig
h
t is th
e
v
id
eo
r
eso
lu
tio
n
,
N
r
ep
r
esen
tin
g
t
h
e
n
u
m
b
er
o
f
u
s
er
s
r
eq
u
ested
th
e
v
id
eo
s
tr
ea
m
in
g
at
s
am
e
tim
e
a
n
d
F
is
th
e
f
ac
to
r
th
at
ad
ap
ts
th
e
r
eso
lu
tio
n
a
n
d
v
i
d
eo
q
u
ality
wh
ich
is
ca
lcu
lated
as f
o
llo
w:
=
/
I
n
wh
ic
h
M
r
ep
r
esen
tin
g
t
h
e
n
u
m
b
er
o
f
u
s
er
s
p
r
ef
e
r
b
y
th
e
s
y
s
tem
ad
m
in
(
t
h
e
r
eso
l
u
tio
n
wh
er
e
th
e
s
y
s
tem
b
elo
w
it will n
o
t b
e
r
ec
o
g
n
iza
b
le)
.
E
.
g
.
if
=
10
an
d
th
e
p
r
ef
e
r
ab
le
n
u
m
b
er
b
y
ad
m
in
is
=
3
th
e
r
esu
lt wi
ll b
e
as f
o
llo
w:
3
/
10
=
0
.
3
wh
ich
will r
ep
r
esen
t th
e
s
ca
le
f
ac
to
r
o
f
th
e
s
y
s
tem
E
x
am
p
le
1
:
v
id
e
o
1
r
eso
lu
tio
n
is
600
∗
600
an
d
th
e
r
eso
lu
tio
n
s
etu
p
b
y
ad
m
in
t
h
at
it
ca
n
b
e
r
e
d
u
ce
d
to
4
tim
es (
A
=
ad
ap
tiv
ely
co
n
tr
o
l a
cc
o
r
d
in
g
to
lin
k
q
u
ality
)
a
n
d
-
4
u
s
er
s
o
r
d
e
r
th
e
v
i
d
eo
th
e
n
=
ℎ
∗
ℎ
ℎ
∗
Sin
ce
n
u
m
b
er
o
f
u
s
er
s
is
<=
A
th
en
F=1
600
∗
600
4
∗
1
An
d
th
e
r
eso
lu
tio
n
will b
e
d
is
tr
ib
u
ted
o
n
f
o
u
r
c
h
an
n
els.
-
1
0
u
s
er
s
o
r
d
er
th
e
v
id
eo
t
h
en
=
ℎ
∗
ℎ
ℎ
∗
Sin
ce
n
u
m
b
er
o
f
u
s
er
s
is
>
A
th
en
=
wh
ich
is
4
10
=
0
.
4
600
∗
600
10
∗
0
.
4
An
d
th
e
r
eso
lu
tio
n
will
b
e
d
is
tr
ib
u
ted
o
n
f
o
u
r
e
v
en
i
f
th
e
u
s
er
s
ar
e
1
0
to
k
ee
p
th
e
q
u
ality
with
th
e
ac
ce
p
ted
lev
els.
3)
Secu
r
ity
p
h
ase
A
p
r
o
b
lem
ass
o
ciate
d
to
u
s
in
g
f
o
g
co
m
p
u
tin
g
tech
n
o
lo
g
y
h
as
b
ee
n
th
e
s
ec
u
r
ity
is
s
u
es,
with
in
th
is
wo
r
k
a
p
r
iv
ate
k
ey
m
eth
o
d
u
s
ed
to
e
n
cr
y
p
t
th
e
d
ata
tr
a
n
s
m
itted
f
r
o
m
s
er
v
er
-
s
id
e
to
clien
t
-
s
id
e
in
s
id
e
th
e
f
o
g
co
m
p
u
tin
g
m
ap
w
h
ich
is
3
D
E
S.
T
h
is
alg
o
r
ith
m
will
b
e
i
n
b
o
th
s
er
v
e
r
-
s
id
e
(
f
o
r
en
c
r
y
p
t
io
n
)
an
d
clien
t
-
s
id
e
(
f
o
r
d
ec
r
y
p
tio
n
)
an
d
th
e
k
e
y
f
o
r
th
is
o
p
e
r
atio
n
is
th
e
u
s
er
p
ass
wo
r
d
.
T
h
e
d
e
v
elo
p
in
g
a
s
y
s
tem
o
f
e
-
lear
n
in
g
wh
ich
h
as
b
ee
n
o
n
th
e
b
asis
o
f
f
o
g
co
m
p
u
tin
g
co
n
ce
p
ts
with
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es
u
tili
ze
d
f
o
r
class
if
icatio
n
to
th
e
d
ata
co
n
te
n
t f
o
r
ac
c
o
m
p
lis
h
in
g
th
e
co
n
te
x
t a
war
e
lear
n
in
g
an
d
u
s
e
th
e
ad
ap
tatio
n
o
f
v
id
e
o
q
u
ali
ty
u
s
in
g
s
p
ec
ial
e
q
u
atio
n
an
d
th
e
d
ata
en
c
r
y
p
ted
a
n
d
d
ec
r
y
p
ted
u
s
in
g
3
DE
S
a
lg
o
r
ith
m
to
e
n
s
u
r
e
th
e
s
ec
u
r
ity
s
id
e
o
f
t
h
e
o
p
e
r
atio
n
.
4)
Data
s
tr
ea
m
in
g
p
h
ase
T
h
e
d
ata
o
f
th
e
v
id
eo
s
tr
ea
m
e
d
as
b
its
u
s
in
g
th
e
ch
an
n
el
o
f
th
e
v
id
eo
s
tr
ea
m
in
g
w
h
ich
b
a
s
ed
o
n
f
o
g
co
m
p
u
tin
g
th
is
allo
w
th
e
clien
t
o
n
th
e
s
er
v
er
s
id
e
to
v
i
ew
th
e
v
id
eo
with
o
u
t
th
e
n
e
ed
to
d
o
wn
l
o
ad
it.
T
h
e
d
ata
Stre
am
in
g
is
co
n
tin
u
o
u
s
ly
g
en
e
r
ated
b
y
d
if
f
er
e
n
t
s
o
u
r
ce
s
.
An
d
it
p
r
o
ce
s
s
ed
in
cr
em
en
tally
u
s
in
g
Stre
am
Pro
ce
s
s
in
g
tech
n
iq
u
es
with
o
u
t
n
ee
d
s
to
ac
ce
s
s
to
all
d
ata.
I
n
ad
d
itio
n
,
it
is
u
s
u
ally
u
s
ed
in
th
e
co
n
tex
t
o
f
b
ig
d
ata
in
wh
ich
it is
g
en
er
ated
b
y
m
a
n
y
d
if
f
er
en
t so
u
r
ce
s
at
h
ig
h
s
p
ee
d
.
5)
User
in
ter
f
ac
e
p
h
ase
T
h
e
d
ata
r
ec
eiv
ed
o
n
th
e
cli
en
t
s
id
e
(
m
o
b
ile
p
h
o
n
e
)
with
p
r
o
g
r
am
m
e
d
ap
p
licatio
n
u
s
i
n
g
an
d
r
o
id
s
tu
d
io
th
at
will
d
ec
r
y
p
t
th
e
d
a
ta
en
cr
y
p
ted
in
th
e
s
er
v
e
r
s
id
e
u
s
in
g
th
e
u
s
er
p
ass
wo
r
d
an
d
s
h
o
w
th
e
v
id
eo
o
n
th
e
u
s
er
d
ev
ice.
Sy
s
tem
o
u
tc
o
m
e
m
a
n
y
d
ataset
elem
en
ts
wer
e
u
s
ed
to
test
s
th
e
ac
tiv
ity
o
f
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
,
th
e
u
s
er
p
r
e
f
er
en
c
es set u
p
s
i
x
tim
es e
ac
h
tim
e
t
h
e
u
s
er
r
eq
u
ests
s
p
ec
ial
lectu
r
e
an
d
th
e
n
u
m
b
er
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
Mo
b
ile
lea
r
n
in
g
a
r
ch
itectu
r
e
u
s
in
g
fo
g
c
o
mp
u
tin
g
a
n
d
a
d
a
p
tive
…
(
S
h
yma
a
Mo
h
a
mme
d
Ja
mee
l
)
2461
u
s
er
s
r
eq
u
ested
th
e
s
am
e
lect
u
r
e
is
ch
an
g
ed
3
tim
es,
with
in
th
e
test
ed
f
r
a
m
ewo
r
k
with
d
ata
s
et
elem
en
ts
,
th
e
n
etwo
r
k
ad
m
in
s
et
th
at
th
ese
r
eso
lu
tio
n
s
ca
n
b
e
r
ed
u
ce
q
u
ality
4
tim
es m
ax
im
u
m
ac
co
r
d
in
g
to
lin
k
q
u
ality
at
th
e
m
o
m
en
t
o
f
r
e
q
u
esti
n
g
th
e
v
id
eo
a
n
d
2
s
ce
n
ar
io
s
ass
u
m
ed
wh
er
e:
a)
O
n
e
u
s
er
r
eq
u
est
th
e
v
id
eo
s
=
ℎ
∗
ℎ
ℎ
∗
N=
n
u
m
b
er
o
f
u
s
er
s
=1
,
F=1
s
in
ce
th
e
n
u
m
b
er
o
f
u
s
er
is
<=
th
e
n
u
m
b
e
r
ass
ig
n
ed
b
y
th
e
s
y
s
tem
ac
co
r
d
in
g
to
th
e
lin
k
q
u
ality
.
484
∗
360
1
∗
1
Sam
e
q
u
ality
will st
r
ea
m
to
th
e
r
eq
u
ested
u
s
er
.
b)
1
0
u
s
er
s
o
r
d
er
th
e
v
id
eo
t
h
en
=
ℎ
∗
ℎ
ℎ
∗
Sin
ce
n
u
m
b
er
o
f
u
s
er
s
is
>
A
th
en
=
wh
ich
is
4
10
=
0
.
4
484
∗
360
10
∗
0
.
4
An
d
th
e
r
eso
lu
tio
n
will
b
e
d
is
tr
ib
u
ted
o
n
f
o
u
r
ev
en
i
f
th
e
u
s
er
s
ar
e
1
0
to
k
ee
p
t
h
e
q
u
ality
with
th
e
ac
ce
p
ted
lev
els.
T
ab
le
1
s
h
o
w
th
e
ex
p
er
im
en
ts
r
esu
lts
o
f
th
e
v
id
eo
s
af
ter
ap
p
ly
in
g
th
e
q
u
ality
r
ed
u
ctio
n
.
In
o
r
d
er
to
c
h
ec
k
t
h
e
ef
f
ec
tiv
ely
r
elate
d
t
o
th
e
s
u
g
g
ested
s
y
s
tem
it
h
as
b
ee
n
co
m
p
ar
ed
to
s
o
m
e
o
f
th
e
s
u
g
g
ested
s
y
s
tem
with
in
th
e
s
am
e
f
ield
as sh
o
wn
i
n
T
ab
le
2
.
T
ab
le
1
.
E
x
p
er
im
en
ts
r
esu
lts
o
f
th
e
v
id
e
o
s
af
ter
ap
p
ly
in
g
t
h
e
q
u
ality
r
ed
u
ctio
n
N
o
.
Le
c
t
u
r
e
n
a
me
R
e
s
o
l
u
t
i
o
n
R
e
s
o
l
u
t
i
o
n
/
2
R
e
s
o
l
u
t
i
o
n
/
4
(
W
i
d
t
h
H
i
g
h
)
(
W
i
d
t
h
H
i
g
h
)
(
W
i
d
t
h
H
i
g
h
)
1.
C
+
+
p
r
o
g
r
a
mi
n
g
L
a
n
g
u
a
g
e
4
8
4
3
6
0
2
4
2
1
8
0
1
2
1
90
2.
I
n
t
r
o
d
u
c
t
i
o
n
t
o
D
a
t
a
M
i
n
i
n
g
1
2
8
0
7
2
0
6
4
0
3
6
0
3
2
0
1
8
0
3.
H
u
b
,
S
w
i
t
c
h
,
&
R
o
u
t
e
r
W
h
a
t
's
t
h
e
d
i
f
f
e
r
e
n
c
e
1
4
4
0
1
0
8
0
7
2
0
4
5
0
3
6
0
2
7
0
4.
N
e
t
w
o
r
k
S
e
c
u
r
i
t
y
1
9
2
0
1
0
8
0
9
6
0
5
4
0
4
8
0
2
7
0
5.
S
e
l
f
-
O
r
g
a
n
i
z
i
n
g
M
a
p
s
6
4
0
4
8
0
3
2
0
2
4
0
1
6
0
1
2
0
6.
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
V
s.
C
o
mp
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
8
5
4
4
8
0
4
2
7
2
4
0
2
1
3
1
2
0
T
ab
le
2
.
B
r
ief
o
f
an
aly
s
is
o
f
d
if
f
er
en
t f
ea
t
u
r
es p
r
o
v
id
ed
p
u
t c
o
m
p
ar
ed
to
o
th
e
r
m
o
d
els
F
e
a
t
u
r
e
s
[
6
]
[
7
]
[
8
]
P
r
o
p
o
se
d
s
y
st
e
m
D
e
t
e
c
t
s
a
n
d
t
a
k
e
s
i
n
t
o
a
c
c
o
u
n
t
t
h
e
r
e
a
l
-
w
o
r
l
d
c
o
n
t
e
x
t
s (r
e
a
l
e
d
u
c
a
t
i
o
n
a
l
v
i
d
e
o
s)
No
No
Y
e
s
Y
e
s
S
i
t
u
a
t
e
s
l
e
a
r
n
e
r
s
i
n
m
o
r
e
t
h
a
n
o
n
e
l
e
a
r
n
i
n
g
s
c
e
n
a
r
i
o
Y
e
s
Y
e
s
Y
e
s
Y
e
s
A
d
a
p
t
i
n
g
l
e
a
r
n
i
n
g
c
o
n
t
e
n
t
f
o
r
i
n
d
i
v
i
d
u
a
l
l
e
a
r
n
e
r
s
Y
e
s
No
No
Y
e
s
A
d
a
p
t
i
n
g
l
e
a
r
n
i
n
g
i
n
t
e
r
f
a
c
e
f
o
r
i
n
d
i
v
i
d
u
a
l
l
e
a
r
n
e
r
s
No
No
No
Y
e
s
P
r
o
v
i
d
e
s l
e
a
r
n
i
n
g
g
u
i
d
a
n
c
e
o
r
s
u
p
p
o
r
t
a
c
r
o
ss
c
o
n
t
e
x
t
s
No
No
Y
e
s
Y
e
s
C
o
n
si
d
e
r
i
n
g
o
n
l
i
n
e
l
e
a
r
n
i
n
g
s
t
a
t
u
s
o
f
l
e
a
r
n
e
r
s
No
Y
e
s
No
Y
e
s
L
e
a
r
n
i
n
g
f
r
o
m
p
r
e
v
i
o
u
s
i
m
p
l
e
m
e
n
t
a
t
i
o
n
s
a
n
d
t
h
u
s
c
h
a
n
g
i
n
g
t
h
e
c
o
n
t
e
n
t
No
No
No
Y
e
s
6.
CO
NCLU
SI
O
N
:
T
h
e
u
s
e
o
f
m
o
b
i
l
e
d
e
v
i
c
e
s
s
u
c
h
a
s
l
a
p
t
o
p
s
,
t
a
b
l
e
t
s
,
a
n
d
s
m
a
r
t
-
p
h
o
n
e
s
,
a
r
e
m
a
k
i
n
g
t
h
e
p
r
o
c
e
s
s
o
f
l
e
a
r
n
i
n
g
m
o
r
e
e
f
f
e
c
t
i
v
e
,
s
i
m
p
l
e
a
n
d
p
e
r
s
o
n
a
l
.
M
o
b
i
l
e
l
e
a
r
n
i
n
g
i
s
t
h
e
t
e
r
m
p
r
o
v
i
d
e
d
f
o
r
s
u
c
h
l
e
a
r
n
i
n
g
t
y
p
e
.
T
h
e
m
o
b
i
l
e
l
e
a
r
n
i
n
g
m
i
g
h
t
b
e
u
t
i
l
i
z
e
d
a
l
o
n
g
w
i
t
h
t
h
e
e
-
l
e
a
r
n
i
n
g
a
n
d
u
b
i
q
u
i
t
o
u
s
l
e
a
r
n
i
n
g
,
a
l
s
o
i
t
m
i
g
h
t
b
e
s
p
e
c
i
f
i
e
d
a
s
a
s
u
b
-
s
e
t
r
e
g
a
r
d
i
n
g
e
l
e
c
t
r
o
n
i
c
-
l
e
a
r
n
i
n
g
w
h
i
c
h
i
n
v
o
l
v
e
s
u
s
i
n
g
m
o
b
i
l
e
d
e
v
i
c
e
s
f
o
r
a
l
l
o
w
i
n
g
t
h
e
p
r
o
c
e
s
s
o
f
l
e
a
r
n
i
n
g
a
n
y
t
i
m
e
a
n
d
a
n
y
w
h
e
r
e
.
I
n
t
h
i
s
p
a
p
e
r
a
p
r
o
p
o
s
e
d
a
r
c
h
i
t
e
c
t
u
r
e
o
f
f
o
g
-
b
a
s
e
d
e
-
le
a
r
n
i
n
g
f
r
a
m
e
w
o
r
k
u
s
i
n
g
m
a
n
y
t
e
c
h
n
i
q
u
e
s
r
e
l
a
t
e
d
t
o
t
h
e
m
a
i
n
m
a
n
n
e
r
o
f
t
h
e
s
y
s
t
e
m
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
c
l
a
s
s
i
f
y
i
n
g
t
h
e
d
a
t
a
t
o
c
o
m
p
l
y
w
i
t
h
u
s
e
r
p
r
e
f
e
r
e
n
c
e
s
a
n
d
q
u
a
l
i
t
y
a
d
a
p
t
a
t
i
o
n
t
o
c
h
a
n
g
e
v
i
d
e
o
r
e
s
o
l
u
t
i
o
n
w
h
i
l
e
s
e
n
d
i
t
v
i
a
d
a
t
a
s
t
r
e
a
m
i
n
g
a
n
d
t
h
e
s
e
n
t
d
a
t
a
w
e
r
e
e
n
c
r
y
p
t
e
d
u
s
i
n
g
3
D
E
S
.
T
h
e
b
e
n
e
f
i
t
s
o
f
t
h
e
f
r
a
m
e
w
o
r
k
a
r
e
t
o
m
e
e
t
t
h
e
u
s
e
r
(
s
t
u
d
e
n
t
n
e
e
d
s
)
a
n
d
u
s
i
n
g
f
o
g
c
o
m
p
u
t
i
n
g
w
h
i
c
h
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
4
5
4
-
2462
2462
f
a
s
t
e
r
t
h
a
n
o
t
h
e
r
t
e
c
h
n
i
q
u
e
s
.
T
h
e
p
r
e
s
e
n
t
e
d
s
t
u
d
y
w
o
r
k
s
o
n
d
e
v
e
l
o
p
i
n
g
a
s
y
s
t
e
m
o
f
e
-
l
e
a
r
n
i
n
g
w
h
i
c
h
h
a
s
b
e
e
n
o
n
t
h
e
b
a
s
i
s
o
f
f
o
g
c
o
m
p
u
t
i
n
g
c
o
n
c
e
p
t
s
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
u
t
i
l
i
z
e
d
f
o
r
c
l
a
s
s
i
f
i
c
a
t
i
o
n
t
o
t
h
e
d
a
t
a
c
o
n
t
e
n
t
f
o
r
a
c
c
o
m
p
l
i
s
h
i
n
g
t
h
e
c
o
n
t
e
x
t
a
w
a
r
e
l
e
a
r
n
i
n
g
a
n
d
u
s
e
t
h
e
a
d
a
p
t
a
t
i
o
n
o
f
v
i
d
e
o
q
u
a
l
i
t
y
u
s
i
n
g
s
p
e
c
i
a
l
e
q
u
a
t
i
o
n
a
n
d
t
h
e
d
a
t
a
e
n
c
r
y
p
t
e
d
a
n
d
d
e
c
r
y
p
t
e
d
u
s
i
n
g
3
D
E
S
a
l
g
o
r
i
t
h
m
t
o
e
n
s
u
r
e
t
h
e
s
e
c
u
r
i
t
y
s
i
d
e
o
f
t
h
e
o
p
e
r
a
t
i
o
n
.
RE
F
E
R
E
NC
E
S
[1
]
H.
Cro
m
p
t
o
n
,
"
A h
ist
o
rica
l
o
v
e
rv
iew
o
f
m
o
b
il
e
lea
rn
i
n
g
:
To
wa
r
d
l
e
a
rn
e
r
-
c
e
n
tere
d
e
d
u
c
a
ti
o
n
,
"
Ha
n
d
b
o
o
k
o
f
M
o
b
il
e
Lea
rn
in
g
,
p
p
.
3
-
14
,
R
o
u
t
led
g
e
,
2
0
1
3
[
2
]
E
r
i
c
K
l
o
p
f
e
r
,
K
u
r
t
S
q
u
i
r
e
,
e
t
a
l
.
,
"
E
n
v
i
r
o
n
m
e
n
t
a
l
d
e
t
e
c
t
i
v
e
s
:
P
D
A
s
a
s
a
w
i
n
d
o
w
i
n
t
o
a
v
i
r
t
u
a
l
s
i
m
u
l
a
t
e
d
w
o
r
l
d
,
"
P
r
o
c
e
e
d
i
n
g
s
.
I
E
E
E
I
n
t
e
r
n
a
t
i
o
n
a
l
W
o
r
k
s
h
o
p
o
n
W
i
r
e
l
e
s
s
a
n
d
M
o
b
i
l
e
T
e
c
h
n
o
l
o
g
i
e
s
i
n
E
d
u
c
a
t
i
o
n
,
p
p
.
9
5
-
98
,
2002.
[3
]
He
n
d
rik
T
h
ü
s,
M
o
h
a
m
e
d
Am
in
e
Ch
a
tt
i
,
e
t
a
l.
,
"
M
o
b
il
e
lea
r
n
i
n
g
i
n
c
o
n
tex
t
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
T
e
c
h
n
o
l
o
g
y
En
h
a
n
c
e
d
L
e
a
rn
i
n
g
,
v
o
l.
4
,
n
o
.
5
-
6
,
p
p
.
3
3
2
-
3
4
4
,
2
0
1
2
.
[4
]
Y.
K.
Wan
g
,
“
C
o
n
te
x
t
a
wa
re
n
e
ss
a
n
d
a
d
a
p
tatio
n
i
n
m
o
b
il
e
lea
rn
in
g
,”
T
h
e
2
n
d
IE
EE
I
n
ter
n
a
ti
o
n
a
l
W
o
rk
sh
o
p
o
n
W
ire
les
s a
n
d
M
o
b
i
le
T
e
c
h
n
o
lo
g
ie
s in
E
d
u
c
a
ti
o
n
,
p
p
.
1
5
4
-
1
5
8
,
2
0
0
4
.
[5
]
Ra
m
u
P
a
ru
p
a
ll
i,
S
a
ra
t
Ch
a
n
d
ra
Ba
b
u
Ne
latu
ru
,
a
n
d
D
h
a
n
a
n
d
e
r
Ku
m
a
r
Ja
in
.
"
Th
e
ro
le
o
f
c
o
n
ten
t
a
d
a
p
tati
o
n
i
n
u
b
i
q
u
it
o
u
s
lea
rn
in
g
,
”
2
0
1
1
IE
EE
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
T
e
c
h
n
o
l
o
g
y
f
o
r E
d
u
c
a
t
io
n
,
p
p
.
1
7
7
-
1
8
2
,
2
0
1
1
.
[6
]
Weiq
in
g
Zh
a
o
,
Ya
fe
i
S
u
n
,
a
n
d
Li
ju
a
n
Da
i.
"
Im
p
ro
v
in
g
c
o
m
p
u
ter b
a
si
c
tea
c
h
in
g
th
r
o
u
g
h
m
o
b
il
e
c
o
m
m
u
n
ica
ti
o
n
a
n
d
c
lo
u
d
c
o
m
p
u
ti
n
g
tec
h
n
o
lo
g
y
,
"
2
0
1
0
3
r
d
In
ter
n
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
d
Co
mp
u
te
r
T
h
e
o
ry
a
n
d
En
g
i
n
e
e
rin
g
(ICAC
T
E)
,
p
p
.
V1
-
4
5
2
,
2
0
1
0
.
[7
]
P.
He
n
d
ra
d
i
,
M
.
Kh
a
n
a
p
i,
a
n
d
S
.
N.
M
a
h
fu
z
a
h
,
"
Clo
u
d
c
o
m
p
u
ti
n
g
-
b
a
se
d
e
-
lea
rn
in
g
s
y
ste
m
a
rc
h
it
e
c
tu
re
in
e
d
u
c
a
ti
o
n
4
.
0
,
"
J
o
u
rn
a
l
o
f
Ph
y
sic
s: Co
n
fer
e
n
c
e
S
e
rie
s
,
v
o
l.
1
1
9
6
,
n
o
.
1
,
IOP
P
u
b
li
sh
i
n
g
,
2
0
1
9
.
[8
]
P
a
u
la
F
ra
g
a
-
Lam
a
s,
e
t
a
l.
,
"
D
e
sig
n
a
n
d
E
x
p
e
rime
n
tal
Va
li
d
a
ti
o
n
o
f
a
Lo
Ra
WAN
F
o
g
Co
m
p
u
ti
n
g
Ba
se
d
Arc
h
it
e
c
tu
re
fo
r
I
o
T
E
n
a
b
led
S
m
a
rt
Ca
m
p
u
s Ap
p
li
c
a
ti
o
n
s
,
"
S
e
n
so
r
s
,
v
o
l
.
19
,
n
o
.
15
,
2
0
1
9
.
[9
]
Re
d
o
wa
n
M
a
h
m
u
d
,
Ra
m
a
m
o
h
a
n
a
ra
o
Ko
tag
iri
,
a
n
d
Ra
j
k
u
m
a
r
Bu
y
y
a
,
"
F
o
g
c
o
m
p
u
ti
n
g
:
A
tax
o
n
o
m
y
,
su
rv
e
y
a
n
d
fu
tu
re
d
irec
ti
o
n
s
,
"
I
n
te
rn
e
t
o
f
e
v
e
ry
th
in
g
,
S
p
rin
g
e
r,
S
i
n
g
a
p
o
re
,
p
p
.
103
-
1
3
0
,
2
0
1
8
.
[1
0
]
A
.
V.
Da
stjerd
i,
a
n
d
Ra
j
k
u
m
a
r
Bu
y
y
a
,
"
F
o
g
c
o
m
p
u
ti
n
g
:
He
lp
i
n
g
t
h
e
In
tern
e
t
o
f
T
h
i
n
g
s
re
a
li
z
e
it
s
p
o
te
n
ti
a
l
,
"
Co
mp
u
ter
,
v
o
l.
49
,
n
o
.
8
,
p
p
.
1
1
2
-
116
,
2
0
1
6
.
[1
1
]
Ko
u
sta
b
h
Do
l
u
i,
a
n
d
S
o
u
m
y
a
Ka
n
ti
Da
tt
a
,
"
C
o
m
p
a
riso
n
o
f
e
d
g
e
c
o
m
p
u
ti
n
g
im
p
lem
e
n
tatio
n
s:
F
o
g
c
o
m
p
u
ti
n
g
,
c
lo
u
d
let
a
n
d
m
o
b
i
le ed
g
e
c
o
m
p
u
ti
n
g
,
"
2
0
1
7
Gl
o
b
a
l
I
n
ter
n
e
t
o
f
T
h
in
g
s S
u
mm
it
(GIo
T
S
)
,
2
0
1
7
.
[
1
2
]
A
.
V
.
D
a
s
t
j
e
r
d
i
,
e
t
a
l
.
,
"
F
o
g
c
o
m
p
u
t
i
n
g
:
P
r
i
n
c
i
p
l
e
s
,
a
r
c
h
i
t
e
c
t
u
r
e
s
,
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
,
"
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
,
p
p
.
61
-
75
,
2
0
1
6
.
[1
3
]
Ya
n
n
LeCu
n
,
Yo
s
h
u
a
Be
n
g
i
o
,
a
n
d
G
e
o
ffre
y
Hin
to
n
,
"
De
e
p
lea
rn
i
n
g
,
"
N
a
t
u
re
,
v
o
l.
5
2
1
,
p
p
.
4
3
6
-
4
4
4
,
2
0
1
5
.
[1
4
]
Li
De
n
g
,
Do
n
g
Yu
,
"
De
e
p
lea
rn
in
g
:
m
e
th
o
d
s
a
n
d
a
p
p
li
c
a
ti
o
n
s
,
"
Fo
u
n
d
a
ti
o
n
s
a
n
d
T
re
n
d
s
i
n
S
i
g
n
a
l
Pr
o
c
e
ss
in
g
,
v
o
l.
7
,
n
o
.
3
–
4
,
p
p
.
1
9
7
-
3
8
7
,
2
0
1
4
.
[
1
5
]
J
ü
r
g
e
n
S
c
h
m
i
d
h
u
b
e
r
,
"
D
e
e
p
l
e
a
r
n
in
g
i
n
n
e
u
r
a
l
n
e
t
w
o
r
k
s
:
A
n
o
v
e
r
v
i
e
w
,
"
N
e
u
r
a
l
N
e
t
w
o
rk
s
,
v
o
l
.
61
,
p
p
.
85
-
1
1
7
,
2
0
1
5
.
[1
6
]
Ch
iy
u
a
n
Z
h
a
n
g
,
e
t
a
l.
,
"
U
n
d
e
rsta
n
d
in
g
d
e
e
p
lea
rn
in
g
re
q
u
ir
e
s
re
th
in
k
i
n
g
g
e
n
e
ra
li
z
a
ti
o
n
,
"
a
rXiv
p
re
p
ri
n
t
a
rXiv
:1
6
1
1
.
0
3
5
3
0
,
2
0
1
6
.
[1
7
]
F
a
u
sto
M
il
leta
ri,
e
t
a
l.
,
"
H
o
u
g
h
-
CNN
:
d
e
e
p
lea
rn
i
n
g
fo
r
se
g
m
e
n
tatio
n
o
f
d
e
e
p
b
ra
i
n
re
g
i
o
n
s
in
M
RI
a
n
d
u
lt
ra
so
u
n
d
,
"
C
o
mp
u
ter
Vi
sio
n
a
n
d
Ima
g
e
Un
d
e
rs
ta
n
d
in
g
,
v
o
l.
1
6
4
,
p
p
.
92
-
1
0
2
,
2
0
1
7
.
[1
8
]
G
u
a
n
p
e
n
g
Li
,
e
t
a
l.
"
Un
d
e
rsta
n
d
in
g
e
rr
o
r
p
ro
p
a
g
a
ti
o
n
i
n
d
e
e
p
le
a
rn
in
g
n
e
u
ra
l
n
e
two
r
k
(DN
N)
a
c
c
e
lera
to
rs
a
n
d
a
p
p
li
c
a
ti
o
n
s
,
"
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
f
o
r
Hi
g
h
Per
f
o
rm
a
n
c
e
C
o
mp
u
ti
n
g
,
Ne
tw
o
rk
in
g
,
S
to
r
a
g
e
a
n
d
An
a
lys
is
,
2
0
1
7
.
[1
9
]
Je
re
m
y
Ka
w
a
h
a
ra
,
G
h
a
ss
a
n
Ha
m
a
rn
e
h
.
"
M
u
lt
i
-
re
so
lu
ti
o
n
-
trac
t
CNN
with
h
y
b
ri
d
p
re
train
e
d
a
n
d
s
k
i
n
-
les
io
n
train
e
d
lay
e
rs
,
"
In
ter
n
a
ti
o
n
a
l
W
o
rk
sh
o
p
o
n
M
a
c
h
i
n
e
L
e
a
rn
in
g
in
M
e
d
ica
l
I
ma
g
in
g
,
S
p
ri
n
g
e
r,
Ch
a
m
,
2
0
1
6
.
[2
0
]
G
e
e
rt
Li
tj
e
n
s,
e
t
a
l.
,
"
A
su
rv
e
y
o
n
d
e
e
p
lea
rn
i
n
g
i
n
m
e
d
ica
l
ima
g
e
a
n
a
ly
sis
,
"
M
e
d
ica
l
Ima
g
e
An
a
lys
is
,
v
o
l
.
42
,
p
p
.
60
-
88
,
2
0
1
7
.
[2
1
]
Xia
o
g
u
a
n
g
C
h
e
n
,
e
t
a
l.
,
"
C
o
n
v
o
l
u
ti
o
n
n
e
u
ra
l
n
e
two
r
k
f
o
r
a
u
to
m
a
ti
c
fa
c
ial
e
x
p
re
ss
io
n
re
c
o
g
n
it
io
n
,
"
2
0
1
7
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
A
p
p
l
ied
S
y
ste
m In
n
o
v
a
t
io
n
(ICA
S
I)
,
2
0
1
7
.
[2
2
]
M
o
h
a
m
m
a
d
Lo
tf
o
ll
a
h
i,
e
t
a
l.
,
"
De
e
p
p
a
c
k
e
t:
A
n
o
v
e
l
a
p
p
r
o
a
c
h
fo
r
e
n
c
ry
p
ted
traffic
c
las
sifica
ti
o
n
u
sin
g
d
e
e
p
lea
rn
in
g
,
"
S
o
ft
Co
mp
u
ti
n
g
,
p
p
.
1
-
14
,
2
0
1
7
.
[2
3
]
A.
Brit
to
M
a
tt
o
s,
Da
rio
Au
g
u
st
o
Bo
rg
e
s
Oliv
e
ira,
E
d
m
il
so
n
Da
silv
a
M
o
ra
is
,
"
Im
p
r
o
v
i
n
g
CNN
-
b
a
se
d
v
ise
m
e
re
c
o
g
n
it
i
o
n
u
si
n
g
s
y
n
t
h
e
ti
c
d
a
ta
,
"
2
0
1
8
IEE
E
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
M
u
lt
ime
d
ia
a
n
d
Ex
p
o
(IC
M
E)
,
2
0
1
8
.
[2
4
]
He
in
z
Bo
e
h
m
e
r
F
ieh
n
,
e
t
a
l.
,
"
S
m
a
rt
a
g
ricu
lt
u
re
sy
ste
m
b
a
se
d
o
n
d
e
e
p
lea
rn
in
g
,
"
Pr
o
c
e
e
d
in
g
s
o
f
t
h
e
2
n
d
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
ma
rt Di
g
it
a
l
E
n
v
iro
n
me
n
t
,
2
0
1
8
.
[2
5
]
Tsu
n
g
-
Ha
n
Ch
a
n
,
e
t
a
l.
,
"
P
CAN
e
t:
A
sim
p
le
d
e
e
p
lea
rn
in
g
b
a
se
li
n
e
fo
r
ima
g
e
c
las
sifica
ti
o
n
?
,
"
I
E
EE
tra
n
s
a
c
ti
o
n
s
o
n
im
a
g
e
p
ro
c
e
ss
in
g
,
v
o
l.
24
,
n
o
.
12
,
p
p
.
5
0
1
7
-
5
0
3
2
,
2
0
1
5
.
[2
6
]
M
o
h
a
m
a
d
M
a
h
m
o
u
d
Al
Ra
h
h
a
l,
e
t
a
l.
,
"
De
e
p
lea
rn
i
n
g
a
p
p
r
o
a
c
h
fo
r
a
c
ti
v
e
c
las
sifica
ti
o
n
o
f
e
le
c
tro
c
a
rd
io
g
ra
m
sig
n
a
ls
,
"
In
f
o
rm
a
ti
o
n
S
c
ien
ces
,
v
o
l.
3
4
5
,
p
p
.
3
4
0
-
3
5
4
,
2
0
1
6
.
[2
7
]
Qin
Z
o
u
,
e
t
a
l.
,
"
De
e
p
lea
rn
in
g
b
a
se
d
fe
a
tu
re
se
lec
ti
o
n
fo
r
re
m
o
te
se
n
sin
g
sc
e
n
e
c
las
sifica
ti
o
n
,
"
IE
EE
Ge
o
sc
ien
c
e
a
n
d
Rem
o
te
S
e
n
sin
g
L
e
tt
e
rs
,
v
o
l
.
12
,
n
o
.
11
,
p
p
.
2
3
2
1
-
2
3
2
5
,
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.