I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
9
,
No
.
1
,
Ju
ly
2
0
2
5
,
p
p
.
353
~
3
6
3
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
3
9
.i
1
.
pp
353
-
3
6
3
353
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Enha
ncing
TV pr
o
g
ra
m success
pr
ediction usin
g
ma
chine
lea
rning
by integr
a
ting peo
ple me
te
r audience
metr
ic
s with
dig
ital eng
a
g
ement me
trics
K
ha
lid
E
l F
a
y
q,
Sa
id T
k
a
t
ek,
L
a
hcen
I
do
ug
li
d
La
b
o
r
a
t
o
r
y
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
s
R
e
s
e
a
r
c
h
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
,
I
b
n
To
f
a
i
l
U
n
i
v
e
r
si
t
y
,
K
e
n
i
t
r
a
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
27
,
2
0
2
4
R
ev
is
ed
Mar
11
,
2
0
2
5
Acc
ep
ted
Mar
25
,
2
0
2
5
Wi
th
t
h
e
e
m
e
rg
e
n
c
e
o
f
n
u
m
e
ro
u
s
m
e
d
ia
se
rv
ice
s
o
n
th
e
in
tern
e
t
,
tele
v
isio
n
(TV)
re
m
a
in
s
a
h
ig
h
ly
d
e
m
a
n
d
e
d
m
e
d
iu
m
in
term
s
o
f
re
li
a
b
il
it
y
a
n
d
in
n
o
v
a
ti
o
n
,
d
e
sp
i
te
in
te
n
se
c
o
m
p
e
ti
ti
o
n
th
a
t
c
o
m
p
e
ls
u
s
to
d
e
v
ise
stra
teg
ies
fo
r
m
a
in
tain
i
n
g
a
u
d
ien
c
e
e
n
g
a
g
e
m
e
n
t.
A
k
e
y
in
d
ica
to
r
o
f
a
TV
c
h
a
n
n
e
l’s
su
c
c
e
ss
is
it
s
re
a
c
h
,
re
p
re
se
n
ti
n
g
th
e
p
e
rc
e
n
tag
e
o
f
th
e
targ
e
t
a
u
d
ien
c
e
th
a
t
v
iew
s
th
e
b
r
o
a
d
c
a
sts.
To
a
id
TV
c
h
a
n
n
e
l
m
a
n
a
g
e
rs,
th
e
in
d
u
str
y
is
e
x
p
l
o
ri
n
g
n
e
w
m
e
th
o
d
s
to
p
re
d
ict
TV
r
e
a
c
h
with
g
re
a
ter
a
c
c
u
ra
c
y
.
Th
is
p
a
p
e
r
in
v
e
stig
a
tes
th
e
p
o
ten
ti
a
l
o
f
a
d
v
a
n
c
e
d
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
ls
in
p
re
d
ictin
g
TV
p
r
o
g
ra
m
su
c
c
e
ss
b
y
i
n
teg
ra
ti
n
g
p
e
o
p
le
m
e
ter
a
u
d
ien
c
e
m
e
t
rics
with
d
ig
it
a
l
e
n
g
a
g
e
m
e
n
t
m
e
tri
c
s.
Ou
r
a
p
p
ro
a
c
h
c
o
m
b
i
n
e
s
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
s
(CNN
s)
fo
r
p
r
o
c
e
ss
in
g
d
i
g
it
a
l
e
n
g
a
g
e
m
e
n
t
d
a
ta,
lo
n
g
sh
o
rt
-
term
m
e
m
o
ry
(LS
TM
)
n
e
two
r
k
s
fo
r
c
a
p
tu
rin
g
tem
p
o
ra
l
d
e
p
e
n
d
e
n
c
ies
,
a
n
d
g
a
u
ss
ian
p
r
o
c
e
ss
e
s
(
G
P
s)
fo
r
m
o
d
e
li
n
g
u
n
c
e
rtain
ti
e
s.
Ou
r
re
su
lt
s
d
e
m
o
n
stra
te
t
h
a
t
t
h
e
b
e
st
-
p
e
rfo
r
m
in
g
h
y
b
ri
d
m
o
d
e
l
a
c
h
ie
v
e
s
a
p
re
d
ictio
n
a
c
c
u
ra
c
y
o
f
9
5
%
.
Th
is
st
u
d
y
c
o
n
tri
b
u
tes
to
t
h
e
field
b
y
a
d
d
re
ss
i
n
g
m
a
n
u
a
l
sc
h
e
d
u
li
n
g
e
rr
o
rs,
fi
n
a
n
c
ial
lo
ss
e
s,
a
n
d
d
e
c
re
a
se
d
v
iew
e
rsh
ip
,
p
ro
v
i
d
in
g
a
m
o
re
c
o
m
p
re
h
e
n
si
v
e
u
n
d
e
rsta
n
d
in
g
o
f
a
u
d
ien
c
e
b
e
h
a
v
i
o
r
a
n
d
e
n
h
a
n
c
in
g
p
re
d
ictiv
e
a
c
c
u
ra
c
y
t
h
ro
u
g
h
th
e
in
teg
ra
ti
o
n
o
f
d
i
v
e
rse
d
a
ta
so
u
rc
e
s
a
n
d
a
d
v
a
n
c
e
d
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
i
q
u
e
s.
K
ey
w
o
r
d
s
:
Au
d
ien
ce
r
ea
ch
es
Data
r
eg
r
ess
io
n
m
o
d
els
Dig
ital e
n
g
ag
em
en
t
Me
d
ia
an
aly
tics
T
elev
is
io
n
au
d
ien
ce
p
r
ed
ictio
n
W
ater
m
ar
k
in
g
au
d
ien
ce
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
:
Kh
alid
E
l Fay
q
L
ab
o
r
ato
r
y
o
f
C
o
m
p
u
ter
Scien
ce
s
R
esear
ch
,
Facu
lty
o
f
Scien
ce
,
I
b
n
T
o
f
ail
Un
iv
e
r
s
ity
Ken
itra
,
Mo
r
o
cc
o
E
m
ail: k
h
alid
elf
ay
q
@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
m
ar
k
etin
g
in
d
u
s
tr
y
is
o
n
e
o
f
th
e
lar
g
est
g
lo
b
ally
,
with
telev
is
io
n
(
T
V)
co
m
p
an
ies
in
v
esti
n
g
m
illi
o
n
s
o
f
d
o
llar
s
in
a
d
v
er
t
is
in
g
.
Au
d
ien
ce
r
atin
g
s
p
lay
a
p
iv
o
tal
r
o
le
in
g
u
id
in
g
a
d
v
er
tis
er
s
to
tailo
r
ca
m
p
aig
n
s
a
n
d
h
elp
in
g
co
n
t
en
t
cr
ea
to
r
s
an
d
T
V
n
etwo
r
k
s
r
ef
in
e
p
r
o
g
r
am
m
in
g
s
tr
ateg
ies
to
m
a
x
im
ize
au
d
ien
ce
en
g
a
g
em
en
t
an
d
o
p
tim
ize
co
n
ten
t
p
r
o
m
o
tio
n
.
I
n
Mo
r
o
cc
o
,
au
d
ie
n
ce
m
ea
s
u
r
e
m
en
t
h
as
ac
h
iev
ed
s
ig
n
if
ican
t
ad
v
an
ce
m
e
n
ts
,
s
p
ea
r
h
ea
d
ed
b
y
o
r
g
an
izatio
n
s
s
u
c
h
as
th
e
in
ter
p
r
o
f
ess
io
n
al
m
ed
ia
au
d
ien
ce
ce
n
ter
(
C
I
AUM
E
D)
an
d
Ma
r
o
cm
et
r
ie.
Usi
n
g
tech
n
iq
u
es
lik
e
wate
r
m
ar
k
in
g
a
n
d
f
in
g
er
p
r
i
n
tin
g
,
M
ar
o
cm
etr
ie
m
o
n
ito
r
s
T
V
c
o
n
s
u
m
p
tio
n
f
o
r
o
v
e
r
1
,
0
0
0
h
o
u
s
eh
o
ld
s
,
p
r
o
v
id
in
g
v
alu
ab
le
i
n
s
ig
h
ts
in
to
au
d
ien
ce
b
eh
av
io
r
.
Desp
ite
th
ese
ad
v
an
ce
m
e
n
ts
,
ch
allen
g
es
p
er
s
is
t
-
p
ar
ticu
lar
ly
f
o
r
L
aa
y
o
u
n
e
T
V,
wh
e
r
e
m
a
n
u
al
s
ch
ed
u
lin
g
o
f
d
aily
T
V
g
u
id
es
o
f
ten
r
esu
l
ts
in
m
is
ju
d
g
ed
d
em
o
g
r
ap
h
i
c
d
ata,
in
ac
c
u
r
ate
T
V
r
atin
g
s
,
an
d
s
u
b
o
p
tim
al
ad
v
er
tis
em
en
t
p
r
icin
g
.
T
h
ese
in
ef
f
icien
cies
ca
n
lead
to
f
i
n
a
n
cial
lo
s
s
es,
d
ec
r
ea
s
ed
ad
v
e
r
tis
in
g
ef
f
ec
tiv
en
ess
,
an
d
d
im
i
n
is
h
ed
v
iewe
r
s
h
ip
,
e
m
p
h
asizin
g
th
e
n
ec
ess
ity
o
f
a
n
au
to
m
ate
d
,
d
ata
-
d
r
iv
e
n
ap
p
r
o
ac
h
f
o
r
p
r
ed
ictin
g
T
V
p
r
o
g
r
am
s
u
cc
ess
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
353
-
3
6
3
354
T
o
ad
d
r
ess
th
ese
ch
allen
g
es,
th
is
s
tu
d
y
in
tr
o
d
u
ce
s
a
n
o
v
el
p
r
ed
ictiv
e
f
r
am
ewo
r
k
th
at
in
teg
r
ates
p
eo
p
le
m
eter
a
u
d
ien
ce
m
etr
ics
with
d
ig
ital
en
g
ag
em
en
t
m
etr
ics
to
im
p
r
o
v
e
t
h
e
ac
cu
r
ac
y
o
f
b
r
o
a
d
ca
s
t
s
ch
ed
u
lin
g
an
d
p
r
o
g
r
am
s
u
cc
ess
f
o
r
ec
asti
n
g
.
Un
lik
e
tr
ad
itio
n
al
m
eth
o
d
s
th
at
r
ely
s
o
lely
o
n
au
d
ien
ce
p
a
n
el
d
ata,
o
u
r
a
p
p
r
o
ac
h
in
co
r
p
o
r
at
es
ad
v
an
ce
d
m
ac
h
in
e
lea
r
n
in
g
m
o
d
els
t
o
a
n
aly
ze
a
n
d
s
y
n
ch
r
o
n
ize
m
u
ltip
le
d
at
a
s
o
u
r
ce
s
,
ca
p
tu
r
in
g
b
o
t
h
r
ea
l
-
tim
e
TV
a
u
d
ien
ce
b
e
h
av
io
r
an
d
d
ig
i
tal
i
n
ter
ac
tio
n
s
,
s
p
ec
if
ical
ly
f
r
o
m
Y
o
u
T
u
b
e.
Sp
ec
if
ically
,
th
is
s
tu
d
y
lev
er
ag
es
a
h
y
b
r
id
m
ac
h
in
e
lear
n
in
g
ar
ch
itectu
r
e
th
at
co
m
b
in
es
co
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs
)
to
ex
tr
ac
t
d
ee
p
r
ep
r
esen
tatio
n
s
f
r
o
m
d
i
g
ital
en
g
ag
em
en
t
d
ata,
s
u
ch
as
u
s
er
in
ter
ac
tio
n
s
,
co
m
m
en
ts
,
an
d
c
o
n
ten
t
s
h
ar
es
o
n
Yo
u
T
u
b
e,
lo
n
g
s
h
o
r
t
-
te
r
m
m
em
o
r
y
(
L
STM
)
n
etwo
r
k
s
,
a
ty
p
e
o
f
r
ec
u
r
r
e
n
t
n
eu
r
al
n
etwo
r
k
(
R
NN
)
,
to
ef
f
ec
tiv
ely
m
o
d
el
tem
p
o
r
al
d
ep
en
d
e
n
cies
in
au
d
ien
ce
b
eh
av
io
r
o
v
er
tim
e,
ca
p
tu
r
in
g
f
lu
ctu
atio
n
s
in
T
V
v
iewe
r
s
h
ip
p
atter
n
s
,
a
n
d
g
au
s
s
ian
p
r
o
ce
s
s
es
(
GPs
)
to
ac
co
u
n
t
f
o
r
u
n
ce
r
tain
ties
an
d
v
ar
iatio
n
s
in
au
d
ien
ce
m
e
tr
ics,
allo
win
g
f
o
r
a
m
o
r
e
r
o
b
u
s
t
an
d
in
ter
p
r
etab
le
p
r
e
d
ictio
n
f
r
am
ewo
r
k
.
T
h
is
m
u
lti
-
lay
er
ed
ap
p
r
o
ac
h
en
h
a
n
ce
s
p
r
ed
ictiv
e
ac
cu
r
ac
y
b
y
in
teg
r
atin
g
d
iv
e
r
s
e
s
tr
u
ctu
r
ed
d
ata
(
T
V
r
atin
g
s
,
s
ch
ed
u
lin
g
m
etad
ata)
an
d
u
n
s
tr
u
ctu
r
ed
d
ata
(
d
ig
ital
en
g
ag
e
m
en
t
m
etr
ics),
en
ab
lin
g
a
m
o
r
e
ad
ap
tiv
e
m
o
d
elin
g
p
r
o
ce
s
s
co
m
p
ar
e
d
to
s
tatic
p
an
el
-
b
ased
au
d
ie
n
ce
m
ea
s
u
r
e
m
en
t
m
eth
o
d
s
.
B
y
r
e
d
u
cin
g
m
an
u
al
s
ch
ed
u
lin
g
er
r
o
r
s
an
d
o
p
tim
izin
g
ad
v
er
t
is
in
g
p
lace
m
e
n
ts
,
th
is
in
teg
r
atio
n
f
ac
ilit
ates
im
p
r
o
v
ed
d
e
cisi
o
n
-
m
ak
in
g
f
o
r
co
n
ten
t
s
ch
ed
u
lin
g
w
h
ile
en
s
u
r
in
g
g
r
ea
ter
r
esil
ien
ce
to
m
ar
k
et
f
lu
ctu
ati
o
n
s
,
as
th
e
in
cl
u
s
io
n
o
f
r
ea
l
-
tim
e
d
ig
ital e
n
g
ag
em
e
n
t d
ata
allo
w
s
f
o
r
r
ap
id
ad
ap
tatio
n
to
s
h
if
ts
in
au
d
ien
ce
p
r
ef
er
e
n
ce
s
.
Pre
v
io
u
s
s
tu
d
ies,
s
u
ch
as
th
o
s
e
co
n
d
u
cted
b
y
Nix
o
n
[
1
]
,
C
am
m
ar
an
o
et
a
l.
[
2
]
,
an
d
L
u
ca
s
an
d
L
az
ar
u
s
[
3
]
,
h
av
e
e
x
p
lo
r
e
d
au
d
ien
ce
p
r
e
d
ictio
n
u
s
in
g
m
ac
h
i
n
e
lear
n
in
g
,
th
ey
p
r
im
ar
ily
f
o
c
u
s
ed
o
n
s
in
g
le
d
ata
s
o
u
r
ce
s
o
r
lim
ited
m
etr
ics.
Ou
r
p
r
ev
io
u
s
wo
r
k
[4
]
u
tili
ze
d
o
n
ly
p
eo
p
le
m
eter
au
d
ien
ce
m
e
tr
ics
,
d
em
o
n
s
tr
atin
g
th
e
p
o
te
n
tial
o
f
m
ac
h
in
e
lear
n
in
g
f
o
r
p
r
o
g
r
am
p
r
e
d
ictio
n
b
u
t
lack
in
g
th
e
in
teg
r
atio
n
o
f
d
ig
ital
en
g
ag
em
e
n
t
d
ata,
a
cr
itical
co
m
p
o
n
en
t in
m
o
d
er
n
a
u
d
ien
ce
m
ea
s
u
r
em
e
n
t.
B
y
b
r
id
g
in
g
th
is
g
ap
,
th
e
c
u
r
r
en
t stu
d
y
ad
v
an
ce
s
p
r
ed
ictiv
e
an
aly
tics
f
o
r
TV
p
r
o
g
r
am
m
in
g
.
R
ec
en
t
wo
r
k
s
,
s
u
ch
as
Z
h
o
u
e
t
a
l
.
[
5
]
an
d
J
ey
av
ad
h
a
n
am
et
a
l.
[
6
]
,
h
av
e
d
e
m
o
n
s
tr
ated
th
e
u
tili
ty
o
f
m
ac
h
in
e
lear
n
in
g
in
p
r
ed
ictin
g
o
n
lin
e
TV
v
id
eo
s
u
cc
ess
.
Similar
ly
,
Ver
m
a
[
7
]
,
Oy
ewo
la
a
n
d
Dad
a
[
8
]
an
d
Gu
p
ta
et
a
l.
[
9
]
i
n
v
esti
g
ated
m
o
d
els
f
o
r
m
o
v
ie
s
u
cc
ess
p
r
e
d
ictio
n
.
Stu
d
ies
b
y
A
b
ar
ja
[
1
0
]
,
Sh
ar
m
a
et
a
l.
[
1
1
]
,
C
izm
ec
i
an
d
Og
u
d
u
c
u
[
1
2
]
,
an
d
C
r
is
ci
et
a
l.
[
1
3
]
h
ig
h
lig
h
ted
t
h
e
r
o
le
o
f
s
o
cial
m
ed
ia
m
etr
ics
in
u
n
d
er
s
tan
d
i
n
g
au
d
ien
ce
b
e
h
a
v
io
r
,
wh
ile
Ku
p
av
s
k
ii
et
a
l.
[
1
4
]
u
n
d
e
r
s
co
r
ed
th
e
im
p
o
r
ta
n
ce
o
f
in
te
g
r
atin
g
s
o
cial
an
d
tr
ad
itio
n
al
m
etr
ic
s
.
Ho
wev
er
,
th
ese
ap
p
r
o
ac
h
es
o
f
ten
lack
t
h
e
in
teg
r
atio
n
o
f
tem
p
o
r
al
an
d
u
n
ce
r
tain
ty
m
o
d
elin
g
,
as r
eq
u
i
r
ed
f
o
r
d
y
n
am
ic
au
d
ien
ce
p
r
ed
ictio
n
.
Stu
d
ies
b
y
So
n
g
et
a
l.
[
1
5
]
an
d
Ak
g
ü
l
an
d
Kü
çü
k
y
ilm
az
[
1
6
]
u
tili
ze
d
ag
g
r
eg
ated
p
eo
p
le
m
eter
d
ata
to
f
o
r
ec
ast
T
V
r
atin
g
s
.
Ad
v
an
ce
d
m
o
d
els,
in
clu
d
i
n
g
n
eu
r
al
n
etwo
r
k
s
[
1
7
]
,
[
1
8
]
,
g
r
ad
ien
t
-
b
o
o
s
tin
g
m
ac
h
i
n
es
[
1
9
]
,
r
id
g
e
r
eg
r
ess
io
n
b
y
Ma
e
t
a
l.
[
2
0
]
,
Ser
ic
et
a
l.
[
2
1
]
,
an
d
C
h
o
i
et
a
l.
[
1
8
]
,
d
ec
is
io
n
tr
ee
s
[
2
2
]
,
an
d
g
en
etic
alg
o
r
ith
m
s
b
y
Geg
r
es
et
a
l.
[
2
3
]
h
av
e
b
ee
n
ap
p
lied
to
o
p
tim
ize
ac
cu
r
ac
y
.
T
h
ese
ap
p
r
o
ac
h
es,
h
o
wev
er
,
o
f
ten
lack
th
e
in
teg
r
atio
n
o
f
tem
p
o
r
al
an
d
u
n
ce
r
tain
ty
m
o
d
elin
g
,
wh
ich
ar
e
cr
itical
f
o
r
d
y
n
am
ic
au
d
ien
ce
b
eh
av
io
r
.
T
h
is
s
tu
d
y
b
u
ild
s
u
p
o
n
p
r
io
r
wo
r
k
s
b
y
in
teg
r
atin
g
p
eo
p
le
m
eter
a
u
d
ien
ce
m
etr
ics
w
ith
d
ig
ital
en
g
ag
em
e
n
t
m
etr
ics,
ad
d
r
ess
in
g
lim
itatio
n
s
in
s
ilo
ed
ap
p
r
o
a
ch
es.
W
e
em
p
lo
y
r
an
d
o
m
f
o
r
est
(
R
F)
[
2
4
]
,
K
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN)
[
2
5
]
,
an
d
ad
v
a
n
ce
d
m
o
d
els
s
u
ch
as
C
NN
s
,
L
STM
n
etwo
r
k
s
[
2
6
]
,
ef
f
ec
tiv
el
y
ca
p
tu
r
e
tem
p
o
r
al
d
ep
en
d
en
c
ies
in
v
iewin
g
p
atter
n
s
,
wh
ile
GPs
m
o
d
el
u
n
ce
r
tain
ties
,
en
ab
lin
g
r
o
b
u
s
t
p
r
ed
ictio
n
s
.
B
y
b
r
id
g
i
n
g
t
h
e
g
ap
b
etwe
en
t
r
ad
itio
n
al
a
n
d
d
ig
ital
m
etr
ics,
th
is
s
tu
d
y
o
f
f
er
s
a
n
o
v
el
ap
p
r
o
ac
h
to
en
h
an
cin
g
T
V
p
r
o
g
r
am
s
u
cc
ess
p
r
e
d
ictio
n
.
T
h
e
r
em
ain
d
er
o
f
th
is
p
ap
e
r
is
s
tr
u
ctu
r
ed
as
f
o
llo
ws:
s
ec
tio
n
2
d
escr
ib
es
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
y
,
co
v
er
in
g
d
ata
ac
q
u
is
itio
n
,
p
r
ep
r
o
ce
s
s
in
g
,
alg
o
r
ith
m
s
elec
tio
n
,
p
er
f
o
r
m
a
n
ce
ev
alu
atio
n
,
d
ep
lo
y
m
e
n
t,
an
d
r
ec
o
m
m
en
d
atio
n
s
.
Sectio
n
3
p
r
esen
ts
th
e
ex
p
e
r
im
en
tal
r
esu
lts
an
d
d
is
cu
s
s
io
n
,
in
clu
d
in
g
m
o
d
el
p
er
f
o
r
m
a
n
ce
,
co
m
p
ar
ativ
e
an
al
y
s
is
,
ca
s
e
s
t
u
d
ies,
an
d
an
in
-
d
ep
th
d
is
cu
s
s
io
n
o
f
th
e
f
in
d
in
g
s
.
Fin
ally
,
s
ec
tio
n
4
co
n
clu
d
es
with
k
ey
in
s
ig
h
ts
an
d
p
o
ten
tial
d
ir
ec
tio
n
s
f
o
r
f
u
tu
r
e
r
esear
ch
.
2.
M
E
T
H
O
D
I
n
th
is
s
ec
t
io
n
,
we
d
escr
ib
e
th
e
m
eth
o
d
o
lo
g
y
a
d
o
p
ted
in
t
h
is
s
tu
d
y
,
d
etailin
g
th
e
o
v
er
a
ll
s
y
s
tem
ar
ch
itectu
r
e,
d
ata
ac
q
u
is
itio
n
p
r
o
ce
s
s
,
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
,
m
o
d
el
s
elec
tio
n
,
ev
alu
atio
n
,
an
d
d
e
p
lo
y
m
en
t
s
tr
ateg
ies.
T
h
e
p
r
o
p
o
s
ed
f
r
a
m
ewo
r
k
in
teg
r
ates
p
eo
p
le
m
eter
au
d
ien
c
e
m
etr
ics
with
d
ig
ital
en
g
ag
em
e
n
t
m
etr
ics
to
en
h
an
ce
T
V
p
r
o
g
r
a
m
s
u
cc
ess
p
r
ed
ictio
n
th
r
o
u
g
h
m
ac
h
in
e
lear
n
i
n
g
tech
n
iq
u
es.
Fig
u
r
e
1
illu
s
tr
ates
th
e
d
y
n
am
ic
s
y
s
tem
a
r
ch
itect
u
r
e,
wh
ic
h
o
u
tlin
es
th
e
en
d
-
to
-
en
d
p
r
o
ce
s
s
,
f
r
o
m
d
ata
ac
q
u
is
itio
n
to
m
o
d
el
d
ep
lo
y
m
e
n
t.
T
h
e
s
y
s
tem
b
e
g
in
s
with
d
ata
co
llectio
n
f
r
o
m
two
p
r
im
ar
y
s
o
u
r
ce
s
-
p
e
o
p
le
m
et
er
au
d
ien
ce
m
etr
ics
f
r
o
m
C
I
AUM
E
D
an
d
Yo
u
T
u
b
e
en
g
ag
em
e
n
t
d
ata
-
f
o
llo
wed
b
y
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
tu
r
e
ex
tr
ac
tio
n
,
an
d
m
o
d
el
tr
ain
in
g
.
T
h
e
p
r
e
d
ic
tio
n
s
g
en
er
ated
b
y
t
h
e
m
o
d
el
ar
e
th
e
n
u
s
ed
f
o
r
c
o
n
ten
t
s
ch
ed
u
lin
g
r
ec
o
m
m
en
d
atio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
n
h
a
n
ci
n
g
TV
p
r
o
g
r
a
m
s
u
cc
ess
p
r
ed
ictio
n
u
s
in
g
ma
ch
in
e
le
a
r
n
in
g
b
y
i
n
teg
r
a
tin
g
…
(
K
h
a
lid
E
l F
a
yq
)
355
Fig
u
r
e
1
.
Dy
n
am
ic
p
r
o
p
o
s
ed
s
y
s
tem
ar
ch
itectu
r
e
2
.
1
.
Da
t
a
a
cquis
it
io
n
T
o
d
ev
elo
p
a
r
o
b
u
s
t
p
r
e
d
ictio
n
m
o
d
el,
d
ata
wer
e
co
llected
f
r
o
m
two
p
r
im
a
r
y
s
o
u
r
ce
s
.
T
h
e
f
ir
s
t
s
o
u
r
ce
is
th
e
p
eo
p
le
m
eter
a
u
d
ien
ce
m
etr
ics
,
co
llected
b
y
C
I
AUM
E
D,
th
is
d
ata
p
r
o
v
id
es
d
etailed
s
tatis
tic
s
o
n
tr
ad
itio
n
al
T
V
v
iewe
r
s
h
ip
ac
r
o
s
s
Mo
r
o
cc
o
.
Me
tr
ics
s
u
c
h
a
s
th
e
n
u
m
b
er
o
f
v
iewe
r
s
,
p
r
o
g
r
am
d
u
r
atio
n
,
an
d
au
d
ien
ce
d
e
m
o
g
r
ap
h
ics
wer
e
ca
p
tu
r
ed
u
s
in
g
p
e
o
p
le
m
ete
r
s
in
s
talled
in
a
r
ep
r
esen
tativ
e
s
am
p
le
o
f
o
v
er
1
,
0
0
0
h
o
u
s
eh
o
ld
s
.
T
h
e
s
ec
o
n
d
s
o
u
r
ce
,
d
ig
ital e
n
g
ag
em
en
t m
etr
ics
,
co
m
p
r
is
es d
ata
f
r
o
m
3
,
5
0
0
v
id
eo
s
co
llect
e
d
f
r
o
m
t
h
e
Yo
u
T
u
b
e
ch
a
n
n
el
o
f
T
V
L
aa
y
o
u
n
e.
T
h
is
d
ataset
in
clu
d
es
v
iews,
lik
es,
co
m
m
en
ts
,
an
d
en
g
ag
em
e
n
t
r
ates
f
o
r
o
n
lin
e
co
n
ten
t.
T
h
e
in
teg
r
atio
n
o
f
th
ese
two
d
ata
s
o
u
r
ce
s
is
ess
en
tial
to
b
r
id
g
e
th
e
g
ap
b
et
wee
n
tr
ad
itio
n
al
TV
au
d
ien
ce
m
ea
s
u
r
em
e
n
t
an
d
o
n
li
n
e
d
ig
ital
co
n
s
u
m
p
tio
n
tr
e
n
d
s
.
Fig
u
r
e
2
p
r
esen
ts
th
e
p
r
o
ce
s
s
o
f
co
m
b
in
in
g
tr
ad
itio
n
al
T
V
s
u
cc
ess
m
etr
ic
s
with
o
n
lin
e
v
id
eo
en
g
a
g
em
e
n
t,
d
em
o
n
s
tr
atin
g
h
o
w
th
ese
d
atasets
ar
e
alig
n
ed
to
en
h
an
ce
p
r
ed
ictiv
e
m
o
d
elin
g
.
Fig
u
r
e
2
.
Pro
ce
s
s
o
f
tr
ad
itio
n
a
l T
V
s
u
c
ce
s
s
an
d
o
n
lin
e
v
i
d
eo
s
u
cc
ess
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
353
-
3
6
3
356
2
.
2
.
Da
t
a
clea
nin
g
a
nd
prepro
ce
s
s
ing
Data
p
r
ep
r
o
ce
s
s
in
g
is
a
cr
itical
s
tep
to
en
s
u
r
e
th
e
q
u
ality
a
n
d
r
eliab
ilit
y
o
f
t
h
e
in
p
u
t
d
ata
u
s
ed
f
o
r
m
o
d
el
d
ev
elo
p
m
en
t.
I
t
in
v
o
lv
es
s
ev
er
al
s
tag
es
to
p
r
ep
ar
e
an
d
s
tan
d
ar
d
ize
th
e
d
ata
f
o
r
o
p
tim
al
p
er
f
o
r
m
a
n
ce
i
n
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
.
T
h
e
f
ir
s
t
s
tep
i
n
v
o
lv
es
clea
n
in
g
th
e
r
aw
d
ata
f
r
o
m
b
o
th
p
eo
p
le
m
eter
a
u
d
ien
ce
m
etr
ics
an
d
d
ig
ital
e
n
g
ag
e
m
e
n
t
m
etr
ics
to
r
em
o
v
e
in
co
n
s
is
ten
cies
an
d
er
r
o
r
s
.
Miss
in
g
v
alu
es
ar
e
h
an
d
led
th
r
o
u
g
h
im
p
u
tatio
n
tech
n
iq
u
e
s
,
wh
er
e
m
is
s
in
g
d
ata
p
o
in
ts
ar
e
esti
m
ated
u
s
in
g
s
tatis
tica
l
m
eth
o
d
s
o
r
v
al
u
es
d
er
iv
ed
f
r
o
m
s
im
ilar
r
ec
o
r
d
s
in
th
e
d
ataset.
T
h
is
en
s
u
r
es
th
a
t
in
co
m
p
lete
d
ata
d
o
es
n
o
t
n
e
g
ativ
ely
im
p
ac
t
th
e
m
o
d
el’
s
p
er
f
o
r
m
a
n
ce
.
Nu
m
er
ical
f
ea
tu
r
es
ar
e
n
o
r
m
alize
d
to
b
r
in
g
th
eir
v
alu
e
s
with
in
a
co
m
p
ar
ab
le
r
an
g
e,
en
s
u
r
in
g
u
n
if
o
r
m
ity
ac
r
o
s
s
d
if
f
e
r
en
t scale
s
.
T
h
is
n
o
r
m
aliza
tio
n
is
ac
h
i
ev
ed
u
s
in
g
t
h
e
(
1
)
.
′
=
−
m
i
n
(
)
(
)
−
m
i
n
(
)
(
1
)
W
h
er
e
is
th
e
o
r
ig
i
n
al
v
alu
e,
′
is
th
e
n
o
r
m
alize
d
v
alu
e,
m
in
(
)
is
th
e
m
in
im
u
m
v
alu
e
,
an
d
m
ax
(
)
is
th
e
m
ax
im
u
m
v
alu
e
in
th
e
d
ataset.
C
ateg
o
r
ical
v
ar
iab
les
wer
e
e
n
co
d
ed
in
to
n
u
m
er
ic
r
e
p
r
ese
n
tatio
n
s
u
s
in
g
o
n
e
-
h
o
t
e
n
co
d
in
g
,
wh
ich
co
n
v
er
ts
ca
teg
o
r
ies
in
to
b
in
ar
y
v
ec
to
r
r
e
p
r
esen
tatio
n
s
,
en
s
u
r
in
g
co
m
p
atib
ilit
y
with
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
.
Ou
tlier
s
wer
e
id
en
tifie
d
an
d
a
d
d
r
ess
ed
u
s
in
g
s
tatis
tica
l
m
eth
o
d
s
s
u
ch
as
th
e
Z
-
s
co
r
e,
wh
ich
d
etec
ts
v
alu
es
s
ig
n
if
ican
tly
o
u
ts
id
e
th
e
n
o
r
m
al
r
an
g
e.
T
h
ese
p
r
e
p
r
o
ce
s
s
in
g
s
tep
s
e
n
s
u
r
ed
th
e
d
ata’
s
co
n
s
is
ten
cy
,
ac
cu
r
ac
y
,
an
d
co
m
p
atib
ilit
y
with
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
Fin
ally
,
ex
p
lo
r
at
o
r
y
d
ata
a
n
aly
s
is
(
E
DA)
is
co
n
d
u
cted
to
u
n
d
er
s
tan
d
u
n
d
er
l
y
in
g
p
a
tter
n
s
an
d
r
elatio
n
s
h
ip
s
in
th
e
d
ata.
T
h
is
in
clu
d
es
v
is
u
alizin
g
d
is
tr
ib
u
tio
n
s
,
co
r
r
elatio
n
s
,
an
d
id
e
n
tify
in
g
s
ig
n
if
ica
n
t
f
ea
tu
r
es
th
at
will
in
f
o
r
m
th
e
c
h
o
ice
o
f
alg
o
r
ith
m
s
f
o
r
th
e
m
o
d
el.
B
y
f
o
llo
win
g
th
ese
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
,
th
e
d
ataset
is
p
r
ep
ar
ed
to
en
s
u
r
e
co
n
s
is
ten
cy
,
ac
cu
r
ac
y
,
a
n
d
co
m
p
atib
ilit
y
with
m
ac
h
i
n
e
l
ea
r
n
in
g
al
g
o
r
ith
m
s
,
u
ltima
tely
im
p
r
o
v
in
g
th
e
r
eliab
il
ity
an
d
r
o
b
u
s
tn
ess
o
f
th
e
p
r
ed
ictiv
e
m
o
d
el.
2
.
3
.
Cho
o
s
ing
a
l
g
o
rit
hm
s
T
h
e
p
r
im
ar
y
o
b
jectiv
e
o
f
th
is
s
tu
d
y
is
to
d
ev
elo
p
a
p
r
ed
ictiv
e
m
o
d
el
th
at
id
en
tifie
s
T
V
p
r
o
g
r
a
m
s
lik
ely
to
attr
ac
t
th
e
la
r
g
est
au
d
ien
ce
.
T
o
ac
h
ie
v
e
th
is
,
we
s
elec
ted
a
co
m
b
in
atio
n
o
f
m
a
ch
i
n
e
lear
n
in
g
alg
o
r
ith
m
s
th
at
ca
p
tu
r
e
d
iv
er
s
e
asp
ec
ts
o
f
th
e
d
ataset,
s
u
ch
as
s
p
atial
p
atter
n
s
,
tem
p
o
r
al
d
ep
en
d
e
n
cies,
an
d
u
n
ce
r
tain
ties
,
en
s
u
r
in
g
co
m
p
r
eh
en
s
iv
e
an
d
ac
cu
r
ate
p
r
ed
i
ctio
n
s
.
W
e
ev
alu
ated
v
ar
io
u
s
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
to
id
en
tif
y
th
e
m
o
s
t
s
u
itab
le
o
n
es
f
o
r
p
r
ed
ictin
g
T
V
p
r
o
g
r
am
s
u
cc
ess
.
T
h
e
alg
o
r
ith
m
s
ch
o
s
e
n
in
clu
d
e
s
:
−
R
F:
was
s
elec
ted
f
o
r
its
ab
ilit
y
to
h
a
n
d
le
h
ig
h
-
d
im
en
s
io
n
al
d
ata
ef
f
ec
tiv
ely
wh
ile
m
in
im
i
zin
g
th
e
r
is
k
o
f
o
v
er
f
itti
n
g
.
I
ts
en
s
em
b
le
lear
n
in
g
ap
p
r
o
ac
h
co
m
b
in
es
m
u
ltip
le
d
ec
i
s
io
n
tr
ee
s
to
p
r
o
v
id
e
s
tab
le
an
d
in
ter
p
r
etab
le
p
r
ed
ictio
n
s
.
R
F
i
s
p
ar
ticu
lar
ly
s
u
itab
le
f
o
r
ca
p
t
u
r
in
g
r
elatio
n
s
h
ip
s
in
p
eo
p
le
m
eter
au
d
ien
c
e
m
etr
ics
,
wh
er
e
ca
teg
o
r
ical
a
n
d
n
u
m
er
ical
d
ata
ar
e
ab
u
n
d
a
n
t.
−
KNN:
was
ch
o
s
en
f
o
r
its
s
i
m
p
licity
an
d
ab
ilit
y
to
clas
s
i
f
y
d
ata
p
o
in
ts
b
ased
o
n
lo
ca
l
p
atter
n
s
.
I
t
is
ef
f
ec
tiv
e
in
ca
p
tu
r
i
n
g
s
m
all
-
s
ca
le
tr
en
d
s
with
in
th
e
d
ata,
s
u
ch
as
v
iewe
r
p
r
ef
er
en
ce
s
f
o
r
s
p
ec
if
ic
co
n
ten
t
ca
teg
o
r
ies.
−
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
:
was
s
elec
ted
f
o
r
i
ts
r
o
b
u
s
tn
ess
in
h
ig
h
-
d
im
en
s
io
n
al
s
p
ac
es.
I
ts
ab
ilit
y
to
f
in
d
th
e
o
p
tim
al
h
y
p
er
p
lan
e
f
o
r
s
ep
ar
atin
g
class
es
m
ak
es
it
a
s
tr
o
n
g
ca
n
d
id
at
e
f
o
r
p
r
e
d
ictin
g
wh
eth
er
a
T
V
s
h
o
w
will su
cc
e
ed
b
ased
o
n
m
ix
ed
n
u
m
e
r
ical
an
d
ca
teg
o
r
ical
d
ata.
W
h
ile
tr
ad
itio
n
al
alg
o
r
ith
m
s
lik
e
R
F,
KNN,
an
d
SVM
p
r
o
v
id
e
a
g
o
o
d
f
o
u
n
d
atio
n
,
th
e
y
lack
th
e
ab
ilit
y
to
ef
f
ec
tiv
ely
ca
p
tu
r
e
tem
p
o
r
al
tr
en
d
s
an
d
u
n
ce
r
tai
n
ties
,
wh
ich
ar
e
cr
itical
f
o
r
p
r
ed
ictin
g
d
y
n
am
ic
v
iewe
r
s
h
ip
b
eh
a
v
io
r
.
T
o
ad
d
r
ess
th
e
lim
itatio
n
s
o
f
tr
ad
itio
n
al
alg
o
r
ith
m
s
,
th
is
s
tu
d
y
in
te
g
r
ates
ad
v
an
ce
d
d
ee
p
lear
n
in
g
an
d
p
r
o
b
a
b
ilis
tic
m
eth
o
d
s
in
to
a
h
y
b
r
id
m
o
d
el:
−
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs):
ar
e
in
teg
r
ated
in
to
th
e
h
y
b
r
id
m
o
d
el
t
o
p
r
o
ce
s
s
th
e
d
ig
ital
en
g
ag
em
e
n
t
m
etr
ics
d
ataset
f
r
o
m
Yo
u
T
u
b
e.
T
h
ese
m
etr
ics
o
f
ten
h
av
e
a
s
p
atial
s
tr
u
ctu
r
e
(
e.
g
.
,
s
eq
u
en
tial
d
ata
o
r
v
id
eo
-
s
p
ec
if
ic
p
atter
n
s
)
,
an
d
C
NNs
ex
ce
l
at
r
ec
o
g
n
izin
g
s
u
ch
s
p
atial
r
elatio
n
s
h
ip
s
.
B
y
ex
tr
ac
tin
g
h
ig
h
-
lev
el
f
ea
tu
r
es f
r
o
m
en
g
a
g
em
en
t d
ata
(
e
.
g
.
,
lik
es,
c
o
m
m
en
ts
,
s
h
ar
es),
C
NNs h
elp
id
en
tify
p
atter
n
s
th
at
co
r
r
elate
with
T
V
s
h
o
w
p
o
p
u
l
ar
ity
.
−
L
o
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
:
ar
e
ess
en
tial
f
o
r
ca
p
tu
r
i
n
g
tem
p
o
r
al
d
ep
e
n
d
en
cies
in
t
h
e
d
ata.
Viewe
r
b
eh
av
io
r
o
f
ten
f
o
llo
ws
tem
p
o
r
al
p
atter
n
s
-
s
p
ec
if
ic
tim
es
o
f
d
ay
,
d
ay
s
o
f
th
e
wee
k
,
o
r
s
ea
s
o
n
al
tr
en
d
s
in
f
lu
en
ce
T
V
v
iewe
r
s
h
ip
.
L
STM
s
ar
e
p
ar
ticu
lar
l
y
s
u
ited
f
o
r
m
o
d
elin
g
s
u
ch
s
eq
u
en
tial
d
ep
en
d
en
cies,
en
s
u
r
in
g
th
e
m
o
d
el
ca
n
p
r
e
d
ic
t v
iewe
r
s
h
ip
tr
en
d
s
o
v
er
tim
e.
−
GPs
:
wer
e
in
co
r
p
o
r
ated
in
t
o
th
e
m
o
d
el
to
h
an
d
le
u
n
ce
r
tai
n
ties
in
p
r
ed
ictio
n
s
.
Un
lik
e
o
th
er
alg
o
r
ith
m
s
,
GPs
n
o
t
o
n
ly
p
r
o
v
id
e
a
p
o
in
t
esti
m
ate
b
u
t
also
q
u
an
tify
th
e
co
n
f
i
d
en
ce
o
f
th
e
p
r
ed
ictio
n
.
T
h
is
is
cr
u
cia
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
n
h
a
n
ci
n
g
TV
p
r
o
g
r
a
m
s
u
cc
ess
p
r
ed
ictio
n
u
s
in
g
ma
ch
in
e
le
a
r
n
in
g
b
y
i
n
teg
r
a
tin
g
…
(
K
h
a
lid
E
l F
a
yq
)
357
wh
en
r
ec
o
m
m
e
n
d
in
g
a
T
V
s
h
o
w
f
o
r
o
p
tim
al
s
ch
ed
u
lin
g
,
as
it
allo
ws
d
ec
is
io
n
-
m
ak
er
s
to
u
n
d
er
s
tan
d
th
e
p
o
ten
tial r
is
k
s
ass
o
ciate
d
with
ea
ch
p
r
ed
ictio
n
.
T
h
e
in
teg
r
atio
n
o
f
C
NNs,
L
STM
s
,
an
d
GPs
in
to
a
s
in
g
le
h
y
b
r
id
m
o
d
el
le
v
er
ag
es
th
e
s
tr
en
g
th
s
o
f
ea
ch
alg
o
r
ith
m
,
en
s
u
r
in
g
th
at
th
is
h
y
b
r
id
ap
p
r
o
ac
h
d
eliv
er
s
m
o
r
e
ac
cu
r
ate
an
d
r
eliab
le
p
r
ed
i
ctio
n
o
f
T
V
s
h
o
w
s
u
cc
ess
th
an
s
tan
d
alo
n
e
m
o
d
els.
Fig
u
r
e
3
illu
s
tr
ates th
e
in
teg
r
atio
n
o
f
C
NNs,
L
STM
s
,
an
d
GPs
.
Fig
u
r
e
3
.
Ma
ch
i
n
e
lea
r
n
in
g
m
o
d
el
ar
ch
itectu
r
e
f
o
r
p
r
ed
ictin
g
T
V
p
r
o
g
r
am
s
u
cc
ess
T
ab
le
1
o
u
tlin
es
th
e
h
y
p
er
p
a
r
am
eter
s
g
o
v
er
n
in
g
o
u
r
co
m
b
i
n
ed
C
NN,
L
STM
,
an
d
GP
ar
ch
itectu
r
e.
T
h
ese
h
y
p
er
p
ar
a
m
eter
s
d
ictate
th
e
a
r
ch
itectu
r
e
an
d
tr
ain
in
g
o
f
th
e
C
NN
r
esp
o
n
s
ib
le
f
o
r
f
ea
t
u
r
e
e
x
tr
ac
tio
n
,
th
e
L
STM
n
etwo
r
k
f
o
r
ca
p
tu
r
i
n
g
tem
p
o
r
al
d
ep
e
n
d
en
cies,
an
d
t
h
e
GPs
f
o
r
m
o
d
elin
g
u
n
ce
r
tai
n
ties
.
T
h
is
ap
p
r
o
ac
h
en
s
u
r
es
th
e
ef
f
ec
ti
v
e
ex
tr
ac
tio
n
o
f
in
f
o
r
m
ativ
e
f
ea
t
u
r
es,
ca
p
tu
r
in
g
tem
p
o
r
al
p
atter
n
s
,
an
d
m
o
d
elin
g
u
n
ce
r
tain
ties
f
r
o
m
th
e
in
p
u
t d
a
ta,
lead
in
g
to
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
in
p
r
e
d
ictin
g
T
V
p
r
o
g
r
a
m
s
u
cc
ess
.
Ta
b
le
1
.
Hy
p
er
p
ar
a
m
eter
s
f
o
r
C
NN,
L
STM
,
an
d
GP a
r
ch
itectu
r
e
Le
a
r
n
i
n
g
r
a
t
e
B
a
t
c
h
s
i
z
e
N
u
mb
e
r
o
f
e
p
o
c
h
s
D
r
o
p
o
u
t
r
a
t
e
K
e
r
n
e
l
s
i
z
e
F
i
l
t
e
r
s
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
W
e
i
g
h
t
i
n
i
t
i
a
l
i
z
a
t
i
o
n
0
.
0
0
1
32
30
0
.
5
3
×
3
6
4
,
1
2
8
R
e
c
t
i
f
i
e
d
l
i
n
e
a
r
u
n
i
t
(
R
e
LU
)
H
e
i
n
i
t
i
a
l
i
z
a
t
i
o
n
2
.
4
.
E
v
a
lua
t
i
o
n
o
f
perf
o
r
m
a
nce
m
et
rics
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el
was
ev
alu
ated
u
s
in
g
m
u
ltip
le
m
etr
ics
to
en
s
u
r
e
a
co
m
p
r
eh
en
s
iv
e
ass
es
s
m
en
t
o
f
its
p
r
ed
ictiv
e
c
ap
ab
ilit
ies.
T
h
ese
m
etr
ics
in
c
lu
d
e
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
M
AE
)
(
2
)
,
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
(
3
)
,
R
-
s
q
u
ar
ed
(
R
²)
(
4
)
,
an
d
m
ea
n
ab
s
o
lu
te
p
er
ce
n
tag
e
e
r
r
o
r
(
MA
PE)
(
5
)
.
E
ac
h
m
etr
ic
p
r
o
v
id
es u
n
iq
u
e
in
s
ig
h
ts
in
t
o
t
h
e
m
o
d
el’
s
p
er
f
o
r
m
a
n
ce
,
allo
win
g
u
s
to
m
ea
s
u
r
e
b
o
th
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
.
T
h
e
p
er
f
o
r
m
a
n
ce
f
o
r
m
u
lae
ar
e
g
iv
en
b
elo
w.
=
1
∑
|
−
̂
|
=
1
(
2
)
W
h
er
e
is
th
e
n
u
m
b
er
o
f
o
b
s
er
v
atio
n
s
,
is
th
e
ac
tu
al
v
alu
e,
an
d
̂
is
th
e
p
r
ed
icted
v
alu
e.
MA
E
m
ea
s
u
r
es th
e
av
er
ag
e
m
ag
n
itu
d
e
o
f
er
r
o
r
s
in
a
s
et
o
f
p
r
ed
ictio
n
s
,
with
o
u
t c
o
n
s
id
er
in
g
th
eir
d
ir
ec
tio
n
.
=
√
1
∑
(
−
̂
)
2
=
1
(
3
)
R
MSE
p
r
o
v
id
es
a
m
ea
s
u
r
e
o
f
th
e
d
i
f
f
er
en
ce
s
b
etwe
en
v
alu
es
p
r
ed
icted
b
y
a
m
o
d
el
a
n
d
th
e
v
alu
es
o
b
s
er
v
ed
,
with
a
h
ig
h
er
p
e
n
alty
o
n
lar
g
er
er
r
o
r
s
.
2
=
1
−
∑
(
−
̂
)
2
=
1
∑
(
−
̅
)
2
=
1
(
4
)
W
h
er
e
̅
is
th
e
m
ea
n
o
f
th
e
ac
tu
al
v
alu
es.
R
²
in
d
icate
s
th
e
p
r
o
p
o
r
tio
n
o
f
th
e
v
a
r
ian
ce
in
th
e
d
e
p
e
n
d
e
n
t
v
ar
iab
le
th
at
is
p
r
ed
ictab
le
f
r
o
m
th
e
i
n
d
ep
e
n
d
en
t
v
ar
iab
les,
p
r
o
v
id
in
g
in
s
ig
h
t
in
to
th
e
g
o
o
d
n
ess
-
of
-
f
it
o
f
t
h
e
m
o
d
el.
=
1
∑
|
−
̂
|
=
1
(
5
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
353
-
3
6
3
358
MA
PE
m
ea
s
u
r
es
th
e
ac
cu
r
ac
y
o
f
a
f
o
r
ec
asti
n
g
m
eth
o
d
as
a
p
er
ce
n
tag
e,
o
f
f
e
r
in
g
a
n
in
tu
iti
v
e
u
n
d
er
s
tan
d
in
g
o
f
th
e
p
r
ed
ictio
n
er
r
o
r
s
r
elativ
e
to
th
e
ac
tu
al
v
alu
es.
T
h
ese
m
etr
ics
co
llectiv
ely
p
r
o
v
id
e
a
co
m
p
r
eh
en
s
iv
e
ass
es
s
m
en
t o
f
th
e
m
o
d
el’
s
p
r
e
d
ictiv
e
ac
cu
r
ac
y
,
r
o
b
u
s
tn
ess
,
an
d
g
en
er
aliza
b
ilit
y
.
2
.
5
.
Deplo
y
m
ent
T
h
e
d
ep
lo
y
m
en
t
p
h
ase
in
teg
r
ates
th
e
p
r
ed
ictiv
e
m
o
d
el
in
t
o
T
V
L
aa
y
o
u
n
e’
s
wo
r
k
f
lo
w
to
p
r
o
v
i
d
e
r
ea
l
-
tim
e
in
s
ig
h
ts
f
o
r
p
r
o
g
r
a
m
m
in
g
d
ec
is
io
n
s
.
Ho
s
ted
o
n
a
s
er
v
er
u
s
in
g
T
en
s
o
r
Flo
w
S
er
v
in
g
,
t
h
e
m
o
d
el
is
ac
ce
s
s
ib
le
v
ia
R
E
ST
API
en
d
p
o
in
ts
,
e
n
s
u
r
in
g
s
ea
m
less
in
teg
r
atio
n
with
ex
is
tin
g
in
f
r
a
s
tr
u
ctu
r
e
an
d
h
i
g
h
-
p
er
f
o
r
m
an
ce
p
r
ed
ictio
n
s
.
A
r
ea
l
-
tim
e
d
ata
p
ip
elin
e
co
n
tin
u
o
u
s
ly
f
ee
d
s
n
ew
p
eo
p
le
m
et
er
au
d
ien
ce
m
et
r
ics
an
d
d
ig
ital
en
g
ag
e
m
en
t
m
etr
i
cs
in
to
th
e
m
o
d
el,
p
r
ep
r
o
ce
s
s
in
g
th
e
d
ata
to
en
s
u
r
e
co
n
s
is
te
n
cy
an
d
r
eliab
ilit
y
.
T
h
e
m
o
d
el
is
em
b
ed
d
e
d
in
to
th
e
s
ch
ed
u
l
in
g
an
d
b
r
o
ad
ca
s
tin
g
s
y
s
tem
s
,
au
to
m
atin
g
r
e
co
m
m
en
d
atio
n
s
f
o
r
o
p
tim
al
b
r
o
a
d
ca
s
t tim
es a
n
d
r
e
d
u
cin
g
r
elian
ce
o
n
m
an
u
al
s
ch
ed
u
lin
g
.
Fig
u
r
e
4
illu
s
tr
ates
th
e
in
ter
f
ac
e
web
f
o
r
p
r
ed
ictin
g
T
V
p
r
o
g
r
am
s
u
cc
ess
.
T
h
e
s
y
s
tem
allo
ws
u
s
er
s
to
s
elec
t
a
s
p
ec
if
ic
T
V
p
r
o
g
r
am
,
v
iew
its
au
d
ien
ce
p
er
f
o
r
m
a
n
c
e
o
n
T
V,
an
d
c
o
m
p
a
r
e
it
with
its
d
ig
ital
f
o
o
tp
r
in
t
o
n
Yo
u
T
u
b
e.
B
y
in
teg
r
atin
g
th
ese
in
s
ig
h
ts
,
d
ec
is
io
n
-
m
ak
er
s
ca
n
o
p
tim
ize
s
ch
ed
u
li
n
g
s
tr
ateg
ies
an
d
ad
v
er
tis
in
g
p
lace
m
en
ts
.
T
o
m
ain
tain
ac
cu
r
ac
y
,
t
h
e
m
o
d
e
l
u
n
d
e
r
g
o
es
p
er
io
d
ic
r
etr
ain
i
n
g
b
y
in
c
o
r
p
o
r
atin
g
u
p
d
ated
au
d
ien
ce
d
ata.
T
h
is
a
llo
ws
th
e
s
y
s
tem
to
ad
a
p
t
to
ch
an
g
in
g
v
iewe
r
b
eh
a
v
io
r
s
,
s
ea
s
o
n
al
tr
en
d
s
,
a
n
d
ev
o
lv
in
g
co
n
ten
t
p
r
ef
er
e
n
ce
s
,
en
s
u
r
in
g
co
n
tin
u
o
u
s
im
p
r
o
v
e
m
en
t in
p
r
e
d
ictio
n
ac
c
u
r
ac
y
.
Fig
u
r
e
4
.
I
n
ter
f
ac
e
w
e
b
f
o
r
p
r
e
d
ictin
g
T
V
p
r
o
g
r
am
s
u
cc
ess
2
.
6
.
Rec
o
mm
enda
t
io
ns
T
h
e
p
r
e
d
ictiv
e
m
o
d
el
p
r
o
v
i
d
es
ac
tio
n
ab
le
in
s
ig
h
ts
th
at
en
ab
le
T
V
L
aa
y
o
u
n
e
to
o
p
tim
ize
its
p
r
o
g
r
a
m
m
in
g
s
tr
ateg
y
an
d
en
h
an
ce
au
d
ien
ce
en
g
ag
em
e
n
t.
B
y
an
aly
zin
g
v
iewe
r
b
eh
a
v
io
r
p
atter
n
s
,
th
e
m
o
d
el
id
en
tifie
s
p
ea
k
v
iewin
g
tim
es,
allo
win
g
t
h
e
n
etwo
r
k
t
o
s
tr
at
eg
ically
s
ch
ed
u
le
p
o
p
u
lar
p
r
o
g
r
am
s
to
m
ax
im
ize
v
iewe
r
s
h
ip
.
Ad
d
itio
n
ally
,
r
ea
l
-
tim
e
p
r
o
ce
s
s
in
g
ca
p
a
b
ilit
ies
en
ab
le
d
y
n
am
ic
ad
ju
s
tm
en
ts
to
th
e
s
ch
ed
u
le
b
ased
o
n
liv
e
en
g
ag
em
e
n
t
tr
en
d
s
,
e
n
s
u
r
in
g
th
e
n
etwo
r
k
ca
p
italizes
o
n
em
er
g
i
n
g
o
p
p
o
r
tu
n
ities
.
I
n
teg
r
atin
g
th
es
e
in
s
ig
h
ts
en
s
u
r
es
th
at
h
ig
h
-
d
e
m
an
d
co
n
ten
t
r
ea
c
h
es
th
e
lar
g
est
au
d
ien
ce
,
b
o
ls
ter
in
g
o
v
er
all
p
er
f
o
r
m
a
n
ce
an
d
au
d
ien
ce
r
eten
ti
o
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
n
h
a
n
ci
n
g
TV
p
r
o
g
r
a
m
s
u
cc
ess
p
r
ed
ictio
n
u
s
in
g
ma
ch
in
e
le
a
r
n
in
g
b
y
i
n
teg
r
a
tin
g
…
(
K
h
a
lid
E
l F
a
yq
)
359
T
h
e
in
teg
r
atio
n
o
f
tr
ad
itio
n
al
an
d
d
ig
ital
m
e
tr
ics
o
f
f
er
s
a
d
ee
p
er
u
n
d
er
s
tan
d
i
n
g
o
f
au
d
ien
ce
p
r
ef
er
en
ce
s
,
p
a
v
in
g
th
e
way
f
o
r
p
er
s
o
n
alize
d
co
n
ten
t
s
tr
ateg
ies.
B
y
tailo
r
in
g
p
r
o
g
r
am
m
in
g
b
lo
ck
s
to
s
p
ec
if
ic
v
iewe
r
d
em
o
g
r
ap
h
ics
an
d
in
te
r
ests
,
T
V
L
aa
y
o
u
n
e
ca
n
i
n
cr
e
ase
au
d
ien
ce
lo
y
alty
a
n
d
s
atis
f
ac
tio
n
.
Mo
r
e
o
v
er
,
th
e
m
o
d
el
s
u
p
p
o
r
ts
tar
g
eted
ad
v
er
tis
in
g
b
y
p
r
o
f
ilin
g
v
i
ewe
r
s
eg
m
en
ts
,
allo
win
g
ad
v
er
tis
em
en
ts
to
b
e
s
ch
ed
u
led
f
o
r
m
a
x
im
u
m
r
elev
an
ce
an
d
ef
f
ec
tiv
e
n
ess
.
T
h
ese
in
s
ig
h
ts
en
h
an
ce
ad
p
er
f
o
r
m
an
ce
,
b
o
o
s
tin
g
r
ev
en
u
e
g
en
er
atio
n
wh
ile
en
s
u
r
in
g
th
at
p
r
o
m
o
tio
n
al
r
eso
u
r
ce
s
ar
e
allo
ca
ted
to
p
r
o
g
r
am
s
with
th
e
h
ig
h
est
g
r
o
wth
p
o
ten
tial.
Fin
ally
,
th
e
m
o
d
el’
s
r
ec
o
m
m
en
d
atio
n
s
ex
te
n
d
to
co
n
te
n
t
cr
ea
tio
n
a
n
d
p
r
o
m
o
tio
n
al
ca
m
p
aig
n
s
,
g
u
id
in
g
th
e
d
ev
el
o
p
m
en
t
o
f
n
e
w
p
r
o
g
r
am
s
b
ased
o
n
e
n
g
ag
e
m
en
t
d
ata
an
d
id
en
tif
y
in
g
u
n
d
er
p
er
f
o
r
m
i
n
g
s
h
o
ws
th
at
co
u
ld
b
en
ef
it f
r
o
m
tar
g
ete
d
m
ar
k
etin
g
ef
f
o
r
ts
.
I
n
c
o
r
p
o
r
a
tin
g
d
ir
ec
t
v
iewe
r
f
ee
d
b
ac
k
in
t
o
th
e
d
ata
p
ip
elin
e
en
s
u
r
es
co
n
tin
u
o
u
s
r
ef
in
em
e
n
t
o
f
p
r
ed
ictio
n
s
,
en
a
b
lin
g
th
e
n
etwo
r
k
to
ev
o
lv
e
its
s
tr
ateg
ies
an
d
m
ain
tain
co
m
p
etitiv
en
ess
.
T
h
r
o
u
g
h
th
e
s
e
d
ata
-
d
r
iv
en
a
p
p
r
o
ac
h
es,
c
an
ac
h
iev
e
s
u
s
tain
ed
g
r
o
wth
,
o
p
tim
ize
r
eso
u
r
ce
allo
ca
tio
n
,
an
d
d
eliv
er
a
m
o
r
e
en
g
ag
in
g
an
d
p
er
s
o
n
alize
d
v
ie
win
g
ex
p
er
ie
n
ce
f
o
r
its
au
d
ien
ce
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
in
teg
r
atio
n
o
f
C
I
AUM
E
D
p
eo
p
le
m
eter
au
d
ien
ce
m
e
tr
i
cs
with
Yo
u
T
u
b
e
d
ig
ital
e
n
g
ag
em
e
n
t
m
etr
ics
in
t
r
o
d
u
ce
s
a
n
o
v
el
d
i
m
en
s
io
n
to
au
d
ien
ce
a
n
aly
s
is
.
T
r
ad
itio
n
al
m
etr
ics
p
r
o
v
i
d
e
g
r
an
u
lar
in
s
ig
h
ts
in
to
h
o
u
s
eh
o
ld
-
lev
el
T
V
v
iewe
r
s
h
ip
,
ca
p
tu
r
in
g
d
ata
s
u
ch
as
p
r
o
g
r
a
m
d
u
r
atio
n
,
au
d
ien
ce
d
em
o
g
r
a
p
h
ics,
an
d
ch
an
n
el
r
atin
g
s
.
I
n
co
n
t
r
ast,
d
ig
ital
m
etr
ics
o
f
f
er
a
r
ea
l
-
tim
e
p
er
s
p
ec
tiv
e
o
n
o
n
lin
e
au
d
ien
ce
b
eh
a
v
io
r
,
in
clu
d
in
g
v
id
e
o
v
iews,
lik
es,
an
d
co
m
m
en
ts
.
B
y
co
m
b
in
i
n
g
th
ese
s
tr
u
ctu
r
ed
an
d
u
n
s
tr
u
ctu
r
ed
d
ata
s
o
u
r
ce
s
,
th
e
in
teg
r
ated
d
ataset
p
r
o
v
i
d
es a
h
o
lis
tic
v
iew
o
f
au
d
ien
ce
en
g
ag
em
en
t
ac
r
o
s
s
p
latf
o
r
m
s
.
T
h
is
d
u
al
-
s
o
u
r
ce
ap
p
r
o
ac
h
ad
d
r
ess
es
lim
ita
tio
n
s
in
p
r
io
r
s
tu
d
ies,
wh
ich
o
f
ten
r
elied
s
o
lely
o
n
eith
er
tr
ad
itio
n
al
o
r
d
ig
ital m
etr
ics.
T
h
e
ab
ilit
y
to
b
r
id
g
e
in
-
h
o
m
e
T
V
v
iewe
r
s
h
ip
with
o
n
lin
e
en
g
ag
em
en
t a
llo
ws th
e
m
o
d
el
to
ca
p
tu
r
e
th
e
h
y
b
r
id
n
atu
r
e
o
f
co
n
tem
p
o
r
ar
y
m
e
d
ia
co
n
s
u
m
p
tio
n
,
m
ak
in
g
p
r
e
d
ictio
n
s
b
o
th
m
o
r
e
ac
cu
r
ate
an
d
m
o
r
e
ac
tio
n
a
b
le
.
Ad
d
itio
n
ally
,
th
is
m
u
lti
-
s
o
u
r
ce
in
teg
r
atio
n
em
p
o
wer
s
s
tr
ateg
ic
p
r
o
g
r
am
m
i
n
g
b
y
id
en
tif
y
in
g
c
o
n
ten
t w
ith
cr
o
s
s
o
v
er
ap
p
ea
l a
n
d
ad
a
p
tin
g
t
o
ch
an
g
in
g
v
iewin
g
h
a
b
its
.
T
o
en
s
u
r
e
an
u
n
b
iased
ev
alu
at
io
n
,
th
e
d
ataset
was d
iv
id
ed
in
to
tr
ain
in
g
(
7
0
%),
v
alid
atio
n
(
1
5
%),
an
d
test
(
1
5
%)
s
ets.
T
h
e
m
o
d
el,
im
p
lem
en
ted
in
T
e
n
s
o
r
Flo
w,
u
n
d
er
wen
t
h
y
p
e
r
p
ar
am
ete
r
tu
n
in
g
u
s
in
g
th
e
v
alid
atio
n
s
et.
Key
p
ar
am
eter
s
-
in
clu
d
in
g
lear
n
in
g
r
ate,
b
atch
s
ize,
n
u
m
b
er
o
f
e
p
o
ch
s
,
d
r
o
p
o
u
t
r
ate,
an
d
k
er
n
el
s
ize
-
wer
e
o
p
tim
ized
to
en
h
an
c
e
m
o
d
el
p
e
r
f
o
r
m
an
ce
an
d
g
e
n
er
aliza
tio
n
ab
ilit
y
.
3
.
1
.
M
o
del per
f
o
rma
nce
T
h
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
ac
h
iev
ed
r
o
b
u
s
t
p
e
r
f
o
r
m
an
ce
,
ev
id
en
ce
d
b
y
a
p
r
e
d
ictio
n
a
cc
u
r
ac
y
o
f
9
5
%.
Key
m
etr
ics
in
clu
d
ed
a
MA
E
o
f
0
.
0
4
5
,
R
MSE
o
f
0
.
0
6
3
,
R
²
o
f
0
.
8
9
,
an
d
MA
PE
o
f
4
.
7
%.
T
h
ese
r
esu
lts
co
n
f
ir
m
t
h
e
m
o
d
el’
s
r
eliab
il
ity
in
p
r
e
d
ictin
g
T
V
p
r
o
g
r
a
m
s
u
cc
ess
,
d
em
o
n
s
tr
atin
g
it
s
ab
ilit
y
to
h
an
d
le
co
m
p
lex
,
in
teg
r
ated
d
ata
f
r
o
m
tr
ad
itio
n
al
an
d
d
ig
ita
l
s
o
u
r
ce
s
ef
f
ec
tiv
ely
.
T
h
e
p
er
f
o
r
m
an
ce
m
etr
ics
ar
e
d
etailed
in
T
ab
le
2
.
T
ab
le
2
.
Mo
d
el
p
er
f
o
r
m
a
n
ce
m
etr
ics
M
e
t
r
i
c
V
a
l
u
e
M
A
E
0
.
0
4
5
R
M
S
E
0
.
0
6
3
R²
0
.
8
9
M
A
P
E
4
.
7%
T
o
en
s
u
r
e
r
o
b
u
s
t
e
v
alu
atio
n
,
a
K
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
a
p
p
r
o
ac
h
(
k
=5
)
was
em
p
lo
y
e
d
.
T
h
e
d
ataset
was
d
iv
id
ed
in
to
f
iv
e
s
u
b
s
ets,
with
ea
ch
f
o
ld
s
er
v
in
g
as
th
e
v
alid
atio
n
s
et
o
n
ce
wh
ile
th
e
r
em
ain
in
g
f
o
u
r
wer
e
u
s
ed
f
o
r
tr
ain
in
g
.
T
h
is
m
eth
o
d
m
in
im
ized
b
ias
an
d
v
ar
ian
ce
,
p
r
o
v
id
in
g
a
th
o
r
o
u
g
h
ass
ess
m
en
t
o
f
th
e
m
o
d
el’
s
g
en
er
aliza
b
ilit
y
.
T
h
e
cr
o
s
s
-
v
alid
atio
n
p
r
o
ce
s
s
d
em
o
n
s
tr
ated
co
n
s
is
ten
t
p
e
r
f
o
r
m
an
ce
ac
r
o
s
s
f
o
ld
s
,
with
m
in
im
al
v
ar
ian
ce
o
b
s
er
v
ed
.
F
o
r
ex
am
p
le,
MA
E
v
alu
es
r
an
g
ed
f
r
o
m
0
.
0
4
3
to
0
.
0
4
6
,
h
ig
h
li
g
h
tin
g
th
e
m
o
d
el’
s
s
tab
ilit
y
an
d
r
eliab
ilit
y
in
r
ea
l
-
wo
r
ld
ap
p
licatio
n
s
.
3
.
2
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
T
o
ass
es
s
it
s
ef
f
ec
tiv
en
ess
,
t
h
e
h
y
b
r
id
m
o
d
el
was
co
m
p
ar
ed
ag
ain
s
t
b
aselin
e
m
o
d
els,
in
clu
d
in
g
l
in
ea
r
r
eg
r
ess
io
n
,
RF
,
SVM
,
KNNs
,
an
d
a
s
tan
d
alo
n
e
C
NN
.
As
s
h
o
wn
in
T
ab
le
3
,
th
e
h
y
b
r
id
m
o
d
el
o
u
tp
er
f
o
r
m
ed
all
alter
n
ativ
es,
d
em
o
n
s
tr
atin
g
th
e
b
en
ef
its
o
f
in
teg
r
atin
g
s
p
atial,
tem
p
o
r
al,
an
d
u
n
ce
r
tain
ty
m
o
d
elin
g
tech
n
iq
u
es.
T
h
e
s
u
p
er
io
r
p
e
r
f
o
r
m
an
ce
o
f
th
e
h
y
b
r
id
m
o
d
el
is
f
u
r
th
e
r
illu
s
tr
ated
in
Fig
u
r
e
5
,
wh
ich
v
is
u
ally
co
m
p
a
r
es
MA
E
v
al
u
es
ac
r
o
s
s
d
if
f
e
r
en
t
m
o
d
els.
B
y
in
teg
r
atin
g
C
NNs,
L
STM
s
,
an
d
GPs
,
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
353
-
3
6
3
360
p
r
o
p
o
s
ed
m
o
d
el
e
f
f
ec
tiv
ely
ca
p
tu
r
es
s
p
atial,
tem
p
o
r
al,
a
n
d
u
n
ce
r
tain
ty
asp
ec
ts
o
f
au
d
ien
ce
en
g
ag
em
e
n
t.
Sp
ec
if
ically
,
C
NNs
ex
tr
ac
t
m
ea
n
in
g
f
u
l
p
atter
n
s
f
r
o
m
d
i
g
ital
en
g
ag
e
m
en
t
d
ata,
L
ST
Ms
m
o
d
el
tem
p
o
r
al
d
ep
en
d
e
n
cies
in
v
iewe
r
s
h
ip
b
eh
av
io
r
,
an
d
GPs
p
r
o
v
id
e
u
n
ce
r
tain
ty
esti
m
atio
n
,
en
h
a
n
cin
g
t
h
e
m
o
d
el’
s
in
ter
p
r
etab
ilit
y
an
d
r
eliab
ilit
y
.
T
h
is
co
m
p
r
eh
en
s
iv
e
a
p
p
r
o
ac
h
h
ig
h
lig
h
ts
th
e
im
p
o
r
tan
ce
o
f
m
u
lti
-
s
o
u
r
ce
d
ata
in
teg
r
atio
n
,
lea
d
in
g
to
h
ig
h
e
r
p
r
ed
ictio
n
ac
cu
r
ac
y
,
im
p
r
o
v
ed
s
ch
ed
u
lin
g
s
tr
ateg
ies,
a
n
d
b
etter
d
ec
is
io
n
-
m
ak
in
g
in
T
V
p
r
o
g
r
am
m
i
n
g
.
T
ab
le
3
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
o
f
d
i
f
f
er
en
t
m
o
d
els
M
o
d
e
l
M
A
E
R
M
S
E
R²
M
A
P
E
Li
n
e
a
r
r
e
g
r
e
s
si
o
n
0
.
0
8
5
0
.
0
9
8
0
.
7
2
9
.
3
%
RF
0
.
0
6
7
0
.
0
8
2
0
.
8
1
6
.
8
%
S
V
M
0
.
0
7
3
0
.
0
8
9
0
.
7
7
7
.
5
%
K
N
N
s
0
.
0
7
9
0
.
0
9
3
0
.
7
4
8
.
2
%
C
N
N
0
.
0
5
2
0
.
0
6
8
0
.
8
5
5
.
1
%
P
r
o
p
o
se
d
h
y
b
r
i
d
mo
d
e
l
0
.
0
4
5
0
.
0
6
3
0
.
8
9
4
.
7
%
Fig
u
r
e
5
.
C
o
m
p
a
r
ativ
e
an
aly
s
i
s
o
f
MA
E
v
alu
es
3
.
3
.
Ca
s
e
s
t
ud
ies
T
o
f
u
r
th
er
ev
alu
ate
th
e
p
r
ac
tic
al
u
tili
ty
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el,
we
co
n
d
u
cted
an
in
-
d
ep
th
an
aly
s
is
o
f
th
r
ee
s
p
ec
if
ic
T
V
p
r
o
g
r
am
s
b
r
o
ad
ca
s
t o
n
L
aa
y
o
u
n
e
T
V.
T
h
e
s
e
ca
s
e
s
tu
d
ies d
em
o
n
s
tr
ate
th
e
m
o
d
el’
s
ab
ilit
y
to
g
en
er
ate
ac
tio
n
ab
le
in
s
ig
h
ts
th
at
en
h
an
ce
p
r
o
g
r
a
m
m
in
g
s
tr
ateg
ies
an
d
au
d
ien
ce
en
g
a
g
e
m
en
t.
Pro
g
r
am
A,
t
h
e
m
o
d
el’
s
p
r
ed
ictio
n
s
ac
h
iev
ed
a
9
5
%
alig
n
m
en
t
with
ac
t
u
al
a
u
d
ien
ce
r
atin
g
s
,
c
o
n
f
ir
m
in
g
its
h
ig
h
p
r
ec
is
io
n
f
o
r
th
is
p
r
o
g
r
am
.
T
h
is
d
em
o
n
s
tr
a
tes
th
e
m
o
d
el’
s
ab
ilit
y
to
ac
cu
r
ately
ca
p
tu
r
e
a
u
d
ien
ce
p
r
ef
er
en
ce
s
f
o
r
s
p
ec
if
ic
co
n
ten
t
ty
p
es.
Pro
g
r
a
m
B
,
t
h
e
m
o
d
el
c
o
r
r
ec
tly
f
o
r
ec
asted
a
d
ec
lin
e
in
v
iewe
r
s
h
ip
,
wh
ich
was
later
co
n
f
ir
m
e
d
b
y
s
u
b
s
eq
u
en
t
au
d
ien
ce
d
at
a.
T
h
is
ea
r
ly
war
n
in
g
en
a
b
led
th
e
n
etwo
r
k
t
o
r
ea
llo
ca
te
m
ar
k
etin
g
an
d
p
r
o
m
o
tio
n
al
e
f
f
o
r
ts
,
m
itig
atin
g
t
h
e
im
p
ac
t
o
f
d
ec
lin
i
n
g
au
d
i
en
ce
n
u
m
b
er
s
.
Pro
g
r
am
C
,
b
ased
o
n
th
e
m
o
d
el’
s
p
r
ed
ictio
n
s
,
s
tr
ateg
ic
s
ch
ed
u
lin
g
ad
ju
s
tm
en
ts
wer
e
im
p
lem
en
ted
,
lead
in
g
to
a
1
0
%
in
cr
ea
s
e
in
v
iewe
r
s
h
ip
.
T
h
is
illu
s
tr
ates
h
o
w
p
r
ed
ictiv
e
in
s
ig
h
ts
ca
n
b
e
lev
er
ag
ed
to
o
p
tim
ize
b
r
o
ad
ca
s
t tim
in
g
an
d
m
ax
im
ize
au
d
ien
ce
en
g
ag
em
e
n
t.
T
h
ese
ex
am
p
les
illu
s
tr
ate
th
e
m
o
d
el’
s
ab
i
lity
to
p
r
o
v
i
d
e
ac
tio
n
ab
le
i
n
s
ig
h
ts
,
en
h
a
n
cin
g
p
r
o
g
r
a
m
m
in
g
s
tr
ateg
ies an
d
o
p
tim
izin
g
au
d
ie
n
ce
en
g
a
g
em
e
n
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
n
h
a
n
ci
n
g
TV
p
r
o
g
r
a
m
s
u
cc
ess
p
r
ed
ictio
n
u
s
in
g
ma
ch
in
e
le
a
r
n
in
g
b
y
i
n
teg
r
a
tin
g
…
(
K
h
a
lid
E
l F
a
yq
)
361
3
.
4
.
Dis
cus
s
io
n
T
h
is
s
tu
d
y
d
em
o
n
s
tr
ates
th
e
e
f
f
ec
tiv
en
ess
o
f
in
teg
r
atin
g
tr
a
d
itio
n
al
T
V
a
u
d
ien
ce
m
etr
ics
with
d
ig
ital
en
g
ag
em
e
n
t
d
ata
t
o
p
r
ed
ict
p
r
o
g
r
am
s
u
cc
ess
.
Un
lik
e
p
r
e
v
io
u
s
m
o
d
els
th
at
r
elied
s
o
lely
o
n
p
eo
p
le
m
eter
d
ata
o
r
d
ig
ital
in
ter
ac
tio
n
s
,
o
u
r
h
y
b
r
id
ap
p
r
o
ac
h
en
h
an
ce
s
p
r
e
d
ictiv
e
ac
cu
r
ac
y
b
y
co
m
b
in
i
n
g
s
tr
u
ctu
r
ed
an
d
u
n
s
tr
u
ctu
r
ed
d
ata
s
o
u
r
ce
s
.
T
h
e
r
esu
lts
co
n
f
ir
m
th
at
f
u
s
i
n
g
h
is
to
r
ical
T
V
r
atin
g
s
with
r
ea
l
-
tim
e
o
n
lin
e
en
g
ag
em
e
n
t im
p
r
o
v
es f
o
r
ec
ast
in
g
,
ca
p
tu
r
in
g
b
o
th
lo
n
g
-
ter
m
au
d
ien
ce
tr
en
d
s
an
d
im
m
ed
iat
e
v
iewe
r
r
ea
ctio
n
s
.
T
h
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el,
c
o
m
b
in
in
g
C
NNs,
L
STM
s
,
an
d
GPs
,
o
u
tp
er
f
o
r
m
ed
all
b
aselin
e
m
o
d
els,
ac
h
iev
in
g
an
R
²
o
f
0
.
8
9
,
d
em
o
n
s
tr
atin
g
its
s
tr
o
n
g
p
r
ed
ictiv
e
ca
p
ab
ilit
y
.
B
y
in
co
r
p
o
r
atin
g
C
NNs
f
o
r
s
p
atial
f
ea
tu
r
e
ex
tr
ac
tio
n
,
L
STM
s
f
o
r
ca
p
tu
r
in
g
tem
p
o
r
al
p
atter
n
s
,
an
d
GPs
f
o
r
u
n
ce
r
tain
ty
m
o
d
elin
g
,
t
h
e
m
o
d
el
en
h
an
ce
s
d
ec
is
io
n
-
m
ak
in
g
f
o
r
T
V
s
ch
ed
u
lin
g
,
a
u
d
ien
ce
tar
g
etin
g
,
an
d
co
n
ten
t
s
tr
ateg
y
.
C
o
m
p
ar
ativ
e
an
aly
s
is
s
h
o
wed
th
at
tr
ad
itio
n
al
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els,
s
u
ch
as
RF
an
d
SVM,
s
tr
u
g
g
led
to
ca
p
tu
r
e
th
e
d
y
n
am
ic
n
atu
r
e
o
f
v
iewe
r
s
h
ip
tr
e
n
d
s
,
wh
ile
d
ee
p
lear
n
in
g
m
o
d
els
al
o
n
e,
s
u
c
h
as
s
tan
d
al
o
n
e
C
NNs,
lack
ed
t
h
e
ab
ilit
y
to
m
o
d
el
s
eq
u
en
tial
d
ep
en
d
e
n
cies.
T
h
e
s
u
p
er
i
o
r
p
e
r
f
o
r
m
a
n
ce
o
f
t
h
e
h
y
b
r
id
ap
p
r
o
ac
h
c
o
n
f
ir
m
s
th
at
m
u
lti
-
s
o
u
r
ce
in
teg
r
atio
n
an
d
d
ee
p
le
ar
n
in
g
te
ch
n
iq
u
es p
r
o
v
id
e
a
s
ig
n
if
ican
t a
d
v
an
tag
e
i
n
au
d
ie
n
c
e
p
r
ed
ictio
n
.
Desp
ite
it
s
s
tr
en
g
th
s
,
th
e
m
o
d
el
h
as
lim
itat
io
n
s
.
Yo
u
T
u
b
e
e
n
g
ag
em
e
n
t
d
ata
m
ay
in
tr
o
d
u
c
e
p
latf
o
r
m
-
s
p
ec
if
ic
b
iases
,
as
alg
o
r
ith
m
i
c
r
ec
o
m
m
e
n
d
atio
n
s
in
f
lu
en
ce
co
n
ten
t
v
is
ib
ilit
y
an
d
in
ter
a
ctio
n
s
.
T
h
is
r
aises
co
n
ce
r
n
s
ab
o
u
t
g
en
er
aliza
b
ilit
y
,
s
u
g
g
esti
n
g
th
at
f
u
t
u
r
e
s
tu
d
ies
s
h
o
u
ld
in
teg
r
ate
cr
o
s
s
-
p
la
tf
o
r
m
en
g
ag
em
e
n
t
d
ata
f
r
o
m
T
ik
T
o
k
,
Face
b
o
o
k
,
an
d
T
witter
.
Ad
d
itio
n
ally
,
th
e
co
m
p
u
tatio
n
al
co
m
p
lex
ity
o
f
th
e
C
NN
-
L
STM
-
GP
m
o
d
el
p
o
s
es
ch
allen
g
es
f
o
r
r
ea
l
-
tim
e
d
ep
lo
y
m
en
t,
r
e
q
u
ir
in
g
o
p
tim
izatio
n
tech
n
iq
u
es
s
u
ch
as
m
o
d
el
c
o
m
p
r
ess
io
n
,
q
u
an
tizatio
n
,
a
n
d
p
r
u
n
i
n
g
.
Fin
ally
,
s
in
ce
th
e
m
o
d
el
was
tr
ain
ed
o
n
L
aa
y
o
u
n
e
T
V
d
ata,
its
ap
p
licab
ilit
y
to
o
th
er
b
r
o
ad
ca
s
ter
s
an
d
m
ar
k
ets
r
em
ai
n
s
an
o
p
en
q
u
esti
o
n
.
E
x
p
a
n
d
in
g
th
e
d
ataset
to
g
lo
b
al
TV
n
etwo
r
k
s
wo
u
ld
im
p
r
o
v
e
r
o
b
u
s
tn
ess
an
d
ad
ap
tab
i
lity
.
Fu
tu
r
e
r
esear
ch
co
u
ld
ex
p
lo
r
e
s
o
cial
m
ed
ia
s
en
tim
en
t
an
aly
s
is
an
d
tr
an
s
f
o
r
m
er
-
b
ased
ar
c
h
itectu
r
es
(
e.
g
.
,
b
id
ir
ec
tio
n
al
e
n
co
d
e
r
r
e
p
r
esen
tatio
n
s
f
r
o
m
tr
an
s
f
o
r
m
e
r
s
(
B
E
R
T
)
,
g
en
er
ativ
e
p
r
e
-
tr
a
in
ed
tr
an
s
f
o
r
m
er
4
(
GPT
-
4
)
)
t
o
r
e
f
in
e
a
u
d
ien
ce
p
r
ef
e
r
en
ce
m
o
d
el
in
g
.
A
d
d
it
io
n
ally
,
r
ein
f
o
r
ce
m
en
t
lea
r
n
i
n
g
-
b
ased
ad
ap
tiv
e
s
ch
ed
u
lin
g
co
u
ld
en
a
b
le
d
y
n
a
m
ic,
r
ea
l
-
tim
e
p
r
o
g
r
am
a
d
ju
s
tm
en
ts
.
Ad
d
r
ess
in
g
th
ese
ch
allen
g
es
will
f
u
r
th
e
r
en
h
an
ce
ar
tific
ial
in
tellig
en
c
e
(
AI
)
-
d
r
iv
e
n
p
r
ed
ictiv
e
an
a
ly
tics
,
o
p
tim
izin
g
p
r
o
g
r
am
m
in
g
s
tr
at
eg
ies
an
d
tr
an
s
f
o
r
m
in
g
au
d
ie
n
ce
en
g
a
g
e
m
en
t in
th
e
TV
in
d
u
s
tr
y
.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
tack
led
th
e
ch
allen
g
es
o
f
o
p
tim
izin
g
p
r
o
g
r
am
m
i
n
g
s
ch
ed
u
les
an
d
p
r
ed
ictin
g
T
V
p
r
o
g
r
am
s
u
cc
ess
f
o
r
T
V
L
aa
y
o
u
n
e
b
y
in
teg
r
atin
g
p
eo
p
le
m
ete
r
au
d
ie
n
ce
m
etr
ics
with
d
ig
ital
en
g
ag
em
en
t
m
etr
ics
an
d
em
p
lo
y
in
g
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es.
Ou
r
f
in
d
in
g
s
p
r
o
v
id
e
co
n
clu
s
iv
e
ev
id
e
n
ce
th
at
co
m
b
in
in
g
tr
ad
itio
n
al
T
V
r
atin
g
s
with
d
ig
ital
au
d
ien
ce
in
ter
ac
tio
n
s
e
n
h
an
ce
s
f
o
r
ec
asti
n
g
ac
c
u
r
ac
y
,
b
r
id
g
in
g
th
e
g
ap
b
etwe
en
co
n
v
en
tio
n
al
TV
c
o
n
s
u
m
p
tio
n
an
d
m
o
d
er
n
o
n
lin
e
v
iewin
g
b
eh
av
io
r
s
.
B
y
lev
er
ag
in
g
a
h
y
b
r
id
d
ee
p
lear
n
in
g
m
o
d
el
i
n
teg
r
atin
g
C
NNs,
L
STM
s
,
an
d
GPs
,
th
is
s
tu
d
y
d
em
o
n
s
tr
ated
s
ig
n
if
ica
n
t
im
p
r
o
v
em
en
ts
in
p
r
ed
ictin
g
au
d
ien
ce
en
g
ag
em
e
n
t.
T
h
e
r
esu
lts
co
n
f
ir
m
e
d
th
at
m
u
lti
-
s
o
u
r
ce
d
ata
f
u
s
io
n
en
h
a
n
ce
s
T
V
s
c
h
e
d
u
l
i
n
g
e
f
f
i
c
i
e
n
c
y
a
n
d
s
u
p
p
o
r
t
s
d
a
t
a
-
d
r
i
v
e
n
d
e
c
is
i
o
n
-
m
a
k
i
n
g
.
T
h
is
m
o
d
e
l
o
f
f
e
r
s
a
s
c
a
la
b
l
e
a
n
d
a
d
a
p
ta
b
l
e
f
r
a
m
e
w
o
r
k
f
o
r
o
p
t
i
m
i
z
i
n
g
p
r
o
g
r
a
m
m
i
n
g
s
t
r
at
eg
i
e
s
,
e
n
s
u
r
i
n
g
c
o
n
t
e
n
t
r
e
a
c
h
es
th
e
r
i
g
h
t
a
u
d
i
e
n
c
e
a
t
t
h
e
r
i
g
h
t
t
im
e
.
B
ey
o
n
d
im
p
r
o
v
in
g
c
o
n
ten
t
s
ch
ed
u
lin
g
f
o
r
T
V
L
aa
y
o
u
n
e
,
th
ese
in
s
ig
h
ts
p
av
e
th
e
way
f
o
r
m
o
r
e
in
tellig
en
t
b
r
o
ad
ca
s
tin
g
d
ec
i
s
io
n
s
.
Fu
tu
r
e
r
esear
ch
s
h
o
u
l
d
f
o
cu
s
o
n
ex
p
an
d
i
n
g
d
atas
et
d
iv
er
s
ity
ac
r
o
s
s
m
u
ltip
le
TV
n
etwo
r
k
s
an
d
in
co
r
p
o
r
atin
g
r
ea
l
-
tim
e
au
d
i
en
ce
in
ter
ac
tio
n
s
to
r
ef
in
e
ad
ap
tab
ilit
y
.
T
h
ese
ad
v
an
ce
m
e
n
ts
will
f
u
r
th
er
e
n
h
an
ce
au
d
ien
ce
m
ea
s
u
r
e
m
en
t
m
eth
o
d
o
lo
g
ies
an
d
s
u
p
p
o
r
t
t
h
e
ev
o
lu
tio
n
o
f
AI
-
d
r
iv
en
p
r
o
g
r
am
m
in
g
s
tr
ateg
ies in
th
e
TV
in
d
u
s
tr
y
.
ACK
NO
WL
E
DG
E
M
E
NT
S
W
e
s
in
ce
r
ely
th
an
k
I
B
N
T
o
f
ail
Un
iv
er
s
ity
f
o
r
th
eir
c
o
n
ti
n
u
o
u
s
s
u
p
p
o
r
t
an
d
en
co
u
r
ag
e
m
en
t.
Ou
r
g
r
atitu
d
e
also
g
o
es
to
T
V
L
aa
y
o
u
n
e
f
o
r
th
eir
i
n
v
alu
a
b
le
r
eso
u
r
ce
s
,
co
llab
o
r
atio
n
,
an
d
p
r
ac
tical
in
s
ig
h
ts
,
wh
ich
wer
e
in
s
tr
u
m
en
tal
in
d
ev
elo
p
in
g
an
d
im
p
lem
en
tin
g
o
u
r
m
ac
h
in
e
lear
n
i
n
g
m
o
d
el
f
o
r
p
r
ed
ictin
g
T
V
p
r
o
g
r
a
m
s
u
cc
ess
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
e
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
353
-
3
6
3
362
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Kh
alid
E
l Fay
q
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Said
T
k
atek
✓
✓
✓
✓
✓
✓
✓
✓
✓
L
ah
ce
n
I
d
o
u
g
lid
✓
✓
✓
✓
✓
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
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
co
n
f
lict o
f
in
ter
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
u
s
ed
in
th
is
s
tu
d
y
ar
e
co
n
f
id
en
tial
an
d
ca
n
n
o
t
b
e
m
ad
e
p
u
b
licly
av
ailab
le
o
r
s
h
ar
ed
with
o
th
er
p
ar
ties
.
T
h
ese
d
ata
wer
e
u
s
ed
ex
clu
s
iv
ely
f
o
r
th
e
p
u
r
p
o
s
es
o
f
th
is
r
esear
ch
.
Du
e
to
p
r
iv
ac
y
a
n
d
co
n
f
id
en
tiality
a
g
r
ee
m
en
ts
,
ac
ce
s
s
to
th
e
d
ataset
is
r
estricte
d
.
RE
F
E
R
E
NC
E
S
[
1
]
L.
N
i
x
o
n
,
“
P
r
e
d
i
c
t
i
n
g
y
o
u
r
f
u
t
u
r
e
a
u
d
i
e
n
c
e
’
s
p
o
p
u
l
a
r
t
o
p
i
c
s
t
o
o
p
t
i
mi
z
e
TV
c
o
n
t
e
n
t
mar
k
e
t
i
n
g
s
u
c
c
e
ss
,
”
i
n
AI
4
T
V
2
0
2
0
-
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
W
o
rks
h
o
p
o
n
AI
f
o
r
S
m
a
rt
T
V
C
o
n
t
e
n
t
Pr
o
d
u
c
t
i
o
n
,
Ac
c
e
ss
a
n
d
D
e
l
i
v
e
ry
,
O
c
t
.
2
0
2
0
,
p
p
.
5
–
1
0
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
2
2
8
3
9
.
3
4
2
3
0
6
2
.
[
2
]
M
.
E.
C
a
mm
a
r
a
n
o
,
A
.
G
u
a
r
i
n
o
,
D
.
M
a
l
a
n
d
r
i
n
o
,
a
n
d
R
.
Z
a
c
c
a
g
n
i
n
o
,
“
TV
sh
o
w
s
p
o
p
u
l
a
r
i
t
y
p
r
e
d
i
c
t
i
o
n
o
f
g
e
n
r
e
-
i
n
d
e
p
e
n
d
e
n
t
TV
seri
e
s
t
h
r
o
u
g
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
a
p
p
r
o
a
c
h
e
s
,
”
Mu
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
3
,
n
o
.
3
1
,
p
p
.
7
5
7
5
7
–
7
5
7
8
0
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
024
-
1
8
5
1
8
-
z.
[
3
]
J.
M
.
L
u
c
a
s
a
n
d
S
.
L
a
z
a
r
u
s
,
“
A
u
d
i
e
n
c
e
p
e
r
c
e
p
t
i
o
n
o
n
t
h
e
i
mp
a
c
t
o
f
t
e
l
e
v
i
si
o
n
r
e
a
l
i
t
y
s
h
o
w
s
o
n
t
h
e
mo
r
a
l
l
i
v
e
s
o
f
a
d
o
l
e
s
c
e
n
t
s
i
n
Ta
r
a
b
a
S
t
a
t
e
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
H
u
m
a
n
i
t
i
e
s,
Ed
u
c
a
t
i
o
n
,
a
n
d
S
o
c
i
a
l
S
c
i
e
n
c
e
s
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
2
0
4
–
2
3
0
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
5
8
5
7
8
/
i
j
h
e
ss
.
v
2
i
2
.
3
2
4
2
.
[
4
]
K
.
E
l
F
a
y
q
,
S
.
T
k
a
t
e
k
,
a
n
d
L
.
I
d
o
u
g
l
i
d
,
“
P
r
e
d
i
c
t
i
n
g
t
e
l
e
v
i
s
i
o
n
p
r
o
g
r
a
ms s
u
c
c
e
ss
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
(
I
J
E
C
E)
,
v
o
l
.
1
4
,
n
o
.
5
,
p
p
.
5
5
0
2
–
5
5
1
2
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
5
.
p
p
5
5
0
2
-
5
5
1
2
.
[
5
]
J.
Zh
o
u
,
Z
.
W
e
i
,
B
.
P
e
n
g
,
a
n
d
F
.
C
h
i
,
“
R
e
s
e
a
r
c
h
a
n
d
a
p
p
l
i
c
a
t
i
o
n
o
f
f
i
l
m a
n
d
t
e
l
e
v
i
si
o
n
l
i
t
e
r
a
t
u
r
e
r
e
c
o
mm
e
n
d
a
t
i
o
n
b
a
s
e
d
o
n
sec
u
r
e
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
M
o
b
i
l
e
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
2
0
2
1
,
p
p
.
1
–
1
0
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
4
0
6
6
2
6
7
.
[
6
]
B
.
R
.
Je
y
a
v
a
d
h
a
n
a
m,
V
.
V
.
R
a
m
a
l
i
n
g
a
m,
V
.
S
u
g
u
mara
n
,
a
n
d
D
.
R
a
j
k
u
mar,
“
P
r
e
d
i
c
t
i
v
e
a
n
a
l
y
s
i
s
o
f
o
n
l
i
n
e
t
e
l
e
v
i
s
i
o
n
v
i
d
e
o
s
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
i
n
Fu
n
d
a
m
e
n
t
a
l
s
a
n
d
Me
t
h
o
d
s
o
f
M
a
c
h
i
n
e
a
n
d
D
e
e
p
L
e
a
rn
i
n
g
:
A
l
g
o
ri
t
h
m
s,
T
o
o
l
s,
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
W
i
l
e
y
,
2
0
2
2
,
p
p
.
2
3
7
–
2
5
7
.
[
7
]
G
.
V
e
r
m
a
a
n
d
H
.
V
e
r
m
a
,
“
P
r
e
d
i
c
t
i
n
g
b
o
l
l
y
w
o
o
d
mo
v
i
e
s
s
u
c
c
e
ss
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
-
2019
A
m
i
t
y
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
AI
C
A
I
2
0
1
9
,
F
e
b
.
2
0
1
9
,
p
p
.
1
0
2
–
1
0
5
,
d
o
i
:
1
0
.
1
1
0
9
/
A
I
C
A
I
.
2
0
1
9
.
8
7
0
1
2
3
9
.
[
8
]
D
.
O
.
O
y
e
w
o
l
a
a
n
d
E
.
G
.
D
a
d
a
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
f
o
r
p
r
e
d
i
c
t
i
n
g
t
h
e
p
o
p
u
l
a
r
i
t
y
o
f
m
o
v
i
e
s,”
J
o
u
rn
a
l
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
S
y
s
t
e
m
s
,
v
o
l
.
4
,
n
o
.
1
,
p
p
.
6
5
–
8
2
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
6
9
/
a
i
s.
2
0
2
2
0
4
0
1
0
5
.
[
9
]
V
.
G
u
p
t
a
e
t
a
l
.
,
“
P
r
e
d
i
c
t
i
n
g
a
t
t
r
i
b
u
t
e
s
b
a
se
d
m
o
v
i
e
s
u
c
c
e
ss
t
h
r
o
u
g
h
e
n
sem
b
l
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
2
,
n
o
.
7
,
p
p
.
9
5
9
7
–
9
6
2
6
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
0
4
2
-
0
2
1
-
1
1
5
5
3
-
0.
[
1
0
]
R
.
A
.
A
b
a
r
j
a
,
“
M
o
v
i
e
r
a
t
i
n
g
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
s
e
d
o
n
h
i
s
t
o
r
i
c
a
l
v
a
l
u
e
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
m
e
r
g
i
n
g
T
r
e
n
d
s
i
n
E
n
g
i
n
e
e
r
i
n
g
R
e
s
e
a
r
c
h
,
v
o
l
.
8
,
n
o
.
5
,
p
p
.
2
1
5
6
–
2
1
6
4
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
3
0
5
3
4
/
i
j
e
t
e
r
/
2
0
2
0
/
1
0
9
8
5
2
0
2
0
.
[
1
1
]
H
.
S
h
a
r
ma
,
S
.
P
a
n
g
a
o
n
k
a
r
,
R
.
G
u
n
j
a
n
,
a
n
d
P
.
R
o
k
a
d
e
,
“
S
e
n
t
i
me
n
t
a
l
a
n
a
l
y
si
s o
f
m
o
v
i
e
r
e
v
i
e
w
s
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
T
M
W
e
b
o
f
C
o
n
f
e
r
e
n
c
e
s
,
v
o
l
.
5
3
,
p
.
0
2
0
0
6
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
5
1
/
i
t
m
c
o
n
f
/
2
0
2
3
5
3
0
2
0
0
6
.
[
1
2
]
B
.
C
i
z
mec
i
a
n
d
S
.
G
.
O
g
u
d
u
c
u
,
“
P
r
e
d
i
c
t
i
n
g
I
M
D
b
r
a
t
i
n
g
s
o
f
p
r
e
-
r
e
l
e
a
se
mo
v
i
e
s
w
i
t
h
f
a
c
t
o
r
i
z
a
t
i
o
n
mac
h
i
n
e
s
u
si
n
g
s
o
c
i
a
l
me
d
i
a
,
”
i
n
U
BM
K
2
0
1
8
-
3
r
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
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
e
p
.
2
0
1
8
,
p
p
.
1
7
3
–
1
7
8
,
d
o
i
:
1
0
.
1
1
0
9
/
U
B
M
K
.
2
0
1
8
.
8
5
6
6
6
6
1
.
[
1
3
]
A
.
C
r
i
s
c
i
,
V
.
G
r
a
s
s
o
,
P
.
N
e
s
i
,
G
.
P
a
n
t
a
l
e
o
,
I
.
P
a
o
l
i
,
a
n
d
I
.
Z
a
z
a
,
“
P
r
e
d
i
c
t
i
n
g
T
V
p
r
o
g
r
a
m
m
e
a
u
d
i
e
n
c
e
b
y
u
s
i
n
g
T
w
i
t
t
e
r
b
a
s
e
d
m
e
t
r
i
c
s
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
7
7
,
n
o
.
1
0
,
p
p
.
1
2
2
0
3
–
1
2
2
3
2
,
M
a
y
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
017
-
4880
-
x.
[
1
4
]
A
.
K
u
p
a
v
sk
i
i
,
A
.
U
m
n
o
v
,
G
.
G
u
s
e
v
,
a
n
d
P
.
S
e
r
d
y
u
k
o
v
,
“
P
r
e
d
i
c
t
i
n
g
t
h
e
a
u
d
i
e
n
c
e
si
z
e
o
f
a
t
w
e
e
t
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
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
W
e
b
l
o
g
s
a
n
d
S
o
c
i
a
l
M
e
d
i
a
,
I
C
WS
M
2
0
1
3
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
6
9
3
–
6
9
6
,
A
u
g
.
2
0
1
3
,
d
o
i
:
1
0
.
1
6
0
9
/
i
c
w
sm.
v
7
i
1
.
1
4
4
5
4
.
[
1
5
]
L.
S
o
n
g
,
Y
.
S
h
i
,
a
n
d
G
.
K
.
F
.
Ts
o
,
“
C
o
mm
e
r
c
i
a
l
a
u
d
i
e
n
c
e
r
e
t
e
n
t
i
o
n
o
f
t
e
l
e
v
i
s
i
o
n
p
r
o
g
r
a
ms:
me
a
su
r
e
me
n
t
a
n
d
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
A
d
v
e
rt
i
si
n
g
,
v
o
l
.
4
1
,
n
o
.
3
,
p
p
.
4
3
5
–
4
6
1
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
0
/
0
2
6
5
0
4
8
7
.
2
0
2
1
.
1
9
0
6
5
4
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.