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.
40
,
No
.
1
,
Octo
b
er
2
0
2
5
,
p
p
.
4
8
0
~
4
8
9
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
40
.i
1
.
pp
480
-
4
8
9
480
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Wa
r
stra
tegy
as
sis
ted
Bi
-
LST
M
f
o
r
sentimen
t
a
na
ly
sis
of
custo
mer revie
w
Anils
a
g
a
r
T
.
,
Sy
ed
Abd
ul Sy
ed
S
.
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
r
i
n
g
,
B
.
S
.
A
b
d
u
r
R
a
h
m
a
n
C
r
e
sce
n
t
I
n
st
i
t
u
t
e
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
C
h
e
n
n
a
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
6
,
2
0
2
4
R
ev
is
ed
J
u
n
27
,
2
0
2
5
Acc
ep
ted
J
u
l
4
,
2
0
2
5
S
e
n
ti
m
e
n
t
a
n
a
ly
sis
(S
A)
sta
n
d
s
a
s
a
v
a
lu
a
b
le
to
o
l
fo
r
c
a
teg
o
r
izin
g
r
e
v
iew
s
to
d
isc
e
rn
p
o
sit
iv
e
o
r
n
e
g
a
ti
v
e
se
n
t
ime
n
ts.
S
a
ti
sfa
c
ti
o
n
o
f
c
u
st
o
m
e
rs
h
o
ld
s
a
p
iv
o
tal
ro
le
in
t
h
e
re
a
lm
o
f
c
u
sto
m
e
r
se
rv
ice
.
P
re
se
n
tl
y
,
c
u
sto
m
e
r
e
x
p
re
ss
io
n
e
n
tails
a
sig
n
ifi
c
a
n
t
v
o
l
u
m
e
o
f
r
e
v
iew
s
o
n
o
n
l
in
e
p
latfo
rm
s.
F
o
r
e
x
trac
ti
n
g
u
se
fu
l
i
n
fo
rm
a
ti
o
n
fro
m
m
a
ss
iv
e
re
v
iew
s,
th
e
c
a
teg
o
riza
ti
o
n
o
f
re
v
iew
s
in
to
p
o
siti
v
e
o
r
n
e
g
a
ti
v
e
S
A
is
e
s
se
n
ti
a
l.
F
o
r
e
n
h
a
n
c
in
g
t
h
e
e
ffi
c
ien
c
y
o
f
c
u
sto
m
e
r
re
v
iew
d
e
tec
ti
o
n
,
t
h
is
wo
rk
p
re
se
n
ts
a
wa
r
stra
teg
y
a
lg
o
rit
h
m
(
WS
A
)
-
b
i
d
irec
ti
o
n
a
l
lo
n
g
sh
o
rt
-
term
m
e
m
o
ry
(
Bi
-
LS
TM
)
fo
r
c
u
sto
m
e
r
re
v
iew
c
las
sifica
ti
o
n
u
sin
g
t
h
e
Tri
p
A
d
v
is
o
r
d
a
tas
e
t.
In
i
t
ially
,
th
e
p
re
-
p
ro
c
e
ss
in
g
sta
g
e
is
c
a
rried
o
u
t
,
a
n
d
t
h
e
sk
ip
-
g
ra
m
-
b
a
se
d
wo
rd
e
m
b
e
d
d
i
n
g
i
s
p
e
rfo
rm
e
d
.
F
o
r
c
a
teg
o
rizin
g
t
h
e
e
x
trac
ted
fe
a
tu
re
s,
t
h
e
d
e
e
p
lea
rn
in
g
m
o
d
e
l
Bi
-
LS
TM
-
W
S
A
is
p
re
se
n
ted
.
Ac
c
u
ra
c
y
a
n
d
p
re
c
isio
n
v
a
l
u
e
s
a
c
h
iev
e
d
a
re
9
7
.
1
%
a
n
d
9
7
.
5
%
re
sp
e
c
ti
v
e
l
y
.
K
ey
w
o
r
d
s
:
B
id
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
C
u
s
to
m
er
s
er
v
ice
Po
s
itiv
e
o
r
n
eg
ativ
e
Sen
tim
en
t a
n
aly
s
is
Usef
u
l in
f
o
r
m
atio
n
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
:
An
ils
ag
ar
T
.
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
B
.
S.
Ab
d
u
r
R
ah
m
an
C
r
escen
t
I
n
s
titu
te
o
f
Scien
ce
an
d
T
ec
h
n
o
lo
g
y
C
h
en
n
ai,
T
am
il Na
d
u
,
I
n
d
ia
E
m
ail:
an
ilts
ag
ar
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
C
u
s
to
m
e
r
s
atis
f
ac
tio
n
r
ep
r
esen
ts
th
e
s
u
b
jectiv
e
ass
es
s
m
en
t
th
at
co
n
s
u
m
er
s
m
ak
e,
s
itu
ated
b
etwe
en
th
eir
in
itial
ex
p
ec
tatio
n
s
an
d
t
h
e
ac
tu
al
e
x
p
er
ien
ce
s
t
h
ey
e
n
co
u
n
ter
[
1
]
.
I
n
co
n
tem
p
o
r
ar
y
tim
es,
a
s
ig
n
if
ican
t
n
u
m
b
er
o
f
cu
s
to
m
er
s
a
r
ticu
late
th
eir
o
p
in
io
n
s
t
h
r
o
u
g
h
r
ev
ie
ws
p
o
s
ted
o
n
o
n
lin
e
p
latf
o
r
m
s
s
u
ch
as
Yelp
an
d
T
r
ip
Ad
v
is
o
r
,
d
etailin
g
th
eir
lev
el
o
f
s
atis
f
ac
tio
n
with
th
e
p
r
o
d
u
cts
o
r
s
er
v
ices
th
ey
h
a
v
e
ac
q
u
ir
ed
.
T
h
ese
cu
s
to
m
er
r
ev
iews
wield
co
n
s
id
er
ab
le
in
f
lu
e
n
ce
,
as
th
ey
ca
n
co
n
tr
ib
u
te
to
e
n
h
an
cin
g
th
e
v
is
ib
ilit
y
an
d
ap
p
ea
l
o
f
th
e
s
eller
'
s
o
f
f
er
in
g
s
.
A
r
e
s
tau
r
an
t
o
p
e
r
ates
as
an
estab
l
is
h
m
en
t
th
at
b
o
th
p
r
ep
a
r
es
an
d
p
r
o
v
id
es
f
o
o
d
to
cu
s
to
m
er
s
in
ex
ch
a
n
g
e
f
o
r
p
a
y
m
en
t [
2
]
.
L
ev
er
ag
in
g
c
u
s
to
m
er
r
ev
iews
o
n
r
estau
r
a
n
ts
s
o
u
r
ce
d
f
r
o
m
v
ar
io
u
s
web
s
ites
an
d
s
o
cial
n
etwo
r
k
s
p
r
esen
ts
an
ea
s
y
ap
p
r
o
ac
h
to
ass
is
t
r
estau
r
an
t
o
wn
er
s
in
g
ain
in
g
a
d
ee
p
e
r
u
n
d
e
r
s
tan
d
in
g
o
f
th
eir
cu
s
to
m
er
s
'
p
r
ef
er
en
ce
s
a
n
d
s
u
s
tain
in
g
p
r
o
f
it.
T
h
ese
f
ee
d
b
ac
k
s
p
r
o
v
id
e
cu
s
to
m
er
s
with
a
p
latf
o
r
m
f
o
r
ex
p
r
ess
in
g
th
eir
o
p
in
io
n
s
o
p
e
n
ly
an
d
ca
n
d
id
l
y
[
3
]
.
Ob
tain
in
g
r
ev
iew
d
at
a
th
r
o
u
g
h
th
is
m
eth
o
d
is
f
aster
co
m
p
ar
ed
to
co
n
v
en
tio
n
al
in
ter
v
iews
an
d
s
u
r
v
ey
s
,
with
th
e
ad
d
ed
b
e
n
ef
it
o
f
ac
q
u
i
r
in
g
d
ata
in
r
ea
l
-
tim
e.
Fro
m
th
e
p
er
s
p
ec
tiv
e
o
f
d
ata
co
llectio
n
an
d
a
n
al
y
s
is
,
u
tili
zin
g
s
o
cial
m
ed
ia
d
ata
also
s
tr
ea
m
lin
es
th
e
p
r
o
ce
s
s
,
s
av
in
g
tim
e
an
d
r
ed
u
cin
g
d
ata
co
llect
io
n
ex
p
e
n
s
es [
4
]
.
Sen
tim
en
t
an
aly
s
is
(
SA
)
s
er
v
es
as
a
d
ev
ice
f
o
r
e
x
tr
ac
tin
g
th
e
o
p
in
i
o
n
s
ex
p
r
ess
ed
b
y
a
cu
s
to
m
er
r
eg
ar
d
in
g
a
s
p
ec
if
ic
en
tity
.
W
h
en
ap
p
li
ed
to
r
ev
iews,
SA
d
e
lv
es
in
to
in
v
esti
g
atin
g
th
e
o
p
i
n
io
n
s
s
u
r
r
o
u
n
d
in
g
a
p
r
o
d
u
ct.
T
h
is
an
aly
tical
p
r
o
ce
s
s
r
elies
o
n
n
atu
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
(
NL
P
)
,
an
d
tex
t
an
a
ly
s
is
f
o
r
ex
tr
ac
tin
g
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
Wa
r
s
tr
a
teg
y
a
s
s
i
s
ted
B
i
-
LS
T
M fo
r
s
en
timen
t a
n
a
lysi
s
o
f c
u
s
to
mer revie
w
(
A
n
ils
a
g
a
r
T.
)
481
r
elev
an
t
in
f
o
r
m
atio
n
wh
ile
d
is
r
eg
ar
d
in
g
u
n
n
ec
ess
ar
y
elem
en
ts
.
I
ts
o
b
jectiv
e
is
to
d
is
ce
r
n
th
e
u
n
d
er
ly
in
g
s
en
tim
en
t c
o
n
v
ey
e
d
in
a
s
en
te
n
ce
,
wh
eth
er
it lea
n
s
to
war
d
s
a
n
eg
ativ
e
o
r
p
o
s
itiv
e
ev
al
u
atio
n
[
5
]
.
Dis
tin
g
u
is
h
in
g
n
eg
ativ
e
an
d
p
o
s
itiv
e
r
ev
iews
ca
n
b
e
ac
co
m
p
lis
h
ed
eith
er
in
a
m
an
u
al
o
r
au
to
m
atica
lly
.
Nev
er
th
eless
,
m
an
u
al
d
ete
ctio
n
te
n
d
s
to
b
e
co
s
tly
,
tim
e
-
co
n
s
u
m
in
g
,
an
d
co
m
p
ar
ativ
ely
less
ac
cu
r
ate
wh
en
co
n
tr
asted
with
au
to
m
ate
d
m
eth
o
d
s
[
6
]
,
[
7
]
.
Du
r
in
g
th
e
last
two
d
ec
ad
es
,
s
ig
n
if
ican
t
s
tr
id
es
h
av
e
b
ee
n
m
ad
e
in
e
n
h
an
cin
g
au
to
m
ated
r
ev
iews
d
etec
tio
n
tech
n
i
q
u
es.
Ma
ch
i
n
e
lear
n
in
g
(
ML
)
a
n
d
d
ee
p
lear
n
in
g
(
DL
)
h
av
e
em
e
r
g
ed
as
h
ig
h
ly
ef
f
ec
tiv
e
m
ea
n
s
f
o
r
id
en
tify
in
g
r
ev
iews.
T
h
ese
m
eth
o
d
s
lev
er
ag
e
v
ar
io
u
s
f
ea
tu
r
es,
in
clu
d
in
g
u
s
er
b
eh
av
i
o
r
an
d
r
ev
iew
c
o
n
te
n
t,
to
p
r
ec
is
ely
ca
teg
o
r
ize
r
e
v
iews
as
p
o
s
itiv
e
o
r
n
eg
ativ
e.
M
o
r
eo
v
e
r
,
m
ain
tain
i
n
g
a
h
ig
h
ac
cu
r
ac
y
is
im
p
o
r
ta
n
t.
Failu
r
e
to
d
o
s
o
c
o
u
ld
im
p
ed
e
u
s
er
s
'
ac
ce
s
s
to
tr
u
th
f
u
l
r
e
v
iews
an
d
u
n
d
er
m
in
e
th
e
cr
e
d
ib
ilit
y
o
f
tr
u
s
two
r
th
y
r
e
v
iewe
r
s
,
p
o
ten
tiall
y
d
im
in
is
h
in
g
t
h
eir
in
ce
n
tiv
e
to
co
n
tr
ib
u
te
t
o
th
e
p
latf
o
r
m
.
Mo
tiv
atio
n
:
DL
m
o
d
els
f
o
r
id
en
tify
in
g
f
a
k
e
r
ev
iews
h
av
e
th
r
ee
m
ain
ad
v
an
tag
es.
Firstl
y
,
th
ese
m
o
d
els
lev
er
ag
e
r
ea
l
v
al
u
e
b
a
s
ed
h
id
d
en
lay
er
s
to
au
t
o
m
atica
lly
cr
ea
te
co
m
p
lex
g
l
o
b
al
s
em
an
tical
f
ea
tu
r
es,
wh
ich
is
ch
allen
g
in
g
to
ac
h
i
ev
e
u
s
in
g
m
an
u
ally
cr
a
f
ted
f
ea
tu
r
es.
T
h
is
ap
p
r
o
ac
h
ef
f
ec
t
iv
ely
ad
d
r
ess
es
th
e
lim
itatio
n
s
o
f
co
n
v
e
n
tio
n
al
M
L
m
o
d
els.
Seco
n
d
l
y
,
DL
m
o
d
els
u
s
e
clu
s
ter
-
b
ased
wo
r
d
e
m
b
ed
d
in
g
s
as
in
p
u
t,
wh
ich
ca
n
b
e
d
er
iv
ed
f
r
o
m
r
a
w
in
p
u
t,
th
er
eb
y
o
v
er
co
m
i
n
g
th
e
s
ca
r
city
o
f
lab
elled
d
ata.
L
astl
y
,
DL
m
o
d
els
ca
n
r
ap
id
ly
lear
n
a
n
d
u
n
d
er
s
ta
n
d
th
e
c
o
n
s
is
ten
t stru
ctu
r
e
o
f
t
ex
t.
T
h
e
p
ap
e
r
f
o
llo
ws
th
is
s
tr
u
ctu
r
e:
s
ec
tio
n
2
ex
a
m
in
es
r
elate
d
wo
r
k
s
p
er
tin
en
t
to
th
e
s
u
g
g
ested
m
o
d
el.
Sectio
n
3
p
r
o
v
id
es
a
co
n
cise
d
escr
ip
tio
n
o
f
th
e
s
u
g
g
ested
m
o
d
el.
Sectio
n
4
p
r
esen
ts
th
e
f
in
d
in
g
s
f
r
o
m
th
e
co
n
d
u
c
te
d
ex
p
e
r
im
en
ts
.
L
astl
y
,
Sectio
n
5
co
n
clu
d
es th
e
p
ap
e
r
.
2.
RE
L
AT
E
D
WO
RK
S
Z
h
ao
et
a
l.
[
8
]
p
r
esen
ted
a
lo
c
al
s
ea
r
ch
im
p
r
o
v
ed
b
at
o
p
tim
izer
with
E
lm
an
n
eu
r
al
n
etwo
r
k
(
L
SIBO
-
E
NN
)
f
o
r
SA
o
f
o
n
lin
e
p
r
o
d
u
cts.
I
n
itially
,
d
u
r
in
g
p
r
e
-
p
r
o
ce
s
s
in
g
th
e
p
r
o
ce
s
s
es
lik
e
to
k
en
izatio
n
,
Gen
is
m
lem
m
atiza
tio
n
,
an
d
s
n
o
w
b
all
s
tem
m
in
g
wer
e
ca
r
r
ied
o
u
t.
T
h
en
,
th
e
f
ea
tu
r
es
wer
e
ex
t
r
ac
ted
b
y
th
e
te
r
m
weig
h
tin
g
(TW
)
an
d
class
if
ied
b
y
th
e
L
SIBO
-
E
NN
,
an
d
ac
h
i
ev
ed
a
b
etter
ac
cu
r
ac
y
o
f
9
2
%
o
n
th
e
m
o
v
ie
a
n
d
T
V
d
ataset.
J
ain
et
a
l.
[
9
]
d
ev
elo
p
e
d
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NN
)
with
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
m
o
d
el
f
o
r
SA
b
y
u
s
e
r
-
g
en
er
ate
d
co
n
ten
t.
T
h
is
ex
is
tin
g
m
o
d
el
was
p
r
o
v
id
e
d
o
n
b
atch
n
o
r
m
aliza
tio
n
,
m
ax
p
o
o
lin
g
an
d
d
r
o
p
o
u
t.
E
x
p
er
im
en
tatio
n
was
p
er
f
o
r
m
e
d
o
n
T
witter
air
lin
e
an
d
air
lin
e
q
u
ality
d
atasets
an
d
ac
h
iev
ed
a
b
etter
ac
cu
r
ac
y
o
f
9
1
.
3
%.
Ku
m
ar
et
a
l.
[
1
0
]
d
ev
elo
p
ed
a
SA o
f
p
r
o
d
u
ct
r
e
v
iew
f
o
r
p
r
ed
ictin
g
th
e
s
atis
f
ac
tio
n
o
f
cu
s
to
m
er
u
s
in
g
E
E
G
r
esp
o
n
s
e.
T
h
is
ex
is
tin
g
wo
r
k
aim
ed
f
o
r
en
h
an
cin
g
th
e
p
er
f
o
r
m
an
ce
o
f
r
atin
g
p
r
ed
ictio
n
.
T
h
en
,
th
e
ar
tific
ial
b
ee
co
lo
n
y
(
AB
C
)
was
u
s
ed
f
o
r
o
p
tim
izin
g
r
atin
g
an
d
s
en
tim
en
tal
s
co
r
es
an
d
r
an
d
o
m
f
o
r
est
was
u
s
ed
f
o
r
class
if
icatio
n
.
Fin
ally
,
th
e
R
2
an
d
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
v
alu
es
a
ch
iev
ed
wer
e
0
.
7
2
an
d
0
.
2
9
.
Kau
r
an
d
Sh
a
r
m
a
[
1
1
]
in
t
r
o
d
u
ce
d
a
DL
b
ased
h
y
b
r
id
f
ea
t
u
r
e
e
x
t
r
ac
tio
n
m
o
d
el
f
o
r
cu
s
to
m
er
SA.
Featu
r
e
ex
tr
ac
tio
n
s
tag
es
lik
e
r
ev
iew
an
d
asp
ec
t
b
ased
f
ea
tu
r
es
wer
e
u
s
ed
to
co
n
s
tr
u
ct
th
e
h
y
b
r
id
f
ea
t
u
r
e
v
ec
to
r
.
At
last
,
th
e
L
STM
was u
s
ed
f
o
r
SA a
n
d
ac
h
ie
v
ed
a
b
etter
p
r
ec
is
io
n
o
f
9
4
.
4
%.
Haje
k
et
a
l.
[
1
2
]
p
r
esen
ted
an
as
p
ec
t
b
ased
SA
f
o
r
f
ak
e
r
ev
iew
id
e
n
tific
atio
n
in
e
-
c
o
m
m
er
ce
.
T
h
r
o
u
g
h
an
aly
s
is
o
f
an
Am
a
zo
n
r
ev
iew
d
ataset,
an
asp
ec
t
b
ased
m
o
d
el
id
en
tifie
d
two
cr
itical
f
ac
to
r
s
f
o
r
d
is
ce
r
n
in
g
f
ak
e
r
ev
iews.
T
h
is
u
n
d
er
s
co
r
es
th
e
im
p
o
r
tan
ce
o
f
lin
k
in
g
th
ese
two
f
ac
to
r
s
to
g
eth
er
.
At
last
,
th
e
wo
r
d
2
v
ec
t
-
L
DA
was u
s
ed
f
o
r
p
er
f
o
r
m
in
g
th
e
asp
ec
t b
ased
m
o
d
el.
Z
h
an
g
et
a
l.
[
1
3
]
u
tili
ze
d
n
e
u
tr
al
s
en
tim
en
tal
r
ev
iews
f
o
r
i
m
p
r
o
v
i
n
g
th
e
s
atis
f
ac
tio
n
o
f
cu
s
to
m
er
s
.
T
h
e
Kan
o
m
o
d
el
was
u
s
ed
f
o
r
ca
teg
o
r
izin
g
th
e
id
en
tifie
d
r
eq
u
ir
em
e
n
ts
o
f
cu
s
to
m
er
s
in
to
f
iv
e
p
r
o
d
u
ct
attr
ib
u
tes.
Ass
es
s
m
en
ts
co
n
d
u
cted
o
n
lap
t
o
p
an
d
s
m
ar
tp
h
o
n
e
d
atasets
,
d
em
o
n
s
tr
ate
th
at
th
e
in
clu
s
io
n
o
f
n
eu
tr
al
r
ev
iews
s
ig
n
if
ican
tly
alter
s
th
e
ca
teg
o
r
izatio
n
o
f
p
r
o
d
u
ct
attr
ib
u
tes
co
m
p
ar
e
d
to
co
n
v
en
tio
n
al
m
eth
o
d
s
.
Nilash
i
et
a
l.
[
1
4
]
d
ev
elo
p
ed
d
ee
p
b
elief
n
etwo
r
k
(
DB
N
)
f
o
r
th
e
a
n
aly
s
is
o
f
o
n
lin
e
r
e
v
iews
an
d
r
ed
u
cin
g
d
im
en
s
io
n
ality
.
Her
e
,
th
e
s
elf
o
r
g
an
izin
g
m
a
p
(
SO
M
)
was
u
tili
ze
d
to
p
r
ed
ict
th
e
r
ev
iews.
T
h
e
L
DA
(
laten
t
d
ir
ich
let
allo
ca
tio
n
)
was
u
s
ed
f
o
r
f
ea
tu
r
e
ex
tr
ac
t
io
n
an
d
th
e
DB
N
was
u
s
ed
f
o
r
class
if
icatio
n
.
Sp
ec
if
icity
an
d
s
en
s
itiv
ity
v
al
u
es a
ch
iev
ed
wer
e
0
.
9
0
an
d
0
.
9
3
.
Po
p
u
lar
task
s
in
s
en
tim
en
t
a
n
aly
s
is
u
s
in
g
d
ee
p
lear
n
in
g
a
r
e
C
NN
[
15
]
,
[
1
6
]
,
2
DC
NN
[
1
7
]
,
[
1
8
]
,
3
DC
NN
[
1
9
]
,
L
STM
[
2
0
]
,
[
2
1
]
,
Bi
-
L
STM
[
2
2
]
,
GR
U
[
2
1
]
,
B
iGR
U
[
2
3
]
,
[
2
4
]
.
T
ab
le
1
p
r
o
v
id
es
th
e
s
ev
er
al
p
o
ten
tial
r
esear
ch
g
ap
s
an
d
ar
ea
s
f
o
r
f
u
r
th
e
r
ex
p
lo
r
atio
n
.
B
y
ad
d
r
ess
in
g
th
ese
g
ap
s
,
f
u
tu
r
e
r
esear
ch
ca
n
s
ig
n
if
ican
tly
ad
v
an
ce
th
e
f
iel
d
o
f
s
en
tim
en
t
an
aly
s
is
,
lev
er
ag
in
g
in
n
o
v
ativ
e
s
tr
ateg
ies
to
en
h
an
ce
m
o
d
el
p
er
f
o
r
m
an
ce
a
n
d
ap
p
licab
ilit
y
ac
r
o
s
s
d
iv
er
s
e
s
ce
n
ar
io
s
.
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.
40
,
No
.
1
,
Octo
b
er
20
25
:
480
-
4
8
9
482
T
ab
le
1
.
Po
ten
tial r
esear
ch
g
a
p
s
an
d
ar
ea
s
f
o
r
f
u
r
th
er
e
x
p
lo
r
atio
n
A
r
e
a
R
e
se
a
r
c
h
g
ap
O
p
p
o
r
t
u
n
i
t
y
I
n
t
e
g
r
a
t
i
o
n
o
f
w
a
r
st
r
a
t
e
g
y
c
o
n
c
e
p
t
s
Th
e
sp
e
c
i
f
i
c
a
p
p
l
i
c
a
t
i
o
n
o
f
w
a
r
s
t
r
a
t
e
g
y
p
r
i
n
c
i
p
l
e
s
i
n
se
n
t
i
m
e
n
t
a
n
a
l
y
si
s
h
a
s
n
o
t
b
e
e
n
t
h
o
r
o
u
g
h
l
y
e
x
p
l
o
r
e
d
.
R
e
s
e
a
r
c
h
c
o
u
l
d
i
n
v
e
s
t
i
g
a
t
e
h
o
w
s
t
r
a
t
e
g
i
c
c
o
n
c
e
p
t
s
su
c
h
a
s
t
a
c
t
i
c
a
l
d
e
c
i
si
o
n
-
ma
k
i
n
g
,
r
e
s
o
u
r
c
e
a
l
l
o
c
a
t
i
o
n
,
a
n
d
a
d
v
e
r
sar
i
a
l
st
r
a
t
e
g
i
e
s
c
a
n
b
e
met
a
p
h
o
r
i
c
a
l
l
y
a
p
p
l
i
e
d
t
o
se
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s.
D
e
v
e
l
o
p
n
o
v
e
l
mo
d
e
l
s
o
r
f
r
a
m
e
w
o
r
k
s
t
h
a
t
i
n
c
o
r
p
o
r
a
t
e
e
l
e
m
e
n
t
s
o
f
s
t
r
a
t
e
g
i
c
p
l
a
n
n
i
n
g
a
n
d
d
e
c
i
si
o
n
-
ma
k
i
n
g
i
n
t
o
t
h
e
a
r
c
h
i
t
e
c
t
u
r
e
o
f
B
i
-
LST
M
n
e
t
w
o
r
k
s f
o
r
i
mp
r
o
v
e
d
se
n
t
i
me
n
t
p
r
e
d
i
c
t
i
o
n
.
H
y
b
r
i
d
mo
d
e
l
d
e
v
e
l
o
p
me
n
t
W
h
i
l
e
B
i
-
LSTM
i
s
e
f
f
e
c
t
i
v
e
f
o
r
s
e
q
u
e
n
t
i
a
l
d
a
t
a
,
i
n
t
e
g
r
a
t
i
n
g
i
t
w
i
t
h
d
o
ma
i
n
-
s
p
e
c
i
f
i
c
st
r
a
t
e
g
i
e
s
(
e
.
g
.
,
w
a
r
s
t
r
a
t
e
g
y
)
c
o
u
l
d
b
e
u
n
d
e
r
e
x
p
l
o
r
e
d
.
Ex
p
e
r
i
m
e
n
t
w
i
t
h
h
y
b
r
i
d
mo
d
e
l
s
t
h
a
t
c
o
mb
i
n
e
B
i
-
LS
TM
w
i
t
h
o
t
h
e
r
t
e
c
h
n
i
q
u
e
s s
u
c
h
a
s
a
t
t
e
n
t
i
o
n
m
e
c
h
a
n
i
sms
,
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
,
o
r
g
a
me
t
h
e
o
r
y
t
o
e
n
h
a
n
c
e
t
h
e
mo
d
e
l
's
a
b
i
l
i
t
y
t
o
h
a
n
d
l
e
c
o
m
p
l
e
x
se
n
t
i
m
e
n
t
p
r
e
d
i
c
t
i
o
n
t
a
s
k
s.
D
a
t
a
s
e
t
a
n
d
d
o
m
a
i
n
-
s
p
e
c
i
f
i
c
c
h
a
l
l
e
n
g
e
s
C
u
r
r
e
n
t
d
a
t
a
se
t
s ma
y
n
o
t
f
u
l
l
y
c
a
p
t
u
r
e
t
h
e
n
u
a
n
c
e
s
o
f
w
a
r
st
r
a
t
e
g
y
t
e
r
mi
n
o
l
o
g
y
a
n
d
i
t
s
i
mp
a
c
t
o
n
se
n
t
i
me
n
t
i
n
c
u
s
t
o
mer r
e
v
i
e
w
s.
C
r
e
a
t
e
o
r
u
t
i
l
i
z
e
s
p
e
c
i
a
l
i
z
e
d
d
a
t
a
se
t
s
t
h
a
t
i
n
c
l
u
d
e
c
o
n
t
e
x
t
-
sp
e
c
i
f
i
c
l
a
n
g
u
a
g
e
a
n
d
t
e
r
m
i
n
o
l
o
g
y
r
e
l
a
t
e
d
t
o
w
a
r
st
r
a
t
e
g
y
,
e
n
s
u
r
i
n
g
t
h
a
t
t
h
e
m
o
d
e
l
i
s t
r
a
i
n
e
d
o
n
r
e
l
e
v
a
n
t
d
a
t
a
t
h
a
t
e
n
h
a
n
c
e
s
i
t
s
p
e
r
f
o
r
man
c
e
i
n
t
h
i
s
n
i
c
h
e
d
o
m
a
i
n
.
I
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
a
n
d
e
x
p
l
a
i
n
a
b
i
l
i
t
y
Th
e
i
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
o
f
mo
d
e
l
s
c
o
mb
i
n
i
n
g
c
o
m
p
l
e
x
st
r
a
t
e
g
i
e
s
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
a
r
c
h
i
t
e
c
t
u
r
e
s
l
i
k
e
B
i
-
LST
M
i
s
o
f
t
e
n
l
i
mi
t
e
d
.
D
e
v
e
l
o
p
t
e
c
h
n
i
q
u
e
s
f
o
r
i
m
p
r
o
v
i
n
g
t
h
e
e
x
p
l
a
i
n
a
b
i
l
i
t
y
o
f
t
h
e
m
o
d
e
l
’
s
p
r
e
d
i
c
t
i
o
n
s
,
ma
k
i
n
g
i
t
e
a
s
i
e
r
t
o
u
n
d
e
r
st
a
n
d
h
o
w
w
a
r
st
r
a
t
e
g
y
c
o
n
c
e
p
t
s
i
n
f
l
u
e
n
c
e
s
e
n
t
i
m
e
n
t
a
n
a
l
y
si
s
o
u
t
c
o
mes
.
P
e
r
f
o
r
ma
n
c
e
met
r
i
c
s
a
n
d
e
v
a
l
u
a
t
i
o
n
Ex
i
s
t
i
n
g
r
e
s
e
a
r
c
h
m
a
y
l
a
c
k
c
o
m
p
r
e
h
e
n
si
v
e
e
v
a
l
u
a
t
i
o
n
me
t
r
i
c
s
t
h
a
t
s
p
e
c
i
f
i
c
a
l
l
y
a
s
sess
t
h
e
i
mp
a
c
t
o
f
w
a
r
s
t
r
a
t
e
g
y
i
n
t
e
g
r
a
t
i
o
n
o
n
sen
t
i
m
e
n
t
a
n
a
l
y
si
s
p
e
r
f
o
r
ma
n
c
e
.
P
r
o
p
o
se
a
n
d
v
a
l
i
d
a
t
e
n
e
w
p
e
r
f
o
r
m
a
n
c
e
me
t
r
i
c
s t
h
a
t
c
o
n
si
d
e
r
b
o
t
h
t
h
e
a
c
c
u
r
a
c
y
o
f
s
e
n
t
i
me
n
t
p
r
e
d
i
c
t
i
o
n
a
n
d
t
h
e
e
f
f
e
c
t
i
v
e
n
e
ss
o
f
s
t
r
a
t
e
g
i
c
i
n
t
e
g
r
a
t
i
o
n
.
S
c
a
l
a
b
i
l
i
t
y
a
n
d
r
e
a
l
-
t
i
me
a
n
a
l
y
si
s
Th
e
r
e
i
s
l
i
mi
t
e
d
r
e
s
e
a
r
c
h
o
n
t
h
e
sc
a
l
a
b
i
l
i
t
y
a
n
d
r
e
a
l
-
t
i
me
a
p
p
l
i
c
a
t
i
o
n
o
f
su
c
h
m
o
d
e
l
s,
p
a
r
t
i
c
u
l
a
r
l
y
i
n
d
y
n
a
m
i
c
e
n
v
i
r
o
n
me
n
t
s
w
h
e
r
e
c
u
s
t
o
m
e
r
r
e
v
i
e
w
s a
r
e
g
e
n
e
r
a
t
e
d
c
o
n
t
i
n
u
o
u
sl
y
.
I
n
v
e
st
i
g
a
t
e
sc
a
l
a
b
l
e
a
r
c
h
i
t
e
c
t
u
r
e
s
a
n
d
o
p
t
i
m
i
z
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
t
h
a
t
a
l
l
o
w
t
h
e
mo
d
e
l
t
o
p
e
r
f
o
r
m e
f
f
i
c
i
e
n
t
l
y
i
n
r
e
a
l
-
t
i
m
e
s
c
e
n
a
r
i
o
s,
ma
i
n
t
a
i
n
i
n
g
h
i
g
h
a
c
c
u
r
a
c
y
w
h
i
l
e
p
r
o
c
e
ss
i
n
g
l
a
r
g
e
v
o
l
u
mes
o
f
d
a
t
a
.
C
r
o
ss
-
d
o
m
a
i
n
a
p
p
l
i
c
a
b
i
l
i
t
y
Th
e
c
u
r
r
e
n
t
r
e
s
e
a
r
c
h
f
o
c
u
s
ma
y
b
e
l
i
mi
t
e
d
t
o
sp
e
c
i
f
i
c
d
o
m
a
i
n
s,
w
i
t
h
o
u
t
e
x
p
l
o
r
i
n
g
t
h
e
b
r
o
a
d
e
r
a
p
p
l
i
c
a
b
i
l
i
t
y
o
f
w
a
r
s
t
r
a
t
e
g
y
-
a
s
si
s
t
e
d
s
e
n
t
i
m
e
n
t
a
n
a
l
y
si
s
i
n
o
t
h
e
r
f
i
e
l
d
s
.
Ex
p
l
o
r
e
t
h
e
p
o
t
e
n
t
i
a
l
f
o
r
a
p
p
l
y
i
n
g
w
a
r
st
r
a
t
e
g
y
p
r
i
n
c
i
p
l
e
s
t
o
se
n
t
i
m
e
n
t
a
n
a
l
y
si
s
i
n
o
t
h
e
r
d
o
ma
i
n
s,
s
u
c
h
a
s p
o
l
i
t
i
c
s
,
f
i
n
a
n
c
e
,
o
r
h
e
a
l
t
h
c
a
r
e
,
t
o
d
e
t
e
r
m
i
n
e
i
f
si
mi
l
a
r
b
e
n
e
f
i
t
s
c
a
n
b
e
a
c
h
i
e
v
e
d
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
is
s
tu
d
y
aim
s
to
d
eter
m
in
e
th
e
SA
o
f
th
e
g
iv
en
r
ev
iew,
wh
eth
er
it
is
p
o
s
itiv
e
o
r
n
eg
ativ
e.
T
o
ac
h
iev
e
th
is
,
th
e
p
r
o
p
o
s
ed
m
o
d
el
h
as
ap
p
lied
a
r
an
g
e
o
f
B
i
-
L
STM
with
war
s
tr
ateg
y
alg
o
r
ith
m
(
W
SA
)
t
o
o
b
tain
th
e
r
esu
lts
.
Fig
u
r
e
1
d
ep
icts
th
e
p
r
o
p
o
s
ed
SA
o
f
c
u
s
to
m
er
r
e
v
iew
o
n
B
i
-
L
STM
with
W
SA
wh
ich
co
m
p
r
is
es
o
f
d
if
f
er
en
t
s
tag
es
lik
e
co
llectio
n
o
f
d
ata,
p
r
e
-
p
r
o
ce
s
s
in
g
,
f
ea
t
u
r
e
ex
t
r
ac
tio
n
an
d
r
ev
iew
class
if
icatio
n
.
Fig
u
r
e
1
.
Pro
p
o
s
ed
SA o
f
cu
s
to
m
er
r
e
v
iew
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
Wa
r
s
tr
a
teg
y
a
s
s
i
s
ted
B
i
-
LS
T
M fo
r
s
en
timen
t a
n
a
lysi
s
o
f c
u
s
to
mer revie
w
(
A
n
ils
a
g
a
r
T.
)
483
3
.
1
.
P
re
-
pro
ce
s
s
ing
I
n
th
e
d
ataset
p
r
ep
r
o
ce
s
s
in
g
s
tag
e,
th
e
in
p
u
t
r
ev
iews
u
n
d
er
g
o
r
ef
in
em
e
n
t
b
y
r
em
o
v
in
g
in
tr
icate
an
d
ir
r
elev
an
t
tex
t.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
m
eth
o
d
o
lo
g
y
a
d
o
p
te
d
in
th
is
s
tu
d
y
s
tar
ts
with
to
k
en
iza
tio
n
an
d
c
u
lm
in
ates
in
th
e
elim
in
atio
n
o
f
in
s
ig
n
i
f
ican
t
wo
r
d
s
,
an
d
d
ig
its
.
E
m
p
lo
y
in
g
th
e
t
o
k
en
izatio
n
,
th
e
in
p
u
t
r
ev
iews
ar
e
s
eg
m
en
ted
in
to
to
k
e
n
s
.
Su
b
s
eq
u
en
tly
,
s
tem
m
in
g
is
ap
p
lied
to
all
to
k
en
s
,
r
ed
u
c
in
g
it to
its
s
in
g
u
lar
ter
m
.
T
h
e
n
,
th
e
s
to
p
wo
r
d
s
an
d
s
p
ec
ial
ch
a
r
ac
ter
s
ar
e
elim
in
ated
.
3
.
2
.
Wo
rd
e
m
bedd
ing
T
h
e
s
k
ip
-
g
r
am
a
p
p
r
o
ac
h
f
o
r
cr
ea
tin
g
wo
r
d
em
b
ed
d
in
g
an
d
tr
ain
ed
o
n
th
e
T
r
ip
ad
v
is
o
r
d
ataset.
T
o
p
r
eser
v
e
s
em
an
tic
s
im
ilar
ity
in
wo
r
d
r
e
p
r
esen
tatio
n
s
,
th
e
m
o
d
el
em
p
lo
y
s
a
tech
n
iq
u
e
th
at
m
ap
s
wo
r
d
s
o
r
p
h
r
ases
f
r
o
m
th
e
v
o
ca
b
u
lar
y
to
n
u
m
er
ical
v
ec
to
r
s
.
I
n
o
r
d
e
r
to
tr
ain
th
e
s
k
ip
-
g
r
am
m
o
d
el,
a
tr
ain
in
g
s
et
is
in
itially
co
n
s
tr
u
cted
u
s
in
g
th
e
o
r
d
e
r
o
f
w
o
r
d
s
d
en
o
ted
as
1
,
2
,
3
.
.
.
.
.
.
.
.
,
.
T
h
is
d
atase
t
s
er
v
es
as
t
h
e
in
p
u
t
f
o
r
t
h
e
tr
ain
in
g
p
r
o
ce
s
s
,
allo
win
g
th
e
m
o
d
el
to
lear
n
th
e
r
elatio
n
s
h
ip
s
an
d
co
n
tex
ts
b
etwe
en
wo
r
d
s
an
d
ef
f
ec
tiv
ely
ca
p
tu
r
e
th
eir
s
em
a
n
tic
m
ea
n
in
g
s
.
T
h
e
o
b
jectiv
e
i
s
g
iv
en
as:
_
=
1
∑
∑
(
+
1
|
=
1
)
(
1
)
wh
er
e
is
th
e
s
ize
o
f
th
e
co
n
tex
t a
n
d
(
+
1
|
)
is
th
e
s
o
f
tm
ax
ter
m
.
3
.
3
.
Cus
t
o
m
er
re
v
iew
cla
s
s
if
ica
t
io
n by
t
he
B
i
-
L
ST
M
wit
h
WSA
Fin
ally
,
f
o
r
class
if
y
in
g
th
e
r
e
v
iews
as
p
o
s
itiv
e
an
d
n
eg
ativ
e,
th
e
DL
m
o
d
el
B
i
-
L
STM
with
W
SA
i
s
p
r
esen
ted
.
T
h
e
co
n
v
en
tio
n
al
R
NN
m
o
d
el
h
as
t
h
e
ca
p
ac
ity
in
p
r
o
ce
s
s
in
g
s
eq
u
en
tial
d
at
a,
s
u
ch
as
tex
t,
o
f
v
ar
y
in
g
le
n
g
th
s
.
B
u
t,
R
NN
en
co
u
n
ter
s
a
co
m
m
o
n
is
s
u
e
d
u
r
i
n
g
th
e
g
r
a
d
ien
t
co
m
p
u
tatio
n
p
h
ase
k
n
o
wn
as
th
e
ex
p
lo
d
in
g
an
d
v
a
n
is
h
in
g
g
r
a
d
i
en
t
is
s
u
es.
T
h
is
ch
allen
g
e
ar
is
es
wh
en
th
e
b
ac
k
p
r
o
p
ag
atio
n
alg
o
r
ith
m
attem
p
ts
to
lear
n
lo
n
g
r
an
g
e
d
ep
e
n
d
e
n
cies,
r
esu
ltin
g
in
weig
h
t
p
a
r
am
eter
s
b
ec
o
m
in
g
ex
c
ess
iv
ely
s
m
all
o
r
lar
g
e.
C
o
n
s
eq
u
en
tly
,
th
is
s
lo
ws
d
o
wn
th
e
n
etwo
r
k
’
s
ab
ilit
y
to
ef
f
ec
tiv
ely
lear
n
co
m
p
licated
ter
m
s
.
L
STM
is
p
r
esen
ted
f
o
r
m
itig
atin
g
th
is
p
r
o
b
lem
u
s
in
g
th
e
m
em
o
r
y
u
n
it
to
r
etain
th
e
ess
en
tial
in
f
o
r
m
atio
n
a
n
d
it
h
as
in
p
u
t
,
o
u
tp
u
t
an
d
r
eset
g
ate.
T
h
en
,
th
e
ℎ
is
th
e
o
u
tp
u
t
o
f
ce
ll
an
d
is
th
e
g
lo
b
al
s
tate
th
at
m
ak
es
s
h
ar
in
g
o
f
v
ar
io
u
s
ℎ
o
v
er
th
e
L
STM
.
=
(
+
ℎ
ℎ
−
1
+
−
1
+
)
(
2
)
=
(
+
ℎ
ℎ
−
1
+
−
1
+
)
(
3
)
=
(
+
ℎ
ℎ
−
1
+
−
1
+
)
(
4
)
=
+
−
1
(
5
)
=
(
+
ℎ
ℎ
−
1
+
−
1
+
)
(
6
)
ℎ
=
ℎ
(
)
(
7
)
B
u
t,
in
ce
r
tain
ca
s
es o
f
SA,
it i
s
n
ec
ess
ar
y
to
ca
p
tu
r
e
wo
r
d
’
s
p
ast an
d
f
u
tu
r
e
d
ep
en
d
en
cies.
B
i
-
L
STM
is
p
r
esen
ted
a
o
n
e
m
o
r
e
L
ST
M
in
wh
ich
th
e
h
id
d
en
lin
k
s
f
lo
w
in
th
e
o
p
p
o
s
ite
d
ir
ec
tio
n
.
Fig
u
r
e
2
s
tates
th
e
s
tr
u
ctu
r
e
o
f
B
i
-
L
STM
an
d
it
h
as
two
L
STM
f
o
r
m
o
d
elin
g
th
e
s
eq
u
en
tial
in
f
o
r
m
atio
n
f
r
o
m
b
o
t
h
d
ir
ec
tio
n
s
.
Du
r
in
g
ea
c
h
tim
e
s
tep
,
th
e
f
o
r
war
d
an
d
th
e
b
ac
k
war
d
L
STM
s
o
p
er
ate
o
n
t
h
e
in
p
u
t
in
o
p
p
o
s
in
g
d
ir
ec
tio
n
s
.
T
h
ey
s
u
b
s
eq
u
en
tly
p
r
o
d
u
ce
h
id
d
en
s
tate
v
ec
to
r
s
as
o
u
tp
u
t
as
ℎ
→
an
d
ℎ
←
.
T
h
ese
two
h
id
d
e
n
s
t
a
te
v
ec
to
r
s
a
r
e
co
m
b
in
ed
to
m
ak
e
th
e
f
in
al
o
u
tp
u
t
ℎ
.
ℎ
=
ℎ
→
+
ℎ
←
(
8
)
T
o
o
p
tim
ize
th
e
h
y
p
er
-
p
ar
am
e
ter
s
o
f
t
h
e
s
tan
d
a
r
d
B
i
-
L
STM
m
o
d
el,
i
n
th
is
w
o
r
k
th
e
W
SA
alg
o
r
ith
m
is
p
r
esen
ted
f
o
r
en
h
an
cin
g
th
e
ac
cu
r
ac
y
o
f
th
e
m
o
d
el.
T
h
e
W
SA
m
im
ics
th
e
s
tr
ateg
ic
m
o
ti
o
n
o
f
s
o
ld
ie
r
s
in
th
e
ar
m
y
d
u
r
i
n
g
th
e
war
.
T
h
is
o
p
tim
izer
is
b
ased
o
n
two
m
ec
h
an
is
m
s
lik
e
attac
k
in
g
m
ec
h
a
n
is
m
an
d
a
d
ef
en
s
e
m
ec
h
an
is
m
.
E
v
er
y
s
o
ld
ier
u
p
d
ates
th
eir
p
o
s
itio
n
co
n
tin
u
o
u
s
ly
o
n
th
e
b
asis
o
f
em
p
er
o
r
a
n
d
lead
er
.
R
an
k
a
n
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.
40
,
No
.
1
,
Octo
b
er
20
25
:
480
-
4
8
9
484
weig
h
t
ar
e
allo
ca
te
d
to
ev
er
y
s
o
ld
ier
an
d
th
e
weig
h
t
o
f
ea
c
h
s
o
ld
ier
is
u
p
d
ated
o
n
th
e
b
asis
o
f
th
eir
s
u
cc
ess
in
in
cr
ea
s
in
g
th
e
f
itn
ess
v
alu
e.
M
ath
em
atica
l m
o
d
elin
g
o
f
th
e
AW
SO i
s
ex
p
lain
ed
in
th
e
f
o
llo
win
g
s
ec
tio
n
.
Fig
u
r
e
2
.
Stru
ctu
r
e
o
f
B
i
-
L
STM
A
tta
ck
ing
m
ec
ha
nis
m
:
I
n
th
i
s
m
ec
h
an
is
m
,
th
e
em
p
er
o
r
p
o
s
itio
n
s
h
im
s
elf
to
attac
k
th
e
o
p
p
o
s
itio
n
with
g
r
ea
t
f
o
r
ce
.
T
h
u
s
,
th
e
s
o
ld
ier
wh
o
p
o
s
s
ess
e
s
th
e
s
tr
o
n
g
est
attac
k
f
o
r
ce
o
r
lev
el
o
f
f
itn
ess
is
co
n
s
id
er
ed
th
e
k
in
g
.
At
th
e
b
eg
i
n
n
in
g
o
f
t
h
e
war
,
ev
e
r
y
s
o
ld
ier
will
b
e
th
e
s
am
e
w
eig
h
t
an
d
r
an
k
.
T
h
e
s
o
ld
ier
’
s
r
an
k
in
cr
ea
s
es
if
h
e
s
u
cc
ess
f
u
lly
em
p
lo
y
s
th
e
p
lan
.
B
u
t
as
th
e
war
g
o
es
o
n
,
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
p
lan
will
d
eter
m
in
e
h
o
w
all
s
o
ld
ier
s
ar
e
r
an
k
ed
a
n
d
weig
h
ted
.
T
h
e
s
o
ld
ier
s
,
lead
er
a
n
d
e
m
p
er
o
r
a
r
e
g
ettin
g
clo
s
er
to
t
h
e
tar
g
et
as
th
e
war
d
r
aws to
a
clo
s
e.
(
+
1
)
=
(
)
+
2
×
×
(
−
)
+
×
(
×
−
(
)
)
(
9
)
wh
er
e
(
+
1
)
an
d
(
)
ar
e
th
e
n
ew
a
n
d
p
r
e
v
io
u
s
p
o
s
itio
n
,
is
th
e
co
n
s
tan
t
p
ar
am
eter
,
is
th
e
weig
h
tin
g
ter
m
,
s
o
l
d
ier
s
,
an
d
ar
e
th
e
lead
er
a
n
d
em
p
er
o
r
.
T
h
e
s
o
ld
ier
co
n
s
id
er
s
p
r
io
r
p
o
s
itio
n
,
wh
en
f
itn
ess
in
th
e
n
ew
p
o
s
itio
n
is
less
th
an
t
h
e
p
r
io
r
p
o
s
itio
n
,
th
e
f
o
llo
win
g
e
x
p
r
es
s
io
n
is
u
tili
ze
d
.
(
+
1
)
=
(
(
+
1
)
)
+
(
≥
)
+
(
)
)
×
(
<
)
(
1
0
)
W
h
en
th
e
p
o
s
itio
n
o
f
s
o
ld
ier
’
s
ar
e
s
u
cc
ess
f
u
lly
u
p
d
ates,
th
e
r
an
k
o
f
th
e
s
o
ld
ier
’
s
ar
e
u
p
d
ated
as:
=
(
+
1
)
×
(
≥
)
+
(
)
×
×
(
<
)
(
1
1
)
E
ac
h
s
o
ld
ier
’
s
r
an
k
is
d
eter
m
in
ed
b
y
h
is
r
ec
o
r
d
o
f
s
u
c
ce
s
s
in
war
,
wh
ich
is
d
eter
m
in
ed
b
y
f
o
llo
win
g
ex
p
r
ess
io
n
an
d
it is
i
n
f
lu
en
ce
d
b
y
th
e
.
=
×
(
1
−
_
)
(
1
2
)
wh
er
e
is
th
e
ex
p
o
n
en
tial te
r
m
.
Def
en
s
e
m
ec
h
an
is
m
:
i
n
th
is
m
ec
h
an
is
m
,
th
e
p
o
s
itio
n
o
f
t
h
e
ar
m
y
h
ea
d
,
r
an
d
o
m
s
o
ld
ier
an
d
em
p
er
o
r
ar
e
u
tili
ze
d
to
u
p
d
ate
p
o
s
itio
n
.
I
t is g
iv
en
as:
(
+
1
)
=
(
)
+
2
×
×
(
−
(
)
)
+
×
×
(
−
(
)
)
)
(
1
3
)
R
elo
ca
tin
g
wea
k
s
o
ld
ier
:
Fo
r
ea
ch
iter
atio
n
,
l
o
ca
te
th
e
s
o
ld
ier
s
with
th
e
lo
west
lev
els
o
f
f
itn
ess
.
I
n
th
is
p
r
o
ce
s
s
,
th
e
ap
p
r
o
ac
h
in
v
o
l
v
es su
b
s
titu
tin
g
th
e
wea
k
est s
o
ld
ier
with
a
r
an
d
o
m
ly
c
h
o
s
en
o
n
e
an
d
it is
g
iv
en
as:
(
+
1
)
=
+
×
(
−
)
(
1
4
)
wh
er
e
,
an
d
ar
e
th
e
r
an
d
o
m
n
u
m
b
er
,
u
p
p
e
r
an
d
lo
wer
b
o
u
n
d
s
.
Alg
o
r
ith
m
1
d
ef
in
e
s
th
e
p
s
eu
d
o
co
d
e
o
f
t
h
e
W
SA.
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
Wa
r
s
tr
a
teg
y
a
s
s
i
s
ted
B
i
-
LS
T
M fo
r
s
en
timen
t a
n
a
lysi
s
o
f c
u
s
to
mer revie
w
(
A
n
ils
a
g
a
r
T.
)
485
Alg
o
r
ith
m
1
.
Ps
eu
d
o
co
d
e
o
f
t
h
e
W
SA
Initialize the size of soldiers, dimensions, upper and lower bounds
for 1: size of soldiers
For every soldier, attacking force is obtained
While t<
〖
max_
〗
i ter
Arrange the attacking force of all soldiers
Fi
rs
t
be
st
fi
tn
es
s
is
co
n
si
de
re
d
as
th
e
ki
ng
an
d
t
he
se
co
nd
-
be
st
fi
tn
es
s
is
co
ns
id
er
as
th
e
emperor
The position of all soldiers is updated by Equation (12)
Else
The position of all soldiers is updated by Equation (8)
Arrange every soldier’s fitness
when fitness in the new position is less than the prior position Equation (9) is updated
Rank R_kof the soldier’s are updated by Equation (10)
Update the king and emperor’s positions
t=t+1
End
4.
RE
SU
L
T
S AN
A
L
YS
I
S
T
h
e
f
o
llo
win
g
s
ec
tio
n
,
ass
ess
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
s
u
g
g
ested
m
o
d
el
in
ac
cu
r
ately
c
ateg
o
r
izin
g
p
o
s
itiv
e
an
d
n
eg
ativ
e
r
ev
iew
t
ex
ts
b
y
a
n
aly
zin
g
an
d
ar
e
t
h
e
tr
u
e
a
n
d
f
alse
p
o
s
itiv
es,
an
d
tr
u
e
an
d
f
alse
n
eg
ativ
es
.
T
o
ev
alu
a
te
th
e
class
if
icatio
n
p
er
f
o
r
m
an
ce
o
f
th
e
Bi
-
L
STM
with
W
SA
,
th
is
wo
r
k
u
tili
ze
d
v
ar
io
u
s
p
er
f
o
r
m
a
n
ce
m
etr
ics a
s
o
u
tlin
ed
in
T
a
b
le
2
.
T
ab
le
2
.
Per
f
o
r
m
an
ce
m
ea
s
u
r
e
s
M
e
t
r
i
c
s
Ex
p
r
e
ssi
o
n
s
A
c
c
u
r
a
c
y
+
+
+
+
P
r
e
c
i
s
i
o
n
+
F
-
sco
r
e
2
×
×
+
4
.
1
.
Da
t
a
s
et
det
a
il
T
h
e
d
ataset
c
o
m
p
r
is
es
1
,
6
0
0
h
o
tel
r
ev
iews,
with
8
0
0
b
ein
g
tr
u
th
f
u
l
an
d
8
0
0
b
ein
g
f
ak
e,
s
o
u
r
ce
d
f
r
o
m
a
well
-
k
n
o
wn
h
o
tel
b
o
o
k
in
g
p
latf
o
r
m
,
T
r
i
p
ad
v
is
o
r
[
2
5
]
.
T
h
e
d
ataset
cr
ea
to
r
s
m
eticu
lo
u
s
ly
s
elec
ted
an
d
r
ef
in
ed
r
ev
iews
r
ated
eith
e
r
5
o
r
3
s
tar
s
f
r
o
m
twen
ty
h
o
tels
lo
ca
ted
in
C
h
icag
o
.
Key
attr
ib
u
tes
o
f
th
e
d
ataset
in
clu
d
e
th
e
r
e
v
iew
tex
t,
class
lab
el,
h
o
tel
n
a
m
e,
r
ev
iewe
r
n
a
m
e,
an
d
s
en
tim
en
t
p
o
lar
ity
.
4
.
2
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
T
h
e
f
o
llo
win
g
s
ec
tio
n
s
h
o
ws
th
e
co
m
p
ar
ativ
e
an
al
y
s
is
o
f
th
e
d
if
f
er
en
t
m
o
d
els
lik
e
R
NN,
L
STM
,
B
i
-
L
STM
an
d
th
e
p
r
o
p
o
s
ed
Bi
-
L
STM
with
W
S
A.
Fig
u
r
e
3
p
r
esen
ts
th
e
co
m
p
ar
is
o
n
o
f
th
e
m
ea
s
u
r
es
lik
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
an
d
f
-
s
co
r
e
o
n
th
e
tr
ip
a
d
v
is
o
r
d
atas
et.
Her
e,
t
h
e
m
et
h
o
d
s
lik
e
R
NN,
L
STM
an
d
B
i
-
L
STM
ar
e
co
m
p
ar
ed
with
th
e
p
r
o
p
o
s
ed
Bi
-
L
STM
with
W
S
A.
T
h
e
p
er
f
o
r
m
an
ce
is
ca
r
r
ied
o
u
t
b
y
v
ar
y
i
n
g
th
e
k
-
Fo
ld
v
alu
es
as
in
Fig
u
r
e
s
3
(
a)
-
(
c)
.
I
n
all
co
m
p
ar
ativ
e
a
n
al
y
s
is
,
th
e
p
r
o
p
o
s
ed
B
i
-
L
STM
with
W
SA
o
b
tain
ed
b
etter
p
er
f
o
r
m
an
ce
.
T
h
e
ex
is
tin
g
m
o
d
els
s
u
f
f
er
f
r
o
m
t
h
e
v
an
is
h
in
g
g
r
ad
ien
t
p
r
o
b
lem
a
n
d
a
r
e
co
m
p
u
tatio
n
ally
in
ten
s
iv
e
d
u
e
to
th
eir
co
m
p
le
x
ar
ch
itectu
r
e,
wh
ich
ca
n
r
esu
lt
in
h
ig
h
tr
ain
in
g
tim
e
an
d
h
i
g
h
r
eso
u
r
ce
n
ee
d
s
.
So
,
m
eth
o
d
s
lik
e
R
NN,
L
STM
an
d
B
i
-
L
STM
ac
h
iev
e
d
p
o
o
r
p
er
f
o
r
m
an
ce
.
Fig
u
r
e
4
d
ef
i
n
es
th
e
co
n
f
u
s
io
n
m
atr
ix
o
f
th
e
Bi
-
L
STM
with
W
SA
m
o
d
el.
I
n
th
is
m
atr
ix
,
th
er
e
ar
e
4
5
.
9
4
%
o
f
s
am
p
les
ar
e
ca
teg
o
r
ized
as
tr
u
e
n
eg
ativ
e,
4
.
0
6
%
o
f
s
am
p
les
ar
e
ca
teg
o
r
ized
as
f
alse
p
o
s
itiv
e
,
1
1
.
2
5
%
o
f
s
am
p
les ar
e
ca
teg
o
r
ized
as f
alse n
eg
ativ
e
an
d
3
8
.
7
5
% o
f
s
am
p
les ar
e
ca
teg
o
r
ize
d
as tr
u
e
p
o
s
i
tiv
e.
4
.
3
.
Dis
cus
s
io
n
4
.
3
.
1
.
O
v
er
a
ll
s
up
er
io
rit
y
o
f
t
he
pro
po
s
ed
m
o
del
T
h
e
p
r
o
p
o
s
ed
war
s
tr
ateg
y
as
s
is
ted
Bi
-
L
STM
m
o
d
el
o
u
tp
er
f
o
r
m
s
th
e
tr
ad
itio
n
al
B
i
-
L
STM
,
L
STM
,
an
d
R
NN
m
o
d
els
ac
r
o
s
s
all
m
etr
ics
(
Acc
u
r
ac
y
,
F
-
s
co
r
e,
a
n
d
Pre
cisi
o
n
)
.
T
h
is
s
u
g
g
ests
t
h
at
i
n
teg
r
atin
g
war
s
tr
ateg
y
co
n
ce
p
ts
in
to
th
e
B
i
-
L
STM
ar
ch
itectu
r
e
s
ig
n
if
ican
tly
en
h
an
ce
s
its
ab
ilit
y
to
an
aly
ze
s
en
tim
en
t
in
cu
s
to
m
er
r
ev
iews.
T
h
e
h
ig
h
p
er
f
o
r
m
an
ce
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
el,
esp
ec
ially
in
p
r
e
cisi
o
n
,
in
d
icate
s
it
s
ef
f
ec
tiv
en
ess
in
co
r
r
ec
tly
id
en
ti
f
y
in
g
p
o
s
itiv
e
an
d
n
e
g
ativ
e
s
en
tim
en
ts
with
m
in
im
al
er
r
o
r
s
.
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.
40
,
No
.
1
,
Octo
b
er
20
25
:
480
-
4
8
9
486
4
.
3
.
2
.
Sta
bil
it
y
a
cr
o
s
s
K
-
F
o
lds
T
h
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
co
n
s
is
ten
t
ac
r
o
s
s
d
if
f
e
r
en
t
K
-
Fo
l
d
s
,
wh
ich
d
e
m
o
n
s
tr
ates
its
r
o
b
u
s
tn
ess
an
d
r
eliab
ilit
y
in
s
en
tim
en
t
an
aly
s
is
tas
k
s
.
T
h
is
co
n
s
is
ten
cy
is
cr
u
cial
f
o
r
r
ea
l
-
wo
r
ld
ap
p
licatio
n
s
wh
er
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
s
h
o
u
ld
r
e
m
ain
s
tab
le
ac
r
o
s
s
v
ar
io
u
s
d
ata
s
p
lits
.
T
h
e
s
tan
d
ar
d
d
ev
iatio
n
s
in
th
e
m
et
r
ics f
o
r
th
e
p
r
o
p
o
s
ed
m
o
d
el
ar
e
r
elativ
el
y
lo
w,
f
u
r
th
er
r
ei
n
f
o
r
cin
g
its
s
tab
ilit
y
.
(
a)
(
b
)
(
c)
Fig
u
r
e
3
.
C
o
m
p
a
r
is
o
n
o
f
(
a)
a
cc
u
r
ac
y
,
(
b
)
p
r
ec
is
io
n
,
an
d
(
c)
F
-
s
co
r
e
Fig
u
r
e
4
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
th
e
B
i
-
L
STM
with
W
SA
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
Wa
r
s
tr
a
teg
y
a
s
s
i
s
ted
B
i
-
LS
T
M fo
r
s
en
timen
t a
n
a
lysi
s
o
f c
u
s
to
mer revie
w
(
A
n
ils
a
g
a
r
T.
)
487
4
.
3
.
3
.
Co
m
pa
riso
n wit
h
t
ra
di
t
io
na
l m
o
dels
T
h
e
tr
ad
itio
n
al
B
i
-
L
STM
,
L
STM
,
an
d
R
NN
m
o
d
els
s
h
o
w
a
n
o
ticea
b
le
g
ap
in
p
er
f
o
r
m
a
n
ce
wh
en
co
m
p
ar
ed
to
th
e
p
r
o
p
o
s
ed
m
o
d
el.
T
h
is
g
ap
h
ig
h
lig
h
ts
th
e
lim
itatio
n
s
o
f
th
ese
m
o
d
els
in
ca
p
tu
r
in
g
co
m
p
lex
p
atter
n
s
in
s
en
tim
en
t
d
ata
th
a
t
th
e
p
r
o
p
o
s
ed
m
o
d
el
ca
n
ef
f
ec
tiv
ely
ad
d
r
ess
.
T
h
e
B
i
-
L
STM
o
u
tp
er
f
o
r
m
s
th
e
L
STM
an
d
R
NN
m
o
d
els,
wh
ich
ali
g
n
s
with
th
e
g
en
er
al
u
n
d
e
r
s
tan
d
in
g
th
at
B
i
-
L
STM
ca
n
ca
p
tu
r
e
d
ep
en
d
e
n
cies f
r
o
m
b
o
th
p
ast an
d
f
u
t
u
r
e
co
n
tex
ts
b
etter
th
an
u
n
id
ir
ec
tio
n
al
L
STM
a
n
d
R
NN.
4
.
3
.
4
.
I
m
pli
ca
t
io
ns
f
o
r
f
uture
re
s
ea
rc
h
T
h
e
r
esu
lts
s
u
g
g
est
th
at
f
u
r
t
h
er
ex
p
lo
r
atio
n
in
to
h
y
b
r
i
d
m
o
d
els
th
at
in
teg
r
ate
d
o
m
ai
n
-
s
p
ec
if
ic
s
tr
ateg
ies
(
lik
e
war
s
tr
ateg
ies)
ca
n
y
ield
s
ig
n
if
ican
t
im
p
r
o
v
em
en
ts
in
p
e
r
f
o
r
m
an
ce
.
Fu
t
u
r
e
r
esear
ch
c
o
u
ld
f
o
cu
s
o
n
o
p
tim
izin
g
th
e
in
te
g
r
atio
n
o
f
war
s
tr
ateg
y
c
o
n
c
ep
ts
an
d
ex
p
l
o
r
in
g
th
eir
ap
p
licab
ilit
y
in
o
th
er
d
o
m
ain
s
b
ey
o
n
d
cu
s
to
m
er
r
ev
iew
s
en
tim
en
t a
n
aly
s
is
.
I
n
s
u
m
m
ar
y
,
th
e
f
ig
u
r
es
clea
r
ly
in
d
icate
th
at
t
h
e
W
ar
Stra
teg
y
Ass
is
ted
B
i
-
L
STM
m
o
d
el
p
r
o
v
id
es
a
s
u
b
s
tan
tial
im
p
r
o
v
em
en
t
in
s
en
tim
en
t
an
aly
s
is
o
f
cu
s
to
m
e
r
r
ev
iews,
o
f
f
er
i
n
g
h
ig
h
er
ac
c
u
r
ac
y
,
F
-
s
co
r
e,
a
n
d
p
r
ec
is
io
n
co
m
p
a
r
ed
to
tr
ad
itio
n
al
m
o
d
els.
T
h
is
u
n
d
er
s
co
r
es
th
e
p
o
ten
tial
o
f
in
co
r
p
o
r
atin
g
s
tr
ateg
ic
elem
en
ts
in
to
m
ac
h
in
e
lea
r
n
in
g
m
o
d
els
to
en
h
an
ce
th
eir
p
e
r
f
o
r
m
an
ce
an
d
r
eliab
ilit
y
.
5.
CO
NCLU
SI
O
N
T
h
e
p
r
o
p
o
s
ed
wo
r
k
p
r
esen
te
d
Bi
-
L
STM
with
W
SA
m
o
d
el
to
d
etec
t
cu
s
to
m
er
r
ev
iew
s
u
s
in
g
th
e
wo
r
d
em
b
ed
d
in
g
m
o
d
el.
T
h
e
p
r
o
p
o
s
ed
wo
r
k
u
n
d
er
g
o
es
d
if
f
er
en
t
p
r
e
-
p
r
o
ce
s
s
in
g
s
tag
es
f
o
r
r
ed
u
cin
g
th
e
tr
ain
in
g
tim
e.
T
h
e
p
r
o
p
o
s
ed
B
i
-
L
STM
wi
th
W
SA
m
o
d
el
ef
f
icien
tly
id
en
tifie
d
th
e
p
o
s
itiv
e
an
d
n
eg
ati
v
e
r
ev
iews
in
an
e
f
f
icien
t
way
.
T
h
e
W
SA
is
p
r
esen
ted
to
e
n
h
an
cin
g
th
e
ac
cu
r
ac
y
p
e
r
f
o
r
m
a
n
ce
an
d
p
r
e
v
en
tin
g
o
v
er
f
itti
n
g
is
s
u
es.
T
h
e
e
x
p
er
i
m
en
tatio
n
was
d
em
o
n
s
tr
ated
o
n
th
e
T
r
ip
ad
v
is
o
r
d
ataset
a
n
d
ac
h
iev
e
d
b
etter
ac
cu
r
ac
y
an
d
p
r
ec
is
io
n
v
alu
es
o
f
9
7
.
1
%
an
d
9
7
.
5
%.
B
y
p
r
o
v
id
in
g
ac
c
u
r
ate
an
d
ef
f
icien
t
s
en
tim
en
t
an
aly
s
is
,
th
e
p
r
o
p
o
s
ed
m
o
d
el
ca
n
s
ig
n
if
ican
tly
ass
is
t
cu
s
to
m
er
s
in
m
ak
in
g
in
f
o
r
m
ed
d
ec
is
io
n
s
ab
o
u
t
p
r
o
d
u
cts.
Fo
r
in
s
tan
ce
,
id
en
tify
in
g
t
r
en
d
s
in
p
o
s
itiv
e
an
d
n
eg
ativ
e
r
ev
iew
s
ca
n
h
elp
cu
s
to
m
er
s
g
au
g
e
p
r
o
d
u
c
t
q
u
ality
an
d
s
u
itab
ilit
y
m
o
r
e
ef
f
ec
tiv
ely
.
Fo
r
b
u
s
in
ess
es,
s
u
ch
a
m
o
d
el
ca
n
p
r
o
v
id
e
d
ee
p
e
r
in
s
ig
h
ts
in
to
cu
s
to
m
er
s
en
tim
en
t,
h
elp
in
g
in
b
etter
p
r
o
d
u
ct
d
ev
elo
p
m
en
t,
tar
g
ete
d
m
ar
k
etin
g
s
tr
ateg
ies,
an
d
i
m
p
r
o
v
e
d
cu
s
to
m
er
s
er
v
ice.
I
n
f
u
tu
r
e
,
th
e
s
u
g
g
ested
m
eth
o
d
o
lo
g
y
will
b
e
ev
alu
ated
o
n
th
e
r
ea
l
-
tim
e
an
d
ass
is
t
th
e
cu
s
to
m
er
s
in
an
aly
zin
g
th
e
p
o
s
itiv
e
an
d
n
eg
ativ
e
r
ev
iews o
f
th
e
d
if
f
er
e
n
t
p
r
o
d
u
cts.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
w
o
u
ld
lik
e
to
ex
p
r
ess
h
is
h
ea
r
tf
elt
g
r
atitu
d
e
to
th
e
s
u
p
er
v
is
o
r
f
o
r
h
is
g
u
i
d
an
ce
an
d
u
n
wav
er
in
g
s
u
p
p
o
r
t d
u
r
in
g
t
h
is
r
esear
ch
f
o
r
h
is
g
u
id
an
ce
an
d
s
u
p
p
o
r
t.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
An
ils
ag
ar
T
.
,
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Sy
ed
Ab
d
u
l Sy
e
d
S.
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
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.
40
,
No
.
1
,
Octo
b
er
20
25
:
480
-
4
8
9
488
DATA AV
AI
L
AB
I
L
I
T
Y
Data
av
ailab
ilit
y
is
n
o
t
a
p
p
li
ca
b
le
to
th
is
p
ap
er
as
n
o
n
e
w
d
ata
wer
e
c
r
ea
ted
o
r
an
al
y
ze
d
in
t
h
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
R
.
S
.
Ja
g
d
a
l
e
,
V
.
S
.
S
h
i
r
sa
t
,
a
n
d
S
.
N
.
D
e
s
h
m
u
k
h
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
o
n
p
r
o
d
u
c
t
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
t
e
c
h
n
i
q
u
e
s,
”
In
C
o
g
n
i
t
i
v
e
I
n
f
o
rm
a
t
i
c
s
a
n
d
S
o
f
t
C
o
m
p
u
t
i
n
g
:
Pro
c
e
e
d
i
n
g
o
f
C
I
S
C
2
0
1
7
,
p
p
.
6
3
9
-
6
4
7
,
2
0
1
9
.
S
p
r
i
n
g
e
r
S
i
n
g
a
p
o
r
e
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
1
3
-
0
6
1
7
-
4
_
6
1
.
[
2
]
S
.
Y
i
,
a
n
d
X
.
L
i
u
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
c
u
s
t
o
mer
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
f
o
r
r
e
c
o
mm
e
n
d
i
n
g
s
h
o
p
p
e
r
s,
sh
o
p
s
b
a
s
e
d
o
n
c
u
st
o
mers
’
r
e
v
i
e
w
,
”
C
o
m
p
l
e
x
& I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
,
v
o
l
.
6
,
n
o
.
3
,
6
2
1
-
6
3
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
7
4
7
-
0
2
0
-
0
0
1
5
5
-
2
.
[
3
]
R
.
B
o
se,
R
.
K
.
D
e
y
,
S
.
R
o
y
,
a
n
d
D
.
S
a
r
d
d
a
r
,
“
S
e
n
t
i
m
e
n
t
a
n
a
l
y
si
s
o
n
o
n
l
i
n
e
p
r
o
d
u
c
t
r
e
v
i
e
w
s
,
”
I
n
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
f
o
r
S
u
s
t
a
i
n
a
b
l
e
D
e
v
e
l
o
p
m
e
n
t
:
Pr
o
c
e
e
d
i
n
g
s
o
f
I
C
T
4
S
D
2
0
1
8
,
p
p
.
5
5
9
-
5
6
9
,
2
0
2
0
.
S
p
r
i
n
g
e
r
S
i
n
g
a
p
o
r
e
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
13
-
7
1
6
6
-
0
_
5
6
.
[
4
]
A
.
L.
K
a
r
n
,
R
.
K
.
K
a
r
n
a
,
B
.
R
.
K
o
n
d
a
m
u
d
i
,
G
.
B
a
g
a
l
e
,
D
.
A
.
P
u
st
o
k
h
i
n
,
I
.
V
.
P
u
st
o
k
h
i
n
a
,
a
n
d
S
.
S
e
n
g
a
n
,
“
C
u
s
t
o
mer
c
e
n
t
r
i
c
h
y
b
r
i
d
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
st
e
m
f
o
r
E
-
C
o
m
merc
e
a
p
p
l
i
c
a
t
i
o
n
s
b
y
i
n
t
e
g
r
a
t
i
n
g
h
y
b
r
i
d
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s,”
E
l
e
c
t
ro
n
i
c
C
o
m
m
e
rce
Re
se
a
rc
h
,
v
o
l
.
2
3
,
n
o
.
1
,
p
p
.
2
7
9
-
3
1
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
6
6
0
-
022
-
0
9
6
3
0
-
z
.
[
5
]
P
.
K
.
Ja
i
n
,
R
.
P
a
m
u
l
a
,
a
n
d
G
.
S
r
i
v
a
st
a
v
a
,
“
A
s
y
s
t
e
m
a
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s
f
o
r
c
o
n
s
u
m
e
r
sen
t
i
m
e
n
t
a
n
a
l
y
si
s
u
s
i
n
g
o
n
l
i
n
e
r
e
v
i
e
w
s
,
”
C
o
m
p
u
t
e
r
sc
i
e
n
c
e
rev
i
e
w
,
v
o
l
.
4
1
,
p
p
.
1
0
0
4
1
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
sr
e
v
.
2
0
2
1
.
1
0
0
4
1
3
.
[
6
]
N
.
P
u
n
e
t
h
a
,
a
n
d
G
.
J
a
i
n
,
“
A
s
p
e
c
t
a
n
d
o
r
i
e
n
t
a
t
i
o
n
-
b
a
s
e
d
se
n
t
i
m
e
n
t
a
n
a
l
y
si
s
o
f
c
u
s
t
o
mer
f
e
e
d
b
a
c
k
u
s
i
n
g
ma
t
h
e
ma
t
i
c
a
l
o
p
t
i
mi
z
a
t
i
o
n
mo
d
e
l
s
,
”
K
n
o
w
l
e
d
g
e
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
6
5
,
n
o
.
6
,
p
p
.
2
7
3
1
-
2
7
6
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
1
1
5
-
0
2
3
-
0
1
8
4
8
-
z
[
7
]
A
.
D
a
d
h
i
c
h
,
a
n
d
B
.
Th
a
n
k
a
c
h
a
n
,
“
S
e
n
t
i
m
e
n
t
a
n
a
l
y
si
s
o
f
a
ma
z
o
n
p
r
o
d
u
c
t
r
e
v
i
e
w
s
u
si
n
g
h
y
b
r
i
d
r
u
l
e
-
b
a
se
d
a
p
p
r
o
a
c
h
,
”
In
S
m
a
rt
S
y
s
t
e
m
s:
I
n
n
o
v
a
t
i
o
n
s
i
n
C
o
m
p
u
t
i
n
g
:
Pro
c
e
e
d
i
n
g
s
o
f
S
S
I
C
2
0
2
1
,
p
p
.
1
7
3
-
1
9
3
,
2
0
2
2
.
S
p
r
i
n
g
e
r
S
i
n
g
a
p
o
r
e
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
16
-
2
8
7
7
-
1
_
1
7
.
[
8
]
H
.
Z
h
a
o
,
Z
.
L
i
u
,
X
.
Y
a
o
,
a
n
d
Q
.
Y
a
n
g
,
“
A
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
s
e
n
t
i
m
e
n
t
a
n
a
l
y
si
s
o
f
o
n
l
i
n
e
p
r
o
d
u
c
t
r
e
v
i
e
w
s
w
i
t
h
a
n
o
v
e
l
t
e
r
m
w
e
i
g
h
t
i
n
g
a
n
d
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
a
p
p
r
o
a
c
h
,
”
I
n
f
o
rm
a
t
i
o
n
Pr
o
c
e
s
si
n
g
&
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
5
8
,
n
o
.
5
,
1
0
2
6
5
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
p
m.
2
0
2
1
.
1
0
2
6
5
6
.
[
9
]
P
.
K
.
J
a
i
n
,
V
.
S
a
r
a
v
a
n
a
n
,
a
n
d
R
.
P
a
mu
l
a
,
“
A
h
y
b
r
i
d
C
N
N
-
LSTM
:
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
c
o
n
s
u
m
e
r
sen
t
i
m
e
n
t
a
n
a
l
y
s
i
s
u
si
n
g
q
u
a
l
i
t
a
t
i
v
e
u
ser
-
g
e
n
e
r
a
t
e
d
c
o
n
t
e
n
t
s,”
T
ra
n
s
a
c
t
i
o
n
s
o
n
As
i
a
n
a
n
d
L
o
w
-
Re
s
o
u
r
c
e
L
a
n
g
u
a
g
e
I
n
f
o
rm
a
t
i
o
n
P
ro
c
e
ssi
n
g
,
v
o
l
.
2
0
,
n
o
.
5
,
p
p
.
1
-
1
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
5
7
2
0
6
.
[
1
0
]
S
.
K
u
m
a
r
,
M
.
Y
a
d
a
v
a
,
a
n
d
P
.
P
.
R
o
y
,
“
F
u
s
i
o
n
o
f
EEG
r
e
s
p
o
n
s
e
a
n
d
se
n
t
i
me
n
t
a
n
a
l
y
s
i
s
o
f
p
r
o
d
u
c
t
s
r
e
v
i
e
w
t
o
p
r
e
d
i
c
t
c
u
s
t
o
mer
sat
i
sf
a
c
t
i
o
n
,
”
I
n
f
o
rm
a
t
i
o
n
f
u
s
i
o
n
,
v
o
l
.
5
2
,
p
p
.
4
1
-
5
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
f
u
s.2
0
1
8
.
1
1
.
0
0
1
.
[
1
1
]
G
.
K
a
u
r
,
a
n
d
A
.
S
h
a
r
m
a
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
m
o
d
e
l
u
si
n
g
h
y
b
r
i
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
p
p
r
o
a
c
h
f
o
r
c
o
n
su
mer
se
n
t
i
me
n
t
a
n
a
l
y
si
s
,
”
J
o
u
r
n
a
l
o
f
b
i
g
d
a
t
a
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
0
5
3
7
-
0
2
2
-
0
0
6
8
0
-
6
.
[
1
2
]
P
.
H
a
j
e
k
,
L.
H
i
k
k
e
r
o
v
a
,
a
n
d
J
.
M
.
S
a
h
u
t
,
“
F
a
k
e
r
e
v
i
e
w
d
e
t
e
c
t
i
o
n
i
n
e
-
C
o
mm
e
r
c
e
p
l
a
t
f
o
r
ms
u
si
n
g
a
sp
e
c
t
-
b
a
se
d
se
n
t
i
me
n
t
a
n
a
l
y
si
s
,
”
J
o
u
r
n
a
l
o
f
B
u
si
n
e
ss
Re
s
e
a
r
c
h
,
v
o
l
.
1
6
7
,
p
p
.
1
1
4
1
4
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
b
u
s
r
e
s.
2
0
2
3
.
1
1
4
1
4
3
.
[
1
3
]
M
.
Z
h
a
n
g
,
L.
S
u
n
,
G
.
A
.
W
a
n
g
,
Y
.
L
i
,
a
n
d
S
.
H
e
,
“
U
s
i
n
g
n
e
u
t
r
a
l
sen
t
i
m
e
n
t
r
e
v
i
e
w
s
t
o
i
m
p
r
o
v
e
c
u
st
o
mer
r
e
q
u
i
r
e
m
e
n
t
i
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
p
r
o
d
u
c
t
d
e
s
i
g
n
s
t
r
a
t
e
g
i
e
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Pr
o
d
u
c
t
i
o
n
E
c
o
n
o
m
i
c
s
,
v
o
l
.
2
5
4
,
p
p
.
1
0
8
6
4
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
p
e
.
2
0
2
2
.
1
0
8
6
4
1
.
[
1
4
]
M
.
N
i
l
a
s
h
i
,
S
.
S
a
m
a
d
,
B
.
M
i
n
a
e
i
-
B
i
d
g
o
l
i
,
F
.
G
h
a
b
b
a
n
,
a
n
d
E.
S
u
p
r
i
y
a
n
t
o
,
“
O
n
l
i
n
e
r
e
v
i
e
w
s
a
n
a
l
y
s
i
s
f
o
r
c
u
s
t
o
m
e
r
se
g
m
e
n
t
a
t
i
o
n
t
h
r
o
u
g
h
d
i
me
n
s
i
o
n
a
l
i
t
y
r
e
d
u
c
t
i
o
n
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
Ar
a
b
i
a
n
J
o
u
r
n
a
l
f
o
r
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
4
6
,
n
o
.
9
,
p
p
.
8
6
9
7
-
8
7
0
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
3
6
9
-
0
2
1
-
0
5
6
3
8
-
z
.
[
1
5
]
T.
D
i
w
a
n
,
J.V.
T
e
m
b
h
u
r
n
e
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
:
a
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
s
p
e
r
sp
e
c
t
i
v
e
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
A
p
p
l
,
v
o
l
.
8
1
,
n
o
.
3
0
,
p
p
.
4
4
4
0
5
–
4
4
4
2
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
2
1
-
1
1
7
5
9
-
2
.
[
1
6
]
D
.
D
a
n
g
i
,
A
.
B
h
a
g
a
t
,
D
.
K
.
D
i
x
i
t
,
“
S
e
n
t
i
m
e
n
t
a
n
a
l
y
si
s
o
n
so
c
i
a
l
m
e
d
i
a
u
s
i
n
g
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
w
i
t
h
c
n
n
,
”
C
M
C
-
C
o
m
p
u
t
Ma
t
e
r
C
o
n
t
,
v
o
l
.
7
0
,
n
o
.
3
,
p
p
.
5
3
9
9
–
5
4
1
9
,
2
0
2
2
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
mc
.
2
0
2
2
.
0
2
0
4
3
1
.
[
1
7
]
M
.
K
a
m
y
a
b
,
G
.
Li
u
,
A
.
R
a
s
o
o
l
,
M
.
A
d
j
e
i
sa
h
,
“
A
c
r
-
sa
:
a
t
t
e
n
t
i
o
n
-
b
a
se
d
d
e
e
p
m
o
d
e
l
t
h
r
o
u
g
h
t
w
o
-
c
h
a
n
n
e
l
c
n
n
a
n
d
b
i
-
r
n
n
f
o
r
sen
t
i
m
e
n
t
a
n
a
l
y
si
s
,
”
Pe
e
r J
C
o
m
p
u
t
S
c
i
,
v
o
l
.
8
,
p
p
.
1
–
1
2
,
2
0
2
2
,
d
o
i
:
1
0
.
7
7
1
7
/
p
e
e
r
j
-
c
s.
8
7
7
.
[
1
8
]
F
.
B
.
S
i
l
v
a
,
R
.
D
.
O
.
W
e
r
n
e
c
k
,
S
.
G
o
l
d
e
n
s
t
e
i
n
,
S
.
Ta
b
b
o
n
e
,
R
.
D
.
S
.
T
o
r
r
e
s,
“
G
r
a
p
h
-
b
a
se
d
b
a
g
-
of
-
w
o
r
d
s
f
o
r
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
Pa
t
t
Re
c
o
g
n
,
v
o
l
.
7
4
,
p
p
.
2
6
6
–
2
8
5
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
1
7
.
0
9
.
0
1
8
.
[
1
9
]
Y
.
S
h
e
n
,
H
.
G
u
o
,
“
N
e
w
b
r
e
a
k
t
h
r
o
u
g
h
s
a
n
d
i
n
n
o
v
a
t
i
o
n
m
o
d
e
s
i
n
e
n
g
l
i
sh
e
d
u
c
a
t
i
o
n
i
n
p
o
s
t
-
p
a
n
d
e
mi
c
e
r
a
,
”
Fr
o
n
t
Psy
c
h
o
l
,
v
o
l
.
1
3
,
p
p
.
8
3
9
4
4
0
–
8
3
9
4
4
0
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
s
y
g
.
2
0
2
2
.
8
3
9
4
4
0
.
[
2
0
]
V
.
M
i
t
t
a
l
,
D
.
G
a
n
g
o
d
k
a
r
,
B
.
P
a
n
t
,
“
D
e
e
p
g
r
a
p
h
-
l
o
n
g
s
h
o
r
t
-
t
e
r
m
mem
o
r
y
:
a
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
a
p
p
r
o
a
c
h
f
o
r
t
e
x
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
Wi
re
l
P
e
rs
o
n
a
l
C
o
m
m
u
n
,
v
o
l
.
1
1
9
,
n
o
.
3
,
p
p
.
2
2
8
7
–
2
3
0
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
7
7
-
0
2
1
-
0
8
3
3
1
-
4
.
[
2
1
]
L.
H
a
n
,
W
.
P
a
n
,
H
.
Zh
a
n
g
,
“
M
i
c
r
o
b
l
o
g
r
u
m
o
r
s
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
b
e
r
t
-
g
r
u
,
”
I
n
:
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
C
h
i
n
a
,
p
p
.
4
5
0
–
4
5
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
15
-
8
5
9
9
-
9
_
5
2
.
[
2
2
]
M
.
S
c
h
u
s
t
e
r
,
&
K
.
K
.
P
a
l
i
w
a
l
,
“
B
i
d
i
r
e
c
t
i
o
n
a
l
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
I
EEE
T
r
a
n
s
S
i
g
n
a
l
Pro
c
e
ss
,
v
o
l
.
4
5
,
n
o
.
1
1
,
p
p
.
2
6
7
3
–
2
6
8
1
,
1
9
9
7
,
d
o
i
:
1
0
.
1
1
0
9
/
7
8
.
6
5
0
0
9
3
.
[
2
3
]
W
.
L
i
,
W
.
S
h
a
o
,
S
.
J
i
,
E.
C
a
m
b
r
i
a
,
“
B
i
e
r
u
:
b
i
d
i
r
e
c
t
i
o
n
a
l
e
m
o
t
i
o
n
a
l
r
e
c
u
r
r
e
n
t
u
n
i
t
f
o
r
c
o
n
v
e
r
sa
t
i
o
n
a
l
se
n
t
i
m
e
n
t
a
n
a
l
y
si
s
,
”
Ne
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
4
6
7
,
p
p
.
7
3
–
8
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m
.
2
0
2
1
.
0
9
.
0
5
7
.
[
2
4
]
X
.
Ji
a
,
L
.
W
a
n
g
,
“
A
t
t
e
n
t
i
o
n
e
n
h
a
n
c
e
d
c
a
p
s
u
l
e
n
e
t
w
o
r
k
f
o
r
t
e
x
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
y
e
n
c
o
d
i
n
g
s
y
n
t
a
c
t
i
c
d
e
p
e
n
d
e
n
c
y
t
r
e
e
s
w
i
t
h
g
r
a
p
h
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
,
”
P
e
e
r
J
C
o
m
p
u
t
S
c
i
,
v
o
l
.
7
,
p
p
.
2
4
6
6
–
2
4
8
0
,
2
0
2
2
,
d
o
i
:
1
0
.
7
2
8
7
/
p
e
e
r
j
-
c
s.
8
3
1
v
0
.
1
/
r
e
v
i
e
w
s/
2
.
[
2
5
]
“
Tr
i
p
A
d
v
i
s
o
r
H
o
t
e
l
R
e
v
i
e
w
s”
2
0
1
3
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m/
d
a
t
a
s
e
t
s
/
a
n
d
r
e
w
mv
d
/
t
r
i
p
-
a
d
v
i
s
o
r
-
h
o
t
e
l
-
r
e
v
i
e
w
s
,
d
o
i
:
1
0
.
3
4
2
7
6
/
1
8
2
2
-
009
-
0
0
3
-
0
3
3
.
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
Wa
r
s
tr
a
teg
y
a
s
s
i
s
ted
B
i
-
LS
T
M fo
r
s
en
timen
t a
n
a
lysi
s
o
f c
u
s
to
mer revie
w
(
A
n
ils
a
g
a
r
T.
)
489
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ani
lsa
g
a
r
T
.
e
a
rn
e
d
h
is
Ba
c
h
e
lo
r
o
f
En
g
i
n
e
e
rin
g
(B
.
E.
)
i
n
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
fro
m
Visv
e
sw
a
ra
iah
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsit
y
,
Be
lag
a
v
i,
Ka
rn
a
tak
a
,
in
2
0
1
3
,
w
h
e
re
h
e
laid
a
s
o
li
d
fo
u
n
d
a
ti
o
n
in
c
o
re
c
o
n
c
e
p
ts
o
f
c
o
m
p
u
ter
sc
ien
c
e
.
Bu
il
d
in
g
u
p
o
n
th
is,
h
e
p
u
rs
u
e
d
a
n
d
su
c
c
e
ss
fu
ll
y
c
o
m
p
lete
d
h
is M
a
ste
r
o
f
Tec
h
n
o
l
o
g
y
(M
.
Tec
h
.
)
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
fr
o
m
th
e
sa
m
e
u
n
iv
e
rsity
i
n
2
0
1
5
,
fu
rt
h
e
r
d
e
e
p
e
n
in
g
h
is
k
n
o
wle
d
g
e
a
n
d
e
x
p
e
rti
se
in
t
h
e
field
.
C
u
rr
e
n
tl
y
,
A
n
il
sa
g
a
r
is
e
n
g
a
g
e
d
i
n
th
e
p
u
rsu
it
o
f
a
P
h
.
D.
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
a
t
B
S
Ab
d
u
r
Ra
h
m
a
n
Cre
sc
e
n
t
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
,
V
a
n
d
a
lu
r,
Ch
e
n
n
a
i,
wh
e
re
h
e
c
o
n
ti
n
u
e
s
t
o
e
x
p
lo
re
n
o
v
e
l
a
v
e
n
u
e
s
o
f
re
se
a
rc
h
a
n
d
in
n
o
v
a
ti
o
n
.
An
il
sa
g
a
r'
s
re
se
a
rc
h
i
n
tere
sts
sp
a
n
a
wi
d
e
ra
n
g
e
o
f
t
o
p
ics
,
in
c
l
u
d
i
n
g
c
o
n
v
e
rsa
ti
o
n
a
l
AI
,
se
n
ti
m
e
n
t
a
n
a
ly
sis,
we
b
a
p
p
d
e
v
e
l
o
p
m
e
n
t,
a
n
d
c
l
o
u
d
se
rv
ice
s
.
He
is
p
a
rti
c
u
lar
ly
fa
sc
in
a
ted
b
y
t
h
e
i
n
ters
e
c
ti
o
n
o
f
th
e
se
a
re
a
s
a
n
d
t
h
e
p
o
ten
t
ial
t
h
e
y
h
o
ld
f
o
r
re
v
o
lu
ti
o
n
izin
g
v
a
ri
o
u
s
a
sp
e
c
ts
o
f
tec
h
n
o
l
o
g
y
a
n
d
h
u
m
a
n
in
tera
c
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
il
sa
g
a
r1
2
3
t@o
u
tl
o
o
k
.
c
o
m
a
n
d
a
n
il
tsa
g
a
r@g
m
a
il
.
c
o
m
.
S
y
e
d
Abd
u
l
S
y
e
d
S.
re
c
e
iv
e
d
h
is
B.
Tec
h
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
in
2
0
0
4
fr
o
m
Un
iv
e
rsit
y
o
f
M
a
d
ra
s,
M
.
Tec
h
CS
E
in
2
0
0
9
fro
m
Dr.
M
G
R
Ed
u
c
a
ti
o
n
a
l
&
Re
se
a
rc
h
In
stit
u
te,
Ch
e
n
n
a
i
a
n
d
P
h
.
D.
IT
i
n
2
0
2
1
fro
m
AME
T
Un
iv
e
rsity
,
Ch
e
n
n
a
i.
His
p
rima
ry
re
se
a
rc
h
wo
r
k
is
r
o
u
t
i
n
g
p
r
o
t
o
c
o
l
i
n
M
AN
ET
.
Cu
rre
n
tl
y
w
o
rk
i
n
g
a
s
As
so
c
iate
P
ro
fe
ss
o
r
a
n
d
DCO
E
i
n
B
S
A
b
d
u
r
Ra
h
m
a
n
Cre
sc
e
n
t
I
n
stit
u
te
o
f
S
c
ie
n
c
e
&
Tec
h
n
o
l
o
g
y
,
Ch
e
n
n
a
i,
In
d
ia.
Dr.
S
S
y
e
d
Ab
d
u
l
S
y
e
d
h
a
s
p
u
b
li
sh
e
d
h
is
re
se
a
rc
h
a
rti
c
les
in
m
a
n
y
re
p
u
te
d
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls
o
u
t
o
f
wh
ic
h
2
p
a
p
e
rs
a
re
i
n
u
n
p
a
id
S
c
o
p
u
s
in
d
e
x
e
d
j
o
u
r
n
a
ls,
a
n
d
a
lso
g
u
i
d
e
d
m
a
n
y
B.
Tec
h
.
a
n
d
M
.
Tec
h
.
st
u
d
e
n
ts
f
o
r
th
e
ir
a
c
a
d
e
m
ic
p
r
o
jec
ts
a
n
d
p
u
b
li
c
a
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sy
e
d
a
b
d
u
lsy
e
d
@c
re
sc
e
n
t.
e
d
u
c
a
ti
o
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.