I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
10
,
No
.
2
,
May
201
8
,
p
p
.
7
7
0
~7
7
7
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
1
0
.
i2
.
p
p
770
-
7
7
7
770
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
Technica
l Ap
pro
a
ch in
Tex
t
M
in
in
g
f
o
r St
o
c
k Ma
rket
Predic
tion:
A Sys
te
m
a
tic
Rev
iew
M
o
ha
m
m
a
d Ra
bi
ul I
s
la
m
1
,
I
m
a
d F
a
kh
ri
Al
-
Sh
a
i
kh
li
2
,
Ri
za
l B
in
M
o
hd
No
r
3
,
Vij
a
y
a
k
u
m
a
r
Va
ra
da
ra
j
a
n
4
1
,
2,
3
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
In
tern
a
ti
o
n
a
l
Isla
m
ic Un
iv
e
sity
M
a
la
y
sia
,
Ku
a
la L
u
m
p
u
r,
M
a
lay
sia
.
4
S
c
h
o
o
l
o
f
Co
m
p
u
ti
n
g
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
V
IT
Un
iv
e
rsity
Ch
e
n
n
a
i,
In
d
ia.
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
N
ov
23
,
2
0
1
7
R
ev
i
s
ed
J
an
25
,
2
0
1
8
A
cc
ep
ted
F
eb
17
,
2
0
1
8
T
e
x
t
m
in
in
g
m
e
th
o
d
s
a
n
d
tec
h
n
i
q
u
e
s
h
a
v
e
d
isc
lo
se
d
th
e
m
in
in
g
tas
k
th
ro
u
g
h
o
u
t
in
f
o
rm
a
ti
o
n
re
tri
e
v
a
l
d
isc
ip
li
n
e
in
t
h
e
f
ield
o
f
so
f
t
c
o
m
p
u
ti
n
g
tec
h
n
iq
u
e
s.
T
o
f
in
d
th
e
m
e
a
n
in
g
f
u
l
in
f
o
rm
a
ti
o
n
f
ro
m
th
e
v
a
st
a
m
o
u
n
t
o
f
e
lec
tro
n
ic
tex
tu
a
l
d
a
ta
b
e
c
o
m
e
a
h
u
m
o
n
g
o
u
s
t
a
sk
f
o
r
trad
in
g
d
e
c
isio
n
.
T
h
is
e
m
p
iri
c
a
l
re
se
a
rc
h
o
f
tex
t
m
in
in
g
ro
le
o
n
f
in
a
n
c
ial
tex
t
a
n
a
ly
sin
g
in
w
h
e
re
sto
c
k
p
re
d
ictiv
e
m
o
d
e
l
n
e
e
d
to
i
m
p
ro
v
e
b
a
se
d
o
n
ra
n
k
se
a
rc
h
m
e
th
o
d
.
T
h
e
re
v
ie
w
o
f
th
is
p
a
p
e
r
b
a
sic
a
ll
y
f
o
c
u
se
d
o
n
tex
t
m
in
in
g
tec
h
n
i
q
u
e
s
,
m
e
th
o
d
s
a
n
d
p
rin
c
i
p
le
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
th
a
t
h
e
lp
re
d
u
c
e
th
e
d
ime
n
sio
n
a
l
it
y
w
it
h
in
th
e
c
h
a
ra
c
teristics
a
n
d
o
p
ti
m
a
l
fe
a
tu
re
s.
M
o
re
o
v
e
r,
m
o
st
so
p
h
ist
i
c
a
ted
so
f
t
-
c
o
m
p
u
ti
n
g
m
e
th
o
d
s
a
n
d
tec
h
n
i
q
u
e
s
a
re
re
v
ie
w
e
d
in
term
s
o
f
a
n
a
ly
sis,
c
o
m
p
a
riso
n
a
n
d
e
v
a
lu
a
ti
o
n
f
o
r
it
s
p
e
rf
o
r
m
a
n
c
e
b
a
se
d
o
n
e
lec
tro
n
ic
tex
tu
a
l
d
a
ta.
Du
e
to
re
se
a
rc
h
sig
n
if
ica
n
c
e
,
th
is
e
m
p
iri
c
a
l
re
se
a
rc
h
a
lso
h
ig
h
li
g
h
ts
th
e
li
m
it
a
ti
o
n
o
f
d
iffere
n
t
stra
te
g
ies
a
n
d
m
e
th
o
d
s
o
n
e
x
a
c
t
a
sp
e
c
ts
o
f
th
e
o
re
ti
c
a
l
f
ra
m
e
w
o
rk
f
o
r
e
n
h
a
n
c
in
g
o
f
p
e
rf
o
rm
a
n
c
e
.
K
ey
w
o
r
d
s
:
On
li
n
e
n
e
w
s
m
in
in
g
Sto
ck
m
ar
k
et
p
r
ed
ictio
n
T
ex
t m
in
i
n
g
ap
p
r
o
ac
h
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Mo
h
a
m
m
ad
R
ab
i
u
l I
s
la
m
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
I
n
ter
n
atio
n
al
I
s
la
m
ic
U
n
iv
er
s
it
y
Ma
la
y
s
ia.
5
0
7
2
8
,
Go
m
b
ak
,
K
u
ala
L
u
m
p
u
r
,
Ma
la
y
s
ia.
E
m
ail: r
ab
iu
l.i
s
la
m
@
li
v
e.
iiu
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
Sin
ce
l
ast
d
ec
ad
e,
ec
o
n
o
m
ic
t
ex
tu
al
n
ew
s
ca
teg
o
r
iz
ati
o
n
im
m
en
s
el
y
in
f
lu
en
ce
o
n
s
to
ck
p
r
ed
i
cti
o
n
in
ter
m
s
ch
an
g
in
g
o
u
r
s
o
ci
o
e
co
n
o
m
y
.
I
n
g
en
er
al,
s
t
o
ck
p
r
ice
tr
en
d
s
an
d
d
ec
is
i
o
n
tak
en
th
r
o
u
g
h
d
a
ta
m
in
in
g
tech
n
i
q
u
es
f
r
o
m
h
is
to
r
ic
al
p
r
ic
e
d
e
co
r
a
ti
o
n
s
,
h
u
m
an
b
eh
av
io
u
r
an
d
in
d
ic
at
o
r
s
.
W
ith
i
n
th
e
tex
t
m
in
in
g
tech
n
i
q
u
es,
s
t
o
ck
p
r
e
d
ict
iv
e
m
o
d
el
(
S
P
M
)
n
e
ed
t
o
im
p
r
o
v
e
b
y
th
e
r
an
k
s
e
ar
ch
m
eth
o
d
w
ith
th
e
in
clu
s
i
o
n
o
f
g
ain
s
an
d
r
ati
o
s
a
lo
n
g
w
ith
f
o
r
w
ar
d
s
elec
ti
o
n
m
eth
o
d
s
b
y
in
teg
r
a
tin
g
d
im
en
s
io
n
al
ity
r
ed
u
ct
io
n
te
ch
n
iq
u
es
e.
g
.
p
r
in
ci
p
l
e
c
o
m
p
o
n
en
t
an
a
ly
s
is
(
P
C
A
)
f
o
r
h
u
g
e
q
u
an
tity
o
f
ch
ar
ac
t
er
is
t
i
cs
tex
t
[
4
]
.
T
h
r
o
u
g
h
o
u
t
th
is
m
o
d
el,
en
o
r
m
o
u
s
ch
ar
ac
te
r
is
ti
cs
tex
t
u
al
d
at
a
n
ee
d
th
e
d
eg
r
a
d
ati
o
n
o
f
ac
cu
r
at
en
ess
w
ith
less
ef
f
icien
cy
f
o
r
its
ap
p
r
o
p
r
ia
te
c
lass
if
i
ca
t
io
n
.
Va
r
i
o
u
s
ex
ec
u
t
iv
e
m
eth
o
d
s
in
s
o
f
t
-
co
m
p
u
tin
g
,
e
.
g
.
tex
t
class
if
ica
t
io
n
,
t
ex
t
d
o
cu
m
en
t
su
m
m
ar
izat
io
n
,
tax
o
n
o
m
y
cr
e
ati
o
n
,
c
lu
s
te
r
in
g
an
d
o
th
e
r
c
o
m
p
u
tatio
n
al
ap
p
r
o
ac
h
b
o
o
s
t
t
h
e
in
ter
d
is
ci
p
lin
a
r
y
f
ield
o
f
d
a
ta
m
in
in
g
ac
tiv
it
ie
s
[
1
]
.
B
asi
ca
lly
,
th
e
s
tu
d
y
o
f
th
e
r
ese
ar
ch
f
o
cu
s
ed
o
n
d
if
f
er
en
t
m
eth
o
d
s
an
d
tech
n
i
q
u
es
b
as
ed
o
n
th
e
p
r
o
p
o
s
e
d
P
C
A
tech
n
i
q
u
es
f
o
r
u
s
a
b
il
ity
o
f
tex
tu
al
an
d
n
u
m
er
ica
l
d
ata
o
n
th
e
s
t
o
ck
p
r
ic
e
t
r
en
d
.
2.
E
L
E
C
T
RO
NIC
T
E
XT
M
I
NING
E
lectr
o
n
ic
f
o
r
m
s
o
f
te
x
t
d
o
cu
m
en
t
b
ec
o
m
e
an
i
m
p
o
r
tan
t
f
ie
ld
o
f
r
esear
ch
d
u
e
to
av
ailab
il
it
y
o
f
w
eb
tex
t
an
d
tex
t
m
i
n
in
g
ca
teg
o
r
iz
atio
n
[
3
]
.
Ov
er
th
e
last
f
e
w
d
ec
ad
es,
h
is
to
r
ical
lar
g
e
a
m
o
u
n
t
o
f
d
ata
h
as
b
ee
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Tech
n
ica
l A
p
p
r
o
a
ch
in
Text
M
in
i
n
g
fo
r
S
to
ck
Ma
r
ke
t P
r
ed
ict
io
n
…
(
Mo
h
a
mma
d
R
a
b
iu
l I
s
l
a
m
)
771
s
to
r
ed
elec
tr
o
n
icall
y
a
n
d
ex
te
n
d
th
e
le
v
el
o
f
v
o
lu
m
e
i
n
f
u
t
u
r
e
[
1
2
]
.
T
h
eo
r
etica
l,
co
n
ce
p
t
u
al
an
d
ca
te
g
o
r
ized
b
ased
elec
tr
o
n
ic
tex
t
m
in
in
g
f
o
r
m
s
ab
le
to
b
r
in
g
t
h
e
s
i
g
n
i
f
ican
ce
r
esear
ch
v
al
u
es
f
o
r
its
ad
v
a
n
ta
g
es
th
at
b
r
ief
l
y
d
escr
ib
ed
b
lo
w
.
2
.
1
.
T
heo
re
t
ica
l
M
e
t
ho
ds
in T
ex
t
M
ini
ng
His
to
r
ic
d
ata
is
w
ell
f
o
u
n
d
ed
th
at
h
o
ld
s
th
e
e
s
s
e
n
tial
i
n
f
o
r
m
atio
n
f
o
r
p
r
ed
ictin
g
t
h
e
f
u
tu
r
e
d
ir
ec
tio
n
o
f
s
to
ck
m
ar
k
e
t
th
at
b
r
i
n
g
o
u
t
t
h
e
ad
v
an
tag
e
s
o
f
K
n
o
w
le
d
g
e
Dis
co
v
er
y
i
n
T
ex
t
(
KDT
)
w
h
ich
d
ea
l
w
it
h
ex
tr
ac
tio
n
o
f
p
atter
n
f
r
o
m
tex
t
u
al
d
ata
[
9
]
.
B
esid
e
o
f
th
i
s
t
h
eo
r
y
o
f
R
a
n
d
o
m
W
al
k
s
i
s
b
as
ed
o
n
th
e
e
f
f
icie
n
t
-
m
ar
k
et
h
y
p
o
t
h
esi
s
(
E
MH
)
th
at
h
o
ld
th
e
b
est
tr
ad
in
g
s
tr
ate
g
y
“
b
u
y
a
n
d
h
o
ld
”
[
1
0
]
.
I
n
th
is
ca
s
e,
tex
t
m
i
n
i
n
g
o
f
n
e
w
s
ar
tic
les
g
i
v
es
t
h
e
i
n
tr
i
n
s
ic
v
al
u
e
f
o
r
tr
ad
in
g
d
ec
i
s
io
n
t
h
r
o
u
g
h
a
n
al
y
tical
tec
h
n
iq
u
e.
On
t
h
e
o
th
er
h
a
n
d
,
Su
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e
(
S
VM
s
)
is
w
el
l
-
f
o
u
n
d
ed
f
o
r
th
eo
r
etica
l
u
n
d
er
s
tan
d
i
n
g
an
d
an
al
y
s
is
[
1
1
]
.
T
h
eo
r
etica
lly
d
ata
m
in
in
g
is
well
f
o
u
n
d
ed
d
u
e
to
h
is
to
r
ical
d
ata
th
at
h
o
ld
s
k
e
y
f
ac
t
s
f
o
r
p
r
ed
ictio
n
[
1
2
]
.
2
.
2
.
Co
ncept
ua
l Tex
t
M
ini
ng
C
o
n
ce
p
t
b
ased
tex
t
m
o
d
el
an
a
l
y
ze
d
an
d
f
o
llo
w
ed
b
y
t
h
r
ee
c
o
m
p
o
n
en
t
s
[
2
]
.
First,
s
tati
s
tica
l
an
al
y
s
er
ab
le
to
an
aly
s
is
t
h
r
o
u
g
h
ea
c
h
ter
m
o
f
th
e
s
e
n
te
n
ce
an
d
lev
els
o
f
d
o
cu
m
en
t
s
w
h
ic
h
e
n
ab
le
to
s
et
u
p
th
e
w
ei
g
h
ti
n
g
s
c
h
e
m
e
b
ased
o
n
i
m
p
o
r
tan
t
o
r
n
o
n
-
i
m
p
o
r
ta
n
t
t
er
m
s
.
Seco
n
d
is
C
o
n
ce
p
t
u
al
On
to
lo
g
ical
Gr
ap
h
(
C
OG)
t
h
at
r
ep
r
esen
t
s
t
h
e
co
n
ce
p
t
ac
co
r
d
in
g
to
t
h
e
s
e
n
te
n
ce
m
ea
n
in
g
.
T
h
ir
d
is
co
n
ce
p
tu
al
e
x
tr
ac
to
r
th
at
co
u
ld
b
e
d
is
tin
g
u
i
s
h
ed
b
ased
o
n
C
OG
a
n
d
d
en
o
te
i
m
p
o
r
tan
t
co
n
ce
p
ts
.
Oth
er
p
o
p
u
lar
ter
m
o
n
te
x
t
m
i
n
i
n
g
is
b
ag
-
of
-
w
o
r
d
s
(
B
OW
)
th
at
h
o
l
d
s
e
m
an
tic
co
n
ce
p
tu
a
l
in
f
o
r
m
atio
n
to
class
i
f
y
th
e
tex
t
b
ased
o
n
ca
teg
o
r
ies
f
r
o
m
th
e
ex
ter
n
al
k
n
o
w
led
g
e
r
ep
o
s
ito
r
ies [
3
]
.
Fig
u
r
e
1
:
T
ex
t
Min
in
g
in
C
o
n
c
ep
t
-
B
as
e
d
M
o
d
e
l
[
4
]
T
h
e
m
ain
f
ac
to
r
o
f
c
o
n
ce
p
tu
al
d
o
cu
m
en
t
an
d
s
en
ten
ce
a
r
e
d
e
p
en
d
in
g
o
n
w
eig
h
tin
g
ca
p
tu
r
e
d
th
at
ex
tr
ac
t
ed
f
r
o
m
it.
B
as
ed
o
n
w
eig
h
tin
g
s
ch
em
e,
s
en
ten
ce
s
e
m
an
tics
is
ass
ig
n
ed
th
r
o
u
g
h
c
o
n
ce
p
tu
al
s
tat
is
ti
ca
l
an
aly
s
er
an
d
c
o
n
c
e
p
tu
al
o
n
t
o
l
o
g
ical
g
r
a
p
h
[
4
]
.
Fig
u
r
e
1
r
e
p
r
e
s
en
ts
th
e
co
n
ce
p
t
-
b
ase
d
m
o
d
el
.
T
h
is
tex
tu
a
l
b
ase
d
co
n
c
e
p
tu
al
m
o
d
el
b
r
in
g
s
an
a
ly
s
is
o
f
r
aw
tex
t
d
o
cu
m
en
t
f
r
o
m
co
n
ce
p
t
-
b
as
ed
s
t
atis
t
ic
a
l
an
aly
s
er
,
co
n
c
e
p
t
ex
tr
ac
t
o
r
an
d
c
o
n
c
ep
tu
al
o
n
to
lo
g
ic
al
g
r
ap
h
r
e
p
r
esen
t
ati
o
n
.
I
n
th
is
m
an
n
er
,
co
n
ce
p
t
-
b
ase
d
s
tatis
t
ic
al
te
r
m
r
u
n
o
v
e
r
th
e
s
en
t
en
ce
o
r
d
o
cu
m
en
t
lev
els
t
o
f
i
n
d
th
e
s
t
atis
t
ic
al
ter
m
s
in
s
tea
d
o
f
s
in
g
le
te
r
m
[
4
]
.
B
asi
ca
l
ly
,
th
is
m
o
d
el
b
r
in
g
s
th
e
a
d
v
an
tag
es
o
f
s
tatis
tic
al
c
o
n
c
ep
t
-
b
as
e
d
w
eig
h
tin
g
s
ch
em
e
th
at
en
h
an
ce
th
e
co
n
ce
p
t
t
o
C
OG
d
o
cu
m
en
t le
v
el
th
a
t
ab
le
t
o
b
r
i
n
g
o
u
t m
o
r
e
ac
cu
r
ate
r
esu
lt
in
t
ex
t m
in
in
g
[
4
]
.
2
.3
.
Ca
t
eg
o
rize
d B
a
s
e
T
ex
t
M
ini
ng
T
ex
t
ca
teg
o
r
i
za
ti
o
n
w
eig
h
tin
g
s
ch
em
es
o
n
te
r
m
d
o
cu
m
e
n
ts
f
o
ll
o
w
ed
b
y
s
tatis
tic
al
i
n
f
o
r
m
ativ
e
th
r
o
u
g
h
in
t
o
tw
o
ca
teg
o
r
i
es:
u
n
s
u
p
er
v
is
ed
an
d
s
u
p
e
r
v
is
e
d
th
at
a
p
p
r
o
a
ch
e
d
b
y
m
u
ltil
in
g
u
al
tex
t
ca
teg
o
r
i
za
t
io
n
[
3
]
-
[
6
]
.
T
h
e
a
d
v
an
t
ag
e
s
o
f
th
is
tex
t
c
ateg
o
r
iz
ati
o
n
a
r
e
b
r
o
u
g
h
t
b
y
g
en
eti
c
alg
o
r
i
th
m
th
at
u
s
ed
t
o
o
p
tim
ize
an
d
b
u
il
d
u
s
e
r
tem
p
lat
e
[
5
]
.
I
n
s
u
c
h
ca
s
e
,
b
est
tex
t
ca
teg
o
r
i
za
ti
o
n
c
o
u
ld
b
e
o
b
t
ain
e
d
b
y
u
s
in
g
lo
ca
l
d
ict
io
n
a
r
i
es
an
d
lo
c
al
f
ea
tu
r
es
[
7
]
.
M
o
r
e
o
v
e
r
,
I
n
s
tan
t
b
ase
d
le
ar
n
in
g
alg
o
r
ith
m
h
elp
t
o
ca
t
eg
o
r
i
ze
th
e
c
l
o
s
es
t
f
ea
tu
r
e
s
p
ac
e
f
r
o
m
tr
a
in
in
g
s
et
th
at
b
asic
ally
m
ap
p
e
d
in
to
m
u
lti
-
d
im
en
s
io
n
al
f
e
atu
r
e
s
p
ac
e
[
8
]
.
T
ex
t
ca
t
eg
o
r
i
za
ti
o
n
p
e
r
f
o
r
m
an
ce
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
10
,
No
.
2
,
Ma
y
2
0
1
8
:
7
7
0
–
7
7
7
772
h
as
im
p
r
o
v
e
d
b
as
ed
o
n
c
o
r
p
u
s
-
b
ase
d
th
es
au
r
u
s
an
d
W
o
r
d
N
et,
w
h
er
e
k
-
Nea
r
es
t
Ne
ig
h
b
o
u
r
(
k
-
NN
)
a
lg
o
r
ith
m
w
ith
b
a
ck
p
r
o
p
ag
ati
o
n
n
eu
r
al
n
etw
o
r
k
alg
o
r
ith
m
s
ab
l
e
t
o
b
e
ac
h
iev
e
d
tex
t
ca
t
eg
o
r
iz
ati
o
n
r
e
s
u
lt
[
1
6
]
.
3.
T
E
CH
N
I
CA
L
AP
P
RO
ACH
O
F
T
E
X
T
M
I
NING
T
ec
h
n
i
ca
l
ap
p
r
o
ac
h
o
n
f
in
an
c
ial
t
ex
t
d
ata
u
s
ed
to
an
aly
s
e
th
r
o
u
g
h
m
an
y
class
if
ica
ti
o
n
t
ask
s
.
T
h
e
s
tu
d
y
o
f
th
is
a
r
t
icl
e
b
r
ief
ly
p
r
e
s
en
t
s
pe
r
f
o
r
m
an
ce
o
f
t
ec
h
n
ic
al
a
p
p
r
o
a
ch
o
n
s
t
o
ck
m
ar
k
et
.
3
.
1
.
Ana
ly
t
ic
a
l
Appro
a
ch
T
ex
tu
al
d
ata
in
f
i
n
an
c
ial
m
ar
k
et
ar
e
ap
p
lied
th
r
o
u
g
h
t
w
o
an
al
y
tical
ap
p
r
o
ac
h
es
[
1
3
]
.
First:
A
p
p
lied
m
ax
i
m
u
m
e
n
tr
o
p
y
te
x
t
clas
s
i
f
icatio
n
f
o
r
th
e
p
r
ed
ictio
n
o
f
w
h
o
le
b
o
d
y
i
n
te
x
t
ar
ti
cle.
S
ec
o
n
d
:
A
p
p
lied
th
e
g
en
et
ic
alg
o
r
ith
m
f
o
r
lear
n
in
g
s
i
m
p
le
r
u
les
b
ased
o
n
n
u
m
er
ical
d
ata
o
f
tr
ad
in
g
v
o
l
u
m
e.
C
l
u
s
ter
i
n
g
a
n
d
class
i
f
icatio
n
alg
o
r
ith
m
s
ar
e
ap
p
lied
o
v
er
th
e
f
ea
tu
r
e
s
ex
tr
a
cted
th
r
o
u
g
h
tex
t
m
in
i
n
g
ap
p
r
o
ac
h
es
o
n
th
e
s
to
c
k
m
ar
k
et
n
e
w
s
a
n
d
ti
m
e
s
er
ies
tech
n
iq
u
e
s
[
1
4
]
.
I
n
t
h
is
ca
s
e
,
f
r
eq
u
e
n
t
ter
m
-
b
a
s
ed
te
x
t
cl
u
s
ter
i
n
g
(
FT
C
)
an
d
(
HFT
C
)
Hier
ar
ch
ical
clu
s
ter
i
n
g
is
to
b
e
ap
p
lied
f
o
r
tex
t
clu
s
ter
in
g
[
1
5
]
.
T
h
e
ad
v
an
tag
es
f
o
u
n
d
b
y
FT
C
th
a
t
co
v
er
in
g
w
h
o
le
d
atab
ase
an
d
HFT
C
co
v
er
in
g
t
h
e
g
r
ap
h
-
s
tr
u
ctu
r
in
g
cl
u
s
ter
i
n
g
.
3
.
2
.
Co
nte
x
t
ua
l
Appro
a
ch
T
h
e
ad
v
an
tag
e
s
o
f
co
n
te
x
t
u
a
l
ap
p
r
o
ac
h
h
elp
to
d
ef
in
e
t
h
e
s
e
n
ti
m
en
t
clu
e
t
h
at
i
s
s
y
n
tactica
ll
y
en
g
a
g
ed
to
s
en
t
i
m
e
n
t
to
p
ic
in
a
s
en
te
n
ce
.
I
n
th
i
s
ca
s
e,
t
h
e
co
n
tex
t
u
al
f
ea
tu
r
e
p
ar
t
is
as
s
i
s
tin
g
b
y
e
x
tr
ac
ted
s
en
ti
m
e
n
t
cl
u
es
o
f
p
o
lar
ities
w
it
h
t
h
e
lar
g
e
a
m
o
u
n
t
o
f
tr
ain
i
n
g
d
ata
w
h
ic
h
is
co
n
te
x
t
u
all
y
in
c
lu
d
ed
th
a
t
id
en
ti
f
ied
b
y
B
o
o
ts
tr
ap
p
in
g
al
g
o
r
ith
m
[
1
7
]
.
3
.
3
.
T
ex
t
Do
cu
m
e
nt
Appro
a
ch
I
n
th
e
tr
ad
itio
n
al
ter
m
w
ei
g
h
ti
n
g
s
ch
e
m
e
s
,
tex
t
u
al
d
o
cu
m
e
n
t a
n
al
y
ze
d
t
h
r
o
u
g
h
t
f
-
id
f
m
e
t
h
o
d
th
at
o
n
l
y
e
x
p
lo
ited
b
y
s
tatis
tical
i
n
f
o
r
m
atio
n
ter
m
s
w
it
h
in
d
o
cu
m
en
ts
[
3
]
.
I
n
th
e
T
ex
t d
o
cu
m
e
n
t
ap
p
r
o
ac
h
T
F
-
I
DF
eq
u
atio
n
u
s
ed
in
t
h
e
i
n
f
o
r
m
ati
o
n
r
etr
iev
al
f
ield
.
TF
-
I
DF
(
t
i,
d
j
)
= c
o
u
n
t(
t
i,
d
j
)
× l
o
g
Af
o
r
e
m
e
n
tio
n
ed
eq
u
atio
n
,
d
j
in
d
icate
d
o
cu
m
e
n
t,
t
i,
in
d
ic
ate
ter
m
in
th
e
d
o
cu
m
en
t
s
w
it
h
ter
m
f
r
eq
u
en
c
y
(
tf
)
a
n
d
co
r
p
u
s
r
ef
er
s
d
o
cu
m
e
n
ts
i
n
t
h
e
co
r
p
u
s
w
it
h
co
u
n
t_
d
o
c
(
t
i
,
co
r
p
u
s
)
.
I
n
ter
m
s
o
f
f
ea
t
u
r
es
s
elec
tio
n
,
t
h
e
m
o
d
er
ate
n
u
m
b
er
o
f
d
is
tin
ct
ter
m
s
a
s
co
llect
io
n
o
f
te
x
t
d
o
cu
m
e
n
t
s
o
p
er
ated
b
y
t
h
is
m
et
h
o
d
.
M
o
r
eo
v
er
,
tex
t f
ea
t
u
r
es select
i
o
n
also
i
m
p
r
o
v
es t
h
e
clas
s
i
f
ica
tio
n
ac
cu
r
ac
y
v
ia
t
h
is
m
et
h
o
d
[
1
8
]
.
3
.
4
.
T
ex
t
Do
cu
m
e
nt
Appro
a
ch
Featu
r
es
b
ased
te
x
t
m
in
i
n
g
in
s
to
c
k
m
ar
k
e
t
p
r
ed
ictio
n
atte
m
p
t
to
ap
p
r
o
ac
h
t
h
r
o
u
g
h
v
ar
io
u
s
an
al
y
tical
tec
h
n
iq
u
es a
s
b
r
ie
f
l
y
d
escr
ib
ed
h
er
e.
3
.
4
.
1
.
P
a
tter
n
B
a
s
ed
P
a
tte
r
n
b
ase
d
d
is
co
v
er
in
g
d
a
ta
f
o
cu
s
o
n
h
ig
h
-
lev
el
l
an
g
u
ag
e
th
at
d
i
r
e
ctly
u
s
ed
b
y
h
u
m
an
lik
e
s
em
an
tic
q
u
e
r
y
o
p
tim
ize
r
an
d
ex
p
e
r
t
s
y
s
tem
[
2
4
]
.
T
h
e
o
n
ly
d
is
a
d
v
an
tag
es
o
f
p
att
er
n
b
ase
d
f
ea
tu
r
es
is
d
is
c
o
v
e
r
e
d
th
e
k
n
o
w
led
g
e
f
r
o
m
d
ata
b
as
e
th
at
c
o
u
ld
b
e
tau
t
o
l
o
g
ic
al
o
r
u
n
in
t
er
esti
n
g
.
3
.
4
.
2
.
Dictio
na
r
y
B
a
s
ed
T
h
e
a
d
v
an
t
ag
es
o
f
d
a
ta
d
i
cti
o
n
ar
y
in
tex
t
m
in
in
g
d
ef
in
e
d
a
s
th
e
s
y
n
tax
o
f
d
a
ta
b
as
e.
B
y
s
y
s
te
m
atic
ap
p
r
o
ac
h
d
ata
ca
n
b
e
s
to
r
e
d
i
n
th
e
d
ata
d
i
cti
o
n
a
r
y
o
r
m
an
u
ally
b
y
ex
p
er
t
[
2
4
]
.
E
.
g
.
R
et
r
iev
al
s
y
s
te
m
f
r
o
m
clin
ic
al
d
ata
b
ase
t
o
k
n
o
w
p
atien
t
m
ajo
r
d
i
ag
n
o
s
ti
c
ca
t
eg
o
r
ies
an
d
r
esu
lt
m
ay
co
m
e
as
e
r
r
o
r
o
r
c
o
r
r
e
ct
ca
t
eg
o
r
ies
f
r
o
m
d
a
ta
s
t
o
r
ag
e.
3
.
4
.
3
.
We
ig
hti
ng
Schem
es B
a
s
ed
I
n
th
e
f
ie
ld
o
f
in
f
o
r
m
atio
n
r
et
r
i
ev
al,
w
eig
h
tin
g
s
ch
em
es f
ea
tu
r
es
a
b
l
e
to
en
h
an
ce
cl
ass
if
ic
ati
o
n
ac
cu
r
a
cy
in
w
h
er
e
d
o
c
u
m
e
n
t r
ep
r
ese
n
t
a
ti
o
n
ac
t
o
n
im
p
li
cit
s
y
n
tacti
c
in
d
i
ca
t
o
r
s
[
2
5
]
,
f
av
o
u
r
ab
i
lity
m
ea
s
u
r
es
[
2
6
]
,
s
ty
lis
tic
an
d
s
y
n
tactic
f
ea
tu
r
e
[
2
7
]
th
at
m
ay
s
elec
t f
r
o
m
d
iv
e
r
s
e
s
o
u
r
c
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Tech
n
ica
l A
p
p
r
o
a
ch
in
Text
M
in
i
n
g
fo
r
S
to
ck
Ma
r
ke
t P
r
ed
ict
io
n
…
(
Mo
h
a
mma
d
R
a
b
iu
l I
s
l
a
m
)
773
4.
I
NF
O
RM
AT
I
O
N
RE
T
RI
E
V
AL
(
I
E
)
M
E
T
H
O
D
I
N
T
H
E
F
I
E
L
D
O
F
T
E
X
T
M
I
NIN
G
L
ast
f
e
w
y
ea
r
s
,
m
an
y
in
n
o
v
ativ
e
m
eth
o
d
s
o
f
tex
t
m
in
in
g
h
av
e
b
e
en
u
s
ed
f
o
r
tex
t
an
aly
s
is
in
d
if
f
er
en
t
p
u
r
p
o
s
e
as
b
r
ief
ly
d
esc
r
i
b
e
h
er
e
w
ith
its
a
d
v
an
t
ag
es
[
1
]
.
L
ar
g
e
am
o
u
n
t
o
f
M
ea
n
in
g
f
u
l
c
o
r
p
u
s
d
a
ta
is
a
ls
o
p
e
r
f
o
r
m
ed
b
y
I
E
[
5
5
]
.
4
.
1
.
Ne
w
s
Cla
s
s
if
ica
t
io
n
Au
to
m
a
ted
te
x
tu
a
l
n
e
w
s
clas
s
i
f
icatio
n
m
et
h
o
d
ap
p
lied
o
n
t
h
e
f
i
n
a
n
cial
f
ie
ld
o
f
s
to
c
k
p
r
ice
p
r
ed
ictio
n
w
it
h
t
h
e
s
e
m
a
n
tics
te
x
t a
n
d
p
o
s
iti
v
e
o
r
n
eg
ati
v
e
f
ee
d
b
ac
k
o
f
s
to
ck
p
r
ice
[
1
9
]
.
4
.
2
.
T
i
m
e
Serie
s
P
re
dict
io
n
T
im
e
s
er
ies
a
n
al
y
s
i
s
tec
h
n
iq
u
es
ap
p
lied
i
n
t
h
e
f
ield
o
f
in
f
o
r
m
atio
n
r
etr
iev
al
f
o
r
s
to
ck
m
ar
k
e
t
p
r
ed
ictio
n
w
h
ic
h
is
a
n
o
th
er
ap
p
r
o
ac
h
th
at
r
etr
iev
e
t
h
e
f
i
n
an
cial
i
n
f
o
r
m
ati
v
e
tex
t
th
r
o
u
g
h
cla
s
s
i
f
ica
tio
n
o
r
clu
s
ter
i
n
g
alg
o
r
it
h
m
w
it
h
t
f
-
i
d
f
an
d
s
i
g
n
al
p
r
o
ce
s
s
in
g
m
et
h
o
d
s
o
v
er
th
e
f
ea
t
u
r
es
e
x
tr
ac
ted
[
2
0
]
.
T
h
e
ti
m
e
s
er
ies
p
r
ed
ictio
n
b
r
in
g
s
t
h
e
a
d
v
an
ta
g
es
w
it
h
it
s
o
w
n
in
ter
n
al
m
o
d
el
w
h
ic
h
is
o
r
ig
i
n
al
ap
p
r
o
ac
h
b
y
ar
tific
ial
n
eu
r
al
n
et
w
o
r
k
s
(
a
n
n
s
)
.
T
h
is
m
o
d
el
also
o
f
f
er
s
o
n
A
NN
f
o
r
q
u
alitat
iv
e
m
et
h
o
d
s
t
h
at
u
s
u
all
y
ap
p
lied
o
n
w
ea
t
h
er
,
s
to
ck
m
ar
k
er
,
m
ed
ical,
ec
o
n
o
m
ic
an
d
b
u
s
in
e
s
s
i
n
wh
er
e
tr
ad
itio
n
al
m
e
th
o
d
s
f
ailed
to
p
r
o
v
id
e
[
2
1
]
.
4
.
3
.
F
uzzy
M
et
ho
ds
Mu
lti
v
a
r
ia
b
l
e
f
u
zz
y
f
o
r
ec
asti
n
g
is
also
a
p
p
li
ca
b
l
e
to
f
u
z
zy
r
u
le
in
t
er
p
o
la
ti
o
n
an
d
f
u
zz
y
clu
s
te
r
in
g
tech
n
i
q
u
es
[
2
3
]
.
T
h
i
s
p
r
o
p
o
s
e
d
m
eth
o
d
a
p
p
lie
d
o
n
T
aiw
an
Sto
ck
E
x
ch
an
g
e
C
a
p
it
ali
za
t
i
o
n
W
e
ig
h
ted
St
o
ck
I
n
d
ex
(
T
A
I
E
X
)
d
at
a.
T
h
e
ex
p
er
im
en
tal
r
esu
lts
s
h
o
w
ed
th
at
th
e
p
r
o
p
o
s
ed
m
eth
o
d
p
r
o
d
u
ce
s
f
o
r
ec
as
tin
g
r
esu
l
ts
b
et
te
r
th
an
s
ev
er
al
ex
is
t
in
g
m
eth
o
d
s
[
2
2
]
.
5.
VARIO
US A
L
G
O
RI
T
H
M
A
ND
AP
P
L
I
C
AT
I
O
N
T
E
CH
NIQU
E
S IN T
E
X
T
M
I
NIN
G
.
Dif
f
er
en
t
alg
o
r
ith
m
s
an
d
t
ec
h
n
iq
u
es
ar
e
ap
p
l
ica
b
l
e
o
n
b
ig
d
at
a
b
ase
.
Ma
ch
in
e
l
ea
r
n
in
g
m
eth
o
d
s
ar
e
m
o
s
tly
u
s
ed
f
o
r
en
h
an
c
in
g
b
e
t
ter
d
ea
l
w
ith
th
e
is
s
u
es
t
o
d
is
c
o
v
e
r
a
b
le
d
ata
b
ase
[
2
4
]
.
Oth
e
r
m
in
in
g
tech
n
iq
u
es
w
h
ich
ar
e
als
o
ap
p
l
ica
b
l
e
b
ase
d
o
n
r
e
q
u
i
r
em
en
t f
o
r
r
et
r
iev
a
l
ar
e
b
r
ief
ly
g
iv
en
b
el
o
w
.
5
.
1
.
T
ex
t
M
ini
ng
Via
Sp
a
rse
M
a
t
rix
F
a
ct
o
riza
t
io
n
Mo
s
t
ele
m
e
n
ts
in
s
p
ar
s
e
m
at
r
ix
is
ze
r
o
,
if
m
o
s
t
o
f
t
h
e
el
e
m
en
ts
ar
e
n
o
n
ze
r
o
th
en
i
ts
co
n
s
id
er
as
d
en
s
e,
i
n
t
h
i
s
ca
s
e
ze
r
o
v
al
u
ed
ele
m
e
n
t
s
d
iv
id
ed
b
y
t
h
e
to
tal
n
u
m
b
er
o
f
ele
m
en
t
s
t
h
at
k
n
o
wn
as
s
p
ar
s
it
y
o
f
t
h
e
m
atr
i
x
.
I
n
ter
m
s
o
f
te
x
t
m
i
n
in
g
,
s
p
ar
s
e
m
atr
i
x
f
ac
to
r
izati
o
n
tech
n
iq
u
e
s
in
co
r
p
o
r
ate
w
i
th
i
n
th
r
ee
u
n
if
ied
f
r
a
m
e
w
o
r
k
s
[
2
8
]
.
(
1
)
C
o
r
r
ela
tio
n
a
m
o
n
g
d
if
f
er
e
n
t
s
to
c
k
s
,
(
2
)
h
is
to
r
ical
s
to
c
k
p
r
ices
a
n
d
(
3
)
n
e
w
s
p
ap
er
s
co
n
ten
t
to
p
r
ed
ict
s
to
ck
p
r
ice
m
o
v
e
m
e
n
t.
A
d
v
an
ta
g
e
s
o
f
th
i
s
tech
n
iq
u
es
is
late
n
t
f
ac
to
r
m
o
d
el
w
h
ic
h
ca
n
b
e
ch
ar
ac
ter
ized
th
e
s
to
ck
p
r
ice
b
ased
o
n
ce
r
tain
d
a
y
f
u
n
ctio
n
o
f
th
e
la
ten
t
f
ea
t
u
r
es.
5
.
2
.
P
o
la
riza
t
io
n
T
ec
hn
iqu
e
Stru
ct
u
r
al
s
e
n
te
n
ce
b
ased
s
e
n
ti
m
e
n
t
a
n
al
y
s
i
s
,
o
p
in
io
n
s
,
e
m
o
tio
n
s
a
n
d
s
e
n
ti
m
e
n
ts
ex
p
r
es
s
ed
in
te
x
t
th
at
m
a
y
f
o
c
u
s
ed
o
n
s
en
t
i
m
e
n
t
p
o
lar
ity
class
if
icatio
n
w
h
ich
d
eter
m
in
i
n
g
th
e
o
p
in
io
n
o
f
te
x
t
an
d
h
o
ld
p
o
s
itiv
e
o
r
n
eg
ati
v
e
s
e
n
ti
m
e
n
t
[
2
9
]
,
[
3
0
]
.
T
h
e
ad
v
an
ta
g
es
o
f
s
en
t
i
m
e
n
t
cla
s
s
i
f
icatio
n
i
n
p
o
lar
it
y
f
o
r
m
t
h
at
d
ep
en
d
s
o
n
s
u
b
j
ec
tiv
el
y
clas
s
if
icatio
n
i
n
s
t
ea
d
o
f
o
b
j
ec
tiv
el
y
f
o
r
m
o
f
s
e
n
ten
ce
s
.
B
u
t
d
is
ad
v
a
n
ta
g
es
o
f
s
u
c
h
clas
s
if
icatio
n
ar
e
th
at
th
e
s
en
t
i
m
e
n
t p
o
lar
it
y
p
r
o
d
u
ce
am
b
i
g
u
o
u
s
i
n
s
e
n
ti
m
e
n
t liter
at
u
r
e
as it c
o
n
s
id
er
s
o
b
jectiv
e
te
x
t o
r
lab
el
f
o
r
s
en
ti
m
e
n
t t
h
at
lies
b
et
w
ee
n
p
o
s
itiv
e
o
r
n
eg
ati
v
e
f
o
r
m
.
5
.
3
.
T
ex
t
ua
l
Da
t
a
M
ini
ng
T
hro
ug
h M
a
chine Lea
rning
Dif
f
er
en
t
m
ac
h
i
n
e
lear
n
i
n
g
(
M.
L
ea
r
n
i
n
g
)
tech
n
iq
u
e
s
ar
e
a
v
ailab
le
to
u
s
e
f
o
r
s
to
c
k
m
ar
k
et
p
r
ed
ictio
n
[
3
6
]
.
E
.
g
.
GA
/T
DNN,
A
N
FIS
,
I
C
A
-
B
P
N,
G
A
/
A
T
NN.
T
ex
t
class
i
f
ica
tio
n
v
ia
m
ac
h
i
n
e
le
ar
n
in
g
co
n
s
id
er
ab
le
g
o
o
d
m
et
h
o
d
b
u
t
p
er
f
o
r
m
an
ce
o
f
v
er
y
lar
g
e
tr
ain
i
n
g
co
r
p
u
s
is
co
n
ce
r
n
ed
f
o
r
i
ts
i
n
e
f
f
icie
n
c
y
[
3
3
]
.
B
esid
e
th
i
s
p
er
f
o
r
m
a
n
ce
,
M.
L
ea
r
n
in
g
a
ls
o
co
m
b
i
n
e
th
e
co
n
ce
p
t
o
f
class
i
f
ier
s
t
h
a
t
cr
ea
te
n
e
w
d
ir
ec
tio
n
f
o
r
th
e
i
m
p
r
o
v
e
m
en
t
o
f
in
d
i
v
id
u
al
s
’
class
i
f
ier
s
.
N
u
m
b
er
o
f
r
esea
r
ch
er
s
p
r
o
v
ed
th
a
t
t
h
e
co
m
b
i
n
atio
n
o
f
d
i
f
f
er
en
t
class
i
f
ier
s
ca
n
i
m
p
r
o
v
e
t
h
e
ac
c
u
r
ac
y
o
f
cla
s
s
i
f
icat
io
n
[
3
4
]
,
[
3
5
]
.
5
.
4
.
Dee
p
L
ea
rning
f
o
r
L
a
rg
e
Sca
le
Da
t
a
Cla
s
s
if
ica
t
io
n
Dee
p
l
ea
r
n
in
g
is
o
n
e
o
f
th
e
m
o
s
t p
o
p
u
la
r
m
eth
o
d
s
in
m
ac
h
in
e
lea
r
n
in
g
.
T
h
e
n
ew
ar
e
a
o
f
d
ee
p
l
ea
r
n
in
g
is
ab
le
t
o
a
p
p
r
o
ac
h
v
ar
iety
o
f
ap
p
li
ca
t
io
n
s
.
E
.
g
.
s
p
e
ec
h
r
ec
o
g
n
iti
o
n
[
3
9
]
,
n
atu
r
al
l
an
g
u
ag
e
p
r
o
ce
s
s
in
g
[
4
1
]
,
o
b
je
ct
r
e
c
o
g
n
iti
o
n
[
4
0
]
an
d
o
th
er
s
.
T
h
e
a
d
v
an
tag
es
o
f
d
ee
p
l
ea
r
n
in
g
m
eth
o
d
b
r
i
n
g
th
e
m
ea
n
in
g
f
u
l
r
e
p
r
esen
t
ati
o
n
f
r
o
m
an
u
n
s
u
p
e
r
v
is
e
d
f
ash
i
o
n
[
3
7
]
.
B
es
id
e
th
i
s
te
ch
n
iq
u
e
,
d
e
e
p
l
ea
r
n
in
g
is
al
s
o
u
s
ef
u
l
f
o
r
ev
en
t
-
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
10
,
No
.
2
,
Ma
y
2
0
1
8
:
7
7
0
–
7
7
7
774
d
r
iv
en
s
t
o
ck
p
r
i
ce
m
o
v
em
en
t
p
r
e
d
ic
ti
o
n
th
at
b
asi
ca
l
ly
m
o
d
e
lle
d
w
ith
th
e
c
o
m
b
in
ati
o
n
o
f
l
o
n
g
-
ter
m
an
d
s
h
o
r
t
-
ter
m
ev
en
ts
[
3
8
]
.
6.
T
E
X
T
M
I
NIN
G
I
N
W
E
B
-
B
ASE
D
AP
P
L
I
C
AT
I
O
N
W
eb
-
b
ased
ap
p
licatio
n
m
u
ch
atten
tio
n
th
r
o
u
g
h
w
eb
i
n
telli
g
en
ce
t
h
at
a
n
al
y
s
ed
t
h
e
n
e
w
s
f
ilter
i
n
g
,
s
u
m
m
ar
y
o
f
w
eb
a
n
d
n
e
w
s
r
ec
o
m
m
e
n
d
atio
n
s
y
s
te
m
[
3
1
]
.
Am
o
n
g
t
h
ese,
s
y
s
te
m
n
e
w
s
r
ec
o
m
m
e
n
d
atio
n
i
s
m
u
c
h
cla
s
s
i
f
ier
th
a
n
o
th
er
s
.
E
.
g
.
•
C
o
n
ten
t
-
b
ase
d
r
ec
o
m
m
en
d
ati
o
n
•
Utili
ty
-
b
ased
r
ec
o
m
m
en
d
ati
o
n
•
C
o
ll
ab
o
r
at
iv
e
r
e
c
o
m
m
en
d
atio
n
•
Kn
o
w
led
g
e
-
b
as
e
d
r
e
co
m
m
en
d
ati
o
n
•
Dem
o
g
r
a
p
h
ic
r
ec
o
m
m
en
d
ati
o
n
As
s
ee
n
f
r
o
m
th
e
r
esear
ch
n
e
w
s
r
ec
o
m
m
e
n
d
atio
n
is
p
o
ten
ti
al
f
ield
th
at
h
elp
ed
th
r
o
u
g
h
u
s
er
’
s
n
e
w
s
in
ter
est,
f
ilter
i
n
g
a
n
d
s
u
m
m
ar
izatio
n
o
f
p
er
s
o
n
alize
d
w
eb
n
e
w
s
[
3
1
]
.
Sa
m
e
as
t
h
e
f
o
r
e
ca
s
tin
g
d
ata
o
b
tain
th
r
o
u
g
h
d
ec
is
io
n
s
u
p
p
o
r
t
s
y
s
t
e
m
t
h
at
h
e
lp
b
y
p
r
o
v
id
i
n
g
in
v
est
m
e
n
t
d
ec
is
io
n
f
o
r
tr
ad
er
s
in
f
o
r
ex
m
ar
k
et
[
3
2
]
as sh
o
w
n
b
elo
w
i
n
F
i
g
u
r
e
2
th
at
p
r
o
d
u
ce
d
b
y
B
P
NNFR
FS
.
Fig
u
r
e
2
.
Gen
er
al
I
n
te
g
r
ated
Fra
m
e
w
o
r
k
f
o
r
W
eb
W
eb
-
b
ased
tr
ad
in
g
d
ec
i
s
io
n
s
u
p
p
o
r
t
s
y
s
te
m
(
W
FT
DSS)
co
n
s
tr
u
cted
b
ased
o
n
t
h
r
ee
-
tier
s
tr
u
ct
u
r
e.
E
.
g
.
Mo
d
el
B
ase
(
MB
)
th
at
ca
n
h
an
d
le
m
o
d
els,
K
n
o
w
led
g
e
B
ase
(
KB
)
u
s
ed
to
j
u
d
g
e
s
to
ck
d
ec
i
s
io
n
o
r
d
eter
m
in
at
io
n
an
d
Data
b
ase
(
DB
)
h
elp
to
r
ep
o
s
ito
r
y
o
f
h
i
s
t
o
r
ical
d
ata
w
h
ich
al
s
o
p
r
o
v
id
e
d
ata
as
r
eq
u
ir
ed
f
o
r
th
e
KB
an
d
MB
[
3
2
]
.
7.
M
O
ST
E
F
F
I
C
I
E
N
T
T
E
CH
NIQU
E
S
AND
CO
M
P
ARIS
O
N
Sto
ck
m
ar
k
et
p
r
ed
ictio
n
f
o
llo
w
ed
b
y
m
an
y
ap
p
licatio
n
tec
h
n
iq
u
e
s
f
o
r
th
e
n
u
m
er
ical
o
r
te
x
tu
a
l
d
ata.
B
u
t
d
u
e
to
lar
g
e
tex
t,
m
aj
o
r
tech
n
iq
u
es
u
s
u
a
ll
y
f
o
llo
w
f
o
r
b
etter
p
er
f
o
r
m
an
ce
.
B
elo
w
ar
e
s
o
m
e
m
aj
o
r
tech
n
iq
u
es
w
i
th
d
is
c
u
s
s
io
n
o
f
ad
v
an
ta
g
es a
n
d
d
is
ad
v
an
tag
e
s
.
T
ab
le
1
.
E
v
alu
a
tio
n
o
f
Di
f
f
er
en
t T
ec
h
n
iq
u
es a
n
d
Me
t
h
o
d
s
No
A
d
v
a
n
t
a
g
e
s a
n
d
D
i
sa
d
v
a
n
t
a
g
e
s o
f
D
i
f
f
e
r
e
n
t
M
e
t
h
o
d
s
T
e
x
t
M
i
n
i
n
g
M
e
t
h
o
d
s
A
d
v
a
n
t
a
g
e
s
D
i
sad
v
a
n
t
a
g
e
s
1
G
e
n
e
t
i
c
A
l
g
o
r
i
t
h
ms
.
G
e
n
e
t
i
c
A
l
g
o
r
i
t
h
m
r
u
n
s
i
n
t
o
a
s
i
n
g
l
e
f
i
n
a
n
c
i
a
l
p
r
e
d
i
c
t
o
r
f
o
r
b
e
t
t
e
r
p
e
r
f
o
r
man
c
e
[
4
6
]
.
B
u
t
i
t
c
a
n
’
t
p
e
r
f
o
r
m o
n
f
i
n
a
n
c
i
a
l
d
a
t
a
,
b
e
c
a
u
se
mu
l
t
i
p
l
e
d
a
t
a
so
u
r
c
e
s
a
n
d
t
e
c
h
n
i
q
u
e
s
i
s
k
e
y
t
o
p
r
o
g
r
e
ss [
4
6
]
.
2
D
e
e
p
L
e
a
r
n
i
n
g
D
e
e
p
l
e
a
r
n
i
n
g
me
t
h
o
d
p
e
r
f
o
r
ms b
e
t
t
e
r
t
h
a
n
t
r
a
d
i
t
i
o
n
a
l
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s
[
4
3
]
.
T
h
i
s me
t
h
o
d
s
t
i
l
l
u
n
a
b
l
e
t
o
e
x
p
l
o
r
e
r
st
r
e
a
mi
n
g
d
a
t
a
,
d
i
s
t
r
i
b
u
t
e
d
c
o
mp
u
t
i
n
g
,
sca
l
a
b
i
l
i
t
y
c
o
mp
u
t
i
n
g
[
4
2
]
.
3
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
N
a
ï
v
e
B
a
y
e
s c
l
a
ssi
f
i
c
a
t
i
o
n
a
p
p
r
o
a
c
h
r
e
l
a
t
i
v
e
l
y
l
o
w
e
r
t
h
a
n
o
t
h
e
r
d
i
s
c
r
i
mi
n
a
t
i
v
e
a
l
g
o
r
i
t
h
ms
[
4
4
]
.
A
N
N
c
a
p
a
b
l
e
o
f
l
e
a
r
n
i
n
g
c
o
mp
l
e
x
n
o
n
l
i
n
e
a
r
r
e
l
a
t
i
o
n
s
h
i
p
s
b
u
t
d
i
f
f
i
c
u
l
t
t
o
f
i
n
e
l
y
mo
d
e
l
f
o
r
h
u
ma
n
r
e
a
so
n
i
n
g
o
f
l
o
g
i
c
a
l
p
r
o
c
e
ss [4
5
]
.
4
A
p
r
i
o
r
i
-
l
i
k
e
a
l
g
o
r
i
t
h
m
I
t
c
a
n
o
n
l
y
p
e
r
f
o
r
m w
e
l
l
i
n
d
a
t
a
b
a
se
c
o
n
si
s
t
i
n
g
o
f
sh
o
r
t
f
r
e
q
u
e
n
t
se
q
u
e
n
c
e
s
[
5
1
]
.
T
h
i
s a
l
g
o
r
i
t
h
m i
s
t
i
me
-
c
o
n
s
u
mi
n
g
f
o
r
g
e
n
e
r
a
t
i
n
g
o
f
n
T
e
r
ms se
q
u
e
n
c
e
s i
n
t
h
e
f
r
a
mew
o
r
k
[
5
2
]
.
5
F
u
z
z
y
A
l
g
o
r
i
t
h
m
N
e
u
r
o
-
F
u
z
z
y
f
r
a
mew
o
r
k
h
a
s e
me
r
g
e
d
b
y
c
o
mb
i
n
i
n
g
l
e
a
r
n
i
n
g
a
b
i
l
i
t
y
i
n
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
f
u
n
c
t
i
o
n
a
l
i
t
y
o
f
t
h
e
f
u
z
z
y
e
x
p
e
r
t
s
y
st
e
m [
5
3
]
.
F
u
z
z
y
s
y
st
e
m h
a
v
e
t
h
e
i
n
s
u
f
f
i
c
i
e
n
t
l
e
a
r
n
i
n
g
a
b
i
l
i
t
y
a
n
d
d
i
f
f
i
c
u
l
t
l
y
f
o
r
i
t
s
t
i
me
c
o
n
su
m
i
n
g
t
o
d
e
t
e
r
mi
n
e
f
o
r
t
h
e
c
o
r
r
e
c
t
se
t
o
f
p
a
r
a
me
t
e
r
s [5
4
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Tech
n
ica
l A
p
p
r
o
a
ch
in
Text
M
in
i
n
g
fo
r
S
to
ck
Ma
r
ke
t P
r
ed
ict
io
n
…
(
Mo
h
a
mma
d
R
a
b
iu
l I
s
l
a
m
)
775
8.
T
E
X
T
M
I
NIN
G
F
O
CUS
O
N
F
I
NANC
I
AL
M
ARK
E
T
Sin
ce
f
in
an
ci
al
m
ar
k
et
is
c
o
n
t
in
u
o
u
s
n
ew
s
f
ee
d
in
g
tech
n
i
q
u
es
s
o
m
o
s
t
r
es
ea
r
ch
er
s
t
r
y
to
p
r
esen
t
th
e
im
p
ac
t
o
f
n
ew
s
item
s
b
y
an
aly
s
is
o
r
m
ar
k
et
m
o
v
em
en
t.
T
e
x
t
ca
teg
o
r
i
za
t
io
n
c
o
m
p
o
n
en
t
p
r
o
v
i
d
e
th
r
o
u
g
h
th
e
r
esu
lt
o
f
p
o
s
i
tiv
e
,
n
eu
tr
al
an
d
n
eg
ativ
e
c
ateg
o
r
ies
t
ex
t
b
ase
d
o
n
f
in
an
c
ial
d
a
ily
n
e
w
s
[
4
7
]
.
Fin
an
ci
al
tex
tu
al
in
f
o
r
m
atio
n
an
d
n
u
m
er
ical
d
at
a
h
elp
t
o
an
a
ly
s
is
f
o
r
tr
ad
in
g
d
ec
is
i
o
n
.
I
n
s
o
m
e
ca
s
e
,
tex
t a
n
d
d
at
a
b
r
in
g
n
o
t
o
n
ly
th
e
ef
f
e
ct
b
u
t
a
ls
o
f
in
d
th
e
r
ea
s
o
n
o
f
h
a
p
p
e
d
[
5
0
]
.
8
.
1
.
F
ina
ncia
l
T
ex
t
ua
l In
f
o
rm
a
t
io
n
Min
i
n
g
te
x
tu
a
l
f
o
r
m
o
f
f
i
n
an
ci
al
n
e
w
s
i
s
ab
le
to
a
s
s
i
s
t i
n
tr
ad
in
g
s
ec
to
r
f
o
r
g
u
es
s
i
n
g
p
r
o
b
ab
ilit
y
[
4
8
]
.
I
n
d
ee
d
,
it
h
as
b
ee
n
p
r
o
v
ed
th
at
r
eg
r
ess
io
n
a
n
d
tech
n
ical
an
al
y
s
i
s
w
it
h
m
i
n
i
n
g
tec
h
n
o
lo
g
y
th
at
tak
e
n
as
in
p
u
t
tex
t
u
al
i
n
f
o
r
m
atio
n
i
n
th
e
f
r
a
m
e
w
o
r
k
f
o
r
ec
o
n
o
m
ical
r
es
u
lts
a
n
al
y
s
is
,
p
o
liti
ca
l
n
e
w
s
th
o
s
e
co
n
s
eq
u
e
n
tl
y
in
f
lu
e
n
ce
o
n
b
an
k
er
s
a
n
d
p
o
liti
cian
s
[
4
9
]
.
8
.
2
.
F
ina
ncia
l
Nu
m
er
ica
l D
a
t
a
I
t
co
u
ld
b
e
u
n
ab
le
to
m
a
n
ag
e
lar
g
e
a
m
o
u
n
t
o
f
n
u
m
er
ical
d
ata
b
y
h
u
m
a
n
,
s
o
k
n
o
w
led
g
e
d
is
co
v
er
y
tex
t
u
al
d
ata
ap
p
ar
en
tl
y
e
f
f
ec
t
o
n
all
o
f
u
s
[
4
9
]
.
I
n
s
tead
o
f
th
is
,
n
u
m
er
ical
ti
m
e
s
er
ies
d
ata
also
u
tili
ze
d
b
y
m
o
d
el
t
h
at
ab
le
to
f
o
r
ec
ast t
h
e
f
in
a
n
cial
m
ar
k
e
t [
5
0
]
.
9.
CO
NCLU
SI
O
N
Ma
n
y
s
o
f
t
-
co
m
p
u
tin
g
m
eth
o
d
s
h
av
e
b
asi
ca
l
ly
b
ee
n
d
ev
el
o
p
e
d
f
o
r
an
aly
tic
al
p
u
r
p
o
s
e
o
n
th
e
l
ar
g
e
-
s
ca
l
e
d
a
ta
s
et
.
Fr
o
m
th
e
ab
o
v
e
d
is
cu
s
s
i
o
n
w
ith
in
p
r
o
s
an
d
c
o
n
s
,
it
c
o
u
l
d
b
e
i
d
en
tif
ie
d
th
at
f
ea
tu
r
ed
b
as
e
d
w
eig
h
tin
g
s
ch
e
m
es
s
till
n
ee
d
to
w
o
r
k
f
o
r
en
h
an
c
in
g
th
e
f
r
am
e
w
o
r
k
p
er
f
o
r
m
an
ce
in
te
r
m
s
o
f
class
if
ic
ati
o
n
ac
cu
r
a
cy
.
E
v
er
y
n
o
w
an
d
th
en
,
s
o
f
t
-
co
m
p
u
tin
g
m
eth
o
d
s
an
d
tech
n
i
q
u
es
a
r
e
u
s
a
b
le
t
o
b
e
ap
p
li
e
d
o
n
b
ig
d
at
a
an
aly
s
is
b
as
e
d
o
n
th
e
r
eq
u
i
r
em
en
ts
o
f
r
esea
r
ch
a
r
e
a.
E
.
g
.
F
in
a
n
cial
tex
t
m
in
in
g
ea
r
ly
r
el
at
ed
en
o
u
g
h
r
esea
r
ch
t
o
p
r
o
v
e
th
r
o
u
g
h
au
to
m
atic
n
ew
s
ar
t
icl
e
an
aly
s
is
te
ch
n
iq
u
es th
at
a
b
le
t
o
p
r
e
d
i
ct
s
t
o
ck
m
ar
k
e
t
p
r
ice
[
4
7
]
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
r
esea
r
ch
w
o
r
k
w
as
p
ar
tia
ll
y
s
u
p
p
o
r
ted
b
y
I
n
ter
n
a
tio
n
al
I
s
la
m
ic
Un
iv
er
s
it
y
Ma
la
y
s
ia,
FR
G
S1
4
-
127
-
0
3
6
8
an
d
E
R
GS1
3
-
018
-
0
0
5
1
f
r
o
m
Mi
n
is
tr
y
o
f
Hi
g
h
er
E
d
u
ca
tio
n
o
f
Ma
la
y
s
ia.
RE
F
E
R
E
NC
E
S
[1
]
M
.
S
h
ra
b
a
n
ti
a
n
d
P
.
A
n
it
a
.
“
Ne
w
a
p
p
ro
a
c
h
o
f
T
e
x
t
M
in
in
g
in
R
”
,
GES
J
:
Co
mp
u
ti
n
g
S
c
ien
c
e
a
n
d
T
e
lec
o
mu
n
ica
ti
o
n
.
V
o
l
u
m
e
:
1
,
Iss
u
e
:
1
,
P
a
g
e
s: 3
0
-
3
6
,
2
0
1
5
[2
]
S
.
S
h
e
h
a
ta,
A
u
g
u
st
1
2
-
1
5
,
“
A
C
o
n
c
e
p
t
-
b
a
se
d
M
o
d
e
l
fo
r
E
n
h
a
n
c
i
n
g
T
e
x
t
Ca
teg
o
riz
a
ti
o
n
”
,
In
ter
n
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
o
n
K
n
o
w
led
g
e
d
isc
o
v
e
r
y
a
n
d
d
a
ta m
in
in
g
-
KD
D.
S
u
n
J
o
se
,
Ca
li
f
o
rn
ia,
USA
.
2
0
0
7
.
P
a
g
e
:
6
2
9
.
[3
]
Q.
L
u
o
,
e
t
a
l
.
“
A
se
m
a
n
ti
c
term
w
e
i
g
h
ti
n
g
sc
h
e
m
e
f
o
r
tex
t
c
a
te
g
o
riza
ti
o
n
”
.
Ex
p
e
rt
S
y
ste
ms
wit
h
A
p
p
li
c
a
ti
o
n
,
Vo
l:
3
8
,
Iss
u
e
:
1
0
,
2
0
1
1
,
P
a
g
e
s: 1
2
7
0
8
-
1
2
7
1
6
.
[4
]
Ca
se
S
tu
d
y
:
T
h
a
il
a
n
d
S
to
c
k
Ex
c
h
a
n
g
e
.
“
S
to
c
k
P
rice
T
re
n
d
P
re
d
icti
o
n
u
si
n
g
A
rti
f
icia
l
N
e
u
ra
l
Ne
t
w
o
rk
T
e
c
h
n
iq
u
e
s”
2
0
1
6
IE
EE
,
I
S
BN:
9
7
8
1
5
0
9
0
4
4
2
0
7
.
[5
]
B.
Ba
h
a
ru
d
i
n
,
e
t
a
l.
“
A
Re
v
ie
w
o
f
M
a
c
h
in
e
L
e
a
rn
in
g
A
l
g
o
rit
h
m
s
f
o
r
T
e
x
t
-
Do
c
u
m
e
n
ts
Clas
si
f
ic
a
ti
o
n
”
.
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
s i
n
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
Vo
l
:
1
,
Iss
u
e
:
1
,
F
e
b
2
0
1
0
.
P
a
g
e
s: 4
-
2
0
.
[6
]
Ch
u
n
g
-
Ho
n
g
L
e
e
a
n
d
Hs
in
-
Ch
a
n
g
Ya
n
g
,
“
Co
n
stru
c
ti
o
n
o
f
su
p
e
rv
ise
d
a
n
d
u
n
su
p
e
rv
ise
d
lea
rn
in
g
s
y
st
e
m
s
f
o
r
m
u
lt
il
in
g
u
a
l
tex
t
c
a
teg
o
riza
ti
o
n
”
.
Exp
e
rt S
y
ste
m wi
th
Ap
p
li
c
a
ti
o
n
,
V
o
l
:
3
6
,
Iss
u
e
:
2
,
M
a
rc
h
2
0
0
9
,
P
a
g
e
:2
4
0
0
-
2
4
1
0
.
[7
]
B.
C
Ho
w
a
n
d
W
.
T
.
Ki
o
n
g
.
“
An
e
x
a
min
a
ti
o
n
o
f
th
e
fea
t
u
re
se
lec
ti
o
n
fra
me
wo
rk
s
in
t
h
e
tex
t
c
a
te
g
o
riza
ti
o
n
”
.
A
sia
In
f
o
rm
a
ti
o
n
Re
tri
e
v
a
l
S
y
m
p
o
siu
m
.
V
o
l:
3
6
8
9
,
In
A
IRS
.
2
0
0
5
P
a
g
e
:
5
5
8
-
5
6
4
.
[8
]
E.
H.
S
a
m
,
e
t
a
l
;
“
T
e
x
t
Ca
teg
o
riz
a
ti
o
n
Us
in
g
W
e
ig
h
ti
n
g
A
d
ju
ste
d
k
-
Ne
a
re
st
Ne
ig
h
b
o
r
Cla
ss
if
ica
ti
o
n
”
,
5
th
P
a
c
if
ic
-
A
sia
Co
n
fe
re
n
c
e
o
n
Kn
o
w
led
g
e
Disc
o
v
e
r
y
a
n
d
Da
ta M
in
in
g
.
P
a
g
e
:
5
-
6
5
,
2
0
0
1
.
[9
]
R.
De
sa
i,
“
S
to
c
k
M
rk
e
t
P
re
d
ic
d
ti
o
n
Us
i
n
g
Da
ta
M
in
i
n
g
”
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
in
e
e
rin
g
De
v
e
lo
p
me
n
t
a
n
d
Res
e
a
rc
h
.
2
0
1
4
,
V
o
l
:
2
,
Iss
u
e
:
2
,
P
a
g
e
s: 2
7
8
0
-
2
7
8
4
.
[1
0
]
K.
A
a
s
e
a
n
d
P
.
Oz
tu
rk
.
“
T
e
x
t
M
in
in
g
o
f
Ne
w
s
Article
s
f
o
r
S
to
c
k
P
rice
P
re
d
ictio
n
s”
.
De
p
a
rtme
tn
o
f
Co
mp
u
ter
a
n
d
In
fo
rm
a
t
io
n
S
c
ien
c
.
Vo
l:
3
M
sc
,
Is
su
e
:
6
,
P
a
g
e
s: 8
2
.
J
u
n
e
2
0
1
1
.
[1
1
]
T
h
o
rste
n
Jo
a
c
h
im
s,
“
T
e
x
t
Ca
teg
o
riza
ti
o
n
wit
h
S
u
p
p
o
rt
Vec
to
r
M
a
c
in
e
s:
L
e
a
rn
in
g
wit
h
M
a
n
y
Rela
v
e
n
t
Fea
tu
re
s
”
:
ECM
L
-
9
8
1
0
th
Eu
ro
p
e
a
n
C
o
n
f
e
re
n
c
e
o
n
M
a
c
h
in
e
L
e
a
rn
in
g
,
P
a
g
e
s: 1
3
7
-
1
4
2
,
1
9
9
8
.
[1
2
]
P
.
S
e
k
a
r,
e
t
a
l
.
“
F
in
a
n
c
ial
S
t
o
c
k
M
a
rk
e
t
F
o
re
c
a
stin
g
u
sin
g
d
a
ta
m
in
in
g
tec
h
n
iq
u
e
s”
In
ter
n
a
ti
o
n
a
l
M
u
lt
iCo
n
fer
e
n
c
e
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
C
o
mp
u
ter
S
c
i
e
n
ti
sts
.
V
o
l
u
m
e
:
1
,
P
a
g
e
s: 5
.
M
a
r
c
h
1
7
-
1
9
,
2
0
1
0
.
[1
3
]
J.
T
h
o
m
a
s
a
n
d
K.
S
y
c
a
ra
.
“
In
te
g
ra
ti
n
g
G
e
n
e
ti
c
A
lg
o
rit
h
m
s
a
n
d
T
e
x
t
L
e
a
rn
in
g
f
o
r
F
in
a
n
c
ial
P
r
e
d
ictio
n
”
.
D
a
ta
min
in
g
wit
h
Evo
l
u
ti
o
n
a
ry
Al
g
o
rit
h
ms
.
P
a
g
e
s: 7
2
-
7
5
.
2
0
0
0
.
[1
4
]
S
.
S
e
k
e
r,
e
t
a
l
.
“
T
i
m
e
S
e
ries
An
a
lay
sis
o
n
t
h
e
S
to
c
k
M
a
rk
e
t
f
o
r
T
e
x
t
M
in
in
g
C
o
rre
latio
n
o
f
Eco
n
o
m
y
Ne
ws
”
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
S
o
c
i
a
l
S
c
ien
c
e
a
n
d
Hu
ma
n
it
y
.
Vo
l:
6
.
Iss
u
e
:
1
.
P
a
g
e
s: 2
3
,
2
0
1
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
10
,
No
.
2
,
Ma
y
2
0
1
8
:
7
7
0
–
7
7
7
776
[1
5
]
F
.
Be
il
,
M
.
Ester,
X.
Xu
e
t
a
l
,
“
Fre
q
u
e
n
t
ter
m
-
Ba
se
d
T
e
x
t
Clu
ste
rin
g
”
,
KD
D’0
2
:
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
e
ig
h
th
A
CM
S
IG
KD
D i
n
tern
a
ti
o
n
a
l
c
o
n
f
e
r
e
n
c
e
o
n
k
n
o
w
led
g
e
d
isc
o
v
e
r
y
a
n
d
d
a
ta m
in
in
.
P
a
g
e
s: 4
3
6
-
4
4
2
,
2
0
0
2
[1
6
]
C.
L
i,
e
t
a
l
.
“
T
e
x
t
Ca
teg
o
rica
to
n
a
lg
o
rit
h
m
s
u
sin
g
se
m
a
n
ti
c
a
p
p
ro
a
c
h
e
s
c
o
u
r
p
u
s
-
b
a
se
d
th
e
sa
u
ru
s
a
n
d
w
o
rd
n
e
t”.
Exp
e
rt S
y
ste
m wi
th
Ap
p
li
c
a
i
o
n
s
.
V
o
l
:
3
9
,
Iss
u
e
:
1
,
P
a
g
e
s: 7
6
5
-
7
7
2
,
2
0
1
2
[1
7
]
Y.
Ch
o
i,
e
t
a
l
.
“
Do
m
a
in
-
S
p
e
c
i
f
ic
S
e
n
ti
m
e
n
t
A
n
a
la
y
sis
u
sin
g
Co
n
tex
tu
a
l
F
e
a
tu
re
G
e
n
e
ra
ti
o
n
”
,
S
c
icn
e
a
n
d
T
e
c
h
n
o
l
o
g
y
.
P
a
g
e
s: 3
7
-
4
4
,
Iss
u
e
:
Ju
ly
,
2
0
0
9
.
[1
8
]
A
.
U
y
sa
l
a
n
d
S
.
G
u
n
a
l.
“
Kn
o
w
led
g
e
-
Ba
se
d
S
y
st
e
m
A
n
o
v
e
l
p
ro
b
a
b
il
isti
c
f
e
a
tu
re
se
le
c
ti
o
n
m
e
th
o
d
f
o
r
tex
t
c
las
si
f
ica
ti
o
n
”
,
Kn
o
w
led
g
e
B
a
se
d
S
y
ste
ms
.
Vo
lu
m
e
:
3
6
,
P
a
g
e
s: 2
2
6
-
2
3
5
.
2
0
1
2
[1
9
]
M
.
Ha
g
e
n
a
u
,
e
t
a
l
.
“
A
u
to
m
a
ted
n
e
w
s
re
a
d
in
g
:
S
to
c
k
p
rie
p
re
d
ictio
n
b
a
se
d
o
n
f
in
a
n
c
ial
n
e
w
s
u
sin
g
c
o
n
tex
t
-
c
a
p
tu
rin
g
f
e
a
tu
re
s”
,
De
c
isio
n
S
u
p
p
o
rt
S
y
ste
ms
.
Vo
l:
5
5
,
Iss
u
e
:
3
.
P
a
g
e
s: 6
8
5
-
6
9
7
.
2
0
1
3
[2
0
]
S.
S
e
k
e
r,
e
t
a
l.
“
T
i
m
e
S
e
ries
A
n
a
l
y
si
s
o
n
S
to
c
k
M
a
rk
e
t
f
o
r
T
e
x
t
M
in
in
g
Co
re
latio
n
o
f
Eco
n
o
m
y
Ne
ws
”
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
S
o
c
i
a
l
S
c
ien
c
e
s a
n
d
Hu
ma
n
it
y
.
Vo
l:
6
,
Iss
u
e
:
1
,
P
a
g
e
s: 2
3
.
2
0
1
4
.
[2
1
]
M
.
S
a
in
i,
“
F
o
re
c
a
stin
g
S
t
o
c
k
Ex
c
h
a
n
g
e
M
a
rk
e
t
a
n
d
W
e
a
th
e
r
Us
in
g
S
o
f
t
C
o
m
p
u
ti
n
g
”
,
Vo
l:
4
,
Iss
u
e
:
5
,
P
a
g
e
s:
8
7
7
-
8
8
2
,
2
0
1
4
.
[2
2
]
D.K.
Kira
n
g
e
,
e
t
a
l
.
“
S
e
n
ti
m
e
n
t
A
n
a
l
y
si
s
o
f
N
e
w
s
He
a
d
li
n
e
s
f
o
r
S
to
c
k
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis
o
f
N
e
w
s
He
a
d
li
n
e
s
f
o
r
S
to
c
k
P
r
ice
P
re
d
ictio
n
”
COM
PUS
OFT
,
“
A
n
i
n
ter
n
a
t
io
n
a
l
j
o
u
r
n
a
l
o
f
a
d
v
a
n
c
e
c
o
mp
u
ter
tec
h
n
o
lo
g
y
”
,
V
o
l
:V,
IS
S
UE
-
III,
M
a
rc
h
-
2
0
1
6
.
[2
3
]
S
h
y
i
-
M
in
g
Ch
e
n
a
n
d
Y
u
-
Ch
u
a
n
Ch
a
n
g
,
“
M
u
lt
i
-
V
a
riab
le
F
u
z
z
y
F
o
re
c
a
stin
g
Ba
se
d
o
n
F
u
z
z
y
Clu
ste
rin
g
a
n
d
F
u
z
z
y
Ru
le In
terp
o
lati
o
n
T
e
c
h
n
i
q
u
e
s”
,
I
n
fo
rm
a
t
io
n
S
c
ien
c
e
s
,
V
o
l.
1
8
0
,
No
.
2
4
,
P
a
g
e
s: 4
7
7
2
-
4
7
8
3
,
2
0
1
0
.
[2
4
]
W
.
F
ra
w
le
y
&
G
.
P
iate
tsk
y
-
S
h
a
p
iro
.
“
Kn
o
w
led
g
e
Disc
o
v
e
r
y
in
Da
tab
a
se
:
A
n
Ov
e
rv
ie
w”
AI
M
a
g
a
zi
n
e
.
P
a
g
e
s:
1
2
7
,
1
9
9
2
[2
5
]
T
.
W
il
so
n
,
e
t
a
l.
“
Re
c
o
g
n
izin
g
c
o
n
tex
tu
a
l
p
o
larity
in
p
h
ra
se
-
lev
e
l
se
n
ti
m
e
n
t
a
n
a
l
y
sis
”
.
Co
mp
u
ta
ti
o
n
a
l
L
in
g
u
isti
c
s
,
V
o
l
:
3
5
,
Iss
u
e
:
3
,
S
e
p
tem
b
e
r
0
8
,
P
a
g
e
s: 3
9
9
-
4
3
3
,
2
0
0
9
.
[2
6
]
T
o
n
y
M
u
ll
e
n
a
n
d
Nig
e
l
Co
ll
ier.
“
S
e
n
ti
me
n
t
a
n
a
lys
is
u
sin
g
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
i
n
e
s
wit
h
d
ive
rs
e
in
fo
rm
a
ti
o
n
so
u
rc
e
s”
.
P
ro
c
e
e
d
i
n
g
s o
f
EM
NL
P
,
p
a
g
e
s 4
1
2
–
4
1
8
,
A
ss
o
c
iatio
n
f
o
r
Co
m
-
p
u
tatio
n
a
l
L
in
g
u
isti
c
s.
Ju
l
y
2
0
0
4
.
[2
7
]
A
h
m
e
d
A
b
b
a
si,
e
t
a
l.
“
S
e
n
ti
m
e
n
t
a
n
a
ly
sis
in
m
u
l
ti
p
le
lan
g
u
a
g
e
s:
F
e
a
tu
re
se
lec
ti
o
n
f
o
r
o
p
in
i
o
n
c
las
sif
ica
ti
o
n
in
w
e
b
f
o
ru
m
s
”
.
ACM
T
ra
n
s.
V
o
l:
2
6
,
Iss
u
e
:3
,
J
u
n
1
,
2
0
0
8
.
[2
8
]
F
.
M
in
g
F
a
i
W
o
n
g
,
e
t
a
l
.
“
S
t
o
c
k
M
a
rk
e
t
Pre
d
ictio
n
fro
m
W
S
J
:
T
e
x
t
M
in
in
g
v
ia
S
p
a
rs
e
M
a
trix
Fa
c
to
riza
t
io
n
”
.
In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Da
t
a
M
in
i
n
g
.
IEE
E
2
0
1
4
,
P
a
g
e
s: 4
3
0
-
4
3
9
.
De
c
e
m
b
e
r
1
4
-
1
7
,
2
0
1
4
.
[2
9
]
O.
He
rn
á
n
d
e
z
,
e
t
a
l.
“
A
p
p
ro
a
c
h
i
n
g
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis
b
y
u
sin
g
se
m
i
-
su
p
e
rv
ise
d
lea
rn
in
g
o
f
m
u
lt
i
-
d
im
e
n
sio
n
a
l
c
las
si
f
iers
”
Ne
u
ro
-
c
o
mp
u
ti
n
g
,
Vo
l:
9
2
.
P
a
g
e
s: 9
8
-
1
5
5
.
2
0
1
2
.
[3
0
]
B.
P
a
n
g
,
e
t
a
l.
“
S
e
n
ti
me
n
t
c
la
ss
if
i
c
a
ti
o
n
u
si
n
g
ma
c
h
in
e
lea
r
n
in
g
te
c
h
n
iq
u
e
s”,
Co
n
f
e
re
n
c
e
o
n
Em
p
iri
c
a
l
M
e
th
o
d
s
i
n
Na
tu
ra
l
L
a
n
g
u
a
g
e
P
ro
c
e
ss
in
g
(EM
NL
P
’0
2
),
2
0
0
2
,
p
p
.
7
9
–
8
6
.
[3
1
]
Ku
m
a
r
a
n
d
K
M
u
th
u
,
“
Ne
w
s
Re
c
o
m
m
e
n
d
a
ti
o
n
S
y
ste
m
U
sin
g
Web
M
in
i
n
g
:
A
S
tu
d
y
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
rin
g
T
r
e
n
d
s
a
n
d
T
e
c
h
n
o
l
o
g
y
(
IJ
ET
T
)
.
V
o
l
:
1
2
,
I
S
S
UE:
6
.
P
a
g
e
s: 2
9
3
-
2
9
9
,
Ja
n
u
a
ry
2
0
1
4
.
[3
2
]
K.
L
a
i,
e
t
a
l.
“
A
n
e
u
ra
l
n
e
tw
o
rk
a
n
d
w
e
b
b
a
se
d
d
e
c
isio
n
s
u
p
p
o
rt
sy
ste
m
f
o
r
f
o
re
x
f
o
re
c
a
stin
g
a
n
d
trad
in
g
.
”
L
e
c
tu
re
No
tes
in
A
rti
f
icia
l
In
telli
g
e
n
c
e
,
P
a
g
e
s: 2
4
3
-
2
5
3
,
2
0
0
4
[3
3
]
M
.
Ik
o
n
o
m
a
k
is,
e
t
a
l,
“
T
e
x
t
Clas
sif
ica
ti
o
n
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
i
q
u
e
s”
W
S
EA
S
T
ra
n
sa
c
ti
o
n
s
o
n
c
o
mp
u
ter
s.
V
o
l
:
4
,
Iss
u
e
:8
;
P
a
g
e
s: 9
6
6
-
9
7
4
.
2
0
0
5
.
[3
4
]
Y.
Ba
o
a
n
d
N.
Ish
ii
,
“
Co
m
b
in
in
g
M
u
lt
i
p
le k
NN
Clas
sif
ier
s f
o
r
T
e
x
t
Ca
teg
o
riza
ti
o
n
b
y
Re
d
u
c
ts”
,
L
N
CS
2
5
3
4
,
2
0
0
2
,
V
o
l
:
2
5
3
4
,
p
p
.
3
4
0
-
3
4
7
,
0
8
No
v
e
m
b
e
r
2
0
0
2
.
[3
5
]
S
u
n
g
-
Ba
e
Ch
o
a
n
d
Je
e
-
Ha
e
n
g
L
e
e
,
“
Lea
rn
in
g
Ne
u
ra
l
Ne
t
w
o
rk
En
se
m
b
le
f
o
r
P
ra
c
ti
c
a
l
T
e
x
t
Clas
si
f
ic
a
ti
o
n
”
,
L
e
c
tu
re
No
tes
in
C
o
m
p
u
ter S
c
ien
c
e
,
V
o
l
u
m
e
:
2
6
9
0
,
p
p
.
1
0
3
2
–
1
0
3
6
.
M
a
rc
h
2
1
-
2
3
,
2
0
0
3
.
[3
6
]
Z.
Iq
b
a
l
e
t
a
l
.
“
Ef
f
icie
n
t
M
a
c
h
in
e
L
e
a
rn
in
g
f
o
r
S
to
c
k
M
a
rk
e
t
P
re
d
ictio
n
”
,
J
o
u
rn
a
l
o
f
En
g
in
e
e
rin
g
Res
e
a
rc
h
a
n
d
Ap
p
li
c
a
ti
o
n
s.
Vo
l:
3
,
Iss
u
e
-
6
,
No
v
-
De
c
2
0
1
3
,
p
p
.
8
5
5
-
8
6
7
.
[3
7
]
X
.
G
lo
ro
t,
e
t
a
l.
“
D
o
ma
i
n
Ad
a
p
ta
ti
o
n
f
o
r
L
a
rg
e
S
c
a
le
S
e
n
ti
me
n
t
Cla
ss
if
ica
t
io
n
:
A
De
e
p
L
e
a
rn
in
g
A
p
p
ro
a
c
h
”
P
r
o
c
e
e
d
in
g
o
f
th
e
2
8
th
In
tern
a
t
io
n
a
l
Co
n
f
e
re
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
rn
in
g
.
p
p
.
5
1
3
-
5
2
0
.
2
0
1
1
.
[3
8
]
X
.
Di
n
g
,
e
t
a
l
.
“
De
e
p
L
e
a
rn
i
n
g
f
o
r
Eve
n
t
Dr
ive
n
S
t
o
c
k
Pre
d
icto
in
”
P
ro
c
e
e
d
in
g
s
o
f
th
e
T
w
e
n
t
y
-
F
o
rth
In
ter
n
a
ti
o
n
a
l
Jo
in
t
C
o
n
f
e
re
n
c
e
o
n
A
rti
f
icia
l
In
telli
g
e
n
t.
p
p
.
2
3
2
7
-
2
3
3
3
,
Iss
u
e
:
Ijc
a
i,
2
0
1
5
,
[3
9
]
P
.
S
w
ieto
jan
sk
i
e
t
a
l,
“
Co
n
v
o
lu
ti
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
s
f
o
r
Dis
tan
t
S
p
e
e
c
h
Re
c
o
g
n
it
io
n
,
”
IEE
E
2
0
1
4
,
S
i
g
n
a
l
Pro
c
e
ss
in
g
L
e
tt
e
rs
,
v
o
l.
2
1
,
n
o
.
9
,
p
p
.
1
1
2
0
-
1
1
2
4
,
S
e
p
tem
b
e
r
2
0
1
4
.
[4
0
]
X
.
Ch
e
n
,
e
t
a
l,
“
V
e
h
icle
De
tec
ti
o
n
in
S
a
telli
te
Im
a
g
e
s
b
y
H
y
b
ri
d
De
e
p
Co
n
v
o
lu
t
io
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
s,
”
IEE
E
2
0
1
4
,
Ge
o
sc
ien
c
e
a
n
d
Rem
o
te
S
e
n
sin
g
L
e
tt
e
rs
,
v
o
l.
1
1
,
n
o
.
1
0
,
p
p
.
1
7
9
7
-
1
8
0
1
,
Oc
to
r
b
e
r
2
0
1
4
.
[4
1
]
Q.
M
a
o
,
e
t
a
l
, “
Lea
rn
in
g
S
a
li
e
n
t
F
e
a
tu
re
s
f
o
r
S
p
e
e
c
h
E
m
o
ti
o
n
Re
c
o
g
n
it
io
n
Us
in
g
Co
n
v
o
lu
ti
o
n
a
l
Ne
u
ra
l
Ne
t
w
o
rk
s,”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
M
u
lt
ime
d
i
a
,
v
o
l.
1
6
,
n
o
.
8
,
p
p
.
2
2
0
3
-
2
2
1
3
,
D
e
c
e
m
b
e
r
2
0
1
4
.
[4
2
]
M
.
Na
jaf
a
b
a
d
i,
e
t
a
l
.
“
De
e
p
lea
rn
in
g
a
p
p
li
c
a
ti
o
n
s
a
n
d
c
h
a
ll
e
n
g
e
s
in
b
ig
d
a
ta
a
n
a
ly
ti
c
s”
J
o
u
rn
a
l
o
f
b
ig
d
a
t
a
.
Vo
l:
2
,
Iss
u
e
:1
,
P
a
g
e
s:1
,
2
0
1
5
.
[4
3
]
Y.
Ya
n
,
e
t
a
l.
“
De
e
p
L
e
a
rn
in
g
f
o
r
Im
b
a
lan
c
e
d
M
u
lt
im
e
d
ia Da
ta
Cla
ss
if
ic
a
ti
o
n
”
Vo
l.
0
0
,
p
p
.
4
8
3
-
4
8
8
,
2
0
1
5
.
[4
4
]
B.
Ba
h
a
ru
d
in
,
e
t
a
l.
“
A
Re
v
ie
w
o
f
M
a
c
h
in
e
L
e
a
rn
in
g
A
lg
o
rit
h
m
f
o
r
T
e
x
t
-
Do
c
u
m
e
n
ts
Clas
sif
ica
ti
o
n
”
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
s i
n
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
.
Vo
l:
1
,
Iss
u
e
:
1
,
P
a
g
e
s: 4
-
2
0
,
2
0
1
0
.
[4
5
]
H.
Nh
u
,
e
t
a
l
.
“
P
re
d
icti
o
n
o
f
S
to
c
k
P
rice
Us
in
g
a
n
A
d
a
p
ti
v
e
Ne
u
ro
-
F
u
z
z
y
In
f
e
r
e
n
c
e
S
y
ste
m
T
r
a
i
n
e
d
b
y
F
ire
f
l
y
A
l
g
o
rit
h
m
”
.
In
ter
n
a
ti
o
n
a
l
Co
mp
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
C
o
n
f
e
re
n
c
e
(
ICS
EC),
2
0
1
3
.
P
a
g
e
s: 3
0
2
-
3
0
7
.
[4
6
]
J.
T
h
o
m
a
s
a
n
d
K.
S
y
c
a
ra
.
“
In
teg
ra
ti
n
g
Ge
n
e
ti
c
Al
g
o
rit
h
ms
a
n
d
T
e
x
t
L
e
a
r
n
in
g
f
o
r
F
in
a
n
c
ia
l
Pr
e
d
ictio
n
”
Da
t
a
M
in
in
g
wit
h
Evo
lu
ti
o
n
a
ry
Al
g
o
rith
ms
.
In
P
ro
c
e
e
d
i
n
g
o
f
th
e
Ge
n
e
ti
c
a
n
d
Ev
o
lu
ti
o
n
a
ry
Co
m
p
u
ti
n
g
Co
n
f
e
re
n
c
e
(G
ECCO)
,
Las
V
e
g
a
s,
Ne
v
a
d
a
,
P
a
g
e
s.
7
2
-
7
5
,
2
0
0
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Tech
n
ica
l A
p
p
r
o
a
ch
in
Text
M
in
i
n
g
fo
r
S
to
ck
Ma
r
ke
t P
r
ed
ict
io
n
…
(
Mo
h
a
mma
d
R
a
b
iu
l I
s
l
a
m
)
777
[4
7
]
K.
Aa
se
a
n
d
P
.
Oz
tu
rk
,
“
T
e
x
t
M
i
n
in
g
o
f
Ne
w
s
Article
s
f
o
r
S
to
c
k
P
rice
P
re
d
icti
o
n
s”
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
a
n
d
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
.
J
u
n
e
2
0
1
1
,
P
a
g
e
:
8
2
.
[4
8
]
M
.
Ha
g
e
n
a
u
,
e
t
a
l
.
“
A
u
to
m
a
ted
n
e
w
s
re
a
d
in
g
:
S
to
c
k
p
rice
p
re
d
ictio
n
b
a
se
d
o
n
f
in
a
n
c
ial
n
e
w
s
u
sin
g
c
o
n
tex
t
-
c
a
p
tu
rin
g
f
e
a
tu
re
s.”
De
sic
o
n
S
u
p
p
o
rt
S
y
ste
ms
.
2
0
1
3
,
V
o
l:
5
5
,
Iss
u
e
:3
,
P
a
g
e
s: 6
8
5
-
6
9
7
.
[4
9
]
B.
W
u
th
rich
,
e
t
a
l.
“
D
a
il
y
S
to
c
k
M
a
rk
e
t
fo
re
c
a
st
fro
m
tex
tu
a
l
we
b
d
a
t
a
”
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
S
y
ste
m
,
M
a
n
a
n
d
Cy
b
e
rn
e
ti
c
s.
Vo
l:
3
,
P
a
g
e
s: 1
-
6
.
1
4
Oc
t
1
9
9
8
.
[5
0
]
S
.
S
e
k
e
r,
e
t
a
l.
“
T
i
m
e
S
e
ries
A
n
a
l
y
si
s
o
n
S
to
c
k
M
a
rk
e
t
f
o
r
T
e
x
t
M
in
in
g
Co
rre
latio
n
o
f
Eco
n
o
m
y
Ne
ws
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
S
o
c
i
a
l
S
c
ien
c
e
a
n
d
Hu
ma
n
it
y
.
2
0
1
4
,
V
o
l
:
6
,
Iss
u
e
:1
P
a
g
e
s:2
3
.
[5
1
]
J.
P
e
i,
e
t
a
l
.
“
Pre
fi
x
S
p
a
n
:
M
in
i
n
g
se
q
u
e
n
ti
a
l
p
a
tt
e
rn
s
e
ff
icie
n
tl
y
b
y
p
re
fi
x
-
p
ro
jec
ted
p
a
tt
e
rn
g
ro
wt
h
,
”
P
r
o
c
e
e
d
in
g
s
o
f
In
t.
Co
n
f
.
o
n
Da
ta E
n
g
in
e
e
rin
g
(I
CDE’0
2
)
,
He
id
e
lb
e
rg
,
G
e
r
m
a
n
y
,
2
0
0
1
,
p
p
.
2
1
5
-
2
2
4
.
[5
2
]
S
.
W
u
,
e
t
a
l
.
“
Au
t
o
ma
ti
c
Pa
t
t
e
rn
-
T
a
x
o
n
o
my
Extra
c
ti
o
n
f
o
r
W
e
b
M
in
in
g
.
”
In
tern
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
o
n
w
e
b
In
telli
g
e
n
c
e
.
IEE
E/
W
IC/A
CM
(W
I
2
0
0
4
)
2
0
-
2
4
S
e
p
t.
2
0
0
4
,
p
p
.
2
4
2
-
2
4
8
.
[5
3
]
Ch
in
-
S
h
ien
L
in
,
“
Ca
n
th
e
n
e
u
ro
f
u
z
z
y
m
o
d
e
l
p
re
d
ict
sto
c
k
in
d
e
x
e
s
b
e
tt
e
r
th
a
n
it
s
riv
a
ls?
”
2
0
0
2
De
p
a
rt
o
f
F
in
a
n
c
e
,
G
ra
d
u
a
te S
c
h
o
o
l
o
f
Bu
sin
e
ss
A
d
m
in
istratio
n
.
P
r
o
v
id
e
n
c
e
Un
iv
e
rsi
ty
.
2
0
0
2
.
[5
4
]
H.
Nh
u
,
e
t
a
l.
“
Pre
d
ictio
n
o
f
sto
c
k
Price
Us
in
g
a
n
Ad
a
p
ti
v
e
Ne
u
ro
-
F
u
zz
y
In
fer
e
n
c
e
S
y
ste
m
T
ra
in
e
d
b
y
Fi
re
fl
y
Al
g
o
rit
h
m”
I
n
tern
a
ti
o
n
a
l
C
o
m
p
u
t
e
r
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
Co
n
f
e
re
n
c
e
,
ICS
EC
2
0
1
3
.
P
a
g
e
:
3
0
2
-
3
0
7
.
[5
5
]
Ra
m
z
a
n
T
a
li
b
a
n
d
M
u
h
a
m
m
a
d
K
a
sh
if
.
“
T
e
x
t
M
in
in
ig
:
T
e
c
h
n
iq
u
e
s,
A
p
p
li
c
a
ti
o
n
s
a
n
d
Iss
u
e
s”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
A
p
p
li
c
a
ti
o
n
s.
IJ
ACS
A
2
0
1
6
,
Vo
l:
7
,
Iss
u
e
No
:1
1
,
2
0
1
6
,
P
a
g
e
:
4
1
4
-
4
1
8
,
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
M
o
h
a
m
m
a
d
Ra
b
iu
l
Isla
m
,
h
e
re
c
e
iv
e
d
h
is
BS
c
-
d
e
g
re
e
in
Bu
si
n
e
ss
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
a
n
d
late
r
h
e
re
c
e
iv
e
d
h
is
M
a
ste
r’s
De
g
r
e
e
in
c
o
m
p
u
ter
s
c
ien
c
e
se
q
u
e
n
ti
a
ll
y
f
ro
m
L
UC
T
a
n
d
Un
iv
e
rsiti
T
u
n
Hu
ss
e
in
On
n
M
a
la
y
sia
.
Cu
rre
n
tl
y
h
e
is
a
P
h
.
D.
c
a
n
d
id
a
te
a
t
In
tern
a
ti
o
n
a
l
Isla
m
ic
U
n
iv
e
rsit
y
M
a
la
y
sia
.
T
h
e
a
re
a
o
f
h
is
re
se
a
rc
h
in
tere
st
li
e
s
i
n
d
a
ta
m
in
in
g
,
se
n
ti
m
e
n
t
a
n
a
l
y
sis
a
n
d
im
p
ro
v
in
g
tex
t
c
a
t
e
g
o
riza
ti
o
n
in
th
e
f
ield
o
f
so
f
t
-
c
o
m
p
u
ti
n
g
tec
h
n
i
q
u
e
s.
He
a
lso
r
o
ll
i
n
g
h
is
re
se
a
rc
h
o
v
e
r
th
e
f
o
re
x
a
n
d
sto
c
k
m
a
rk
e
t
w
it
h
in
c
o
m
p
u
ter
sc
ien
c
e
.
He
h
a
s
se
v
e
ra
l
c
o
n
f
e
r
e
n
c
e
a
n
d
j
o
u
r
n
a
l
p
a
p
e
rs
b
a
se
d
o
n
e
m
e
r
g
in
g
e
c
o
n
o
m
y
.
Im
a
d
A
l
-
sh
a
ik
h
li
is
a
p
ro
f
e
s
so
r
a
n
d
th
e
h
e
a
d
o
f
re
se
a
rc
h
a
t
IIUM
(In
tern
a
ti
o
n
a
l
Isla
m
ic
Un
iv
e
rsit
y
M
a
la
y
sia
).
He
is
a
lso
a
lec
tu
re
r
a
t
t
h
e
F
a
c
u
lt
y
o
f
In
fo
rm
a
ti
o
n
a
n
d
c
o
m
m
u
n
ica
t
io
n
T
e
c
h
n
o
lo
g
y
.
He
is
a
IEE
E
s
e
n
io
r
m
e
m
b
e
r,
o
b
tain
e
d
h
is BS
c
(Ho
n
)
in
M
a
th
e
m
a
t
ics
,
M
S
c
in
Co
m
p
u
ter S
c
ien
c
e
f
ro
m
Ira
q
,
a
n
d
P
h
.
D d
e
g
re
e
f
ro
m
P
u
n
e
U
n
iv
e
rsity
,
In
d
ia,
2
0
0
0
.
He
h
a
s
b
e
e
n
t
h
e
e
d
it
o
r
in
c
h
ief
o
f
In
tern
a
ti
o
n
a
l
jo
u
r
n
a
l
o
n
A
d
v
a
n
c
e
d
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
Re
se
a
rc
h
sin
c
e
2
0
1
1
n
o
w
,
a
n
d
th
e
g
e
n
e
ra
l
c
h
a
ir
o
f
th
e
in
tern
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
d
Co
m
p
u
ter
S
c
ien
c
e
A
p
p
li
c
a
ti
o
n
s
a
n
d
T
e
c
h
n
o
l
o
g
ies
sin
c
e
2
0
1
2
ti
ll
n
o
w
.
He
o
b
tai
n
e
d
a
US
p
a
ten
t
f
o
r
h
is
w
o
rk
w
it
h
h
is
P
h
.
D
st
u
d
e
n
t
o
n
sm
a
rt
tra
ff
ic
li
g
h
t
w
it
h
a
c
c
id
e
n
t
d
e
tec
ti
o
n
sy
ste
m
o
n
2
n
d
De
c
e
m
b
e
r
2
0
1
4
.
P
r
o
f
.
Im
a
d
h
a
s
p
u
b
li
sh
e
d
m
o
re
th
a
n
1
0
0
p
a
p
e
rs,
jo
u
rn
a
ls
a
n
d
b
o
o
k
c
h
a
p
ters
in
a
d
d
it
i
o
n
to
th
re
e
b
o
o
k
s.
Dr.
Riza
l
M
o
h
d
No
r
c
o
m
p
lete
d
h
is
P
h
D
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
Ke
n
t
S
tate
Un
iv
e
rsit
y
,
Ke
n
t,
OH
,
USA
2
0
1
2
a
n
d
M
a
ste
r
in
Bu
sin
e
ss
A
d
m
in
istratio
n
f
ro
m
In
tern
a
ti
o
n
a
l
Isla
m
ic
Un
iv
e
rsit
y
M
a
la
y
sia
,
2
0
0
4
.
He
a
lso
h
o
l
d
th
e
d
o
u
b
le
d
e
g
re
e
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
f
ro
m
Jo
h
n
s
Ho
p
k
in
s
Un
v
iers
it
y
,
M
D,
US
A
2
0
0
0
.
He
is
a
re
se
a
rc
h
e
r
in
c
r
y
p
to
c
u
rre
n
c
y
w
it
h
in
-
d
e
p
th
k
n
o
w
led
g
e
o
f
th
e
c
r
y
p
to
-
c
u
rre
n
c
y
e
c
o
s
y
ste
m
a
n
d
p
ro
f
o
u
n
d
u
n
d
e
rsta
n
d
i
n
g
o
f
it
s
in
d
u
stry
.
Cu
rre
n
tl
y
,
h
e
h
a
s
b
e
e
n
in
v
o
lv
e
d
in
b
lo
c
k
c
h
a
in
p
ro
jec
ts,
f
o
ru
m
s
a
n
d
se
m
in
a
rs
in
f
in
tec
h
a
n
d
b
lo
c
k
c
h
a
in
a
p
p
li
c
a
ti
o
n
s.
He
a
d
v
ise
s
se
v
e
ra
l
c
o
m
p
a
n
ies
a
n
d
NO
G
s
o
n
th
e
ir
f
in
tec
h
a
n
d
b
lo
c
k
c
h
a
in
im
p
lem
e
n
tatio
n
a
s
w
e
ll
a
s
re
g
u
lato
r
y
is
su
e
s
p
e
rtain
in
g
to
c
ry
p
to
-
c
u
rre
n
c
y
re
latin
g
to
S
h
a
riah
.
P
r
o
f
.
Dr.
V
ij
a
y
a
k
u
m
a
r
V
a
ra
d
a
ra
jan
.
Cu
rre
n
tl
y
,
h
e
is
a
P
ro
f
e
ss
o
r
o
f
sc
h
o
o
l
o
f
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
En
g
in
e
e
rin
g
a
t
V
IT
Un
iv
e
rs
it
y
,
Ch
e
n
n
a
i,
In
d
ia.
He
h
a
s
m
o
r
e
th
a
n
1
6
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
c
lu
d
in
g
in
d
u
strial
a
n
d
a
c
a
d
e
m
i
c
.
His
re
se
a
rc
h
in
tere
sts
sp
a
n
in
c
o
m
p
u
tatio
n
a
l
a
re
a
s
c
o
v
e
rin
g
g
rid
c
o
m
p
u
ti
n
g
,
c
lo
u
d
c
o
m
p
u
ti
n
g
,
c
o
m
p
u
ter
n
e
tw
o
rk
s
a
n
d
b
ig
d
a
ta
.
He
h
a
s
c
o
m
p
lete
d
BE,
CS
E
a
n
d
M
BA
HRD
w
it
h
F
irst
Clas
s.
He
h
a
s
a
lso
c
o
m
p
lete
d
M
E,
CS
E
a
n
d
M
BA
HRD
w
it
h
F
irst
Clas
s.
He
c
o
m
p
lete
d
h
is
P
h
D
f
ro
m
A
n
n
a
Un
iv
e
rsit
y
in
2
0
1
2
.
He
ia
a
re
v
i
w
e
r
in
IEE
E
T
ra
n
sa
c
ti
o
n
s,
In
d
e
rsc
ien
c
e
a
n
d
S
p
rin
g
e
r
Jo
u
r
n
a
ls.
Ha
s
h
a
s
i
n
it
iat
e
d
a
n
u
m
b
e
r
o
f
in
tern
a
ti
o
n
a
l
re
se
a
rc
h
c
o
ll
a
b
o
ra
ti
o
n
w
it
h
u
n
iv
e
rsity
in
Eu
rp
o
e
,
A
u
stra
li
a
,
Af
rica
a
n
d
No
rt
h
A
m
e
rica
.
Evaluation Warning : The document was created with Spire.PDF for Python.