I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
201
9
,
p
p
.
5
4
5
4
~5
4
6
2
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v9
i
6
.
p
p
5
4
5
4
-
5462
5454
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
/
I
JE
C
E
Product
rec
o
mm
e
nda
tion sy
ste
m
b
a
sed user pu
rcha
se crit
eria
a
nd prod
uct
revie
w
s
J
iny
o
un
g
K
i
m
,
Do
y
eun H
w
a
ng
,
H
o
ek
y
un
g
J
un
g
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter E
n
g
in
e
e
rin
g
,
P
a
i
C
h
a
i
Un
iv
e
rsity
,
S
o
u
th
Ko
re
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
23
,
2
0
1
9
R
ev
i
s
ed
J
u
l
8
,
2
0
1
9
A
cc
ep
ted
J
u
l
1
7
,
2
0
1
9
In
th
is
p
a
p
e
r,
w
e
p
ro
p
o
se
a
s
y
ste
m
th
a
t
p
ro
v
id
e
s
c
u
sto
m
ize
d
p
ro
d
u
c
t
re
c
o
m
m
e
n
d
a
ti
o
n
i
n
f
o
rm
a
ti
o
n
a
f
t
e
r
c
ra
w
li
n
g
p
ro
d
u
c
t
re
v
iew
d
a
ta
o
f
in
tern
e
t
sh
o
p
p
in
g
m
a
ll
w
it
h
u
n
stru
c
t
u
re
d
d
a
ta
,
m
o
rp
h
o
l
o
g
ica
l
a
n
a
ly
sis
u
sin
g
P
y
th
o
n
.
Us
e
r
se
a
rc
h
e
s
f
o
r
a
p
ro
u
d
c
t
to
b
e
p
u
rc
h
a
se
d
a
n
d
se
lec
t
th
e
m
o
st
im
p
o
rtan
t
p
u
rc
h
a
se
c
rit
e
ria
w
h
e
n
p
u
rc
h
a
si
n
g
th
e
p
ro
d
u
c
t.
Us
e
r
se
a
rc
h
e
s
f
o
r
a
p
ro
u
d
c
t
t
o
b
e
p
u
rc
h
a
se
d
a
n
d
se
lec
t
th
e
m
o
st
im
p
o
rtan
t
p
u
rc
h
a
se
c
rit
e
ria
w
h
e
n
p
u
rc
h
a
sin
g
th
e
p
r
o
d
u
c
t.
A
n
d
e
x
trac
ts
a
n
d
a
n
a
l
y
z
e
s
o
n
ly
th
e
re
v
ie
w
in
c
lu
d
i
n
g
th
e
p
u
rc
h
a
se
c
rit
e
rio
n
se
lec
ted
b
y
th
e
u
se
r
a
m
o
n
g
th
e
p
ro
d
u
c
t
re
v
iew
s
l
e
f
t
b
y
o
th
e
r
u
se
rs.
T
h
e
p
o
sit
iv
e
a
n
d
n
e
g
a
ti
v
e
e
v
a
lu
a
ti
o
n
s
c
o
n
tai
n
e
d
i
n
th
e
e
x
trac
ted
p
ro
d
u
c
t
re
v
iew
d
a
ta
a
re
q
u
a
n
ti
f
i
e
d
a
n
d
u
si
n
g
th
e
a
v
e
ra
g
e
v
a
lu
e
,
w
e
e
x
tr
a
c
t
th
e
t
o
p
1
0
p
ro
d
u
c
ts
w
it
h
g
o
o
d
p
ro
d
u
c
t
e
v
a
lu
a
ti
o
n
,
so
rt
a
n
d
re
c
o
m
m
e
n
d
to
u
se
rs.
A
n
d
p
r
o
v
id
e
s
u
se
r
-
c
u
sto
m
iz
e
d
in
f
o
rm
a
ti
o
n
th
a
t
re
f
lec
ts
th
e
u
se
r'
s
p
re
f
e
re
n
c
e
b
y
a
rra
n
g
in
g
a
n
d
p
ro
v
id
in
g
a
c
e
n
ter
a
ro
u
n
d
t
h
e
c
rit
e
ria
th
a
t
th
e
u
se
r
o
c
c
u
p
ies
t
h
e
larg
e
st p
o
rti
o
n
o
f
th
e
p
ro
d
u
c
t
p
u
rc
h
a
se
.
T
h
is allo
w
s u
se
rs t
o
re
d
u
c
e
th
e
ti
m
e
it
tak
e
s
to
p
u
r
c
h
a
se
a
p
ro
d
u
c
t
a
n
d
m
a
k
e
m
o
r
e
e
ff
icie
n
t
p
u
rc
h
a
sin
g
d
e
c
isio
n
s.
K
ey
w
o
r
d
s
:
C
r
a
w
lin
g
P
r
o
d
u
ct
r
ev
ie
w
R
ec
o
m
m
e
n
d
er
s
y
s
te
m
T
ex
t
-
m
i
n
i
n
g
Co
p
y
rig
h
t
©
2
0
1
9
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
:
Ho
ek
y
u
n
g
J
u
n
g
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
,
P
ai
C
h
ai
Un
iv
er
s
it
y
,
1
55
-
40
B
ae
j
ae
-
ro
,
Seo
g
u
,
Dae
J
eo
n
,
So
u
th
Ko
r
ea
.
E
m
ail:
h
k
j
u
n
g
@
p
c
u
.
ac
.
k
r
1.
I
NT
RO
D
UCT
I
O
N
As
th
e
I
n
ter
n
et
an
d
th
e
m
o
b
il
e
en
v
ir
o
n
m
en
t
d
ev
elo
p
s
,
n
o
t
o
n
l
y
th
e
a
m
o
u
n
t
o
f
d
o
cu
m
e
n
t
s
b
u
t
also
th
e
t
y
p
es
o
f
d
o
cu
m
e
n
t
s
an
d
th
e
p
u
r
p
o
s
e
o
f
th
e
d
o
cu
m
e
n
ts
ar
e
b
ec
o
m
i
n
g
d
i
v
er
s
e
[
1
-
4
].
Am
o
n
g
t
h
e
m
,
r
ev
ie
w
s
o
f
p
r
o
d
u
cts
ar
e
w
r
itte
n
b
y
s
e
v
er
al
co
n
s
u
m
er
s
,
an
d
th
e
a
m
o
u
n
t
o
f
d
ata
is
r
ap
id
l
y
in
cr
ea
s
i
n
g
,
an
d
it
is
s
h
ar
ed
ac
co
r
d
in
g
to
th
e
ch
ar
ac
ter
is
ti
cs
o
f
o
p
en
w
eb
[
5
,
6
]
.
T
h
ese
p
r
o
d
u
ct
r
ev
ie
w
s
co
n
tai
n
d
etailed
an
d
r
eliab
le
in
f
o
r
m
atio
n
ab
o
u
t
t
h
e
u
s
er
's
p
r
ef
er
en
ce
s
ab
o
u
t
th
e
p
r
o
d
u
ct.
T
h
er
ef
o
r
e,
th
is
m
et
h
o
d
ca
n
b
e
ap
p
lied
to
th
e
r
ec
o
m
m
e
n
d
atio
n
s
y
s
te
m
[7
-
1
0
]
,
an
d
v
ar
io
u
s
m
e
th
o
d
s
o
f
a
n
al
y
z
in
g
t
h
e
v
ast
a
m
o
u
n
t
o
f
s
u
g
g
e
s
ted
in
f
o
r
m
atio
n
i
n
t
h
e
p
r
o
d
u
ct
r
ev
ie
w
h
av
e
b
ee
n
p
r
o
p
o
s
ed
[
1
1
-
1
3
]
.
Ho
w
e
v
er
,
m
o
s
t
o
f
th
e
f
ilter
i
n
g
tech
n
iq
u
es
u
s
ed
in
th
e
r
ec
o
m
m
en
d
atio
n
s
y
s
te
m
u
s
e
s
t
h
e
in
f
o
r
m
atio
n
o
f
th
e
u
s
er
to
p
r
o
v
id
e
t
h
e
ap
p
r
o
p
r
iate
in
f
o
r
m
atio
n
,
b
u
t
t
h
e
r
e
is
a
p
r
o
b
lem
o
f
t
h
e
co
ld
s
tar
t
w
h
ic
h
ca
n
n
o
t
p
r
o
v
id
e
p
r
o
p
e
r
in
f
o
r
m
at
io
n
wh
en
a
n
e
w
u
s
er
o
r
a
n
e
w
p
r
o
d
u
ct
i
s
r
elea
s
ed
[
1
4
,
1
5
]
.
A
n
d
T
h
e
ex
is
ti
n
g
p
r
o
d
u
ct
r
ec
o
m
m
e
n
d
atio
n
s
y
s
te
m
is
b
ased
o
n
in
f
o
r
m
at
io
n
th
at
is
n
o
t
o
b
j
ec
tiv
e
o
r
h
as
lo
w
s
ati
s
f
ac
t
io
n
b
ec
au
s
e
it
d
o
es
n
o
t
tak
e
i
n
to
co
n
s
id
er
atio
n
u
s
er
'
s
p
r
ef
er
e
n
ce
[
1
6
]
.
T
h
er
e
f
o
r
e,
if
th
e
u
s
er
co
n
s
id
er
s
th
e
cr
iter
ia
th
at
ar
e
i
m
p
o
r
tan
t
w
h
en
p
u
r
ch
as
in
g
t
h
e
p
r
o
d
u
ct,
th
e
s
atis
f
ac
tio
n
le
v
e
l o
f
th
e
r
ec
o
m
m
e
n
d
ed
p
r
o
d
u
ct
ca
n
b
e
in
cr
ea
s
ed
.
I
n
o
r
d
er
to
s
o
lv
e
th
is
p
r
o
b
lem
i
n
th
i
s
p
ap
er
,
th
e
u
s
er
d
ir
ec
tl
y
s
elec
ts
t
h
e
cr
iter
ia
o
f
'd
u
r
ab
ilit
y
'
,
'
d
esi
g
n
'
,
an
d
'
co
s
t
-
e
f
f
ec
t
iv
e
n
es
s
'
.
T
h
e
to
p
1
0
p
r
o
d
u
cts
ar
e
s
o
r
ted
an
d
r
ec
o
m
m
e
n
d
ed
to
th
e
u
s
er
af
ter
ex
tr
ac
tin
g
th
e
p
r
o
d
u
cts
h
a
v
i
n
g
e
x
ce
lle
n
t
ev
alu
a
tio
n
o
n
t
h
e
p
u
r
ch
a
s
e
cr
iter
ia
u
s
in
g
t
h
e
p
u
r
ch
a
s
e
cr
iter
ia
s
elec
ted
b
y
th
e
u
s
er
an
d
t
h
e
p
r
o
d
u
ct
r
ev
ie
w
s
cr
ea
ted
b
y
t
h
e
u
s
er
s
w
h
o
h
as
p
r
ev
io
u
s
l
y
p
u
r
c
h
ased
t
h
e
p
r
o
d
u
cts.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
P
r
o
d
u
ct
r
ec
o
mme
n
d
a
tio
n
s
ystem
b
a
s
ed
u
s
er p
u
r
ch
a
s
e
crit
eria
a
n
d
p
r
o
d
u
ct
r
ev
iew
s
(
Jin
yo
u
n
g
K
im)
5455
Usi
n
g
th
i
s
an
al
y
s
i
s
r
esu
lt
i
n
p
u
r
ch
asi
n
g
d
ec
is
io
n
m
a
k
i
n
g
,
it
ca
n
s
av
e
ti
m
e
f
o
r
p
u
r
ch
asi
n
g
p
r
o
d
u
ct
an
d
h
elp
ef
f
icien
t d
ec
is
io
n
m
ak
in
g
.
2.
SYST
E
M
DE
SI
G
N
First,
a
u
s
er
s
ea
r
ch
es
f
o
r
a
p
r
o
d
u
ct
to
b
e
p
u
r
ch
ased
,
an
d
s
elec
ts
o
n
e
o
f
th
e
p
u
r
ch
ase
cr
it
er
ia
th
at
is
co
n
s
id
er
ed
as
a
to
p
p
r
io
r
ity
wh
en
p
u
r
c
h
asi
n
g
th
e
p
r
o
d
u
ct
.
T
h
e
p
r
o
d
u
ct
r
etr
iev
ed
b
y
th
e
u
s
er
an
d
th
e
s
elec
ted
p
u
r
ch
ase
cr
iter
io
n
ar
e
u
s
ed
as
in
p
u
t
d
ata
f
o
r
f
u
r
t
h
er
an
al
y
s
i
s
.
T
h
is
s
y
s
te
m
co
llects
a
l
is
t
o
f
th
e
p
r
o
d
u
cts
s
ea
r
ch
ed
b
y
th
e
u
s
er
an
d
a
r
ev
ie
w
o
f
th
e
p
r
o
d
u
ct.
W
e
u
s
e
th
e
P
y
t
h
o
n
W
eb
d
r
iv
er
p
ac
k
ag
e
to
cr
aw
l
th
e
p
r
o
d
u
ct's UR
L
,
p
r
o
d
u
ct
n
a
m
e,
an
d
p
r
o
d
u
ct
r
ev
ie
w
s
.
T
h
en
,
th
e
co
llected
in
p
u
t
d
ata
is
s
to
r
ed
in
th
e
d
atab
ase.
I
n
ca
s
e
o
f
'
G
'
co
m
p
an
y
,
w
h
ic
h
is
th
e
tar
g
et
o
f
d
ata
co
llectio
n
,
th
er
e
is
'
p
r
e
m
i
u
m
p
r
o
d
u
ct
r
ev
ie
w
'
w
h
er
e
u
s
er
s
ca
n
w
r
ite
s
p
ec
if
i
c
p
r
o
d
u
c
t
r
ev
ie
w
s
.
W
e
p
er
f
o
r
m
ed
f
ilter
i
n
g
b
ase
d
o
n
th
e
n
u
m
b
er
o
f
p
r
o
d
u
ct
r
ev
ie
w
s
co
r
r
esp
o
n
d
in
g
to
2
0
o
f
th
ese
p
r
e
m
i
u
m
p
r
o
d
u
ct
r
ev
ie
w
s
.
2
0
p
r
em
i
u
m
p
r
o
d
u
ct
r
ev
ie
w
s
ar
e
th
e
n
u
m
b
er
o
f
4
p
ag
e
r
ev
ie
w
s
.
P
r
o
d
u
cts
w
it
h
f
e
w
er
th
a
n
2
0
p
r
o
d
u
ct
r
ev
ie
w
s
w
er
e
j
u
d
g
ed
to
b
e
in
s
u
f
f
icien
t to
an
al
y
ze
an
d
w
er
e
ex
cl
u
d
ed
f
r
o
m
t
h
e
an
al
y
s
i
s
.
W
h
en
e
x
tr
ac
tio
n
is
co
m
p
le
te
d
,
we
u
s
e
d
t
h
e
k
o
n
lp
y
a
n
d
k
k
m
a
p
ac
k
ag
e
s
o
f
P
y
th
o
n
t
o
p
er
f
o
r
m
m
o
r
p
h
e
m
e
a
n
al
y
s
i
s
.
T
h
er
ea
f
ter
,
a
p
r
o
d
u
ct
lis
t
in
clu
d
i
n
g
p
u
r
ch
a
s
e
cr
iter
ia
s
elec
ted
b
y
t
h
e
u
s
er
is
g
en
er
ated
.
T
h
e
lis
t
is
d
iv
id
ed
f
o
r
ea
ch
p
r
o
d
u
ct
to
ca
lcu
late
th
e
av
er
ag
e
v
al
u
e
o
f
p
o
s
iti
v
e
an
d
n
eg
at
iv
e
s
co
r
es
f
o
r
th
e
p
r
o
d
u
ct
r
ev
ie
w
s
.
T
h
e
r
esu
lts
ar
e
s
o
r
ted
in
a
s
ce
n
d
i
n
g
o
r
d
er
ac
co
r
d
in
g
to
th
e
r
es
u
lt
v
a
lu
e,
an
d
t
h
e
li
s
t
o
f
th
e
to
p
1
0
p
r
o
d
u
cts
is
p
r
o
v
id
ed
to
th
e
u
s
er
to
g
eth
er
w
it
h
th
e
s
co
r
e
o
b
tain
ed
as
a
r
esu
lt.
Fig
u
r
e
1
s
h
o
w
s
th
e
s
tr
u
ctu
r
e
o
f
t
h
e
s
y
s
te
m
a
n
d
Fig
u
r
e
2
s
h
o
w
s
t
h
e
s
y
s
te
m
f
lo
w
c
h
ar
t.
Fig
u
r
e
1
.
S
y
s
te
m
a
r
ch
itect
u
r
e
Fig
u
r
e
2
.
S
y
s
te
m
f
lo
w
ch
ar
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
4
5
4
-
5
4
6
2
5456
T
h
e
d
atab
ase
o
f
th
is
p
ap
er
is
d
esig
n
ed
u
s
i
n
g
M
y
SQ
L
.
Data
b
ase
cr
ea
ted
th
r
ee
tab
les
in
o
n
e
d
atab
ase
ca
lled
'
C
r
w
al
'
.
On
e
o
f
t
h
e
tab
les
is
'
p
r
o
d
u
ctlis
t
'
,
an
d
s
to
r
es
p
r
o
d
u
ct
in
f
o
r
m
a
t
io
n
s
u
ch
as
an
I
D
an
d
a
p
r
o
d
u
ct
n
a
m
e
g
i
v
en
f
o
r
ea
ch
p
r
o
d
u
ct,
an
d
a
UR
L
o
f
th
e
co
r
r
esp
o
n
d
in
g
p
r
o
d
u
ct.
T
h
e
I
D
o
f
th
e
p
r
o
d
u
ct
m
a
y
b
e
a
u
n
iq
u
e
n
u
m
b
er
ass
i
g
n
ed
to
ea
ch
p
r
o
d
u
ct
in
t
h
e
I
n
ter
n
et
s
h
o
p
p
in
g
m
all.
T
h
is
i
s
u
s
e
f
u
l
f
o
r
a
p
r
o
d
u
ct
w
it
h
th
e
s
a
m
e
b
r
an
d
n
a
m
e
t
h
r
o
u
g
h
I
D
w
h
en
s
ea
r
ch
i
n
g
f
o
r
a
p
r
o
d
u
ct,
an
d
it
p
la
y
s
a
r
o
le
o
f
m
atch
i
n
g
r
e
v
ie
w
s
a
n
d
p
r
o
d
u
cts.
An
d
it is
p
o
s
s
ib
le
to
co
n
n
ec
t d
ir
ec
tl
y
to
t
h
e
p
r
o
d
u
ct
p
u
r
ch
ase
s
i
te
th
r
o
u
g
h
UR
L
.
An
o
th
er
tab
le
h
a
s
th
e
n
a
m
e
o
f
'
r
ev
ie
w
lis
t
'
a
n
d
lo
ad
s
th
e
p
r
o
d
u
ct
I
D
an
d
p
r
o
d
u
ct
r
ev
ie
w
s
.
P
r
o
d
u
ct
r
ev
ie
w
a
n
al
y
s
i
s
s
h
o
u
ld
b
e
p
r
ec
ed
e
d
b
y
f
i
n
d
in
g
t
h
e
s
co
r
e
o
f
th
e
s
e
n
ten
ce
to
wh
ich
ea
ch
f
ea
t
u
r
e
b
elo
n
g
s
.
T
o
d
o
th
is
,
w
e
n
ee
d
to
s
ep
ar
ate
s
en
te
n
ce
s
.
I
t
i
s
co
m
m
o
n
f
o
r
ea
c
h
r
ev
ie
w
to
co
n
s
is
t
o
f
o
n
e
le
s
s
s
en
te
n
ce
,
m
o
r
e
t
h
a
n
1
0
s
en
te
n
ce
s
.
T
h
er
ef
o
r
e,
w
h
en
cr
a
w
li
n
g
p
r
o
d
u
ct
r
ev
ie
w
s
,
b
y
s
to
r
in
g
s
en
ten
ce
s
b
ased
o
n
a
p
er
io
d
,
th
ey
ar
e
u
s
ef
u
l
f
o
r
later
m
o
r
p
h
o
lo
g
ica
l a
n
al
y
s
is
.
T
h
e
f
in
al
'
k
e
y
r
ev
ie
w
'
tab
le
ex
tr
ac
ts
a
n
d
s
to
r
es
p
r
o
d
u
ct
r
e
v
ie
w
s
t
h
at
i
n
clu
d
e
t
h
e
p
u
r
ch
ase
cr
iter
ia
s
elec
ted
b
y
t
h
e
u
s
er
an
d
th
e
wo
r
d
r
elate
d
to
th
e
cr
iter
ia.
A
n
d
th
en
it
r
e
m
o
v
es
t
h
e
m
ea
n
i
n
g
les
s
w
o
r
d
s
s
u
c
h
as
'
ㅋ
ㅋㅋㅋ
'
o
r
s
p
ec
ial
ch
ar
ac
t
er
s
.
Fig
u
r
e
3
s
h
o
w
s
t
h
e
d
esi
g
n
ed
DB
an
d
tab
le.
Fig
u
r
e
3
.
C
r
ea
tio
n
d
atab
ase
an
d
tab
les
Fig
u
r
e
4
s
h
o
w
s
t
h
at
th
e
p
r
iv
ileg
es
ar
e
s
et
f
o
r
ea
ch
tab
le.
I
t
is
a
f
u
n
ct
io
n
th
a
t
is
n
ee
d
ed
w
h
e
n
p
er
f
o
r
m
in
g
q
u
er
y
u
s
i
n
g
d
ata
co
llected
an
d
an
al
y
ze
d
b
y
P
y
t
h
o
n
.
T
h
er
ef
o
r
e,
ea
ch
tab
le
is
g
r
an
ted
th
e
r
i
g
h
t
to
s
elec
t,
in
s
er
t,
u
p
d
ate,
d
elete
,
etc.
Fi
g
u
r
e
4
.
Gr
an
t p
r
iv
ile
g
es o
n
t
ab
les
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
P
r
o
d
u
ct
r
ec
o
mme
n
d
a
tio
n
s
ystem
b
a
s
ed
u
s
er p
u
r
ch
a
s
e
crit
eria
a
n
d
p
r
o
d
u
ct
r
ev
iew
s
(
Jin
yo
u
n
g
K
im)
5457
3.
SYST
E
M
I
M
P
L
E
M
E
NT
A
T
I
O
N
W
e
u
s
ed
C
P
U
-
I
n
te
l
i5
-
4
6
9
0
a
n
d
R
A
M
-
8
G
b
ased
o
n
W
in
d
o
w
s
o
p
er
atin
g
s
y
s
te
m
.
T
h
e
lan
g
u
a
g
e
u
s
ed
is
P
y
t
h
o
n
a
n
d
M
y
SQ
L
i
s
u
s
ed
to
b
u
ild
t
h
e
d
atab
ase,
a
n
d
a
ca
s
e
w
h
er
e
th
e
u
s
er
s
elec
t
s
'
co
s
t
-
e
f
f
ec
tiv
e
n
es
s
'
a
s
a
p
u
r
ch
ase
cr
iter
io
n
i
s
i
m
p
le
m
e
n
ted
as a
n
e
x
a
m
p
le.
T
h
e
d
ata
co
llectio
n
s
ite
w
a
s
s
elec
ted
as
'
G
C
o
m
p
an
y
'
i
n
Ko
r
ea
.
I
t
co
llects
r
ev
ie
w
s
m
ad
e
b
y
th
e
u
s
er
ab
o
u
t
p
r
o
d
u
ct
in
f
o
r
m
atio
n
an
d
p
r
o
d
u
cts
o
n
l
y
f
o
r
"
B
a
b
y
C
a
r
r
iag
e"
o
f
ch
ild
ca
r
e
ite
m
a
m
o
n
g
t
h
e
ca
teg
o
r
ies
o
f
th
e
lar
g
est
s
h
o
p
p
in
g
m
all
i
n
Ko
r
ea
.
Sin
ce
th
e
q
u
alit
y
o
f
t
h
e
p
r
o
d
u
ct
r
ev
ie
w
s
i
n
f
lu
e
n
ce
s
th
is
e
x
p
er
i
m
e
n
t,
w
e
c
h
o
s
e
th
e
ca
teg
o
r
y
as
a
c
h
ild
ca
r
e
ite
m
t
h
at
is
r
elati
v
el
y
s
tr
aig
h
t
f
o
r
w
ar
d
a
n
d
h
a
s
m
a
n
y
w
r
itte
n
r
ev
ie
w
s
.
I
t is co
llected
u
s
i
n
g
B
ea
u
ti
f
u
l
So
u
p
,
a
li
b
r
ar
y
o
f
P
y
t
h
o
n
th
a
t
allo
w
s
y
o
u
to
cr
a
w
l p
r
o
d
u
ct
n
a
m
es,
p
r
o
d
u
ct
U
R
L
,
an
d
p
r
o
d
u
ct
r
ev
ie
w
s
o
f
'
s
tr
o
lle
r
'
ite
m
s
.
Ho
w
e
v
er
,
w
h
en
r
ev
ie
w
s
o
f
m
o
r
e
th
an
a
ce
r
tain
n
u
m
b
er
w
er
e
w
r
itte
n
ed
o
n
th
e
o
n
li
n
e
s
h
o
p
p
in
g
m
al
l
s
y
s
te
m
,
all
o
f
t
h
e
m
ca
n
b
e
s
ee
n
b
y
p
r
es
s
i
n
g
th
e
"
M
o
r
e"
b
u
tto
n
.
L
i
k
e
w
i
s
e,
w
h
en
y
o
u
cr
a
w
l
,
y
o
u
m
u
s
t
b
e
ab
le
to
s
ee
a
l
is
t
o
f
all
r
ev
ie
w
s
i
f
an
ac
tio
n
i
s
ta
k
en
o
n
t
h
e
w
eb
b
r
o
w
s
er
to
p
a
g
e
t
h
r
o
u
g
h
.
So
,
w
e
u
s
e
Selen
iu
m
,
a
w
eb
p
ag
e
test
i
n
g
to
o
l
th
at
ca
n
b
e
p
er
f
o
r
m
ed
au
to
m
atica
ll
y
w
h
e
n
w
e
cr
a
w
l
th
ese
ac
ti
o
n
s
.
T
h
e
Selen
iu
m
p
ac
k
ag
e
f
u
n
ctio
n
s
to
la
u
n
c
h
t
h
e
w
eb
b
r
o
w
s
er
t
h
r
o
u
g
h
a
p
r
o
d
u
ct
UR
L
i
n
a
P
y
th
o
n
e
n
v
ir
o
n
m
e
n
t.
C
r
a
w
l th
e
p
r
o
d
u
ct
n
a
m
e,
p
r
o
d
u
ct
clas
s
i
f
icatio
n
,
r
ev
ie
w
,
etc.
u
s
i
n
g
th
e
HT
ML
ta
g
n
a
m
e.
T
h
e
p
r
o
d
u
ct
r
ev
ie
w
s
t
h
at
wer
e
cr
a
w
led
p
r
ev
io
u
s
l
y
i
n
clu
d
e
'
ca
u
s
tic
r
ai
n
'
a
n
d
'
p
r
ice
'
,
an
d
o
n
l
y
th
e
n
u
m
b
er
o
f
r
ev
ie
w
s
ex
ce
e
d
in
g
2
0
is
e
x
tr
ac
ted
an
d
s
to
r
e
d
.
A
s
a
r
es
u
lt,
1
2
ite
m
s
w
er
e
ex
tr
ac
ted
.
Fig
u
r
e
5
s
h
o
w
s
th
e
lis
t
o
f
1
2
ite
m
s
s
t
o
r
ed
in
DB
.
T
h
e
p
u
r
ch
ase
cr
i
ter
ia
'
co
s
t
-
e
f
f
ec
ti
v
en
e
s
s
'
a
n
d
t
h
e
r
elate
d
k
e
y
w
o
r
d
'
p
r
ice
'
ex
tr
ac
t o
n
l
y
t
h
e
n
a
m
e
o
f
th
e
p
r
o
d
u
ct
in
c
lu
d
i
n
g
t
h
e
r
ev
ie
w
s
en
te
n
ce
.
Fig
u
r
e
5
.
L
is
t o
f
ex
tr
ac
ted
p
r
o
d
u
ct
Fo
r
p
r
o
d
u
ct
r
ev
ie
w
s
cr
a
w
led
,
in
s
ta
ll
'Ko
NL
P
'
,
a
p
ac
k
ag
e
f
o
r
p
r
o
ce
s
s
in
g
Ha
n
g
u
l
ch
ar
ac
ter
s
o
f
P
y
t
h
o
n
p
r
o
g
r
am
s
.
T
h
e
m
o
r
p
h
o
lo
g
ica
l
an
al
y
s
i
s
is
b
ased
o
n
t
h
e
KKM
A
d
ictio
n
ar
y
a
n
d
is
ca
r
r
ied
o
u
t
to
ex
tr
ac
t
o
n
l
y
n
o
u
n
s
an
d
ad
j
ec
tiv
es
f
r
o
m
ea
ch
p
r
o
d
u
ct
r
ev
ie
w
s
en
te
n
ce
.
T
h
e
p
a
r
t
-
of
-
s
p
ee
ch
w
h
ic
h
ca
n
j
u
d
g
e
th
e
ch
ar
ac
ter
i
s
tic
o
f
t
h
e
p
r
o
d
u
ct
is
t
h
e
n
o
u
n
,
an
d
th
e
p
ar
t
-
of
-
s
p
ee
c
h
w
h
ich
ca
n
ex
p
r
es
s
th
e
s
en
s
iti
v
it
y
o
f
th
e
u
s
er
to
t
h
e
c
h
ar
ac
ter
is
tic
is
th
e
ad
j
ec
tiv
e.
I
n
th
is
p
r
o
ce
s
s
,
s
en
te
n
ce
s
th
at
d
o
n
o
t
co
n
ta
in
ad
j
ec
tiv
es
th
at
ca
n
j
u
d
g
e
p
o
s
itiv
e
o
r
n
eg
at
iv
e
o
f
t
h
e
s
e
n
ten
ce
s
o
f
t
h
e
r
ev
ie
w
ar
e
j
u
d
g
ed
as n
o
is
e
an
d
ex
c
lu
d
ed
f
r
o
m
t
h
e
an
al
y
s
is
.
Fig
u
r
e
6
s
h
o
w
s
an
e
x
a
m
p
le
o
f
a
r
ev
i
e
w
o
f
m
o
r
p
h
e
m
e
an
al
y
s
i
s
b
y
ex
tr
ac
ti
n
g
o
n
l
y
t
h
e
r
ev
ie
w
s
in
cl
u
d
in
g
th
e
k
e
y
w
o
r
d
'
p
r
ic
e'
as
s
o
ciate
d
w
it
h
t
h
e
co
s
t
-
ef
f
ec
tiv
e
n
e
s
s
b
y
s
elec
t
in
g
th
e
s
o
r
tin
g
cr
iter
io
n
'
co
s
t
-
e
f
f
ec
tiv
e
n
e
s
s
'
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
4
5
4
-
5
4
6
2
5458
Fig
u
r
e
6
.
E
x
a
m
p
le
o
f
m
o
r
p
h
e
m
ic
an
a
l
y
s
is
u
s
i
n
g
KKM
A
d
ic
tio
n
ar
y
I
n
o
r
d
er
t
o
r
ec
o
m
m
e
n
d
a
p
r
o
d
u
ct,
I
t
is
n
ec
ess
ar
y
to
j
u
d
g
e
w
h
ich
e
v
alu
a
tio
n
is
m
o
r
e
p
o
s
itiv
e
o
r
n
eg
at
iv
e
a
m
o
n
g
th
e
p
r
o
d
u
ct
r
ev
ie
w
s
e
x
tr
ac
ted
p
r
ev
io
u
s
l
y
.
T
h
er
ef
o
r
e,
in
th
e
ca
s
e
o
f
a
p
r
o
d
u
ct
r
ev
ie
w
,
a
s
co
r
e
o
f
"
+1
"
is
g
i
v
en
i
f
t
h
er
e
i
s
a
p
o
s
itiv
e
w
o
r
d
to
ev
al
u
ate
it
i
n
a
s
en
te
n
ce
co
n
tain
in
g
t
h
e
k
e
y
wo
r
d
o
r
th
e
cr
eter
ia,
o
r
"
-
1
"
is
g
iv
e
n
if
th
er
e
i
s
a
n
eg
ati
v
e
w
o
r
d
.
T
h
en
t
h
e
av
er
a
g
e
o
f
t
h
e
s
u
m
o
f
p
o
s
iti
v
e
a
n
d
n
eg
at
iv
e
s
co
r
es
i
s
d
iv
id
ed
b
y
t
h
e
to
tal
n
u
m
b
er
o
f
p
r
o
d
u
ct
r
ev
ie
w
s
(
C
)
.
I
n
th
is
ca
s
e,
if
th
e
s
et
o
f
co
ll
ec
ted
r
ev
ie
w
s
=
{
1
,
2
,
…
,
}
an
d
th
e
s
et
o
f
e
m
o
tio
n
al
w
o
r
d
s
=
{
1
,
2
,
…
,
}
r
esen
t
in
an
y
r
e
v
ie
w
,
T
h
e
e
m
o
tio
n
s
co
r
e
(
)
o
f
an
y
r
ev
ie
w
,
w
h
ic
h
is
th
e
s
u
m
o
f
t
h
e
p
o
s
iti
v
e
s
co
r
e
(
P
)
an
d
th
e
n
eg
at
iv
e
s
co
r
e
(
N)
d
iv
id
ed
b
y
t
h
e
to
tal
n
u
m
b
er
o
f
r
e
v
ie
w
s
,
is
ex
p
r
ess
ed
as t
h
e
f
o
llo
w
i
n
g
(
1
)
.
(
)
=
(
)
+
(
−
(
)
)
(
1
)
Ho
w
e
v
er
,
s
i
n
ce
n
e
u
tr
al
o
p
i
n
i
o
n
s
w
er
e
d
i
f
f
ic
u
lt
to
d
is
ti
n
g
u
is
h
,
t
h
e
y
w
er
e
j
u
d
g
ed
to
b
e
n
o
is
e
a
n
d
ex
clu
d
ed
.
An
d
o
v
er
all
p
r
o
d
u
ct
r
ev
ie
w
s
ar
e
p
o
s
itiv
e,
b
u
t
in
c
lu
d
ed
in
th
e
r
atin
g
ex
cl
u
s
io
n
l
is
t,
w
h
ic
h
d
o
es
n
o
t
h
av
e
a
p
o
s
itiv
e
s
r
o
r
e
o
n
th
e
s
o
r
tin
g
k
e
y
w
o
r
d
'
p
r
ice
'
o
r
'
co
s
t
-
e
f
f
ec
ti
v
en
e
s
s
'
.
T
ab
le
1
s
h
o
w
s
t
h
e
p
o
s
itiv
e
a
n
d
n
eg
at
iv
e
s
co
r
es
o
f
ea
c
h
o
f
t
h
e
t
w
el
v
e
p
r
o
d
u
ct
r
ev
ie
w
s
e
x
t
r
ac
ted
,
an
d
is
a
tab
le
s
u
m
m
ar
izin
g
th
e
a
v
er
ag
es.
T
ab
le
2
is
a
tab
le
r
an
k
ed
ac
c
o
r
d
in
g
to
th
e
av
er
ag
e
o
f
p
o
s
itiv
e
an
d
n
e
g
ativ
e
s
co
r
es
o
f
t
h
e
p
r
o
d
u
ct
r
ev
ie
w
s
ex
tr
ac
ted
.
I
t is a
lis
t o
f
p
r
o
d
u
ct
s
r
ec
o
m
m
e
n
d
ed
to
th
e
u
s
er
.
T
ab
le
1
.
R
esu
lt o
f
ca
lc
u
lated
m
ea
n
s
P
r
o
d
u
c
t
I
D
C
o
u
n
t
o
f
R
e
v
i
e
w
R
e
su
l
t
S
c
o
r
e
(
P
+
N
)
A
v
e
r
a
g
e
(
(
P
+
N
)
/
C
)
1
3
3
5
8
0
2
9
5
5
8
5
0
.
6
2
5
1
2
1
1
8
0
1
0
1
1
6
6
1
.
0
1
3
3
5
7
9
9
8
3
5
4
3
0
.
7
5
1
8
0
3
2
8
0
3
2
1
16
15
0
.
9
3
7
5
6
7
9
1
9
0
1
6
8
3
3
1
.
0
9
4
5
1
5
7
5
5
7
8
7
0
.
8
7
5
9
0
7
6
2
4
0
6
9
25
24
0
.
9
6
9
7
9
1
8
4
1
4
7
60
54
0
.
9
9
7
7
5
9
7
7
9
4
10
10
1
.
0
4
6
0
4
5
2
7
7
3
18
13
0
.
7
2
1
1
7
0
2
4
1
9
0
5
9
8
0
.
8
9
1
1
0
4
9
8
1
1
0
0
4
3
0
.
7
5
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
P
r
o
d
u
ct
r
ec
o
mme
n
d
a
tio
n
s
ystem
b
a
s
ed
u
s
er p
u
r
ch
a
s
e
crit
eria
a
n
d
p
r
o
d
u
ct
r
ev
iew
s
(
Jin
yo
u
n
g
K
im)
5459
T
ab
le
2
.
R
an
k
tab
le
w
it
h
s
co
r
es
R
a
n
k
i
n
g
P
r
o
d
u
c
t
I
D
S
c
o
r
e
1
9
7
7
9
7
7
9
4
1
.
0
2
1
2
1
1
8
1
0
1
1
1
.
0
3
6
7
9
1
9
0
1
6
8
1
.
0
4
9
0
7
6
2
4
0
6
9
0
.
9
6
5
1
8
0
3
8
0
3
2
1
0
.
9
3
7
6
9
7
9
1
8
4
1
4
7
0
.
9
7
1
1
7
0
2
4
1
9
0
5
0
.
8
9
8
9
4
5
1
5
7
5
5
7
0
.
8
7
5
9
1
1
0
4
9
8
1
1
0
0
0
.
7
5
10
4
6
0
4
5
2
7
7
3
0
.
7
2
4.
RE
VI
E
W
T
ab
le
3
s
h
o
w
s
th
e
co
n
te
n
ts
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
.
S
y
s
te
m
A
ca
lc
u
lated
p
o
s
itiv
e
w
o
r
d
s
,
n
eg
ati
v
e
w
o
r
d
s
,
k
e
y
w
o
r
d
s
,
an
d
s
o
o
n
f
r
o
m
t
h
e
d
ata
ex
tr
ac
ted
f
r
o
m
th
e
ad
v
er
ti
s
e
m
e
n
t
t
h
r
o
u
g
h
w
e
b
p
ar
s
in
g
i
n
SN
S.
An
d
d
esig
n
ed
a
s
y
s
te
m
t
h
at
d
is
p
la
y
s
t
h
e
an
al
y
s
is
r
es
u
lts
o
n
a
w
eb
s
er
v
er
u
s
i
n
g
a
d
is
tr
ib
u
ted
s
y
s
te
m
[
17
].
B
ec
au
s
e
co
llect
d
ata
f
r
o
m
t
h
e
SNS,
it
ca
n
co
llect
a
n
d
an
al
y
ze
d
ata
in
r
ea
l
ti
m
e,
t
h
e
a
m
o
u
n
t
o
f
ac
c
u
m
u
lated
d
ata
in
cr
ea
s
es
ex
p
o
n
e
n
tiall
y
,
s
o
t
h
er
e
is
a
co
n
ce
r
n
th
a
t
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
m
a
y
b
e
r
ed
u
ce
d
.
I
n
co
r
r
ec
t
in
f
o
r
m
atio
n
m
a
y
b
e
in
cl
u
d
ed
in
th
e
ca
lc
u
latio
n
as a
w
ei
g
h
t
in
g
f
ac
to
r
,
w
h
ic
h
m
a
y
o
r
m
a
y
n
o
t b
e
ac
cu
r
ate.
S
y
s
te
m
B
an
al
y
ze
s
th
e
p
r
o
d
u
ct
r
ev
ie
w
s
co
n
ta
in
i
n
g
th
e
co
n
s
u
m
er
's
r
atin
g
s
u
s
in
g
n
at
u
r
a
l
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
a
n
al
y
s
i
s
an
d
au
to
m
atic
clas
s
i
f
icatio
n
s
y
s
te
m
to
au
to
m
at
icall
y
id
e
n
ti
f
y
t
h
e
co
n
s
u
m
er
'
s
p
r
ef
er
en
ce
s
.
T
h
e
s
y
s
te
m
I
d
en
ti
f
y
th
e
d
is
ad
v
an
ta
g
e
s
o
f
th
e
p
r
o
d
u
ct
t
h
at
t
h
e
co
n
s
u
m
er
th
i
n
k
s
a
n
d
d
esig
n
ed
a
s
y
s
te
m
t
h
at
ass
i
g
n
s
a
q
u
an
titati
v
e
co
m
p
r
e
h
en
s
i
v
e
s
co
r
e
t
h
at
r
ef
lects
it
to
p
r
o
d
u
ct
r
ev
ie
w
s
[
18
]
.
I
n
th
e
s
y
s
te
m
,
clas
s
i
f
y
p
r
o
d
u
ct
r
ev
ie
w
s
i
n
to
f
iv
e
cla
s
s
i
f
icatio
n
co
d
es
s
u
ch
as
v
er
y
p
o
s
iti
v
e,
p
o
s
itiv
e,
ten
ta
tiv
e,
n
eg
ati
v
e,
an
d
v
er
y
n
eg
at
iv
e.
An
d
t
h
e
n
it
is
n
e
ce
s
s
ar
y
to
an
al
y
ze
it
to
cla
r
if
y
w
h
e
th
er
t
h
e
e
m
p
h
asize
d
w
o
r
d
e
m
p
h
as
izes
th
e
m
ea
n
i
n
g
o
f
p
o
s
iti
v
e
o
r
n
eg
ativ
e.
S
y
s
te
m
C
co
m
p
le
m
en
ts
t
h
e
p
r
o
b
lem
t
h
at
it
ta
k
es
m
u
c
h
ti
m
e
to
ex
tr
ac
t
s
en
ti
m
e
n
t
w
o
r
d
s
in
Ko
r
ea
n
lan
g
u
a
g
e
r
esear
c
h
a
n
d
s
u
g
g
es
t
s
a
tec
h
n
iq
u
e
t
h
at
ca
n
b
e
d
ir
ec
tl
y
ap
p
lied
to
Ko
r
ea
n
[
1
9
,
20]
.
I
t
is
a
k
-
s
tr
u
ct
u
r
e,
p
r
o
p
o
s
ed
a
m
et
h
o
d
o
f
ex
tr
ac
tin
g
s
e
n
ti
m
en
t
w
o
r
d
s
a
n
d
attr
ib
u
te
w
o
r
d
s
i
n
a
s
i
m
p
l
e
Ko
r
ea
n
p
r
o
d
u
ct
r
ev
ie
w
[
21
].
B
u
t i
t is in
s
u
f
f
ici
en
t to
r
ef
lect
t
h
e
attr
ib
u
te
ac
co
r
d
in
g
to
th
e
c
h
ar
ac
ter
is
tic
o
f
t
h
e
p
r
o
d
u
cts b
ec
au
s
e
th
e
e
m
o
tio
n
al
w
o
r
d
i
s
e
x
tr
ac
t
ed
b
y
f
i
x
i
n
g
t
h
e
ei
g
h
t
attr
ib
u
t
e
w
o
r
d
s
.
An
d
t
h
er
e
ar
e
li
m
ita
tio
n
s
in
a
n
al
y
zi
n
g
lo
n
g
er
s
e
n
te
n
ce
s
b
ec
au
s
e
th
e
y
ar
e
li
m
ited
to
r
elativ
el
y
s
i
m
p
le
s
en
te
n
ce
s
w
it
h
a
m
ax
i
m
u
m
p
atter
n
len
g
t
h
o
f
3
.
S
y
s
te
m
D
co
m
p
e
n
s
a
te
th
e
d
ef
ec
t
th
at
li
m
ited
in
f
o
r
m
a
tio
n
t
h
at
ca
n
b
e
g
iv
e
n
b
y
r
a
w
d
ata
an
d
s
u
g
g
est
s
a
s
y
s
te
m
th
a
t
p
r
o
v
id
es
p
r
o
ce
s
s
ed
in
f
o
r
m
a
tio
n
t
h
r
o
u
g
h
e
m
o
tio
n
a
n
al
y
s
i
s
o
f
r
e
v
ie
w
s
en
ten
ce
s
as
w
ell
a
s
b
asic in
f
o
r
m
atio
n
.
T
ab
le
3
.
T
a
b
le
o
f
co
m
p
ar
s
io
n
ex
is
t
in
g
s
y
s
te
m
s
S
y
st
e
ms
D
a
t
a
t
o
a
n
a
l
y
z
e
K
e
y
w
o
r
d
A
S
N
S
r
e
v
i
e
w
d
a
t
a
a
b
o
u
t
c
o
sme
t
i
c
s
P
o
si
t
i
v
e
sco
r
e
,
N
e
g
a
t
i
v
e
sco
r
e
,
A
n
a
l
o
g
i
z
e
w
o
r
d
B
P
r
o
d
u
c
t
r
e
v
i
e
w
d
a
t
a
5
C
l
a
ssi
f
i
c
a
t
i
o
n
c
o
d
e
s
C
K
o
r
e
a
n
p
r
o
d
u
c
t
r
e
v
i
e
w
P
r
o
p
e
r
t
y
w
o
r
d
,
Emo
t
i
o
n
a
l
w
o
r
d
D
D
o
me
st
i
c
i
n
t
e
r
n
e
t
b
o
o
k
s
t
o
r
e
r
e
v
i
e
w
d
a
t
a
M
o
d
i
f
i
e
r
w
o
r
d
,
Emp
h
a
s
i
s w
o
r
d
,
K
e
y
w
o
r
d
E
R
e
v
i
e
w
d
a
t
a
f
r
o
m
S
martp
h
o
n
e
a
p
p
m
a
r
k
e
t
p
l
a
c
e
U
se
r
-
to
-
u
se
r
r
e
v
i
e
w
si
mi
l
a
r
i
t
y
,
S
i
mi
l
a
r
i
t
y
sco
r
e
b
e
t
w
e
e
n
u
se
r
s
P
r
o
p
o
se
d
S
y
st
e
m
R
e
v
i
e
w
d
a
t
a
f
o
r
sh
o
p
p
i
n
g
mal
l
G
b
a
b
y
c
a
r
r
i
a
g
e
U
se
r
p
u
r
c
h
a
se
c
r
i
t
e
r
i
a
I
n
th
is
w
a
y
,
th
e
p
r
o
b
lem
s
o
f
ex
is
ti
n
g
s
y
s
te
m
s
th
a
t
d
o
n
o
t
r
ef
lect
th
e
class
i
f
ica
tio
n
an
d
attr
ib
u
tes
o
f
g
o
o
d
s
ar
e
i
m
p
r
o
v
ed
.
I
n
t
h
is
s
y
s
te
m
,
p
r
o
p
o
s
ed
a
s
y
s
t
e
m
t
h
at
p
r
o
v
id
es
e
-
co
m
m
er
c
e
p
r
o
d
u
ct
an
al
y
s
is
an
d
ev
al
u
atio
n
b
y
r
ev
ie
w
e
m
o
tio
n
a
n
al
y
s
i
s
t
h
at
r
e
f
lect
s
class
i
f
icat
io
n
a
n
d
attr
ib
u
tes
o
f
p
r
o
d
u
cts.
C
o
llec
t
p
r
o
d
u
ct
r
ev
ie
w
d
ata
o
f
d
o
m
e
s
t
ic
b
o
o
k
s
to
r
e
s
h
o
p
p
in
g
m
all
s
it
e
an
d
I
m
p
le
m
e
n
t
a
s
y
s
te
m
t
h
a
t
v
i
s
u
al
l
y
p
r
o
v
id
es
th
e
r
esu
lts
t
h
r
o
u
g
h
r
ev
ie
w
e
m
o
tio
n
an
a
l
y
s
is
.
I
t
s
ep
ar
ates
th
e
r
ev
ie
w
d
ata
in
to
k
e
y
wo
r
d
s
,
m
o
d
if
ie
r
s
,
a
n
d
e
m
p
h
a
s
i
s
w
o
r
d
s
b
y
a
m
o
r
p
h
e
m
e
an
al
y
ze
r
an
d
t
h
e
e
v
al
u
at
io
n
o
f
th
e
p
r
o
d
u
ct
is
ca
lc
u
lat
ed
as
th
e
e
m
o
tio
n
an
al
y
s
is
alg
o
r
it
h
m
[
22
]
.
I
t
p
r
o
v
id
es
a
v
i
s
u
al
r
ep
r
esen
tatio
n
o
f
t
h
e
r
es
u
lt
s
o
f
t
h
e
a
n
al
y
s
i
s
,
wh
ich
h
elp
s
t
h
e
u
s
er
m
ak
e
a
b
u
y
i
n
g
d
ec
is
io
n
b
u
t
it
d
o
e
s
n
o
t
r
e
f
lect
u
s
er
's
p
r
ef
er
en
ce
is
in
s
u
f
f
icie
n
t
i
n
ter
m
s
o
f
r
o
le
as
r
ec
o
m
m
e
n
d
atio
n
s
y
s
te
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
4
5
4
-
5
4
6
2
5460
S
y
s
te
m
E
p
r
o
p
o
s
es
a
n
e
w
r
ec
o
m
m
e
n
d
atio
n
al
g
o
r
ith
m
t
h
at
ca
n
i
m
p
r
o
v
e
t
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
co
llab
o
r
ativ
e
f
ilter
i
n
g
r
ec
o
m
m
e
n
d
atio
n
tec
h
n
iq
u
e.
I
t
r
ef
er
s
to
th
e
r
ev
ie
w
s
w
r
it
ten
b
y
t
h
e
u
s
er
w
ith
o
u
t
co
n
s
id
er
in
g
o
n
l
y
t
h
e
s
co
r
e.
I
n
th
is
s
y
s
te
m
,
t
h
e
s
i
m
ila
r
it
y
d
eg
r
ee
o
f
th
e
u
s
er
r
e
v
ie
w
i
s
ca
lcu
lated
b
y
t
h
e
f
r
eq
u
en
c
y
o
f
th
e
in
d
ex
w
o
r
d
s
co
m
m
o
n
l
y
e
x
tr
ac
t
ed
f
r
o
m
th
e
r
ev
ie
w
d
ata
o
r
th
e
w
ei
g
h
t
s
u
m
o
f
th
e
co
r
r
esp
o
n
d
in
g
i
n
d
ex
w
o
r
d
s
[
23
]
.
T
h
is
s
y
s
te
m
co
llec
ts
an
d
an
al
y
ze
s
r
ev
ie
w
d
ata
f
r
o
m
t
h
e
s
m
ar
tp
h
o
n
e
ap
p
m
ar
k
etp
lace
a
n
d
r
ec
o
m
m
e
n
d
s
it
to
u
s
er
s
.
T
h
is
is
a
d
if
f
er
e
n
tiati
n
g
p
ar
t
b
ec
au
s
e
it
ta
k
es
in
to
co
n
s
id
er
atio
n
th
e
s
i
m
ilar
it
y
o
f
u
s
er
r
ev
i
e
w
s
,
w
h
ic
h
is
q
u
alita
tiv
e
in
f
o
r
m
atio
n
.
B
u
t
t
h
e
p
r
ed
ictio
n
ac
cu
r
ac
y
o
f
th
e
r
ec
o
m
m
en
d
atio
n
alg
o
r
it
h
m
co
n
s
id
er
in
g
u
s
er
r
ev
ie
w
s
i
s
lo
w
er
th
a
n
t
h
e
co
m
p
ar
is
o
n
al
g
o
r
ith
m
.
Mo
s
t
co
n
s
u
m
er
s
p
a
y
a
ce
r
tai
n
a
m
o
u
n
t
o
f
m
o
n
e
y
a
n
d
p
u
r
ch
ase
g
o
o
d
s
b
y
n
ec
e
s
s
it
y
.
B
u
t
th
e
cr
iter
i
a
f
o
r
s
elec
tin
g
a
p
r
o
d
u
ct
ar
e
d
if
f
er
en
t
f
o
r
ea
ch
in
d
iv
id
u
al.
T
h
e
cr
iter
ia
f
o
r
p
u
r
ch
asin
g
g
o
o
d
s
is
in
f
o
r
m
atio
n
th
a
t
o
n
l
y
th
e
p
u
r
ch
a
s
er
k
n
o
w
s
s
o
,
i
n
o
r
d
er
to
r
ef
lect
t
h
i
s
,
i
n
t
h
is
s
y
s
te
m
,
u
s
er
s
w
er
e
s
e
lecte
d
to
g
eth
er
w
it
h
p
r
o
d
u
ct
s
ea
r
ch
.
C
alcu
lates
th
e
s
i
m
ilar
i
t
y
w
i
th
o
th
er
u
s
er
s
o
r
th
e
f
r
eq
u
en
c
y
o
r
w
ei
g
h
t
o
f
a
s
p
ec
if
ic
w
o
r
d
an
d
i
t
r
ef
lects
th
e
p
u
r
ch
as
in
g
cr
iter
ia
s
elec
ted
b
y
th
e
u
s
er
u
n
lik
e
t
h
e
ex
is
te
d
r
ec
o
m
m
e
n
d
ed
s
y
s
te
m
.
T
h
e
m
o
s
t
d
if
f
er
en
tia
tin
g
p
ar
t is th
at
g
e
n
er
ated
cu
s
to
m
iz
ed
in
f
o
r
m
at
io
n
f
o
r
ea
ch
n
e
w
i
n
d
iv
id
u
al.
5.
CO
NCLU
SI
O
NS
Mo
s
t
co
n
s
u
m
er
s
co
n
s
id
er
p
r
o
d
u
ct
r
ev
ie
w
s
an
d
i
t
r
ef
lect
th
eir
p
u
r
c
h
asi
n
g
d
ec
is
io
n
s
[
2
4
,
2
5
]
.
B
u
t
e
x
is
tin
g
o
n
li
n
e
s
h
o
p
p
in
g
m
all
s
i
tes
h
a
v
e
a
p
r
o
b
lem
t
h
at
it
tak
es
a
lo
t
o
f
ti
m
e
f
o
r
a
co
n
s
u
m
er
to
s
ea
r
ch
f
o
r
a
p
r
o
d
u
ct
an
d
to
s
e
lect
a
d
es
ir
ed
p
r
o
d
u
ct
a
m
o
n
g
m
an
y
k
i
n
d
s
o
f
p
r
o
d
u
cts.
T
h
e
b
i
g
g
e
s
t
r
ea
s
o
n
th
a
t
t
h
e
g
r
ea
tes
t
a
m
o
u
n
t
o
f
ti
m
e
an
d
ef
f
o
r
t
f
o
r
p
u
r
ch
asi
n
g
is
t
h
e
a
m
o
u
n
t
o
f
u
n
n
ec
es
s
ar
y
i
n
f
o
r
m
atio
n
i
s
h
u
g
e,
a
n
d
t
h
e
cr
iter
ia
f
o
r
s
elec
tin
g
a
p
r
o
d
u
ct
ar
e
d
if
f
er
e
n
t
f
o
r
ea
ch
i
n
d
iv
id
u
al.
B
u
t
d
e
s
p
ite
h
av
i
n
g
d
if
f
er
en
t
p
u
r
ch
ase
cr
it
er
ia,
th
e
s
a
m
e
p
r
o
d
u
ct
lis
t
is
p
r
o
v
id
ed
,
w
h
ich
lead
s
to
in
e
f
f
icie
n
t
p
u
r
ch
asi
n
g
d
ec
is
io
n
s
.
T
h
er
ef
o
r
e,
in
th
is
r
esear
ch
th
e
u
s
er
ca
n
s
elec
t
th
e
p
u
r
ch
a
s
e
cr
iter
io
n
alo
n
g
w
i
t
h
th
e
p
r
o
d
u
ct
s
ea
r
ch
an
d
r
ef
lect
it
an
d
b
y
r
ef
lecti
n
g
t
h
is
,
w
e
co
m
p
le
m
e
n
ted
th
e
i
n
ef
f
i
cie
n
t
p
u
r
c
h
ase
d
ec
is
io
n
p
r
o
ce
s
s
in
w
h
ich
p
r
o
d
u
ct
in
f
o
r
m
atio
n
is
p
r
o
v
id
ed
r
an
d
o
m
l
y
.
T
h
e
u
lti
m
ate
g
o
al
o
f
a
p
r
o
d
u
ct
r
ec
o
m
m
en
d
atio
n
s
y
s
te
m
is
t
o
h
elp
u
s
er
s
m
a
k
e
p
u
r
ch
asi
n
g
d
ec
is
io
n
s
b
y
r
ec
o
m
m
en
d
i
n
g
p
r
o
d
u
cts
t
h
at
ar
e
r
ea
ll
y
n
ee
d
ed
b
y
u
s
er
s
t
o
th
e
r
i
g
h
t
s
i
tu
at
i
o
n
.
I
t
i
s
al
s
o
i
m
p
o
r
tan
t
f
o
r
u
s
er
s
to
k
n
o
w
w
h
a
t
t
h
e
y
n
ee
d
i
n
o
r
d
er
to
r
ec
o
m
m
en
d
p
r
o
d
u
cts
t
o
u
s
er
s
b
u
t
u
n
d
er
s
tan
d
i
n
g
th
e
h
id
d
en
m
ea
n
i
n
g
o
f
th
e
r
ea
s
o
n
f
o
r
p
u
r
c
h
asi
n
g
a
p
r
o
d
u
ct
ca
n
e
n
h
an
ce
th
e
u
s
er
's
s
atis
f
ac
tio
n
.
I
n
o
r
d
er
to
in
cr
ea
s
e
th
e
s
atis
f
ac
tio
n
o
f
th
e
u
s
er
s
,
a
m
et
h
o
d
o
f
r
ec
o
m
m
en
d
i
n
g
p
r
o
d
u
cts
b
ased
o
n
th
e
p
u
r
ch
asin
g
cr
iter
ia
s
elec
ted
b
y
ea
ch
u
s
er
is
n
ee
d
ed
.
T
h
er
ef
o
r
e,
in
th
is
s
y
s
te
m
r
ea
r
r
an
g
e
s
th
e
p
r
o
d
u
ct
lis
t
th
at
r
ef
lec
ts
t
h
e
p
r
o
d
u
cts
th
e
u
s
er
s
ea
r
ch
ed
f
o
r
an
d
th
e
s
elec
ted
p
u
r
c
h
ase
cr
i
ter
ia
.
T
h
is
n
o
t
o
n
l
y
r
ed
u
ce
s
t
h
e
ti
m
e
it
ta
k
es
to
p
u
r
c
h
ase
a
p
r
o
d
u
ct,
b
u
t
also
f
ilter
s
i
n
f
o
r
m
atio
n
r
ef
lect
in
g
its
o
w
n
p
u
r
c
h
ase
cr
iter
ia
an
d
p
r
o
v
id
es
in
f
o
r
m
atio
n
in
c
lu
d
i
n
g
k
e
y
w
o
r
d
s
s
elec
ted
b
y
t
h
e
u
s
er
.
in
o
r
d
er
o
f
p
r
o
d
u
ct
r
atin
g
,
a
n
d
p
r
o
v
id
es it to
th
e
u
s
er
.
A
l
s
o
,
s
in
ce
th
e
f
i
lter
ed
lis
t
is
r
ea
r
r
an
g
ed
in
th
e
o
r
d
er
o
f
g
o
o
d
ev
alu
atio
n
,
th
er
e
is
n
o
n
ee
d
to
r
ea
d
a
lar
g
e
a
m
o
u
n
t
o
f
p
r
o
d
u
ct
lis
t
an
d
p
r
o
d
u
ct
r
ev
ie
w
.
I
t
ca
n
b
e
e
x
p
ec
ted
th
at
u
s
er
s
w
ill
b
e
ab
le
to
r
ec
eiv
e
p
r
o
d
u
ct
in
f
o
r
m
atio
n
q
u
ick
l
y
ac
co
r
d
in
g
to
a
w
a
n
ted
p
u
r
ch
ase
cr
it
e
r
io
n
,
an
d
in
cr
ea
s
i
n
g
t
h
e
s
at
is
f
ac
tio
n
o
f
th
e
u
s
er
.
Ho
w
e
v
er
,
th
er
e
i
s
also
a
ca
s
e
w
h
er
e
t
h
e
p
r
o
d
u
ct
r
ev
ie
w
d
ata
is
cr
ea
ted
w
it
h
m
alicio
u
s
i
n
te
n
tio
n
r
at
h
er
t
h
an
a
p
r
o
d
u
ct
r
ev
ie
w
m
ad
e
b
y
p
u
r
ch
asi
n
g
an
d
d
ir
ec
tl
y
u
s
in
g
th
e
p
r
o
d
u
ct
.
T
h
is
n
ee
d
s
to
b
e
f
ilter
ed
b
e
ca
u
s
e
it
in
ter
f
er
e
s
w
it
h
t
h
e
u
s
er
's
d
ec
is
io
n
to
b
u
y
t
h
e
p
r
o
d
u
ct.
Fu
tu
r
e
r
esear
ch
w
ill
b
e
ab
le
to
s
h
o
w
h
o
w
to
f
il
ter
f
al
s
e
r
ev
ie
w
d
ata.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
w
o
r
k
w
a
s
s
u
p
p
o
r
ted
b
y
th
e
r
esear
ch
g
r
a
n
t o
f
P
aich
a
i U
n
iv
er
s
it
y
in
2
0
1
9
.
RE
F
E
R
E
NC
E
S
[1
]
J.
Y.
Ch
a
n
g
,
“
A
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis
A
l
g
o
rit
h
m
f
o
r
A
u
to
m
a
ti
c
P
ro
d
u
c
t
Re
v
ie
w
s
Clas
s
f
ic
a
ti
o
n
in
On
-
L
in
e
S
h
o
p
p
in
g
M
a
ll
,
”
T
h
e
J
o
u
rn
a
l
o
f
S
o
c
iety
fo
r
e
-
Bu
sin
e
ss
S
t
u
d
ies
,
v
o
l
.
1
4
,
p
p
.
1
9
-
3
3
,
2
0
0
9
.
[2
]
A
.
Esu
li
a
n
d
F.
S
e
b
a
stian
i,
“
De
ter
min
in
g
T
e
rm
S
u
b
jec
ti
v
it
y
a
n
d
T
e
rm
Or
ien
ta
ti
o
n
f
o
r
O
p
in
i
o
n
M
in
i
n
g
,
”
P
r
o
c
e
e
d
in
g
s
o
f
1
1
t
h
c
o
n
f
e
re
n
c
e
o
f
th
e
Eu
r
o
p
e
a
n
c
h
a
p
ter
o
f
t
h
e
A
ss
o
c
iatio
n
f
o
r
C
o
m
p
u
tatio
n
a
l
L
in
g
u
isti
c
s
:
EA
CL
,
p
p
.
1
9
3
-
200
,
2
0
0
6
.
[3
]
E.
J.
Yu
,
e
t
a
l.
,
“
P
re
d
icti
n
g
th
e
Dire
c
ti
o
n
o
f
th
e
st
o
c
k
in
d
e
x
b
y
u
sin
g
a
d
o
m
a
in
-
sp
e
c
if
ic
se
n
ti
m
e
n
t
d
ictio
n
a
ry
,
”
J
o
u
rn
a
l
o
f
in
telli
g
e
n
t
i
n
fo
rm
a
ti
o
n
sy
ste
ms
,
v
o
l.
1
9
,
p
p
.
95
-
1
0
0
,
2
0
1
3
.
[4
]
X
.
Di
n
g
,
e
t
a
l.
,
“
A
h
o
l
isti
c
lex
ico
n
-
b
a
se
d
a
p
p
ro
a
c
h
t
o
o
p
in
i
o
n
mi
n
in
g
,
”
P
r
o
c
e
e
d
in
g
s
o
f
th
e
in
tern
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
o
n
W
e
b
se
a
rc
h
a
n
d
w
e
b
d
a
ta m
in
in
g
,
p
p
.
2
3
1
-
2
4
0
,
2
0
0
8
.
[5
]
S.
M
o
rin
a
g
a
,
e
t
a
l.
,
“
M
in
in
g
Pr
o
d
u
c
t
Rep
u
ta
t
io
n
s
o
n
t
h
e
W
e
b
,
”
P
ro
c
e
e
d
in
g
s
o
f
th
e
8
t
h
S
IG
KD
D
In
tern
a
ti
o
n
a
l
Co
n
f
e
r
-
e
n
c
e
o
n
Kn
o
w
led
g
e
Disc
o
v
e
r
y
a
n
d
Da
ta M
in
i
n
g
,
p
p
.
3
4
1
-
3
4
9
,
2
0
0
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
P
r
o
d
u
ct
r
ec
o
mme
n
d
a
tio
n
s
ystem
b
a
s
ed
u
s
er p
u
r
ch
a
s
e
crit
eria
a
n
d
p
r
o
d
u
ct
r
ev
iew
s
(
Jin
yo
u
n
g
K
im)
5461
[6
]
H.
G
.
L
e
e
a
n
d
H.
K
w
a
k
,
“
I
n
v
e
st
ig
a
ti
o
n
o
f
f
a
c
to
rs
a
ff
e
c
ti
n
g
th
e
e
ff
e
c
ts
o
f
o
n
li
n
e
c
o
n
su
m
e
r
re
v
ie
w
s
,
”
J
o
u
rn
a
l
o
f
n
a
ti
o
n
a
l
i
n
f
o
rm
a
ti
o
n
s
o
c
iety
a
g
e
n
c
y
,
v
o
l.
2
0
,
p
p
.
3
-
1
7
,
2
0
1
3
.
[7
]
Ch
a
n
g
J.
Y.,
“
A
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis
A
l
g
o
rit
h
m
f
o
r
A
u
to
m
a
ti
c
P
ro
d
u
c
t
Re
v
ie
w
s
Clas
s
f
ica
ti
o
n
in
On
-
L
in
e
S
h
o
p
p
in
g
M
a
ll
,
”
T
h
e
J
o
u
rn
a
l
o
f
S
o
c
iety
fo
r
e
-
Bu
sin
e
ss
S
t
u
d
ies
,
v
o
l
.
1
4
,
p
p
.
1
9
-
3
3
,
2
0
0
9
.
[8
]
S.
M
.
A
lex
,
e
t
a
l
.
,
“
De
v
e
lo
p
m
e
n
t
o
f
De
e
p
L
e
a
rn
in
g
M
o
d
e
ls
f
o
r
M
u
lt
i
-
c
las
s
S
e
n
ti
m
e
n
t
A
n
a
l
y
si
s
,
”
J
o
u
rn
a
l
o
f
In
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
y
S
e
rv
ice
s
,
v
o
l.
1
6
,
p
p
.
1
4
9
-
1
6
0
,
2
0
1
7
.
[9
]
S
.
M
.
A
h
n
,
e
t
a
l.
,
“
Un
d
e
rsta
n
d
i
n
g
th
e
P
e
rf
o
rm
a
n
c
e
o
f
C
o
ll
a
b
o
ra
ti
v
e
F
il
terin
g
Re
c
o
m
m
e
n
d
a
ti
o
n
th
ro
u
g
h
S
o
c
ia
l
Ne
tw
o
rk
A
n
a
l
y
sis
,
”
J
o
u
rn
a
l
o
f
S
o
c
iety
fo
r e
-
Bu
sin
e
ss
S
tu
d
ies
,
v
o
l.
1
7
,
p
p
.
1
2
9
-
1
4
7
,
2
0
1
2
.
[1
0
]
Z
.
Z
h
a
n
g
,
e
t
a
l.
,
“
A
h
y
b
rid
f
u
z
z
y
-
b
a
se
d
p
e
rso
n
a
li
z
e
d
re
c
o
m
m
e
n
d
e
r
sy
ste
m
f
o
r
tele
c
o
m
p
ro
d
u
c
ts/se
rv
ice
s
,
”
In
fo
rm
a
t
io
n
S
c
ien
c
e
,
v
o
l.
2
3
5
,
p
p
.
1
1
7
-
1
2
9
,
2
0
1
3
.
[1
1
]
K.
R.
Ja
n
g
,
e
t
a
l.
,
“E
x
trac
ti
n
g
lm
p
li
c
it
c
u
st
o
m
e
r
v
ie
w
p
o
in
ts
f
ro
m
p
ro
d
u
c
t
re
v
iew
tex
t
,
”
J
o
u
rn
a
l
o
f
K
o
re
a
in
fo
rm
a
ti
o
n
sc
ien
c
e
so
c
iety
:
so
ft
w
a
re
a
n
d
a
p
p
li
c
a
ti
o
n
s
,
v
ol
.
4
1
,
p
p
.
376
-
3
8
6
,
2
0
1
4
.
[1
2
]
J.
Y.
Kim
a
n
d
D.
S
.
Kim
,
“
A
stu
d
y
o
n
th
e
m
e
th
o
d
f
o
r
e
x
trac
ti
n
g
t
h
e
p
u
r
p
o
se
-
sp
e
c
if
ic
c
u
sto
m
iz
e
d
in
f
o
rm
a
ti
o
n
f
ro
m
o
n
li
n
e
p
r
o
d
u
c
t
re
v
iew
s b
a
se
d
o
n
t
e
x
t
m
in
in
g
,
”
J
o
u
rn
a
l
o
f
so
c
iety
f
o
r e
-
b
u
sin
e
ss
stu
d
ies
,
v
ol
.
2
1
,
p
p
.
1
5
1
-
1
6
1
,
2
0
1
6
.
[1
3
]
K
.
Ca
o
,
J.
L
e
e
,
a
n
d
H.
Ju
n
g
,
“
K
e
y
w
o
rd
A
n
a
l
y
s
is
Ba
se
d
Do
c
u
m
e
n
t
C
o
m
p
re
ss
io
n
S
y
ste
m
,
”
J
o
u
rn
a
l
o
f
i
n
fo
rm
a
ti
o
n
a
n
d
Co
mm
u
n
ica
t
io
n
Co
n
v
e
rg
e
n
c
e
En
g
i
n
e
e
rin
g
,
v
o
l.
16
,
n
o
.
1
,
p
p
.
48
-
51
,
2
0
1
8
.
[1
4
]
I.
Y.
Je
o
n
g
,
e
t
a
l.
,
“
A
S
tu
d
y
o
n
M
o
v
ies
Re
c
o
m
m
e
n
d
a
ti
o
n
S
y
ste
m
o
f
Hy
b
rid
F
il
terin
g
-
Ba
se
d
,
”
J
o
u
r
n
a
l
o
f
th
e
Ko
re
a
In
stit
u
te
o
f
I
n
f
o
rm
a
ti
o
n
a
n
d
Co
m
mu
n
ica
t
io
n
En
g
i
n
e
e
rin
g
,
v
o
l.
19
,
pp.
1
1
3
-
1
1
8
,
2
0
1
5
.
[1
5
]
J.
Y.
Hy
u
n
,
e
t
a
l
.
,
“
Ho
w
to
im
p
ro
v
e
th
e
a
c
c
u
ra
c
y
o
f
re
c
o
m
m
e
n
d
a
ti
o
n
sy
ste
m
s:
Co
m
b
in
in
g
ra
ti
n
g
s
a
n
d
re
v
iew
tex
ts
se
n
ti
m
e
n
t
sc
o
re
s,
”
J
o
u
rn
a
l
o
f
I
n
te
ll
ig
e
n
c
e
a
n
d
In
f
o
rm
a
ti
o
n
Sy
ste
ms
,
v
o
l.
2
5
,
p
p
.
2
1
9
-
2
3
9
,
2
0
1
9
.
[1
6
]
B.
Je
o
n
a
n
d
H.
A
h
n
,
“
A
Co
ll
a
b
o
ra
ti
v
e
F
il
terin
g
S
y
ste
m
Co
m
b
i
n
e
d
w
it
h
Us
e
rs
Re
v
iew
M
in
in
g
:
A
p
p
li
c
a
ti
o
n
t
o
th
e
Re
c
o
m
m
e
n
d
a
ti
o
n
o
f
S
m
a
rtp
h
o
n
e
A
p
p
s
,
”
J
o
u
rn
a
l
o
f
I
n
telli
g
e
n
c
e
a
n
d
I
n
f
o
rm
a
ti
o
n
S
y
ste
m
,
v
o
l
.
2
1
,
p
p
.
1
-
18
,
2
0
1
5
.
[1
7
]
A
.
R.
L
e
e
,
e
t
a
l
.
,
“
A
De
sig
n
o
f
a
T
V
A
d
v
e
rti
se
m
e
n
t
Eff
e
c
ti
v
e
n
e
ss
A
n
a
l
y
sis
S
y
ste
m
Us
in
g
S
NS
Big
-
d
a
ta
,
”
J
o
u
rn
a
l
o
f
KIIS
E
T
ra
n
sa
c
ti
o
n
s
o
n
Co
mp
u
ti
n
g
Pr
a
c
ti
c
e
s
,
v
o
l.
7
,
pp.
579
-
5
8
6
,
2
0
1
5
.
[1
8
]
G.
Y.
Kim
,
e
t
a
l.
,
“
C
u
sto
m
e
r
P
re
f
e
r
e
n
c
e
Id
e
n
ti
f
ica
ti
o
n
S
y
ste
m
u
sin
g
Na
t
u
ra
l
L
a
n
g
u
a
g
e
P
ro
c
e
ss
in
g
-
b
a
se
d
A
n
a
ly
sis
a
n
d
A
u
to
m
a
ti
c
Clas
si
f
ica
ti
o
n
o
f
P
r
o
d
u
c
t
Re
v
iew
s
,
”
J
o
u
rn
a
l
o
f
Ko
re
a
S
o
c
iety
f
o
r
In
f
o
rm
a
ti
o
n
M
a
n
a
g
e
me
n
t,
vo
l.
5
,
p
p
.
6
5
-
70
,
2
0
0
9
.
[1
9
]
A
n
J.
K
.
a
n
d
H.
W
.
Kim
,
“
Bu
il
d
in
g
a
k
o
re
a
n
se
n
ti
m
e
n
t
L
e
x
i
c
o
n
u
s
in
g
c
o
ll
e
c
ti
v
e
in
telli
g
e
n
ce
,
”
J
o
u
rn
a
l
o
f
I
n
telli
g
e
n
t
In
fo
rm
a
t
io
n
S
y
ste
ms
,
v
o
l.
2
1
,
pp.
46
-
6
7
,
2
0
1
5
.
[2
0
]
M.
Hu
a
n
d
B
.
L
iu
,
“
M
in
i
n
g
a
n
d
su
m
m
a
rizin
g
c
u
sto
m
e
r
re
v
ie
w
s
,
”
Pro
c
e
e
d
in
g
s
o
f
t
h
e
1
0
t
h
ACM
S
IGKD
D
in
ter
n
a
t
io
n
a
l
c
o
n
fer
e
n
c
e
o
n
K
n
o
wled
g
e
Disc
o
v
e
ry
a
n
d
Da
t
a
min
i
n
g
,
p
p
.
1
6
8
-
1
7
7
,
2
0
0
4
.
[2
1
]
H.
H.
Ka
n
g
,
e
t
a
l.
,
“
A
u
to
m
a
ti
c
Ex
trac
ti
o
n
o
f
Op
in
io
n
W
o
rd
s
f
ro
m
Ko
re
a
n
P
r
o
d
u
c
t
Re
v
ie
w
s
Us
in
g
t
h
e
k
-
S
tru
c
tu
re
,
”
J
o
u
rn
a
l
o
f
KIS
S
:
S
o
ft
w
a
re
a
n
d
Ap
p
li
c
a
ti
o
n
s
,
v
o
l.
10
,
p
p
.
4
7
0
-
4
7
9
,
2
0
1
0
.
[2
2
]
J.
E.
Ch
o
i,
e
t
a
l.
,
“
S
y
ste
m
De
si
g
n
f
o
r
A
n
a
ly
sis
a
n
d
Ev
a
lu
a
ti
o
n
o
f
E
-
c
o
m
m
e
rc
e
P
r
o
d
u
c
ts
Us
in
g
Re
v
ie
w
S
e
n
ti
m
e
n
t
W
o
rd
A
n
a
l
y
sis
,
”
J
o
u
rn
a
l
o
f
KIIS
E
T
ra
n
sa
c
ti
o
n
s o
n
C
o
mp
u
ti
n
g
Pr
a
c
ti
c
e
s
,
v
o
l.
2
2
,
p
p
.
2
0
9
-
2
1
7
,
2
0
1
6
.
[2
3
]
B.
K.
Je
o
n
a
n
d
H.
C.
A
h
n
,
“
A
C
o
ll
a
b
o
ra
ti
v
e
F
il
teri
n
g
S
y
ste
m
Co
m
b
in
e
d
w
it
h
Us
e
r’s
Re
v
iew
M
in
in
g
,
”
J
o
u
r
n
a
l
o
f
In
telli
g
e
n
c
e
a
n
d
I
n
fo
rm
a
t
io
n
S
y
st
e
ms
,
v
o
l.
1
9
,
p
p
.
25
-
4
4
,
2
0
1
8
.
[2
4
]
A
.
Esu
li
a
n
d
F
.
S
e
b
a
stian
i
,
“
De
ter
m
in
in
g
T
e
r
m
S
u
b
jec
ti
v
it
y
a
n
d
T
e
r
m
Orie
n
tatio
n
f
o
r
O
p
in
i
o
n
M
i
n
in
g
,
”
Pro
c
e
e
d
in
g
s
o
f
1
1
t
h
c
o
n
fer
e
n
c
e
o
f
th
e
E
u
ro
p
e
a
n
c
h
a
p
ter
o
f
th
e
A
ss
o
c
ia
ti
o
n
f
o
r
Co
mp
u
t
a
ti
o
n
a
l
L
i
n
g
u
isti
c
s
:
EA
C
L
,
p
p
.
1
9
3
-
2
0
0
,
2
0
0
6
.
[2
5
]
Z.
H
u
a
n
g
,
e
t
a
l.
,
“
A
p
p
ly
in
g
As
s
o
c
iativ
e
Re
tri
e
v
a
l
T
e
c
h
n
iq
u
e
s
to
A
ll
e
v
iate
th
e
S
p
a
rsity
P
ro
b
lem
in
Co
ll
a
b
o
ra
ti
v
e
F
il
terin
g
,”
ACM
T
ra
n
s.
I
n
fo
rm
a
ti
o
n
S
y
ste
ms
,
v
o
l.
2
2
,
p
p
.
1
1
6
-
1
4
2
,
2
0
0
4
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
J
in
y
o
u
n
g
K
i
m
re
c
e
iv
e
d
th
e
B.
S
.
d
e
g
re
e
in
2
0
0
1
a
n
d
M
.
S
.
d
e
g
re
e
in
2
0
1
1
f
ro
m
th
e
De
p
a
rtm
e
n
t
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
o
f
Ch
o
n
u
b
k
Na
ti
o
n
a
l
Un
iv
e
rsit
y
,
Ko
re
a
.
S
in
c
e
2
0
0
1
,
h
e
h
a
s w
o
rk
e
d
f
o
r
K
-
wa
ter as
a
m
a
n
a
g
e
r
e
sp
e
c
iall
y
in
Wate
r
T
re
a
t
m
e
n
t
P
lan
ts.
He
is cu
rre
n
tl
y
in
a
Do
c
to
ra
te
c
o
u
rse
in
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
E
n
g
in
e
e
rin
g
o
f
P
a
ich
a
i
Un
iv
e
rsity
.
His
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
5
G
,
Clo
u
d
Co
m
p
u
ti
n
g
,
M
a
c
h
in
e
L
e
a
rn
in
g
,
Big
d
a
ta
a
n
d
A
rti
f
icia
l
In
telli
g
e
n
c
e
.
Do
y
e
u
n
H
w
a
n
g
re
c
e
iv
e
d
h
e
r
B
.
S
.
,
d
e
g
re
e
s
f
ro
m
th
e
De
p
a
rt
m
e
n
t
o
f
Bu
sin
e
ss
A
d
m
in
istrario
n
o
f
P
a
ich
a
i
Un
iv
e
rsit
y
,
Ko
re
a
,
in
2
0
17
.
S
h
e
h
a
s
b
e
e
n
st
u
d
y
in
g
in
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
En
g
in
e
e
rin
g
a
t
P
a
ich
a
i
U
n
iv
e
rsity
.
He
r
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
tex
t
-
m
in
in
g
,
b
ig
d
a
ta,
o
p
i
n
io
n
-
m
in
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
4
5
4
-
5
4
6
2
5462
Ho
e
k
y
u
n
g
J
u
n
g
re
c
e
iv
e
d
th
e
M
.
S
.
d
e
g
re
e
in
1
9
8
7
a
n
d
P
h
.
D.
d
e
g
re
e
in
1
9
9
3
f
ro
m
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
E
n
g
in
e
e
rin
g
o
f
Kw
a
n
g
w
o
o
n
Un
iv
e
rsity
,
Ko
re
a
.
F
r
o
m
1
9
9
4
to
1
9
9
5
,
h
e
w
o
rk
e
d
f
o
r
ET
RI
a
s
a
r
e
se
a
r
c
h
e
r.
S
in
c
e
1
9
9
4
,
h
e
h
a
s
w
o
rk
e
d
in
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
En
g
in
e
e
rin
g
a
t
P
a
ich
a
i
Un
iv
e
rsity
,
w
h
e
r
e
h
e
n
o
w
w
o
rk
s
a
s
a
p
r
o
f
e
ss
o
r.
His
c
u
rre
n
t
re
se
a
r
c
h
in
tere
sts
in
c
l
u
d
e
m
u
lt
im
e
d
ia
d
o
c
u
m
e
n
t
a
rc
h
it
e
c
tu
re
m
o
d
e
li
n
g
,
i
n
f
o
rm
a
ti
o
n
p
ro
c
e
ss
in
g
,
in
f
o
rm
a
ti
o
n
re
tri
e
v
a
l,
m
a
c
h
in
e
lea
rn
in
g
,
b
ig
d
a
ta,
a
n
d
Io
T
.
Evaluation Warning : The document was created with Spire.PDF for Python.