I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d
Science
s
(
I
J
AAS)
Vo
l.
14
,
No
.
3
,
Sep
tem
b
er
20
25
,
p
p
.
7
40
~
7
50
I
SS
N:
2252
-
8
8
1
4
,
DOI
:
1
0
.
1
1
5
9
1
/ijaas
.
v14.
i
3
.
p
p
7
40
-
7
50
740
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
A met
ho
d
clas
sify
ing
t
he dom
es
tic
t
o
urist desti
na
tion ba
se
sim
ila
rity mea
sur
ing
Ng
uy
en
T
hi H
o
i,
T
ra
n T
hi N
hu
ng
,
B
ui Q
ua
ng
T
ruo
ng
,
Ng
uy
en
Q
ua
ng
T
rung
F
a
c
u
l
t
y
o
f
E
c
o
n
o
mi
c
I
n
f
o
r
ma
t
i
o
n
S
y
s
t
e
m
a
n
d
E
-
c
o
mm
e
r
c
e
,
Th
u
o
n
g
m
a
i
U
n
i
v
e
r
si
t
y
,
H
a
n
o
i
,
V
i
e
t
n
a
m
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
6
,
2
0
2
4
R
ev
is
ed
Ma
y
1
0
,
2
0
2
5
Acc
ep
ted
J
u
n
8
,
2
0
2
5
Th
e
c
las
sifica
ti
o
n
p
r
o
b
lem
is
c
ru
c
ial
in
b
u
sin
e
ss
,
p
r
o
v
i
d
i
n
g
a
n
e
ffe
c
ti
v
e
m
e
th
o
d
fo
r
su
p
p
o
rti
n
g
se
a
rc
h
a
c
ti
v
it
ies
in
a
re
a
s
su
c
h
a
s
e
-
c
o
m
m
e
rc
e
,
e
d
u
c
a
ti
o
n
,
a
n
d
m
a
rk
e
ti
n
g
.
T
h
is
h
a
s
b
e
c
o
m
e
e
sp
e
c
ially
imp
o
rtan
t
i
n
th
e
wa
k
e
o
f
th
e
COV
ID
-
1
9
p
a
n
d
e
m
ic,
wh
i
c
h
h
a
s
in
c
re
a
se
d
th
e
n
e
e
d
to
p
r
o
m
o
te
a
n
d
stim
u
late
d
o
m
e
stic
t
o
u
rism
.
Th
is
re
se
a
rc
h
fo
c
u
se
s
o
n
re
c
o
m
m
e
n
d
i
n
g
to
u
rist
d
e
stin
a
ti
o
n
s
b
a
se
d
o
n
h
ist
o
rica
l
se
a
rc
h
d
a
ta
re
late
d
to
d
o
m
e
stic
to
u
rism
.
Th
e
stu
d
y
u
se
s
tec
h
n
i
q
u
e
s
li
k
e
t
e
rm
f
re
q
u
e
n
c
y
-
i
n
v
e
rse
d
o
c
u
m
e
n
t
fre
q
u
e
n
c
y
(
TF
-
IDF
)
we
ig
h
t
v
e
c
to
r
a
n
a
ly
sis
a
n
d
sim
il
a
rit
y
m
e
a
su
re
s
to
c
a
lcu
late
re
c
o
m
m
e
n
d
a
ti
o
n
sc
o
re
s.
Da
ta
wa
s
c
o
ll
e
c
ted
fr
o
m
v
a
rio
u
s
t
o
u
rism
we
b
sites
,
c
o
v
e
rin
g
d
e
stin
a
ti
o
n
s
a
c
ro
ss
a
l
l
6
3
p
ro
v
in
c
e
s
a
n
d
c
it
ies
in
Vie
tn
a
m
.
Ex
p
e
rime
n
ts
we
re
c
o
n
d
u
c
ted
u
si
n
g
t
h
re
e
a
p
p
r
o
a
c
h
e
s:
c
o
sin
e
sim
i
larity
,
t
h
e
b
ru
te
f
o
rc
e
a
lg
o
rit
h
m
,
a
n
d
lo
n
g
sh
o
rt
-
term
m
e
m
o
ry
(
LS
TM
)
fo
r
lo
n
g
-
tex
t
p
ro
c
e
ss
in
g
.
Th
e
re
su
lt
s
in
d
ica
t
e
th
a
t
sim
il
a
rit
y
-
b
a
se
d
m
e
th
o
d
s
p
ro
d
u
c
e
re
c
o
m
m
e
n
d
a
ti
o
n
s
t
h
a
t
c
lo
se
ly
m
a
tch
u
se
r
p
re
fe
re
n
c
e
s.
F
o
r
fu
ll
-
se
n
ten
c
e
q
u
e
ries
,
t
h
e
b
r
u
t
e
fo
rc
e
a
l
g
o
rit
h
m
d
e
li
v
e
rs
m
o
re
a
c
c
u
ra
te
re
su
lt
s,
w
h
il
e
LS
TM
p
ro
v
i
d
e
s
fa
ste
r
p
ro
c
e
ss
in
g
ti
m
e
s.
T
h
e
se
fin
d
in
g
s
o
ffe
r
b
u
sin
e
ss
e
s
m
u
lt
ip
le
stra
teg
ies
f
o
r
imp
ro
v
in
g
re
c
o
m
m
e
n
d
e
r
sy
ste
m
s
i
n
p
ra
c
ti
c
a
l
a
p
p
li
c
a
ti
o
n
s.
K
ey
w
o
r
d
s
:
Do
m
esti
c
to
u
r
is
t
His
to
r
ical
s
ea
r
ch
d
a
ta
Ma
ch
in
e
lear
n
in
g
R
ec
o
m
m
en
d
atio
n
s
y
s
tem
Similar
ity
m
ea
s
u
r
es
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
:
Ng
u
y
en
T
h
i H
o
i
Facu
lty
o
f
E
co
n
o
m
ic
I
n
f
o
r
m
at
io
n
Sy
s
tem
an
d
E
-
co
m
m
e
r
ce
,
T
h
u
o
n
g
m
ai
Un
iv
e
r
s
ity
No
.
7
9
,
H
o
T
u
n
g
Ma
u
Stre
et,
C
au
Giay
Dis
tr
ict,
Han
o
i,
Vietn
am
E
m
ail: h
o
in
t@
tm
u
.
ed
u
.
v
n
1.
I
NT
RO
D
UCT
I
O
N
W
ith
th
e
r
ap
id
d
ev
elo
p
m
en
t
o
f
in
f
o
r
m
atio
n
an
d
co
m
m
u
n
icatio
n
s
tech
n
o
lo
g
y
(
I
C
T
)
an
d
th
e
wid
esp
r
ea
d
av
ailab
ilit
y
o
f
th
e
in
ter
n
et,
u
s
er
s
ar
e
i
n
cr
ea
s
in
g
ly
r
ely
in
g
o
n
d
ig
ital
p
latf
o
r
m
s
,
s
u
ch
as
s
ea
r
ch
en
g
in
es
an
d
o
n
lin
e
en
ter
tain
m
en
t
s
er
v
ices,
to
ac
ce
s
s
a
wi
d
e
r
an
g
e
o
f
in
f
o
r
m
atio
n
a
n
d
u
tili
ties
.
T
h
is
d
ig
ital
tr
an
s
f
o
r
m
atio
n
h
as
s
ig
n
if
ican
t
ly
r
esh
ap
ed
c
o
n
s
u
m
er
b
eh
av
i
o
r
,
f
ac
ilit
atin
g
ea
s
ier
ac
ce
s
s
to
tr
av
el
in
f
o
r
m
atio
n
,
th
e
ab
ilit
y
to
co
m
p
ar
e
d
esti
n
atio
n
s
,
an
d
th
e
co
n
v
en
ien
c
e
o
f
b
o
o
k
in
g
tr
a
v
el
s
er
v
ices
with
ju
s
t
a
f
ew
click
s
[
1
]
–
[
4
]
.
T
o
u
r
is
m
r
em
ain
s
a
v
ital
en
g
in
e
o
f
g
lo
b
al
ec
o
n
o
m
ic
g
r
o
wth
.
Acc
o
r
d
in
g
to
th
e
W
o
r
ld
T
r
av
el
&
T
o
u
r
is
m
C
o
u
n
cil
(
W
T
T
C
)
[
5
]
,
th
e
tr
av
el
an
d
to
u
r
is
m
in
d
u
s
tr
y
co
n
t
r
ib
u
te
d
9
.
1
%
to
g
l
o
b
al
g
r
o
s
s
d
o
m
esti
c
p
r
o
d
u
ct
(
GDP)
in
2
0
2
3
.
I
n
ter
n
atio
n
al
to
u
r
is
m
ex
p
e
n
d
itu
r
es
in
cr
ea
s
ed
b
y
3
3
.
1
%,
r
ea
ch
in
g
USD
1
.
6
3
tr
illi
o
n
,
wh
ile
d
o
m
esti
c
ex
p
en
d
itu
r
es
r
o
s
e
b
y
1
8
%,
s
u
r
p
ass
in
g
USD
5
tr
illi
o
n
[
5
]
,
[
6
]
.
L
eisu
r
e
-
r
ela
ted
s
p
en
d
in
g
s
aw
a
g
r
o
wth
o
f
2
1
.
2
%,
an
d
b
u
s
in
e
s
s
tr
av
el
s
p
en
d
in
g
r
o
s
e
b
y
2
2
.
4
%,
r
ef
lectin
g
a
s
tr
o
n
g
p
o
s
t
-
p
an
d
em
ic
r
ec
o
v
er
y
[
5
]
,
[
6
]
.
I
n
ter
m
s
o
f
d
ir
ec
t
e
co
n
o
m
ic
im
p
ac
t,
th
e
tr
av
el
a
n
d
to
u
r
is
m
s
ec
to
r
a
d
d
ed
US
D
3
,
0
5
9
.
3
b
illi
o
n
t
o
g
lo
b
al
GDP
(
2
.
8
%),
p
r
im
ar
i
ly
d
r
iv
e
n
b
y
i
n
d
u
s
tr
ies
s
u
ch
as
h
o
s
p
itality
,
t
r
av
el
a
g
en
ci
es,
an
d
p
ass
en
g
er
tr
an
s
p
o
r
tatio
n
s
er
v
ices
[
6
]
,
[
7
]
.
Fro
m
2
0
2
4
to
2
0
3
4
,
t
h
e
s
ec
to
r
’
s
co
n
tr
i
b
u
tio
n
is
p
r
o
jecte
d
t
o
g
r
o
w
at
a
n
a
n
n
u
al
r
ate
o
f
3
.
7
%,
r
ea
ch
i
n
g
USD
4
,
8
6
5
.
7
b
illi
o
n
(
3
.
5
% o
f
GD
P)
[
5
]
–
[
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
meth
o
d
cla
s
s
ifyin
g
th
e
d
o
me
s
tic
to
u
r
is
t d
esti
n
a
tio
n
b
a
s
e
s
imila
r
ity
mea
s
u
r
in
g
(
N
g
u
ye
n
Th
i H
o
i
)
741
I
n
Vietn
am
,
th
e
to
u
r
is
m
in
d
u
s
t
r
y
h
as d
em
o
n
s
tr
ated
im
p
r
ess
iv
e
p
o
s
t
-
p
an
d
em
ic
r
ec
o
v
er
y
,
esp
ec
ially
in
th
e
d
o
m
esti
c
s
ec
to
r
.
Acc
o
r
d
in
g
to
t
h
e
Gen
e
r
al
Statis
tics
Of
f
ice
o
f
Vietn
am
[
8
]
,
in
ter
n
ati
o
n
al
to
u
r
is
t
ar
r
iv
als
r
ea
ch
ed
1
2
.
6
m
illi
o
n
in
2
0
2
3
,
ap
p
r
o
x
im
ately
3
.
5
tim
es
h
ig
h
er
th
an
in
2
0
2
2
,
r
ec
o
v
er
i
n
g
to
7
0
%
o
f
p
r
e
-
p
an
d
em
ic
lev
els
[
8
]
,
[
9
]
.
T
h
is
s
u
r
p
ass
ed
Asi
a’
s
av
er
ag
e
r
ec
o
v
er
y
r
ate
o
f
6
5
%.
Do
m
esti
c
to
u
r
is
m
was
ev
e
n
m
o
r
e
r
o
b
u
s
t,
r
ec
o
r
d
in
g
1
1
0
m
illi
o
n
d
o
m
esti
c
tr
ip
s
in
2
0
2
3
[
9
]
.
I
n
f
r
astru
ctu
r
e
im
p
r
o
v
em
en
ts
,
en
h
an
ce
d
s
er
v
ice
q
u
ality
,
an
d
s
tr
ateg
ic
in
v
estme
n
t in
cu
ltu
r
al
p
r
eser
v
atio
n
h
av
e
co
n
tr
ib
u
te
d
to
th
is
g
r
o
wth
[
8
]
–
[
1
1
]
.
T
h
is
g
r
o
wth
h
as g
en
er
ated
s
ig
n
if
ican
t
ec
o
n
o
m
ic
s
p
illo
v
er
e
f
f
ec
ts
ac
r
o
s
s
v
ar
io
u
s
in
d
u
s
tr
ies,
in
clu
d
in
g
h
o
s
p
itality
,
f
o
o
d
a
n
d
b
ev
e
r
a
g
e
s
er
v
ices,
tr
an
s
p
o
r
tatio
n
,
an
d
r
etail.
I
n
ad
d
itio
n
,
cu
lt
u
r
al
f
esti
v
als
an
d
s
ig
h
ts
ee
in
g
ac
tiv
ities
co
n
tr
ib
u
te
to
th
e
d
ev
elo
p
m
en
t
o
f
th
e
cr
ea
tiv
e
an
d
e
n
ter
tain
m
e
n
t
in
d
u
s
tr
ies
wh
il
e
s
u
p
p
o
r
tin
g
lo
ca
l
b
u
s
in
ess
es
an
d
tr
ad
itio
n
al
cr
af
t
v
illag
es
[
1
2
]
–
[
1
5
]
.
T
o
u
r
is
ts
n
o
w
b
e
n
ef
it
f
r
o
m
r
ea
l
-
tim
e
in
f
o
r
m
atio
n
ac
ce
s
s
,
ea
s
y
p
r
ice
co
m
p
ar
is
o
n
s
,
a
n
d
in
s
tan
t
b
o
o
k
in
g
f
ea
tu
r
es.
Ho
wev
er
,
th
e
v
o
lu
m
e
o
f
av
ailab
le
in
f
o
r
m
atio
n
h
as
b
ec
o
m
e
o
v
er
wh
elm
in
g
,
o
f
te
n
h
in
d
e
r
in
g
tr
av
eler
s
f
r
o
m
ef
f
icie
n
tly
id
en
t
if
y
in
g
d
esti
n
a
tio
n
s
th
at
alig
n
with
th
eir
p
r
ef
er
e
n
c
es
[
1
]
,
[
2
]
,
[
1
6
]
–
[
2
0
]
.
T
o
ad
d
r
ess
th
is
,
to
u
r
is
m
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
(
T
R
Ss
)
h
av
e
b
ec
o
m
e
in
cr
ea
s
in
g
ly
im
p
o
r
tan
t.
T
h
ese
s
y
s
tem
s
ap
p
ly
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es to
an
al
y
ze
u
s
er
b
eh
av
i
o
r
,
h
is
to
r
ical
d
ata,
an
d
p
r
e
f
er
en
ce
s
to
o
f
f
er
p
er
s
o
n
alize
d
tr
av
el
s
u
g
g
esti
o
n
s
.
B
y
u
tili
zin
g
b
o
th
s
tatic
an
d
d
y
n
am
ic
(
r
ea
l
-
tim
e
r
ev
i
ews,
s
o
cial
m
ed
ia,
an
d
r
atin
g
s
)
in
f
o
r
m
atio
n
,
T
R
Ss
ca
n
d
eliv
er
co
n
tex
t
-
awa
r
e
r
ec
o
m
m
en
d
atio
n
s
th
at
im
p
r
o
v
e
u
s
er
s
atis
f
ac
tio
n
[
1
]
–
[
3
]
,
[
1
3
]
,
[
1
6
]
–
[
1
9
]
,
[
2
1
]
,
[
2
2
]
.
Su
c
h
s
y
s
tem
s
ar
e
alr
ea
d
y
in
u
s
e
ac
r
o
s
s
v
ar
io
u
s
i
n
d
u
s
tr
ies
in
clu
d
in
g
e
-
co
m
m
er
ce
(
Am
az
o
n
)
,
s
tr
ea
m
in
g
(
Netf
lix
a
n
d
Yo
u
T
u
b
e
)
,
r
ec
r
u
itm
en
t,
a
n
d
to
u
r
is
m
[
2
1
]
–
[
2
4
]
.
Desp
ite
th
e
ec
o
n
o
m
ic
p
o
te
n
tial
o
f
to
u
r
is
m
,
p
ar
ticip
atio
n
am
o
n
g
lo
ca
l
co
m
m
u
n
ities
in
to
u
r
i
sm
-
r
elate
d
ac
tiv
ities
r
em
ain
s
lim
ited
[
2
]
,
[
1
2
]
–
[
1
4
]
,
[
2
5
]
.
Mo
s
t
Vietn
am
ese
tr
av
el
web
s
ites
p
r
o
v
id
e
b
asic
lis
ts
o
f
a
ttra
ctio
n
s
,
b
u
t
lac
k
p
er
s
o
n
alize
d
r
ec
o
m
m
en
d
atio
n
s
tailo
r
ed
to
in
d
iv
id
u
al
b
e
h
av
io
r
s
o
r
p
r
ev
io
u
s
in
ter
ac
tio
n
s
.
T
h
is
lead
s
to
d
ec
is
io
n
f
atig
u
e
a
n
d
in
ef
f
icien
t tr
av
el
p
lan
n
in
g
[
1
0
]
,
[
1
3
]
–
[
1
5
]
,
[
2
5
]
–
[
2
8
]
.
T
o
o
v
er
co
m
e
th
ese
lim
itatio
n
s
,
th
is
s
tu
d
y
p
r
o
p
o
s
es
th
e
d
ev
elo
p
m
en
t
o
f
a
p
er
s
o
n
alize
d
T
R
S
tai
lo
r
ed
to
th
e
d
o
m
esti
c
tr
av
el
m
ar
k
et
in
Vietn
am
.
B
y
lev
er
ag
i
n
g
u
s
er
s
'
b
r
o
wsi
n
g
b
e
h
av
io
r
an
d
s
ea
r
ch
p
atter
n
s
,
th
e
s
y
s
tem
will
s
u
g
g
est
less
er
-
k
n
o
wn
d
esti
n
atio
n
s
t
h
at
alig
n
wi
th
in
d
iv
i
d
u
al
p
r
ef
er
e
n
ce
s
.
T
h
i
s
n
o
t
o
n
ly
en
h
a
n
ce
s
th
e
u
s
er
ex
p
er
ien
ce
b
u
t
also
p
r
o
m
o
tes
eq
u
itab
le
to
u
r
is
m
d
ev
elo
p
m
en
t
ac
r
o
s
s
r
eg
io
n
s
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
in
teg
r
ates
ad
v
an
ce
d
co
m
p
u
tat
io
n
al
tech
n
iq
u
es,
in
clu
d
i
n
g
c
o
s
in
e
s
im
ilar
ity
,
b
r
u
te
f
o
r
ce
m
atch
in
g
,
a
n
d
l
o
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
m
o
d
els
[
1
]
,
[
1
8
]
,
[
1
9
]
,
[
2
6
]
,
[
2
7
]
,
[
2
9
]
–
[
3
1
]
.
T
h
ese
tech
n
i
q
u
es
ar
e
i
m
p
lem
en
ted
o
n
a
p
r
o
to
ty
p
e
web
s
ite
to
ass
ess
r
ec
o
m
m
en
d
ati
o
n
ac
c
u
r
ac
y
a
n
d
u
s
er
r
ele
v
an
ce
.
B
y
in
teg
r
atin
g
th
ese
alg
o
r
ith
m
s
,
th
e
s
y
s
tem
aim
s
to
o
f
f
er
m
o
r
e
ac
cu
r
ate,
r
ea
l
-
tim
e,
a
n
d
in
ter
est
-
b
ased
tr
av
el
s
u
g
g
esti
o
n
s
,
w
h
ile
co
n
tr
i
b
u
tin
g
to
t
h
e
v
is
ib
ilit
y
an
d
ec
o
n
o
m
ic
u
p
lift
o
f
u
n
d
er
ex
p
lo
r
ed
d
esti
n
atio
n
s
ac
r
o
s
s
Vietn
am
.
T
h
e
a
r
t
i
cl
e
i
n
cl
u
d
e
s
t
h
e
f
o
ll
o
w
i
n
g
s
ec
t
i
o
n
s
:
p
r
o
b
l
e
m
s
ta
t
em
e
n
t
,
r
e
l
at
e
d
w
o
r
k
s
,
r
e
s
e
a
r
c
h
m
o
d
e
l
,
r
es
e
a
r
c
h
r
es
u
l
ts
,
a
n
d
s
o
m
e
i
m
p
li
c
a
ti
o
n
s
f
o
r
l
o
c
a
l
i
ti
e
s
w
i
t
h
m
a
n
y
t
o
u
r
is
t
d
es
t
in
a
t
i
o
n
s
i
n
Vi
e
t
n
a
m
.
2.
RE
L
AT
E
D
WO
RK
R
ec
o
m
m
en
d
er
s
y
s
tem
s
f
o
r
d
o
m
esti
c
tr
av
el
d
esti
n
atio
n
s
h
av
e
em
er
g
ed
as
a
v
ital
to
o
l
in
t
h
e
d
ig
ital
tr
an
s
f
o
r
m
atio
n
o
f
th
e
to
u
r
is
m
in
d
u
s
tr
y
,
o
f
f
er
in
g
p
er
s
o
n
al
ized
tr
av
el
s
u
g
g
esti
o
n
s
b
ased
o
n
in
d
iv
id
u
al
u
s
er
p
r
ef
er
en
ce
s
.
T
h
ese
s
y
s
tem
s
a
im
to
g
en
er
ate
tailo
r
ed
lis
ts
o
f
to
u
r
is
t
s
ites
th
at
alig
n
with
u
s
er
ex
p
ec
tatio
n
s
,
th
er
eb
y
im
p
r
o
v
in
g
d
ec
is
io
n
-
m
ak
in
g
an
d
u
s
er
s
atis
f
ac
tio
n
.
A
s
t
r
a
v
e
l
e
r
s
i
n
c
r
e
as
i
n
g
l
y
d
em
a
n
d
c
o
n
v
e
n
i
e
n
t
a
n
d
c
u
s
t
o
m
i
z
e
d
p
l
a
n
n
i
n
g
s
o
l
u
t
i
o
n
s
,
p
a
r
t
i
c
u
l
a
r
l
y
i
n
t
h
e
p
o
s
t
-
p
a
n
d
e
m
i
c
c
o
n
t
e
x
t
,
t
o
u
r
is
m
r
e
c
o
m
m
e
n
d
e
r
s
y
s
t
e
m
s
h
a
v
e
b
e
c
o
m
e
w
i
d
e
l
y
a
d
o
p
t
e
d
n
o
t
o
n
ly
i
n
V
i
e
t
n
a
m
b
u
t
g
l
o
b
a
ll
y
[
1
]
–
[
4
]
,
[
1
2
]
,
[
1
3
]
,
[
1
5
]
,
[
1
7
]
,
[
2
0
]
,
[
2
1
]
,
[
2
9
]
–
[
3
3
]
.
C
u
r
r
en
t
r
esear
ch
in
tr
av
el
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
is
ty
p
ically
s
tr
u
ctu
r
ed
ar
o
u
n
d
two
m
ain
m
eth
o
d
o
l
o
g
ical
a
p
p
r
o
ac
h
es.
T
h
e
f
ir
s
t
a
p
p
r
o
ac
h
in
v
o
lv
es
clu
s
ter
in
g
to
u
r
is
t
d
esti
n
atio
n
s
b
ased
o
n
s
h
a
r
ed
attr
ib
u
tes
s
u
ch
as
n
atu
r
al
l
an
d
s
ca
p
es
(
b
ea
ch
an
d
m
o
u
n
tain
s
)
,
cu
ltu
r
al
an
d
h
is
to
r
ical
v
alu
e,
o
r
u
r
b
a
n
ex
p
er
ien
ce
s
[
3
]
,
[
4
]
,
[
1
2
]
,
[
1
3
]
,
[
1
5
]
,
[
1
8
]
,
[
1
9
]
,
[
2
6
]
,
[
2
9
]
–
[
3
6
]
.
T
h
ese
ca
teg
o
r
izatio
n
s
ar
e
ac
h
iev
ed
u
s
in
g
u
n
s
u
p
er
v
is
ed
lear
n
in
g
tech
n
iq
u
es,
allo
win
g
th
e
s
y
s
tem
to
c
lass
if
y
d
esti
n
atio
n
s
in
to
m
ea
n
in
g
f
u
l
g
r
o
u
p
s
th
at
r
ef
lect
u
s
er
p
r
e
f
er
en
ce
s
.
Fo
r
ex
am
p
le,
[
1
]
,
[
2
]
,
[
2
0
]
,
[
3
0
]
,
[
3
4
]
d
em
o
n
s
tr
ated
th
e
ap
p
licatio
n
o
f
K
-
m
ea
n
s
o
r
class
if
icatio
n
-
b
ased
ass
o
ciatio
n
(
C
B
A)
-
f
u
zz
y
alg
o
r
ith
m
s
f
o
r
d
esti
n
atio
n
clu
s
ter
in
g
,
y
ield
i
n
g
p
r
o
m
is
in
g
r
esu
lts
in
au
to
m
ate
d
r
ec
o
m
m
e
n
d
atio
n
s
.
Similar
ly
,
[
2
3
]
,
[
2
4
]
,
[
3
5
]
ap
p
lied
s
u
p
p
o
r
t
v
ec
to
r
m
a
ch
in
es
(
SVM)
a
n
d
B
ay
esian
alg
o
r
ith
m
s
to
an
al
y
ze
lar
g
e
-
s
ca
le
d
atasets
d
er
i
v
ed
f
r
o
m
u
s
er
b
eh
av
i
o
r
an
d
s
u
r
v
ey
f
ee
d
b
ac
k
,
en
ab
lin
g
im
p
r
o
v
e
d
s
eg
m
en
tati
o
n
o
f
u
s
er
tr
av
el
i
n
ten
tio
n
s
.
Sig
n
if
ican
tly
,
[
2
]
a
n
d
[
2
3
]
in
tr
o
d
u
ce
d
an
in
n
o
v
ativ
e
d
ee
p
lea
r
n
in
g
f
r
am
ewo
r
k
b
ased
o
n
E
f
f
icien
tNet
-
lite,
o
p
tim
ized
f
o
r
m
o
b
ile
d
ep
lo
y
m
en
t,
ac
h
iev
in
g
o
v
er
8
0
%
u
s
er
s
atis
f
ac
tio
n
with
m
o
r
e
th
an
5
0
%
o
f
r
ec
o
m
m
en
d
atio
n
s
m
ee
tin
g
ex
p
ec
tatio
n
s
.
T
h
is
m
o
d
el
u
n
d
er
s
co
r
es
th
e
p
o
ten
tial
o
f
d
ee
p
lea
r
n
in
g
i
n
en
h
a
n
cin
g
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
,
p
ar
ticu
lar
ly
in
r
ea
l
-
tim
e
an
d
u
s
er
-
ce
n
ter
ed
m
o
b
ile
ap
p
lica
tio
n
s
.
T
h
e
s
ec
o
n
d
ap
p
r
o
ac
h
f
o
c
u
s
es
o
n
s
u
p
er
v
i
s
ed
an
d
s
em
i
-
s
u
p
er
v
is
ed
lear
n
i
n
g
m
eth
o
d
s
f
o
r
g
en
e
r
atin
g
r
ec
o
m
m
en
d
atio
n
s
[
1
]
–
[
4
]
,
[
1
6
]
,
[
2
0
]
–
[
2
4
]
,
[
2
6
]
,
[
2
9
]
–
[
3
3
]
,
[
3
5
]
,
[
3
6
]
.
T
h
ese
m
o
d
els
ar
e
tr
ain
ed
o
n
e
x
ten
s
iv
e
lab
eled
d
atasets
to
o
p
tim
ize
th
e
r
elev
a
n
ce
an
d
a
cc
u
r
ac
y
o
f
d
esti
n
atio
n
s
u
g
g
esti
o
n
s
.
Fo
r
in
s
tan
ce
,
[
3
5
]
ev
al
u
ated
s
ix
m
ac
h
in
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
3
,
Sep
tem
b
er
20
25
:
7
40
-
7
50
742
lear
n
in
g
al
g
o
r
ith
m
s
n
aïv
e
B
ay
es
(
NB
)
,
SVM,
lo
g
is
tic
r
eg
r
es
s
io
n
,
n
eu
r
al
n
etwo
r
k
s
,
d
ec
is
io
n
tr
ee
s
,
an
d
r
a
n
d
o
m
f
o
r
ests
o
n
to
u
r
is
m
d
ata,
wi
th
SVM,
lo
g
is
tic
r
eg
r
ess
io
n
,
an
d
n
e
u
r
al
n
etwo
r
k
s
d
em
o
n
s
tr
atin
g
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
in
p
r
ed
ictin
g
u
s
er
p
r
ef
e
r
en
ce
s
.
Fu
r
t
h
er
m
o
r
e
,
[
2
9
]
co
m
p
a
r
ed
Do
c2
Vec
em
b
ed
d
in
g
s
with
tr
ad
itio
n
al
tech
n
iq
u
es
s
u
ch
as
item
-
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KN
N)
an
d
n
eu
r
al
co
llab
o
r
ativ
e
f
ilter
in
g
,
f
in
d
in
g
th
at
Do
c2
Vec
s
ig
n
if
ican
tly
o
u
tp
er
f
o
r
m
ed
c
o
n
v
e
n
tio
n
al
m
o
d
els,
p
ar
ticu
lar
ly
in
h
a
n
d
lin
g
s
p
ar
s
e
d
atasets
.
B
u
ild
in
g
o
n
th
ese
f
o
u
n
d
ati
o
n
s
,
o
u
r
s
tu
d
y
p
r
o
p
o
s
es
a
p
er
s
o
n
alize
d
tr
av
el
r
ec
o
m
m
e
n
d
er
s
y
s
tem
d
esig
n
ed
s
p
ec
if
ically
f
o
r
th
e
Vietn
am
ese
d
o
m
esti
c
to
u
r
is
m
co
n
tex
t.
T
h
is
s
y
s
tem
an
aly
ze
s
u
s
er
in
p
u
t
,
s
u
c
h
as
s
ea
r
ch
q
u
er
ies
an
d
b
r
o
wsi
n
g
p
atter
n
s
,
an
d
co
m
p
a
r
es
th
em
with
s
tr
u
ctu
r
ed
d
esti
n
atio
n
p
r
o
f
iles
to
g
en
er
ate
ac
cu
r
ate
an
d
r
elev
an
t
r
ec
o
m
m
en
d
atio
n
s
.
T
o
f
ac
ilit
ate
th
is
,
w
e
u
tili
ze
N
-
g
r
am
an
aly
s
is
an
d
a
W
ik
ip
ed
ia
-
b
ased
d
ictio
n
ar
y
to
ex
tr
ac
t
s
em
an
t
ic
f
e
atu
r
es
f
r
o
m
u
s
er
in
p
u
t
an
d
d
esti
n
atio
n
m
etad
ata.
T
o
f
u
r
th
er
e
n
h
an
ce
r
ec
o
m
m
en
d
atio
n
ac
c
u
r
ac
y
,
we
ap
p
ly
co
s
in
e
s
im
ilar
ity
an
d
P
ea
r
s
o
n
co
r
r
elatio
n
to
m
ea
s
u
r
e
alig
n
m
en
t
b
etwe
en
u
s
er
in
ter
ests
an
d
d
esti
n
atio
n
c
h
ar
ac
ter
is
tics
.
E
x
p
an
d
i
n
g
th
e
d
ataset
is
an
o
th
er
k
e
y
o
b
jectiv
e
to
im
p
r
o
v
e
s
y
s
tem
r
o
b
u
s
tn
ess
an
d
ac
c
u
r
ac
y
.
B
y
in
clu
d
in
g
m
o
r
e
d
iv
er
s
e
u
s
er
p
r
o
f
iles
an
d
r
eg
i
o
n
al
d
esti
n
atio
n
d
ata,
th
e
s
y
s
tem
’
s
ad
ap
tab
ilit
y
ca
n
b
e
e
n
h
an
ce
d
.
B
ey
o
n
d
to
u
r
is
m
,
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
h
o
ld
s
p
o
ten
ti
al
f
o
r
cr
o
s
s
-
d
o
m
ai
n
ap
p
licat
io
n
s
in
ed
u
ca
tio
n
,
en
ter
tain
m
en
t,
a
n
d
h
ea
lth
ca
r
e,
wh
er
e
p
er
s
o
n
alize
d
in
f
o
r
m
ati
o
n
d
eliv
er
y
is
eq
u
ally
v
alu
ab
le
.
3.
P
RO
P
O
SE
D
RE
SE
ARCH
M
O
DE
L
3
.
1
.
P
r
o
po
s
ed
m
o
del
T
h
e
p
r
o
b
le
m
o
f
s
u
g
g
esti
n
g
d
o
m
esti
c
to
u
r
is
t
d
esti
n
atio
n
s
c
an
b
e
b
r
ief
ly
d
escr
ib
e
d
as
b
ased
o
n
th
e
u
s
er
'
s
r
eq
u
est,
th
e
s
y
s
tem
p
r
o
v
id
es
s
u
g
g
esti
o
n
s
as
a
lis
t
o
f
to
u
r
is
t
d
esti
n
atio
n
s
th
at
ar
e
c
o
n
s
id
er
ed
clo
s
est
to
th
e
u
s
er
'
s
r
eq
u
ests
.
Fro
m
th
is
p
r
o
b
lem
,
th
e
r
esear
ch
p
r
o
p
o
s
e
d
a
m
o
d
el
as f
o
llo
ws:
−
I
n
p
u
t:
q
u
esti
o
n
o
r
q
u
e
r
y
with
a
lis
t o
f
k
ey
wo
r
d
s
th
at
d
escr
ib
e
th
e
u
s
er
'
s
wis
h
es
.
−
Ou
tp
u
t:
a
l
is
t o
f
to
u
r
is
t d
esti
n
a
tio
n
s
clo
s
e
to
th
e
u
s
er
'
s
wis
h
es
.
−
Per
f
o
r
m
:
i)
s
tep
1
:
a
n
aly
ze
t
h
e
q
u
esti
o
n
o
r
q
u
er
y
;
ii)
s
tep
2
:
c
o
m
p
ar
e
b
ased
o
n
s
im
ilar
ity
b
etwe
en
th
e
q
u
esti
o
n
a
n
d
d
atab
ase
b
y
wei
g
h
t
o
r
b
ased
o
n
tr
ai
n
in
g
;
iii)
s
tep
3
:
p
er
f
o
r
m
ev
alu
atio
n
an
d
s
o
r
tin
g
b
ase
d
o
n
s
im
ilar
ity
r
esu
lts
; a
n
d
iv
)
s
t
ep
4
:
p
r
o
v
id
e
a
lis
t o
f
lo
ca
tio
n
s
.
3
.
2
.
Sim
ila
ri
t
y
m
ea
s
ures a
nd
co
rr
ela
t
io
n
T
o
o
p
e
r
atio
n
alize
th
e
p
r
o
p
o
s
ed
r
esear
ch
m
o
d
el,
a
co
m
p
r
e
h
en
s
iv
e,
m
u
lti
-
s
tag
e
m
eth
o
d
o
lo
g
y
was
ad
o
p
ted
.
T
h
is
ap
p
r
o
ac
h
in
teg
r
ates
d
escr
ip
tiv
e
d
ata
an
aly
s
i
s
with
ad
v
an
ce
d
tex
t
n
o
r
m
al
izatio
n
tech
n
iq
u
es,
tailo
r
ed
f
o
r
b
o
t
h
s
tr
u
ctu
r
ed
a
n
d
u
n
s
tr
u
ctu
r
ed
d
ata
with
in
to
u
r
is
m
s
y
s
tem
s
.
T
h
e
p
r
im
ar
y
o
b
jectiv
e
was
to
co
n
s
tr
u
ct
a
r
o
b
u
s
t
r
ec
o
m
m
en
d
atio
n
ar
ch
itectu
r
e
ca
p
ab
le
o
f
a
cc
u
r
ately
in
ter
p
r
etin
g
u
s
er
-
g
e
n
er
ated
q
u
er
ies
an
d
ef
f
ec
tiv
ely
m
atch
in
g
th
em
t
o
r
elev
an
t d
esti
n
atio
n
m
etad
ata.
T
h
e
in
itial
p
h
ase
in
v
o
lv
ed
r
i
g
o
r
o
u
s
p
r
e
p
r
o
ce
s
s
in
g
o
f
te
x
tu
al
d
ata
c
o
llected
f
r
o
m
v
ar
io
u
s
s
o
u
r
ce
s
,
in
clu
d
in
g
d
esti
n
atio
n
d
escr
ip
tio
n
s
,
u
s
er
r
ev
iews,
an
d
b
eh
a
v
i
o
r
al
lo
g
s
.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
en
co
m
p
ass
ed
to
k
en
izatio
n
,
lo
wer
ca
s
in
g
,
s
t
o
p
-
wo
r
d
r
em
o
v
al,
a
n
d
l
em
m
atiza
tio
n
,
aim
in
g
to
n
o
r
m
aliz
e
lin
g
u
is
tic
f
ea
tu
r
es
ac
r
o
s
s
d
atasets
.
Su
b
s
eq
u
en
tly
,
th
e
clea
n
ed
tex
tu
al
d
ata
wa
s
tr
an
s
f
o
r
m
ed
in
to
n
u
m
er
ical
f
o
r
m
u
s
in
g
SVM
,
p
r
im
ar
ily
t
h
r
o
u
g
h
ter
m
f
r
eq
u
en
cy
-
in
v
e
r
s
e
d
o
c
u
m
en
t
f
r
e
q
u
en
cy
(
T
F
-
I
DF)
weig
h
tin
g
s
ch
em
es.
T
F
-
I
DF
h
as
b
ee
n
s
h
o
wn
t
o
b
e
ef
f
ec
tiv
e
i
n
r
ed
u
cin
g
n
o
is
e
an
d
em
p
h
asizin
g
s
em
an
tically
s
ig
n
if
ican
t
ter
m
s
in
s
p
ar
s
e
tex
tu
al
d
atasets
[
1
8
]
,
[
1
9
]
,
[
2
7
]
,
[
2
9
]
,
[
3
7
]
–
[
4
0
]
.
C
alcu
late
wei
g
h
t
i
s
ca
lcu
lated
b
ased
o
n
k
ey
wo
r
d
T
F,
th
e
I
DF,
a
n
d
th
e
T
F×I
DF is ca
l
cu
lated
as
(
1
)
.
=
{
∗
=
(
1
+
(
)
)
∗
(
1
+
)
≥
1
0
=
0
(
1
)
W
h
er
e
is
th
e
weig
h
t o
f
in
tex
t
,
is
th
e
f
r
eq
u
en
cy
o
f
a
p
p
ea
r
a
n
ce
o
f
in
tex
t
.
T
h
is
tr
an
s
f
o
r
m
atio
n
e
n
ab
les
th
e
ap
p
licatio
n
o
f
v
ar
io
u
s
co
m
p
u
tatio
n
al
tech
n
i
q
u
es
s
u
ch
as
co
s
in
e
s
im
ilar
ity
,
SVM,
an
d
K
-
m
ea
n
s
clu
s
ter
in
g
,
wh
ich
o
p
e
r
ate
ef
f
ec
tiv
ely
i
n
h
ig
h
-
d
im
e
n
s
io
n
al
f
ea
tu
r
e
s
p
ac
es
[
1
7
]
–
[
1
9
]
,
[
2
6
]
,
[
2
7
]
,
[
3
0
]
–
[
3
6
]
,
[
4
0
]
.
T
o
id
e
n
tify
s
em
an
tic
alig
n
m
en
t
b
etwe
en
u
s
er
q
u
er
ies
an
d
d
esti
n
atio
n
p
r
o
f
iles
,
th
e
co
s
in
e
s
im
ilar
ity
m
etr
ic
was
em
p
lo
y
ed
.
T
h
is
m
ea
s
u
r
e
ev
alu
ates
t
h
e
c
o
s
in
e
o
f
th
e
a
n
g
le
b
etwe
en
two
n
o
n
-
ze
r
o
v
ec
to
r
s
in
a
m
u
lti
-
d
im
e
n
s
io
n
al
s
p
ac
e,
m
ak
in
g
it
h
ig
h
ly
e
f
f
ec
tiv
e
in
tex
t
m
i
n
in
g
an
d
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
.
Su
ch
cr
o
s
s
-
d
o
m
ai
n
ad
ap
tab
il
ity
is
m
ad
e
p
o
s
s
ib
le
b
y
th
e
s
y
s
tem
’
s
r
elian
ce
o
n
g
en
e
r
alize
d
d
ee
p
lear
n
in
g
an
d
in
f
o
r
m
atio
n
r
etr
i
ev
al
tech
n
iq
u
es,
r
ath
er
th
a
n
d
o
m
ain
-
s
p
ec
if
ic
r
u
les o
r
h
ar
d
c
o
d
ed
lo
g
ic.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
meth
o
d
cla
s
s
ifyin
g
th
e
d
o
me
s
tic
to
u
r
is
t d
esti
n
a
tio
n
b
a
s
e
s
imila
r
ity
mea
s
u
r
in
g
(
N
g
u
ye
n
Th
i H
o
i
)
743
(
⃗
,
⃗
⃗
)
=
⃗
×
⃗
⃗
|
|
×
|
|
(
2
)
I
n
wh
ich
:
⃗
⃗
⃗
⃗
×
⃗
⃗
is
th
e
d
o
t
p
r
o
d
u
ct
o
f
two
v
ec
to
r
s
; |
A|
,
|
B
|
is
th
e
m
ag
n
itu
d
e
o
f
th
e
two
v
ec
to
r
s
.
C
o
s
in
e
s
im
ilar
ity
i
s
p
ar
ticu
lar
ly
ad
v
an
tag
e
o
u
s
f
o
r
h
ig
h
-
d
im
en
s
io
n
al
T
F
-
I
DF
v
ec
to
r
s
,
wh
er
e
tr
ad
itio
n
al
d
is
tan
ce
m
etr
ics
lik
e
E
u
clid
ea
n
d
is
tan
ce
ar
e
less
r
eliab
le
d
u
e
to
th
e
cu
r
s
e
o
f
d
im
en
s
io
n
ality
[
1
7
]
,
[
2
7
]
,
[
3
1
]
,
[
3
5
]
,
[
4
0
]
.
A
b
r
u
t
e
f
o
r
ce
alg
o
r
ith
m
was
also
i
m
p
lem
en
ted
to
s
er
v
e
as
a
b
a
s
elin
e
m
eth
o
d
.
T
h
is
ap
p
r
o
ac
h
ex
h
au
s
tiv
ely
co
m
p
ar
es
ea
ch
u
s
er
p
r
o
f
ile
v
ec
to
r
with
all
av
ailab
le
d
esti
n
ati
o
n
v
ec
to
r
s
.
W
h
ile
co
m
p
u
tatio
n
ally
i
n
ten
s
iv
e,
b
r
u
te
f
o
r
ce
en
s
u
r
es
m
ax
im
u
m
m
atch
in
g
p
r
ec
is
io
n
,
m
ak
in
g
it
a
u
s
ef
u
l
b
en
ch
m
a
r
k
f
o
r
ev
al
u
a
tin
g
m
o
r
e
s
ca
lab
le
a
lg
o
r
ith
m
s
[
2
]
,
[
1
7
]
,
[
2
5
]
,
[
3
6
]
.
I
n
s
m
aller
d
atasets
o
r
co
n
tr
o
lled
ex
p
er
im
e
n
tal
s
ce
n
ar
i
o
s
,
b
r
u
te
f
o
r
ce
m
eth
o
d
s
ar
e
h
ig
h
ly
in
ter
p
r
etab
le
an
d
o
f
t
en
o
u
tp
er
f
o
r
m
m
o
r
e
co
m
p
lex
m
o
d
els
in
ter
m
s
o
f
r
aw
ac
cu
r
ac
y
.
T
o
c
ap
tu
r
e
th
e
tem
p
o
r
al
an
d
c
o
n
tex
tu
al
d
y
n
am
ics
o
f
u
s
er
b
eh
a
v
io
r
,
a
n
L
STM
n
etwo
r
k
,
a
v
ar
ian
t
o
f
r
ec
u
r
r
en
t n
eu
r
al
n
etwo
r
k
s
(
R
NNs),
was
in
teg
r
ated
in
t
o
th
e
r
ec
o
m
m
en
d
atio
n
en
g
in
e.
L
STM
n
etwo
r
k
s
ar
e
p
ar
ticu
lar
ly
well
-
s
u
ited
f
o
r
s
eq
u
en
ce
m
o
d
elin
g
d
u
e
to
th
eir
a
b
ilit
y
to
m
ain
tain
lo
n
g
-
ter
m
d
e
p
en
d
en
cies
v
ia
g
ated
m
ec
h
an
is
m
s
[
1
]
,
[
2
]
,
[
1
6
]
–
[
1
9
]
,
[
3
9
]
.
T
h
e
L
STM
m
o
d
el
u
s
ed
in
th
is
s
tu
d
y
co
m
p
r
is
es
th
r
ee
k
e
y
g
ates:
i)
f
o
r
g
et
g
ate
:
f
ilter
s
ir
r
elev
an
t
in
f
o
r
m
atio
n
f
r
o
m
t
h
e
p
r
ev
io
u
s
ce
ll
s
tate;
ii)
i
n
p
u
t
g
ate:
in
teg
r
ates
n
ew
in
p
u
t
in
t
o
th
e
cu
r
r
e
n
t
s
tate;
an
d
iii)
o
u
tp
u
t
g
ate:
d
eter
m
i
n
es
wh
ich
in
f
o
r
m
atio
n
co
n
tr
i
b
u
tes
t
o
th
e
o
u
tp
u
t.
T
h
is
ar
ch
itectu
r
e
en
ab
les
th
e
s
y
s
tem
to
d
is
tin
g
u
is
h
b
etwe
en
s
h
o
r
t
-
ter
m
an
d
lo
n
g
-
ter
m
u
s
er
p
r
ef
er
en
ce
s
(
e.
g
.
,
tem
p
o
r
ar
y
in
ter
est
in
b
ea
c
h
r
eso
r
ts
v
s
.
co
n
s
is
ten
t p
r
ef
er
en
ce
f
o
r
h
is
to
r
ical
lan
d
m
ar
k
s
)
[
1
3
]
,
[
2
1
]
,
[
2
3
]
,
[
2
5
]
,
[
2
6
]
,
[
2
9
]
,
[
3
0
]
,
[
3
7
]
–
[
3
9
]
.
T
o
o
v
er
c
o
m
e
th
e
s
p
ar
s
ity
an
d
h
ig
h
d
im
en
s
io
n
ality
p
r
o
b
lem
s
in
h
er
en
t
in
T
F
-
I
DF
m
atr
ices,
en
h
an
ce
m
e
n
ts
to
th
e
co
s
in
e
s
i
m
ilar
ity
m
ea
s
u
r
e
wer
e
ad
o
p
te
d
.
T
h
ese
in
clu
d
ed
ad
a
p
tiv
e
ter
m
weig
h
tin
g
,
s
o
f
t
co
s
in
e
s
im
ilar
ity
,
an
d
lo
ca
l
s
im
ilar
ity
th
r
esh
o
ld
s
,
wh
ich
t
o
g
eth
er
in
cr
ea
s
ed
b
o
th
r
ec
all
an
d
p
r
ec
is
io
n
in
s
p
a
r
s
e
d
atasets
[
1
]
,
[
1
3
]
,
[
1
9
]
,
[
2
1
]
,
[
2
3
]
–
[
2
6
]
,
[
3
5
]
.
Su
ch
e
n
h
a
n
ce
m
en
ts
allo
wed
th
e
s
y
s
tem
to
b
etter
h
an
d
le
s
em
an
tically
s
im
ilar
b
u
t
le
x
ically
d
if
f
er
e
n
t
q
u
er
ies,
esp
ec
ia
lly
in
m
u
ltil
in
g
u
al
o
r
d
o
m
ain
-
s
p
ec
if
ic
co
n
tex
ts
.
T
h
e
in
teg
r
atio
n
o
f
v
ec
to
r
-
b
ased
s
im
ilar
ity
,
b
r
u
te
f
o
r
ce
b
as
elin
es,
an
d
s
eq
u
en
ce
-
awa
r
e
L
S
T
M
m
o
d
els
r
esu
lts
in
a
h
y
b
r
id
m
eth
o
d
o
lo
g
y
th
at
is
n
o
t
o
n
ly
r
o
b
u
s
t
b
u
t
also
s
ca
lab
le
ac
r
o
s
s
d
o
m
ain
s
.
Alth
o
u
g
h
in
itially
im
p
lem
en
ted
f
o
r
Vietn
am
ese
d
o
m
esti
c
to
u
r
is
m
,
th
e
u
n
d
er
ly
in
g
ar
c
h
itectu
r
e
is
tr
an
s
f
er
ab
le
to
a
d
jace
n
t
s
ec
to
r
s
s
u
ch
as e
d
u
ca
tio
n
,
en
ter
tain
m
e
n
t,
an
d
h
ea
lth
ca
r
e
[
4
]
,
[
1
3
]
,
[
1
5
]
,
[
2
5
]
,
[
2
6
]
,
[
2
8
]
.
4.
E
XP
E
R
I
M
E
N
T
R
E
SU
L
T
S AN
D
DIS
CUSS
I
O
N
4
.
1
.
Da
t
a
c
o
llect
io
n
I
n
th
is
s
tu
d
y
,
a
co
m
p
r
eh
en
s
iv
e
d
ataset
o
f
to
u
r
is
t
d
esti
n
atio
n
s
ac
r
o
s
s
all
6
3
p
r
o
v
in
ce
s
an
d
ce
n
tr
ally
g
o
v
er
n
ed
cities in
Vietn
am
was c
o
n
s
tr
u
cted
to
s
u
p
p
o
r
t th
e
tr
ain
in
g
,
ev
alu
atio
n
,
an
d
v
alid
at
io
n
o
f
th
e
p
r
o
p
o
s
ed
T
R
S
.
T
h
e
d
ata
ac
q
u
is
itio
n
p
r
o
ce
s
s
was
co
n
d
u
c
ted
th
r
o
u
g
h
a
s
em
i
-
au
to
m
ated
p
ip
elin
e
lev
er
ag
in
g
p
u
b
licly
av
ailab
le
in
f
o
r
m
atio
n
r
etr
iev
ed
f
r
o
m
m
u
ltip
le
p
r
o
m
in
en
t
tr
av
el
s
er
v
ice
p
latf
o
r
m
s
,
in
clu
d
in
g
T
r
a
v
elo
k
a,
Vin
p
ea
r
l,
Dis
co
v
er
y
T
r
a
v
el,
VietT
r
av
el,
Vn
tr
ip
.
v
n
,
an
d
Viet
n
am
B
o
o
k
in
g
.
T
h
ese
p
latf
o
r
m
s
ar
e
wid
el
y
u
s
ed
in
to
u
r
is
m
d
ata
an
aly
tics
d
u
e
to
th
eir
r
ich
,
d
iv
e
r
s
e,
an
d
r
e
g
u
la
r
ly
u
p
d
ated
r
ep
o
s
ito
r
ies
o
f
d
e
s
tin
atio
n
m
etad
ata
[
1
2
]
–
[
1
5
]
,
[
2
5
]
,
[
2
6
]
,
[
2
8
]
.
An
in
itial c
o
r
p
u
s
o
f
8
,
9
4
0
r
aw
d
escr
ip
tiv
e
r
ec
o
r
d
s
was c
o
llected
f
r
o
m
th
ese
p
latf
o
r
m
s
,
en
c
o
m
p
ass
in
g
v
ar
io
u
s
t
y
p
es
o
f
t
o
u
r
is
t
lo
ca
ti
o
n
s
,
m
etad
ata
ca
te
g
o
r
ies,
an
d
u
s
er
-
g
en
e
r
ated
tex
t
u
al
co
n
te
n
t.
T
o
e
n
s
u
r
e
d
ata
q
u
ality
an
d
elim
in
ate
r
ed
u
n
d
an
cies,
a
co
m
p
r
eh
en
s
iv
e
p
r
e
p
r
o
ce
s
s
in
g
an
d
clea
n
in
g
p
h
ase
was
ap
p
lied
.
T
h
is
p
r
o
ce
s
s
in
clu
d
ed
:
i)
r
em
o
v
al
o
f
d
u
p
licate
en
tr
ies;
ii)
n
o
r
m
aliza
tio
n
o
f
n
a
m
in
g
co
n
v
e
n
tio
n
s
ac
r
o
s
s
s
o
u
r
ce
s
;
an
d
iii)
f
ilter
in
g
o
u
t e
n
tr
ies with
m
is
s
in
g
,
am
b
ig
u
o
u
s
,
o
r
n
o
n
-
i
n
f
o
r
m
ativ
e
co
n
ten
t.
Fo
llo
win
g
th
is
r
ef
in
em
en
t,
a
cu
r
ated
d
ataset
o
f
2
,
1
0
0
h
ig
h
-
q
u
ality
an
d
u
n
iq
u
e
d
esti
n
atio
n
p
r
o
f
iles
was
o
b
tain
ed
,
d
e
em
ed
s
u
itab
le
f
o
r
e
x
p
er
im
e
n
tal
m
o
d
elin
g
a
n
d
m
ac
h
in
e
lear
n
in
g
-
b
ased
t
r
ain
in
g
p
u
r
p
o
s
es.
T
h
e
f
in
alize
d
d
ataset
ca
p
t
u
r
es
cr
it
ical
attr
ib
u
tes
f
o
r
r
ec
o
m
m
en
d
atio
n
m
o
d
elin
g
,
s
u
ch
as
:
i)
lo
ca
tio
n
n
a
m
e
an
d
p
r
o
v
in
ce
;
ii)
g
e
o
g
r
a
p
h
ic
r
e
g
io
n
;
iii)
ca
teg
o
r
y
(
e.
g
.
,
n
atu
r
e
,
h
er
itag
e,
en
ter
tain
m
en
t)
;
iv
)
d
e
s
cr
ip
tiv
e
s
u
m
m
ar
y
;
an
d
v
)
u
s
er
-
g
en
er
ated
tag
s
an
d
tex
t
r
ev
iews.
T
h
ese
f
ea
tu
r
es
wer
e
d
esig
n
ed
to
s
u
p
p
o
r
t
b
o
th
tex
t
v
ec
to
r
izatio
n
an
d
s
em
an
tic
s
im
ilar
ity
co
m
p
u
tatio
n
in
d
o
wn
s
tr
ea
m
r
ec
o
m
m
en
d
atio
n
alg
o
r
ith
m
s
.
T
h
e
s
tatis
tical
d
i
s
tr
ib
u
tio
n
an
d
s
tr
u
ctu
r
al
s
u
m
m
ar
y
o
f
t
h
e
d
ataset
ar
e
p
r
esen
ted
in
T
ab
le
1
an
d
s
er
v
e
as
th
e
b
asis
f
o
r
clu
s
ter
in
g
,
class
if
icatio
n
,
an
d
d
ee
p
lear
n
in
g
m
o
d
els
ap
p
lied
in
s
u
b
s
eq
u
en
t
p
h
ases
[
1
]
,
[
2
]
,
[
1
3
]
,
[
1
8
]
–
[
2
1
]
,
[
2
3
]
,
[
2
4
]
,
[
2
7
]
,
[
2
9
]
–
[
3
1
]
,
[
3
3
]
–
[
3
5
]
,
[
3
8
]
,
[
3
9
]
.
T
o
f
u
r
th
e
r
en
h
an
ce
th
e
d
ataset’
s
tex
tu
al
q
u
ality
,
a
r
ig
o
r
o
u
s
p
r
ep
r
o
c
ess
in
g
p
ip
elin
e
was
im
p
lem
en
ted
.
T
h
is
p
h
ase
alig
n
ed
with
s
tate
-
of
-
th
e
-
a
r
t
m
eth
o
d
o
lo
g
ies
p
r
o
p
o
s
ed
in
[
1
]
,
[
2
]
,
[
1
3
]
,
[
1
8
]
–
[
2
1
]
,
[
2
3
]
,
[
2
4
]
,
[
2
7
]
,
[
2
9
]
–
[
3
1
]
,
[
3
3
]
–
[
3
5
]
,
[
3
8
]
,
[
3
9
]
,
r
ec
o
g
n
izin
g
th
at
r
ea
l
-
w
o
r
ld
tr
av
el
d
escr
ip
tio
n
s
o
f
ten
ex
h
ib
it:
i)
lex
ical
in
co
n
s
is
ten
cies
(
e.
g
.
,
s
p
ellin
g
er
r
o
r
s
)
;
ii
)
r
ed
u
n
d
a
n
cy
an
d
r
ep
etitio
n
;
an
d
iii)
non
-
s
tan
d
ar
d
ized
ter
m
in
o
lo
g
y
an
d
ab
b
r
ev
iatio
n
s
.
T
o
m
itig
a
te
th
ese
is
s
u
es,
th
e
s
tu
d
y
ad
o
p
ted
a
W
ik
ip
ed
ia
-
b
ased
lex
i
ca
l
d
ictio
n
ar
y
as
a
s
em
an
tic
r
ef
er
en
ce
s
o
u
r
ce
.
T
h
is
d
ictio
n
ar
y
was
em
p
l
o
y
ed
to
n
o
r
m
alize
k
ey
ter
m
s
,
id
en
tify
alter
n
ativ
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
3
,
Sep
tem
b
er
20
25
:
7
40
-
7
50
744
ex
p
r
ess
io
n
s
,
an
d
en
r
ic
h
s
p
ar
s
e
co
n
ten
t.
T
h
e
u
s
e
o
f
W
ik
ip
ed
i
a
f
o
r
s
em
an
tic
ex
p
an
s
io
n
is
co
n
s
is
ten
t
with
p
r
io
r
r
esear
ch
th
at
h
ig
h
lig
h
ts
its
ca
p
ac
ity
to
ex
tr
ac
t
d
o
m
ain
-
ag
n
o
s
tic,
s
em
an
tically
r
ich
r
ep
r
esen
tatio
n
s
f
r
o
m
n
o
is
y
tex
t d
ata
[
1
]
,
[
2
7
]
,
[
3
8
]
,
[
3
9
]
.
I
n
p
a
r
allel,
a
c
o
m
p
r
e
h
en
s
iv
e
Vietn
am
ese
s
to
p
-
wo
r
d
lis
t
was
co
m
p
iled
f
r
o
m
b
o
th
W
ik
ip
ed
i
a’
s
lin
g
u
is
tic
to
o
ls
an
d
th
e
Vietn
am
ese
L
an
g
u
ag
e
R
esear
ch
Pro
ject,
as
d
is
cu
s
s
ed
in
[
4
]
,
[
1
3
]
,
[
2
5
]
–
[
2
7
]
,
[
4
0
]
.
T
h
ese
r
eso
u
r
ce
s
wer
e
u
s
ed
to
id
en
tify
an
d
elim
in
ate
n
o
n
-
in
f
o
r
m
ativ
e
te
r
m
s
(
e.
g
.
,
"ở"
,
"
r
ấ
t",
"m
ộ
t
n
ơi")
th
at
co
m
m
o
n
l
y
ap
p
ea
r
in
u
s
er
r
e
v
iews
b
u
t
o
f
f
er
lim
ited
s
em
a
n
tic
co
n
tr
ib
u
tio
n
to
d
esti
n
ati
o
n
p
r
o
f
ilin
g
.
On
ce
clea
n
ed
,
th
e
tex
tu
al
d
ata
was
s
u
b
jecte
d
to
N
-
g
r
am
an
aly
s
is
,
en
ab
lin
g
th
e
ex
tr
ac
tio
n
o
f
co
-
o
cc
u
r
r
e
n
ce
p
atter
n
s
th
at
r
ef
lect
c
o
n
tex
tu
al
an
d
s
y
n
tactic
r
elatio
n
s
h
ip
s
.
E
x
p
er
im
e
n
ts
wer
e
co
n
d
u
cted
u
s
in
g
N
v
alu
es
r
an
g
in
g
f
r
o
m
1
to
4
,
with
b
ig
r
am
s
(
N=
2
)
y
ield
in
g
th
e
m
o
s
t
co
h
er
en
t
r
e
s
u
lts
f
o
r
Vietn
am
ese
s
en
ten
c
e
s
tr
u
ctu
r
es,
wh
er
e
co
m
p
o
u
n
d
co
n
ce
p
ts
o
f
ten
s
p
an
two
o
r
m
o
r
e
s
y
llab
les
[
2
7
]
.
T
r
ig
r
am
s
(
N=
3
)
also
p
r
o
v
id
e
d
p
r
o
m
is
in
g
p
er
f
o
r
m
an
ce
,
esp
ec
ially
f
o
r
c
o
m
p
lex
lo
ca
tio
n
d
escr
ip
to
r
s
.
C
o
n
s
eq
u
en
tly
,
t
h
e
f
i
n
al
f
ea
t
u
r
e
ex
tr
ac
tio
n
f
o
cu
s
ed
o
n
b
ig
r
am
s
an
d
tr
ig
r
am
s
,
wh
ich
wer
e
th
en
tr
an
s
f
o
r
m
e
d
in
to
T
F
-
I
DF v
ec
to
r
s
.
T
h
is
tr
an
s
f
o
r
m
atio
n
ass
ig
n
s
ea
ch
ter
m
a
weig
h
t
th
at
r
ef
lects
its
im
p
o
r
tan
ce
with
in
a
s
p
ec
if
ic
d
o
cu
m
e
n
t
r
elativ
e
to
th
e
en
ti
r
e
co
r
p
u
s
,
en
s
u
r
in
g
th
at
b
o
th
c
o
m
m
o
n
an
d
d
is
tin
ctiv
e
ter
m
s
ar
e
ap
p
r
o
p
r
iately
ca
p
tu
r
ed
.
T
ab
le
1
.
Sam
p
le
lis
t o
f
web
s
it
es
N
a
me
V
o
l
u
me
S
a
mp
l
e
Tr
a
v
e
l
o
k
a
(
h
t
t
p
s:
/
/
w
w
w
.
t
r
a
v
e
l
o
k
a
.
c
o
m
/
v
i
-
vn
)
1
,
8
9
0
5
5
0
V
i
n
p
e
a
r
l
(
h
t
t
p
s:
/
/
v
i
n
p
e
a
r
l
.
c
o
m
/
v
i
)
1
,
7
6
0
5
0
0
D
u
l
ị
c
h
k
h
á
m
p
h
á
(
h
t
t
p
s:
/
/
d
u
l
i
c
h
k
h
a
m
p
h
a
.
c
o
m
.
v
n
/
)
1
,
5
7
5
3
5
0
Du
l
ị
c
h
V
i
ệ
t
(
h
t
t
p
s:
/
/
d
u
l
i
c
h
v
i
e
t
.
c
o
m
.
v
n
/
)
1
,
2
6
0
2
5
0
V
n
t
r
i
p
.
v
n
(
h
t
t
p
s:
/
/
w
w
w
.
v
n
t
r
i
p
.
v
n
/
e
n
)
1
,
5
1
0
2
5
0
V
i
e
t
N
a
m B
o
o
k
i
n
g
(
h
t
t
p
s:
/
/
w
w
w
.
v
i
e
t
n
a
m
b
o
o
k
i
n
g
.
c
o
m
/
)
9
4
5
2
0
0
To
t
a
l
8
,
9
4
0
2
,
1
0
0
(
S
o
u
r
c
e
:
a
u
t
h
o
r
s
'
st
a
t
i
s
t
i
c
s
f
r
o
m res
o
u
r
c
e
s i
n
V
i
e
t
n
a
m)
4
.
2
.
E
x
perim
ent
a
l da
t
a
s
a
mp
le
T
o
im
p
lem
en
t
t
h
e
alg
o
r
ith
m
s
an
d
m
ea
s
u
r
em
e
n
ts
,
th
e
s
tu
d
y
b
u
ilt
a
s
am
p
le
d
ata
s
et
co
n
s
is
t
in
g
of
:
n
o
.
,
n
am
e
o
f
d
esti
n
atio
n
,
city
,
d
es
cr
ip
tio
n
,
an
d
m
u
ltime
d
ia
.
Af
t
er
p
r
o
ce
s
s
in
g
th
e
d
ata,
t
h
e
r
esear
ch
er
s
s
elec
ted
a
s
et
o
f
2
,
1
0
0
lo
ca
tio
n
s
.
T
h
ey
in
clu
d
e
b
ea
c
h
to
u
r
is
m
,
m
o
u
n
tai
n
to
u
r
is
m
,
ec
o
to
u
r
is
m
,
h
is
to
r
i
ca
l
r
elics,
ch
u
r
c
h
es,
p
ag
o
d
as,
a
n
d
en
te
r
tain
m
en
t a
r
ea
s
.
T
ab
le
2
s
h
o
ws
th
e
s
tr
u
ctu
r
e
o
f
a
s
am
p
le
o
f
d
ata
ab
o
u
t a
to
u
r
is
t d
esti
n
atio
n
.
T
ab
le
2
.
A
s
am
p
le
o
f
d
ata
f
o
r
t
h
e
ex
p
er
im
e
n
t
N
o
.
N
a
me
C
i
t
y
D
e
scri
p
t
i
o
n
M
u
l
t
i
me
d
i
a
1
K
h
u
d
u
l
ị
c
h
Ta
m
C
ố
c
-
B
í
c
h
Đ
ộ
n
g
N
i
n
h
B
ì
n
h
K
h
u
d
u
l
ị
c
h
T
a
m
C
ố
c
–
Bí
c
h
Đ
ộ
n
g
đ
ư
ợ
c
v
í
n
h
ư
"v
ị
n
h
Hạ
L
o
n
g
c
ạ
n
"
v
ớ
i
n
h
i
ề
u
c
ả
n
h
đ
ẹ
p
n
h
ư
T
a
m
C
ố
c
,
đ
ề
n
T
h
á
i
V
i
,
c
h
ù
a
B
í
c
h
Đ
ộ
n
g
,
đ
ộ
n
g
T
i
ê
n
,
h
a
n
g
B
ụ
t
,
t
h
u
n
g
N
ắ
n
g
,
t
h
u
n
g
N
h
a
m
,
v
ư
ờ
n
c
h
i
m
.
.
.
N
ổ
i
t
i
ế
n
g
v
ớ
i
d
a
n
h
x
ư
n
g
‘
N
a
m
t
h
i
ê
n
đ
ệ
n
h
ị
đ
ộ
n
g
’
,
T
a
m
C
ố
c
Bí
c
h
Đ
ộ
n
g
sở
h
ữ
u
c
ả
n
h
s
ắ
c
l
à
n
g
q
u
ê
y
ê
n
b
ì
n
h
c
ù
n
g
h
ệ
t
h
ố
n
g
h
a
n
g
đ
ộ
n
g
n
ú
i
đ
á
v
ô
i
ấ
n
t
ư
ợ
n
g
.
L
à
m
ộ
t
p
h
ầ
n
t
ro
n
g
Q
u
ầ
n
t
h
ể
d
a
n
h
t
h
ắ
n
g
T
rà
n
g
An
,
T
a
m
C
ố
c
Bí
c
h
Đ
ộ
n
g
l
à
đ
i
ể
m
đ
ế
n
h
o
à
n
h
ả
o
d
à
n
h
c
h
o
n
h
ữ
n
g
a
i
m
u
ố
n
k
h
á
m
p
h
á
t
r
ọ
n
v
ẹ
n
v
ẻ
đ
ẹ
p
n
o
n
s
ô
n
g
.
Đ
ị
a
c
h
ỉ
:
N
i
n
h
H
ả
i
,
H
o
a
L
ư
,
N
i
n
h
B
ì
n
h
(
đ
ồ
n
g
b
ằ
n
g
sô
n
g
H
ồ
n
g
,
m
i
ề
n
B
ắ
c
Vi
ệ
t
N
a
m
)
Ph
â
n
l
o
ạ
i
d
u
l
ị
c
h
:
d
u
l
ị
c
h
si
n
h
t
h
á
i
,
d
u
l
ị
c
h
v
ă
n
h
ó
a
,
d
u
l
ị
c
h
n
g
h
ỉ
d
ư
ỡ
n
g
v
à
d
u
l
ị
c
h
k
h
á
m
p
h
á
h
t
t
p
s
:
/
/
st
a
t
i
c
-
i
ma
g
e
s.
v
n
n
c
d
n
.
n
e
t
/
f
i
l
e
s/
p
u
b
l
i
sh
/
2
0
2
3
/
7
/
8
/
n
i
n
h
-
b
i
n
h
-
a
n
h
-
so
-
du
-
l
i
c
h
-
cc
-
1
0
2
1
-
8
6
4
.
j
p
e
g
(
S
o
u
r
c
e
:
f
r
o
m
d
a
t
a
sam
p
l
e
se
t
b
u
i
l
t
b
y
a
u
t
h
o
r
s)
4
.
3
.
E
x
perim
ent
a
l scena
rio
R
esear
ch
ca
r
r
ied
o
u
t
b
y
s
ce
n
a
r
io
as
f
o
ll
o
ws:
i)
s
tep
1
:
b
u
ild
a
s
et
o
f
u
s
er
q
u
er
ies
;
ii)
s
tep
2
:
b
u
ild
a
wo
r
d
s
et
f
o
r
ea
c
h
q
u
er
y
,
p
r
e
p
r
o
ce
s
s
in
g
,
N
-
g
r
a
m
s
ep
ar
atio
n
,
s
to
p
-
wo
r
d
r
em
o
v
al;
iii)
s
tep
3
:
c
alcu
late
th
e
weig
h
t
v
ec
to
r
b
y
T
F.
I
DF.
C
alcu
late
th
e
c
o
r
r
elatio
n
o
f
ea
ch
q
u
er
y
with
th
e
lo
ca
tio
n
s
;
iv
)
s
tep
4
:
c
o
n
d
u
ct
m
an
u
al
m
atch
i
n
g
f
r
o
m
v
o
lu
n
teer
s
;
v
)
s
tep
5
:
c
o
n
d
u
ct
s
ea
r
ch
u
s
in
g
m
o
d
els
an
d
e
v
alu
ate
th
e
s
ea
r
ch
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el.
T
h
e
d
etailed
s
tep
s
o
f
th
e
s
ce
n
ar
io
ar
e
as
f
o
llo
ws
:
t
o
r
ig
o
r
o
u
s
ly
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
p
er
s
o
n
alize
d
T
R
S
,
th
e
r
esear
ch
team
d
ev
elo
p
ed
a
s
tr
u
ctu
r
ed
d
ataset
o
f
1
0
0
u
s
er
q
u
er
ies,
ea
ch
s
im
u
latin
g
a
r
ea
l
-
wo
r
ld
s
ea
r
c
h
in
ten
t
in
th
e
to
u
r
is
m
d
o
m
a
in
.
T
h
ese
q
u
er
ies
v
ar
ied
in
wo
r
d
len
g
th
,
lex
ical
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
meth
o
d
cla
s
s
ifyin
g
th
e
d
o
me
s
tic
to
u
r
is
t d
esti
n
a
tio
n
b
a
s
e
s
imila
r
ity
mea
s
u
r
in
g
(
N
g
u
ye
n
Th
i H
o
i
)
745
co
m
p
lex
ity
,
an
d
th
em
atic
f
o
c
u
s
,
co
v
er
in
g
i
n
ter
ests
s
u
ch
as
e
co
to
u
r
is
m
,
c
u
ltu
r
al
h
er
itag
e,
c
o
astal
d
esti
n
atio
n
s
,
an
d
u
r
b
a
n
ex
p
l
o
r
atio
n
.
E
ac
h
q
u
er
y
was
s
to
r
ed
in
an
E
x
ce
l
s
p
r
ea
d
s
h
ee
t
with
two
p
r
im
ar
y
co
lu
m
n
s
:
i)
s
er
ial
n
u
m
b
er
(
q
u
er
y
I
D)
a
n
d
ii)
q
u
er
y
tex
t.
T
h
is
s
tr
u
ctu
r
e
e
n
s
u
r
e
d
tr
ac
ea
b
ilit
y
a
n
d
r
e
p
r
o
d
u
cib
i
lity
th
r
o
u
g
h
o
u
t
th
e
ex
p
er
im
en
tal
wo
r
k
f
lo
w.
An
ad
d
itio
n
al
co
lu
m
n
was
later
ad
d
ed
to
l
o
g
th
e
e
x
p
ec
ted
n
u
m
b
er
o
f
m
atch
in
g
d
esti
n
atio
n
s
,
d
eter
m
in
ed
t
h
r
o
u
g
h
h
u
m
an
a
n
n
o
tatio
n
.
T
h
e
q
u
e
r
y
ev
al
u
atio
n
p
r
o
ce
s
s
f
o
llo
we
d
a
m
u
lti
-
s
tag
e
ar
ch
ite
ctu
r
e,
co
n
s
is
tin
g
o
f
th
e
f
o
llo
win
g
s
tep
s
:
i)
Stag
e
1
:
q
u
er
y
d
esig
n
an
d
g
r
o
u
n
d
tr
u
t
h
an
n
o
tatio
n
:
ea
c
h
q
u
er
y
was
co
n
s
tr
u
cted
to
r
ef
lect
n
atu
r
al
lan
g
u
ag
e
ex
p
r
ess
io
n
s
o
f
tr
av
el
in
ter
est.
A
g
r
o
u
p
o
f
h
u
m
an
ev
alu
ato
r
s
was
r
ec
r
u
ited
to
m
an
u
ally
ass
o
ciate
ea
ch
q
u
er
y
with
a
r
elev
an
t
s
et
o
f
d
esti
n
atio
n
s
f
r
o
m
th
e
cu
r
ate
d
d
atas
et
o
f
2
,
1
0
0
to
u
r
is
t
lo
ca
tio
n
s
,
p
r
ev
i
o
u
s
ly
co
llect
ed
ac
r
o
s
s
all
6
3
p
r
o
v
i
n
ce
s
an
d
m
u
n
icip
alities
in
Vietn
am
.
T
h
ese
ass
o
ciatio
n
s
s
er
v
ed
as
th
e
g
o
ld
s
tan
d
ar
d
r
ef
e
r
en
ce
s
et
f
o
r
e
v
alu
atin
g
alg
o
r
ith
m
ic
o
u
tp
u
ts
[
1
2
]
,
[
2
5
]
–
[
2
7
]
,
[
3
1
]
,
[
3
3
]
,
[
3
7
]
.
ii)
Stag
e
2
:
tex
t
p
r
ep
r
o
c
ess
in
g
an
d
n
o
r
m
aliza
tio
n
:
ea
c
h
q
u
e
r
y
w
as
to
k
en
ized
an
d
n
o
r
m
ali
ze
d
u
s
in
g
s
tan
d
ar
d
n
atu
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
(
NL
P)
tech
n
iq
u
es:
to
k
en
izatio
n
an
d
s
to
p
-
wo
r
d
r
em
o
v
al
b
ased
o
n
lin
g
u
is
tic
r
eso
u
r
ce
s
f
r
o
m
W
ik
ip
ed
ia
an
d
th
e
Vietn
am
ese
L
an
g
u
ag
e
R
e
s
ea
r
ch
Pro
ject
[
1
3
]
,
[
2
6
]
,
[
2
7
]
,
[
3
9
]
. N
-
g
r
a
m
d
ec
o
m
p
o
s
itio
n
with
v
alu
es
o
f
N=
1
to
4
,
to
ca
p
tu
r
e
th
e
f
r
e
q
u
en
t
o
cc
u
r
r
en
ce
o
f
co
m
p
o
u
n
d
a
n
d
m
u
lti
-
s
y
llab
ic
ex
p
r
ess
io
n
s
in
Vietn
a
m
ese
[
1
3
]
,
[
1
5
]
,
[
2
6
]
,
[
2
7
]
.
L
o
wer
ca
s
in
g
an
d
m
o
r
p
h
o
lo
g
ical
n
o
r
m
aliza
tio
n
to
en
s
u
r
e
u
n
if
o
r
m
r
ep
r
esen
tatio
n
ac
r
o
s
s
d
atasets
.
iii)
Stag
e
3
:
q
u
er
y
v
ec
to
r
izatio
n
v
ia
T
F
-
I
DF:
f
o
llo
win
g
p
r
ep
r
o
c
ess
in
g
,
b
o
th
th
e
u
s
er
q
u
er
ies
an
d
th
e
tex
tu
al
m
etad
ata
o
f
ea
ch
to
u
r
is
t
d
esti
n
atio
n
wer
e
tr
a
n
s
f
o
r
m
ed
in
to
h
ig
h
-
d
im
e
n
s
io
n
al
v
ec
to
r
r
ep
r
esen
tatio
n
s
u
s
in
g
th
e
T
F
-
I
DF
m
o
d
el.
T
h
is
weig
h
tin
g
s
ch
em
e
e
f
f
ec
tiv
ely
q
u
a
n
tifie
s
ter
m
s
ig
n
if
ican
ce
with
in
th
e
co
r
p
u
s
,
en
a
b
lin
g
ac
c
u
r
ate
s
em
an
tic
co
m
p
ar
is
o
n
[
4
]
,
[
1
9
]
,
[
2
8
]
,
[
3
8
]
.
iv
)
Stag
e
4
:
alg
o
r
ith
m
ic
e
v
alu
ati
o
n
a
n
d
s
im
ilar
ity
co
m
p
u
tatio
n
:
th
r
ee
alg
o
r
ith
m
s
wer
e
e
m
p
lo
y
ed
t
o
ass
ess
s
em
an
tic
s
im
ilar
ity
b
etwe
en
q
u
er
ies
an
d
d
esti
n
atio
n
d
escr
ip
t
io
n
s
:
co
s
in
e
s
im
ilar
ity
:
co
m
p
u
tes
th
e
co
s
in
e
o
f
th
e
an
g
le
b
etwe
en
T
F
-
I
DF v
ec
to
r
s
,
f
ac
ilit
atin
g
a
s
ca
lab
le
an
d
in
ter
p
r
etab
le
m
atch
in
g
m
e
ch
an
is
m
[
1
7
]
,
[
2
7
]
,
[
3
1
]
,
[
3
5
]
,
[
4
0
]
;
b
r
u
te
f
o
r
ce
m
atch
in
g
:
p
er
f
o
r
m
s
ex
h
au
s
tiv
e
p
air
wis
e
co
m
p
ar
is
o
n
s
b
etwe
en
q
u
er
y
v
ec
to
r
s
an
d
all
d
esti
n
atio
n
v
ec
to
r
s
[
2
3
]
,
[
2
5
]
,
[
3
0
]
,
[
3
7
]
–
[
3
9
]
.
Alth
o
u
g
h
co
m
p
u
tatio
n
ally
in
ten
s
iv
e,
it
g
u
ar
an
tees
m
ax
i
m
u
m
r
ec
all
an
d
s
er
v
es
as
a
b
aselin
e
ev
alu
atio
n
m
eth
o
d
[
1
3
]
,
[
2
1
]
,
[
2
3
]
–
[2
6
]
,
[
3
5
]
;
L
STM
n
eu
r
al
n
etwo
r
k
:
u
tili
ze
s
a
g
ated
R
NN
ar
ch
itectu
r
e
to
ca
p
tu
r
e
tem
p
o
r
al
an
d
c
o
n
tex
t
u
al
d
ep
en
d
en
cies
in
tex
t
s
eq
u
en
ce
s
.
T
h
is
m
eth
o
d
is
p
ar
ticu
l
ar
ly
well
-
s
u
ited
f
o
r
in
ter
p
r
etin
g
n
u
an
ce
d
p
atter
n
s
in
u
s
er
in
ten
t
[
2
3
]
–
[
2
5
]
,
[
3
0
]
,
[
3
1
]
,
[
3
3
]
,
[
3
5
]
,
[
3
7
]
.
E
x
p
er
im
en
t
s
etu
p
:
all
im
p
lem
en
tatio
n
s
wer
e
ca
r
r
ied
o
u
t in
Py
th
o
n
,
u
s
in
g
Vis
u
al
Stu
d
io
C
o
d
e
(
v
2
0
2
0
)
as th
e
in
te
g
r
ated
d
ev
el
o
p
m
en
t
en
v
ir
o
n
m
en
t.
E
x
p
e
r
im
en
ts
we
r
e
ex
ec
u
ted
o
n
a
W
in
d
o
ws 1
1
m
ac
h
in
e
p
o
wer
ed
b
y
a
n
I
n
tel(
R
)
C
o
r
e
i7
-
1
1
8
5
G7
@
3
.
0
0
GHz
C
PU
an
d
3
2
GB
R
AM
,
en
s
u
r
in
g
s
tab
le
a
n
d
r
ep
r
o
d
u
cib
le
co
m
p
u
tatio
n
s
.
T
o
estab
lis
h
an
em
p
ir
ical
p
er
f
o
r
m
a
n
ce
b
e
n
ch
m
ar
k
,
th
e
r
esear
ch
team
co
n
d
u
cted
a
m
an
u
al
ev
alu
atio
n
p
r
o
ce
s
s
in
v
o
lv
i
n
g
a
g
r
o
u
p
o
f
tr
ain
e
d
v
o
lu
n
teer
s
.
E
ac
h
p
ar
ticip
an
t
was
in
s
tr
u
cted
to
s
elec
t
a
s
e
t
o
f
r
elev
an
t
d
esti
n
atio
n
s
f
r
o
m
th
e
m
aster
d
ataset
f
o
r
ea
ch
o
f
th
e
1
0
0
q
u
er
ies.
T
h
ese
m
a
n
u
all
y
s
elec
ted
r
esu
lts
wer
e
co
n
s
o
lid
ated
to
f
o
r
m
th
e
g
r
o
u
n
d
-
tr
u
th
r
elev
a
n
ce
s
et
f
o
r
ea
ch
q
u
er
y
.
Fo
r
ea
ch
alg
o
r
ith
m
,
th
e
s
y
s
tem
-
g
en
er
ate
d
r
ec
o
m
m
e
n
d
atio
n
s
wer
e
co
m
p
ar
ed
to
th
e
g
r
o
u
n
d
tr
u
th
u
s
in
g
a
b
in
ar
y
s
co
r
in
g
m
ec
h
a
n
is
m
:
let
N
d
e
n
o
te
th
e
n
u
m
b
er
o
f
co
r
r
ec
t
lo
ca
tio
n
s
(
f
r
o
m
h
u
m
an
an
n
o
tatio
n
)
,
let
M
r
ep
r
esen
t
th
e
n
u
m
b
er
o
f
l
o
ca
tio
n
s
r
etr
iev
ed
b
y
th
e
alg
o
r
ith
m
;
f
o
r
ea
ch
m
atch
b
etwe
e
n
th
e
r
etr
iev
e
d
an
d
r
ef
er
en
ce
s
ets,
th
e
ac
c
u
r
ac
y
s
co
r
e
was
in
cr
em
e
n
ted
b
y
o
n
e
u
n
it.
T
h
is
p
e
r
-
q
u
e
r
y
m
at
ch
in
g
ac
cu
r
ac
y
was
th
en
ag
g
r
eg
ated
ac
r
o
s
s
all
1
0
0
q
u
e
r
ies
to
ass
ess
o
v
er
all
s
y
s
tem
e
f
f
ec
tiv
en
ess
[
1
3
]
,
[
1
5
]
,
[
2
7
]
.
I
n
ad
d
itio
n
to
b
in
ar
y
ac
cu
r
ac
y
s
co
r
i
n
g
,
t
h
e
s
y
s
tem
's
p
r
ed
ictiv
e
co
r
r
ec
tn
ess
was
ev
alu
ated
u
s
in
g
th
e
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
m
etr
ic.
MSE
m
ea
s
u
r
es
th
e
av
er
ag
e
s
q
u
a
r
ed
d
ev
iatio
n
b
etwe
en
th
e
n
u
m
b
er
o
f
ex
p
ec
ted
a
n
d
r
etr
iev
ed
r
esu
lts
p
er
q
u
e
r
y
,
o
f
f
er
i
n
g
a
q
u
an
titativ
e
in
d
icato
r
o
f
o
v
er
-
o
r
u
n
d
e
r
-
p
r
ed
ictio
n
[
1
]
,
[
2
]
,
[
1
9
]
,
[
2
6
]
,
[
2
7
]
,
[
3
1
]
,
[
3
7
]
.
=
1
∑
(
−
)
2
=
1
(
3
)
W
ith
ea
ch
,
=
1
.
.
.
100
,
,
=
1
.
.
.
2100
,
to
tal
as
(
100
×
2100
)
=
210000
p
air
s
,
an
d
n
=2
1
0
0
0
0
.
T
h
e
MSE
f
o
r
m
u
la
s
tates
th
at
ac
cu
r
a
cy
in
cr
ea
s
es
as
th
e
v
alu
e
o
f
MSE
g
ets
clo
s
er
to
ze
r
o
,
an
d
v
ice
v
e
r
s
a.
Acq
u
ir
e
d
ex
p
er
im
en
tal
f
in
d
in
g
s
as in
(
4
)
.
=
1
∑
(
−
)
2
=
1
=
1
2
1
0
0
0
0
∑
(
−
)
2
=
0
,
1251
210000
=
1
(
4
)
C
o
r
r
esp
o
n
d
in
g
to
th
e
p
r
ec
is
io
n
o
f
th
e
ex
p
e
r
im
en
t w
ith
co
s
in
e
is
(
5
)
.
=
(
1
–
)
×
100%
=
(
1
−
0
,
1251
)
×
100%
=
87
,
49%
(
5
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
3
,
Sep
tem
b
er
20
25
:
7
40
-
7
50
746
T
h
is
ev
alu
atio
n
f
r
am
ewo
r
k
en
s
u
r
ed
th
at
b
o
th
th
e
p
r
ec
is
io
n
o
f
m
atch
in
g
an
d
v
o
lu
m
e
o
f
r
e
lev
an
t
r
esu
lts
wer
e
s
y
s
tem
atica
lly
ass
e
s
s
ed
ac
r
o
s
s
a
ll m
o
d
els an
d
q
u
er
ies.
4
.
4
.
Dis
cus
s
io
n a
nd
lim
i
ta
t
io
n
T
h
e
f
o
llo
win
g
is
th
e
q
u
e
r
y
s
ea
r
ch
r
esu
lts
tab
le
o
f
t
h
e
m
o
d
els:
co
s
in
e
s
im
ilar
ity
,
b
r
u
te
f
o
r
ce
alg
o
r
ith
m
,
an
d
L
STM
m
o
d
el
in
Step
3
.
Acc
u
r
ac
y
in
m
o
d
es
i
s
illu
s
tr
ated
in
T
a
b
le
3
.
Fo
llo
win
g
th
e
co
m
p
letio
n
o
f
e
x
p
er
im
e
n
tal
tr
ials
,
th
e
s
tu
d
y
id
en
tifie
d
th
at
th
e
c
o
s
in
e
s
im
ilar
ity
alg
o
r
ith
m
o
u
tp
er
f
o
r
m
ed
o
th
er
m
o
d
els
in
ter
m
s
o
f
r
ec
o
m
m
en
d
ati
o
n
ac
cu
r
ac
y
,
ac
h
iev
i
n
g
an
a
cc
u
r
ac
y
r
ate
o
f
8
7
.
4
9
%,
f
o
llo
wed
b
y
th
e
b
r
u
te
f
o
r
ce
m
atch
in
g
m
eth
o
d
at
8
4
.
5
5
%,
an
d
th
e
L
STM
m
o
d
el
at
8
2
.
1
8
%.
As
d
etailed
in
T
ab
le
3
,
co
s
in
e
s
im
ilar
ity
n
o
t
o
n
ly
y
ield
e
d
th
e
h
ig
h
est
av
er
ag
e
ac
cu
r
ac
y
b
u
t
also
d
em
o
n
s
tr
ated
th
e
lo
west
s
tan
d
ar
d
d
ev
iatio
n
,
in
d
ica
tin
g
s
tr
o
n
g
s
tab
ilit
y
an
d
c
o
n
s
is
ten
cy
ac
r
o
s
s
v
a
r
io
u
s
q
u
er
y
ty
p
es.
C
o
n
v
er
s
ely
,
th
e
b
r
u
te
f
o
r
ce
m
o
d
el
e
x
h
ib
ited
th
e
h
ig
h
est
v
ar
iab
ilit
y
,
s
u
g
g
esti
n
g
s
en
s
itiv
ity
to
in
p
u
t
q
u
er
y
s
tr
u
ctu
r
e
an
d
v
ec
to
r
s
p
ar
s
ity
[
2
3
]
–
[
2
5
]
,
[
3
0
]
,
[
3
1
]
,
[
3
3
]
,
[
3
5
]
,
[
3
7
]
–
[
3
9
]
.
T
ab
le
3
.
T
h
e
r
esu
lts
o
f
th
e
t
h
r
ee
m
o
d
es
N
o
.
B
r
u
t
e
f
o
r
c
e
(
%)
C
o
s
i
n
e
s
i
mi
l
a
r
i
t
y
(
%)
LSTM
(
%)
1
8
4
.
5
5
8
7
.
4
9
8
2
.
1
8
T
h
e
o
b
s
er
v
ed
s
u
p
er
io
r
ity
o
f
c
o
s
in
e
s
im
ilar
ity
is
p
r
im
ar
ily
a
ttrib
u
ted
to
its
co
m
p
u
tatio
n
al
ef
f
icien
cy
in
m
ea
s
u
r
in
g
a
n
g
u
lar
d
is
tan
ce
b
etwe
en
T
F
-
I
DF v
ec
to
r
s
d
er
iv
ed
f
r
o
m
u
s
er
q
u
er
ies
a
n
d
d
esti
n
atio
n
p
r
o
f
iles
[
1
]
,
[
1
9
]
,
[
2
0
]
.
T
h
is
ap
p
r
o
ac
h
f
ac
ilit
ates th
e
ex
tr
ac
tio
n
o
f
s
em
an
ti
ca
lly
alig
n
ed
r
esu
lts
with
o
u
t r
ely
in
g
o
n
h
is
to
r
ical
u
s
er
in
ter
ac
tio
n
d
ata.
T
h
e
tr
an
s
f
o
r
m
atio
n
o
f
u
n
s
tr
u
ctu
r
ed
te
x
t
in
to
h
ig
h
-
d
im
en
s
io
n
al
s
tr
u
ct
u
r
ed
f
ea
tu
r
e
v
ec
to
r
s
en
ab
led
th
e
m
o
d
el
to
m
atch
u
s
er
in
ten
t
with
d
esti
n
atio
n
m
etad
ata
in
a
p
u
r
ely
c
o
n
ten
t
-
b
ased
f
r
am
ewo
r
k
[
2
]
,
[
2
5
]
–
[
2
7
]
,
[
2
9
]
.
I
n
o
p
er
atio
n
al
ter
m
s
,
th
e
m
o
s
t
r
elev
an
t
d
esti
n
atio
n
s
,
th
o
s
e
with
th
e
h
ig
h
est
co
s
in
e
s
im
ilar
ity
s
co
r
es,
wer
e
au
to
m
atica
lly
r
an
k
e
d
at
th
e
to
p
,
p
r
o
v
id
i
n
g
u
s
er
s
with
s
u
g
g
esti
o
n
s
th
at
clo
s
ely
m
ir
r
o
r
ed
th
eir
in
ten
t.
T
h
e
b
r
u
te
f
o
r
ce
m
atch
in
g
m
o
d
el,
th
o
u
g
h
co
m
p
u
tatio
n
all
y
ex
p
e
n
s
iv
e,
was
s
h
o
wn
to
b
e
p
ar
ticu
lar
ly
ef
f
ec
tiv
e
in
h
an
d
lin
g
f
u
ll
-
s
en
ten
ce
q
u
er
ie
s
wh
er
e
s
em
an
tic
n
u
an
ce
an
d
co
n
tex
t
wer
e
ess
en
tial.
T
h
i
s
m
o
d
el
co
n
d
u
cted
ex
h
au
s
tiv
e
p
air
wis
e
co
m
p
ar
is
o
n
s
b
etwe
en
ev
er
y
q
u
er
y
v
ec
to
r
an
d
th
e
d
esti
n
atio
n
co
r
p
u
s
,
th
u
s
m
ax
im
iz
in
g
co
v
er
ag
e
[
1
7
]
,
[
2
7
]
,
[
3
0
]
,
[
3
1
]
.
Me
an
wh
ile,
th
e
L
STM
m
o
d
el,
d
esp
ite
b
ein
g
s
lig
h
t
ly
less
ac
cu
r
ate
in
to
p
-
1
r
ec
o
m
m
en
d
atio
n
r
an
k
i
n
g
,
d
em
o
n
s
tr
ated
n
o
tab
le
s
tr
en
g
th
s
in
p
r
o
ce
s
s
in
g
s
p
ee
d
a
n
d
s
ca
lab
ilit
y
,
esp
ec
ially
wh
en
d
e
p
lo
y
ed
in
en
v
ir
o
n
m
en
ts
r
eq
u
ir
i
n
g
r
ea
l
-
ti
m
e
r
esp
o
n
s
es
o
r
h
a
n
d
lin
g
lar
g
e
q
u
er
y
v
o
lu
m
es
[
1
7
]
,
[
1
9
]
,
[
2
0
]
,
[
2
3
]
,
[
3
3
]
,
[
3
5
]
,
[
3
8
]
.
T
o
ev
alu
ate
th
e
p
r
ac
tical
ap
p
licab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
els,
a
web
-
b
ased
T
R
S
was
d
ev
elo
p
ed
u
s
in
g
th
e
Fas
tAPI
f
r
am
ewo
r
k
,
d
ep
lo
y
ed
in
a
Py
th
o
n
en
v
ir
o
n
m
e
n
t,
an
d
ex
ec
u
ted
v
ia
Vis
u
al
Stu
d
io
C
o
d
e.
T
h
e
s
y
s
tem
in
ter
f
ac
e
e
n
ab
les
u
s
e
r
s
to
in
p
u
t
f
r
ee
-
tex
t
q
u
e
r
ies
an
d
r
ec
eiv
e
a
n
in
ter
ac
tiv
e
o
u
tp
u
t
in
te
r
f
ac
e
t
h
at
p
r
esen
ts
:
i
)
th
e
n
u
m
b
er
o
f
m
atch
ed
r
esu
lts
;
ii)
a
r
an
k
ed
li
s
t
o
f
d
esti
n
atio
n
s
u
g
g
esti
o
n
s
p
er
alg
o
r
ith
m
;
an
d
iii)
r
ea
l
-
tim
e
v
is
u
al
co
m
p
ar
is
o
n
o
f
o
u
tp
u
ts
f
r
o
m
co
s
in
e
s
i
m
ilar
ity
,
b
r
u
te
f
o
r
ce
,
a
n
d
L
S
T
M
m
eth
o
d
s
.
T
h
is
f
ea
tu
r
e
allo
we
d
r
esear
c
h
er
s
an
d
test
u
s
er
s
to
q
u
alitativ
ely
ass
ess
alg
o
r
ith
m
o
u
tp
u
ts
a
n
d
v
alid
ate
m
o
d
el
b
eh
av
io
r
u
n
d
er
d
if
f
er
en
t lin
g
u
is
tic
s
ce
n
ar
io
s
.
S
ev
er
al
k
ey
in
s
ig
h
ts
d
er
iv
ed
f
r
o
m
s
y
s
tem
ex
p
er
im
en
tati
o
n
ar
e
th
at
th
e
b
r
u
te
f
o
r
ce
m
atch
in
g
ac
h
iev
ed
m
a
r
g
in
ally
h
ig
h
er
ac
cu
r
ac
y
f
o
r
lo
n
g
-
f
o
r
m
q
u
e
r
ies,
alig
n
in
g
well
with
u
s
er
-
s
elec
t
ed
d
esti
n
atio
n
s
ets
in
m
an
u
al
v
alid
atio
n
.
L
STM
,
wh
ile
s
lig
h
tly
tr
ailin
g
in
ac
cu
r
ac
y
,
o
f
f
er
e
d
f
aster
r
u
n
tim
e
an
d
b
etter
r
eso
u
r
ce
o
p
tim
izatio
n
,
s
u
g
g
esti
n
g
p
o
te
n
tial
f
o
r
r
ea
l
-
tim
e
o
r
m
o
b
ile
d
ep
lo
y
m
e
n
t.
C
o
s
in
e
s
im
ilar
ity
,
esp
ec
ially
wh
en
f
in
e
-
tu
n
e
d
with
o
p
tim
ized
T
F
-
I
DF
p
ar
am
eter
s
an
d
b
ig
r
am
m
o
d
elin
g
,
c
o
n
s
is
ten
tly
d
eliv
er
e
d
s
em
an
ticall
y
r
ich
an
d
ac
cu
r
ate
r
esu
lts
ac
r
o
s
s
all
q
u
er
y
t
y
p
es.
T
h
ese
f
in
d
in
g
s
r
ea
f
f
ir
m
t
h
e
s
tr
en
g
th
o
f
tex
tu
al
s
im
ilar
ity
-
b
a
s
ed
m
o
d
els,
p
ar
ticu
lar
ly
wh
en
co
m
b
i
n
ed
with
r
o
b
u
s
t
p
r
ep
r
o
ce
s
s
in
g
an
d
v
ec
to
r
s
p
ac
e
tr
an
s
f
o
r
m
atio
n
tech
n
iq
u
es,
in
ca
p
tu
r
i
n
g
u
s
er
p
r
ef
er
en
ce
s
with
h
ig
h
f
id
elity
.
W
h
en
b
e
n
ch
m
ar
k
ed
a
g
ain
s
t
lead
in
g
r
ec
o
m
m
e
n
d
er
m
o
d
els
f
r
o
m
r
ec
en
t
liter
atu
r
e,
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
f
r
am
ew
o
r
k
d
em
o
n
s
tr
a
ted
s
ev
er
al
n
o
tab
le
ad
v
an
tag
e
s
:
i
n
co
n
tr
ast
to
[
1
8
]
,
wh
ich
p
r
im
ar
ily
r
elies
o
n
u
s
er
r
ev
iews
an
d
h
is
to
r
ical
b
e
h
av
io
r
,
th
e
p
r
o
p
o
s
ed
s
y
s
tem
m
itig
ates
p
o
p
u
lar
ity
b
ias
b
y
p
r
io
r
itizin
g
s
em
an
tic
r
elev
an
ce
b
etwe
en
q
u
er
y
c
o
n
t
en
t
an
d
d
esti
n
atio
n
p
r
o
f
iles
.
C
o
m
p
ar
ed
t
o
[
2
0
]
,
wh
ich
em
p
h
asizes
im
ag
e
-
b
ased
an
d
ac
tiv
it
y
r
ec
o
m
m
en
d
atio
n
s
,
o
u
r
m
o
d
el
o
f
f
er
s
s
t
r
o
n
g
e
r
tex
tu
al
p
r
o
ce
s
s
in
g
ca
p
ab
ili
ties
b
u
t
co
u
l
d
b
e
ex
ten
d
ed
with
im
ag
e
m
eta
d
ata
an
d
ca
p
tio
n
em
b
ed
d
in
g
f
o
r
m
u
ltimo
d
al
in
teg
r
atio
n
.
Un
lik
e
[
2
]
,
wh
ich
ac
tiv
ates
r
ec
o
m
m
en
d
atio
n
s
o
n
ly
af
ter
th
e
u
s
er
s
elec
ts
a
d
esti
n
atio
n
,
o
u
r
s
y
s
tem
en
ab
les
p
r
e
-
d
ec
is
io
n
ex
p
lo
r
atio
n
,
s
u
p
p
o
r
tin
g
d
is
co
v
er
y
o
f
n
o
n
-
m
ai
n
s
tr
ea
m
o
r
u
n
d
er
-
v
is
ited
lo
ca
tio
n
s
.
W
h
ile
[
2
5
]
,
[
3
2
]
,
an
d
[
3
5
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
meth
o
d
cla
s
s
ifyin
g
th
e
d
o
me
s
tic
to
u
r
is
t d
esti
n
a
tio
n
b
a
s
e
s
imila
r
ity
mea
s
u
r
in
g
(
N
g
u
ye
n
Th
i H
o
i
)
747
p
r
esen
t
a
h
y
b
r
i
d
r
ec
o
m
m
en
d
atio
n
f
r
am
ew
o
r
k
,
th
e
ac
c
u
r
ac
y
m
etr
ics
ac
h
iev
e
d
th
r
o
u
g
h
o
u
r
T
F
-
I
DF+c
o
s
in
e
s
im
ilar
ity
+L
STM
en
s
em
b
le
d
em
o
n
s
tr
ated
s
u
p
er
i
o
r
p
e
r
f
o
r
m
an
ce
an
d
l
o
wer
er
r
o
r
r
ates.
B
ased
o
n
em
p
ir
ical
f
in
d
in
g
s
,
s
ev
er
al
s
tr
a
teg
ic
en
h
a
n
ce
m
en
ts
ar
e
r
ec
o
m
m
en
d
ed
to
elev
ate
th
e
s
y
s
te
m
’
s
ac
cu
r
ac
y
an
d
a
p
p
lica
b
ilit
y
:
i)
Data
s
et
ex
p
an
s
io
n
:
in
cr
ea
s
i
n
g
th
e
n
u
m
b
er
o
f
cu
r
ated
d
esti
n
atio
n
en
tr
ies
will
i
m
p
r
o
v
e
m
o
d
el
g
en
er
aliza
tio
n
,
r
ed
u
ce
v
ec
to
r
s
p
ar
s
ity
,
an
d
e
n
h
an
ce
r
ec
o
m
m
e
n
d
atio
n
d
iv
er
s
ity
[
1
]
,
[
1
8
]
,
[
2
2
]
,
[
2
9
]
,
[
3
0
]
.
ii)
Mu
ltimo
d
al
d
ata
in
teg
r
atio
n
:
en
r
ich
in
g
th
e
d
ataset
with
u
s
er
r
ev
iews,
GPS
tr
ac
es,
a
n
d
v
is
u
al
d
at
a
(
im
ag
es,
v
id
e
o
s
)
wo
u
ld
im
p
r
o
v
e
c
o
n
tex
t
awa
r
en
ess
,
en
ab
l
in
g
em
o
tio
n
ally
in
tellig
en
t
an
d
s
itu
atio
n
all
y
r
elev
an
t su
g
g
esti
o
n
s
[
2
0
]
,
[
2
6
]
,
[
3
1
]
,
[
3
8
]
.
iii)
C
r
o
s
s
-
d
o
m
ain
tr
an
s
f
er
ab
ilit
y
:
th
e
cu
r
r
en
t
f
r
am
ewo
r
k
’
s
m
o
d
u
lar
d
esig
n
en
ab
les
ea
s
y
tr
an
s
f
er
to
d
o
m
ain
s
s
u
ch
as
ed
u
ca
tio
n
(
co
u
r
s
e
r
ec
o
m
m
en
d
atio
n
)
,
en
ter
tain
m
en
t
(
m
o
v
ie
o
r
ev
en
t
s
u
g
g
esti
o
n
s
)
,
a
n
d
h
ea
lth
c
ar
e
(
welln
ess
s
er
v
ices)
,
wh
er
e
p
e
r
s
o
n
alize
d
co
n
ten
t
d
eliv
er
y
c
an
d
r
i
v
e
u
s
er
en
g
a
g
em
en
t
[
2
3
]
,
[
3
3
]
,
[
3
5
]
,
[
3
9
]
.
B
y
in
co
r
p
o
r
atin
g
th
ese
en
h
an
ce
m
en
ts
,
th
e
p
r
o
p
o
s
ed
r
ec
o
m
m
en
d
atio
n
en
g
in
e
is
ex
p
ec
te
d
to
ev
o
lv
e
in
to
a
s
ca
lab
le,
d
o
m
ain
-
i
n
d
ep
e
n
d
en
t,
an
d
h
ig
h
ly
ad
ap
tiv
e
s
y
s
tem
ca
p
ab
le
o
f
d
eliv
er
in
g
p
er
s
o
n
alize
d
an
d
co
n
tex
tu
ally
m
ea
n
in
g
f
u
l r
ec
o
m
m
en
d
atio
n
s
in
b
o
th
t
o
u
r
is
m
an
d
b
r
o
ad
er
k
n
o
wled
g
e
-
b
ased
ap
p
licatio
n
ar
ea
s
.
5.
CO
NCLU
SI
O
N
I
n
co
n
clu
s
io
n
,
th
is
s
tu
d
y
p
r
esen
ts
a
p
r
ac
tical
an
d
ef
f
ec
tiv
e
s
o
lu
t
io
n
f
o
r
alig
n
in
g
u
s
er
p
r
ef
er
en
ce
s
,
ex
p
r
ess
ed
in
n
at
u
r
al
lan
g
u
ag
e,
with
s
tr
u
ctu
r
ed
d
esti
n
atio
n
m
etad
ata.
B
y
ap
p
l
y
in
g
c
o
n
t
en
t
-
b
ased
f
ilter
in
g
g
r
o
u
n
d
ed
in
s
em
a
n
tic
s
im
ilar
ity
,
th
e
s
y
s
tem
d
eliv
er
s
p
er
s
o
n
alize
d
d
o
m
esti
c
to
u
r
is
m
r
ec
o
m
m
en
d
atio
n
s
.
C
o
r
e
tech
n
iq
u
es
s
u
ch
as
N
-
g
r
am
d
e
co
m
p
o
s
itio
n
,
T
F
-
I
DF
v
ec
to
r
iz
atio
n
,
an
d
th
e
u
s
e
o
f
a
d
o
m
ain
-
s
p
ec
if
ic
d
ictio
n
ar
y
allo
w
f
o
r
d
ee
p
er
in
ter
p
r
etatio
n
o
f
u
s
er
in
ten
t.
T
h
e
in
teg
r
ati
o
n
o
f
s
im
ilar
ity
m
etr
ics
lik
e
C
o
s
in
e
Similar
ity
an
d
Pear
s
o
n
C
o
r
r
elatio
n
en
s
u
r
es
ac
cu
r
ate
q
u
er
y
m
atc
h
in
g
.
E
x
p
er
im
en
tal
r
esu
lts
d
em
o
n
s
tr
ate
th
e
s
y
s
tem
’
s
ef
f
ec
tiv
en
ess
in
ca
p
tu
r
in
g
u
s
er
ex
p
ec
tatio
n
s
th
r
o
u
g
h
r
elev
an
t
s
u
g
g
esti
o
n
s
.
T
h
e
f
in
d
in
g
s
h
ig
h
lig
h
t
th
e
im
p
o
r
tan
ce
o
f
d
ataset
s
ca
le
an
d
s
em
an
tic
d
iv
er
s
ity
in
o
p
tim
izin
g
r
ec
o
m
m
en
d
atio
n
p
er
f
o
r
m
an
ce
.
T
h
is
ap
p
r
o
ac
h
also
p
r
o
v
es
to
b
e
f
lex
ib
le
an
d
s
ca
lab
le,
with
t
h
e
p
o
ten
tial
f
o
r
ex
ten
s
io
n
to
o
th
er
ap
p
licatio
n
d
o
m
ain
s
.
Ad
d
itio
n
ally
,
th
e
f
r
a
m
ewo
r
k
s
u
p
p
o
r
ts
m
u
ltil
in
g
u
al
ca
p
ab
ilit
ies with
m
in
im
al
ad
ap
tatio
n
.
Ultim
ately
,
th
is
r
esear
ch
co
n
tr
i
b
u
tes
a
r
o
b
u
s
t
f
o
u
n
d
atio
n
f
o
r
i
n
tellig
en
t,
u
s
er
-
ce
n
tr
ic
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
in
th
e
f
ield
o
f
d
ig
ital to
u
r
is
m
.
ACK
NO
WL
E
DG
M
E
N
T
S
W
e
wo
u
ld
lik
e
to
ex
p
r
ess
o
u
r
s
in
ce
r
e
ap
p
r
ec
iatio
n
to
th
e
s
tu
d
en
t
g
r
o
u
p
f
r
o
m
T
h
u
o
n
g
m
ai
Un
iv
er
s
ity
f
o
r
th
eir
v
alu
ab
le
s
u
p
p
o
r
t i
n
d
ata
co
llectio
n
an
d
p
r
ep
r
o
ce
s
s
in
g
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
is
f
u
n
d
e
d
b
y
T
h
u
o
n
g
m
ai
Un
iv
er
s
ity
,
Han
o
i
,
Vietn
am
.
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
Ng
u
y
en
T
h
i H
o
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
T
r
an
T
h
i N
h
u
n
g
✓
✓
✓
✓
✓
✓
✓
✓
✓
B
u
i
Qu
an
g
T
r
u
o
n
g
✓
✓
✓
✓
✓
✓
✓
✓
Ng
u
y
en
Qu
a
n
g
T
r
u
n
g
✓
✓
✓
✓
✓
✓
✓
✓
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
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
3
,
Sep
tem
b
er
20
25
:
7
40
-
7
50
748
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
th
e
r
e
ar
e
n
o
c
o
n
f
licts
o
f
in
ter
est r
ela
ted
to
th
is
s
tu
d
y
.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
all
in
d
iv
id
u
als in
c
lu
d
ed
in
t
h
is
s
tu
d
y
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
e
r
esear
ch
r
elate
d
to
h
u
m
a
n
u
s
e
h
as
b
ee
n
co
m
p
il
e
d
with
all
th
e
r
elev
an
t
n
atio
n
al
r
eg
u
l
atio
n
s
an
d
in
s
titu
tio
n
al
p
o
licies
in
ac
co
r
d
an
ce
with
th
e
te
n
ets
o
f
t
h
e
He
ls
in
k
i
Dec
lar
atio
n
an
d
h
as
b
ee
n
ap
p
r
o
v
e
d
b
y
th
e
au
th
o
r
s
'
in
s
titu
tio
n
al
r
ev
iew
b
o
ar
d
o
r
eq
u
i
v
alen
t c
o
m
m
ittee.
DATA AV
AI
L
AB
I
L
I
T
Y
All
d
ata
u
tili
ze
d
f
o
r
th
e
test
in
g
p
h
ase
wer
e
s
y
s
tem
atica
lly
co
llected
f
r
o
m
r
e
p
u
tab
le
tr
a
v
el
web
s
ites
f
ea
tu
r
in
g
d
o
m
esti
c
d
esti
n
atio
n
s
ac
r
o
s
s
Vietn
am
.
A
co
m
p
r
eh
en
s
iv
e
lis
t
o
f
th
ese
d
ata
s
o
u
r
ce
s
is
p
r
esen
ted
in
T
ab
le
1
o
f
th
is
p
ap
er
.
RE
F
E
R
E
NC
E
S
[
1
]
C
.
H
u
d
a
,
Y
.
H
e
r
y
a
d
i
,
Lu
k
a
s
,
a
n
d
W
.
B
u
d
i
h
a
r
t
o
,
“
S
mar
t
t
o
u
r
i
sm
r
e
c
o
m
me
n
d
e
r
s
y
st
e
m
m
o
d
e
l
i
n
g
b
a
se
d
o
n
h
y
b
r
i
d
t
e
c
h
n
i
q
u
e
a
n
d
c
o
n
t
e
n
t
b
o
o
s
t
e
d
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
1
3
1
7
9
4
–
1
3
1
8
0
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
4
5
0
8
8
2
.
[
2
]
D
.
F
a
h
r
i
z
a
l
,
J.
K
u
s
t
i
j
a
,
a
n
d
M
.
A
.
H
.
A
k
b
a
r
,
“
D
e
v
e
l
o
p
me
n
t
t
o
u
r
i
sm
d
e
s
t
i
n
a
t
i
o
n
r
e
c
o
m
me
n
d
a
t
i
o
n
s
y
s
t
e
ms
u
s
i
n
g
c
o
l
l
a
b
o
r
a
t
i
v
e
a
n
d
c
o
n
t
e
n
t
-
b
a
se
d
f
i
l
t
e
r
i
n
g
o
p
t
i
mi
z
e
d
w
i
t
h
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
D
a
t
a
Mi
n
i
n
g
,
v
o
l
.
7
,
n
o
.
2
,
p
.
2
8
5
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
2
4
0
1
4
/
i
j
a
i
d
m.
v
7
i
2
.
2
8
7
1
3
.
[
3
]
N
.
K
h
a
n
a
n
d
D
r
.
M
.
H
a
r
o
o
n
,
“
Tr
e
n
d
s
a
n
d
t
e
c
h
n
i
q
u
e
s
u
se
d
i
n
t
o
u
r
i
st
r
e
c
o
mm
e
n
d
e
r
sy
s
t
e
m
:
a
r
e
v
i
e
w
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
i
e
n
t
i
f
i
c
Re
s
e
a
r
c
h
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
En
g
i
n
e
e
ri
n
g
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
9
,
n
o
.
3
,
p
p
.
3
3
–
3
9
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
3
2
6
2
8
/
C
S
EI
T2
3
9
0
2
1
0
5
.
[
4
]
W.
-
C
.
Li
n
,
C
.
K
.
W
u
,
T.
K
.
T
.
L
e
,
a
n
d
N
.
A
.
N
g
u
y
e
n
,
“
A
ssessm
e
n
t
o
f
V
i
e
t
n
a
m
t
o
u
r
i
sm
r
e
c
o
v
e
r
y
st
r
a
t
e
g
i
e
s a
f
t
e
r
C
O
V
I
D
-
1
9
u
s
i
n
g
mu
l
t
i
-
c
r
i
t
e
r
i
a
d
e
c
i
si
o
n
-
m
a
k
i
n
g
a
p
p
r
o
a
c
h
,
”
S
u
st
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
5
,
n
o
.
1
3
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
5
1
3
1
0
0
4
7
.
[
5
]
W
o
r
l
d
Tr
a
v
e
l
&
T
o
u
r
i
sm
C
o
u
n
c
i
l
,
“
Tr
a
v
e
l
&
t
o
u
r
i
sm
e
c
o
n
o
mi
c
i
m
p
a
c
t
r
e
sea
r
c
h
(
EI
R
)
,
”
W
o
r
l
d
Tr
a
v
e
l
&
To
u
r
i
sm
C
o
u
n
c
i
l
.
A
c
c
e
ss
e
d
:
M
a
r
.
1
0
,
2
0
2
5
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
t
t
c
.
o
r
g
/
r
e
se
a
r
c
h
/
e
c
o
n
o
m
i
c
-
i
mp
a
c
t
[
6
]
W
o
r
l
d
Tr
a
v
e
l
&
T
o
u
r
i
sm
C
o
u
n
c
i
l
,
“
V
i
e
t
n
a
m’
s
t
r
a
v
e
l
&
t
o
u
r
i
s
m
se
t
f
o
r
a
r
e
c
o
r
d
2
0
2
4
,
”
W
o
r
l
d
Tr
a
v
e
l
&
To
u
r
i
sm
C
o
u
n
c
i
l
.
A
c
c
e
ss
e
d
:
M
a
r
.
1
0
,
2
0
2
5
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
t
t
c
.
o
r
g
/
n
e
w
s/
v
i
e
t
n
a
ms
-
t
r
a
v
e
l
-
a
n
d
-
t
o
u
r
i
s
m
-
se
t
-
f
o
r
-
a
-
r
e
c
o
r
d
-
2
0
2
4
[
7
]
Tr
a
d
i
n
g
Ec
o
n
o
m
i
c
s
,
“
V
i
e
t
n
a
m
G
D
P
a
n
n
u
a
l
g
r
o
w
t
h
r
a
t
e
,
”
Tr
a
d
i
n
g
Ec
o
n
o
mi
c
s
.
A
c
c
e
sse
d
:
A
u
g
.
1
2
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
t
r
a
d
i
n
g
e
c
o
n
o
mi
c
s
.
c
o
m/
v
i
e
t
n
a
m/
g
d
p
-
g
r
o
w
t
h
-
a
n
n
u
a
l
[
8
]
G
e
n
e
r
a
l
S
t
a
t
i
st
i
c
s
O
f
f
i
c
e
o
f
V
i
e
t
n
a
m,
“
S
o
c
i
o
-
e
c
o
n
o
mi
c
si
t
u
a
t
i
o
n
r
e
p
o
r
t
i
n
Ju
l
y
a
n
d
7
m
o
n
t
h
s
o
f
2
0
2
3
,
”
2
0
2
3
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
n
so
.
g
o
v
.
v
n
/
e
n
/
d
a
t
a
-
a
n
d
-
s
t
a
t
i
st
i
c
s
/
2
0
2
3
/
0
8
/
so
c
i
o
-
e
c
o
n
o
mi
c
-
si
t
u
a
t
i
o
n
-
r
e
p
o
r
t
-
in
-
j
u
l
y
-
a
n
d
-
7
-
mo
n
t
h
s
-
of
-
2
0
2
3
/
#
:
~
:
t
e
x
t
=
S
t
a
t
e
b
u
d
g
e
t
r
e
v
e
n
u
e
a
n
d
e
x
p
e
n
d
i
t
u
r
e
&
t
e
x
t
=
To
t
a
l
s
t
a
t
e
b
u
d
g
e
t
e
x
p
e
n
d
i
t
u
r
e
i
n
,
t
h
e
sam
e
p
e
r
i
o
d
l
a
st
y
e
a
r
.
[
9
]
V
i
e
t
n
a
m
N
a
t
i
o
n
a
l
A
u
t
h
o
r
i
t
y
o
f
T
o
u
r
i
sm,
“
V
i
e
t
n
a
m
t
o
u
r
i
sm
st
a
t
i
st
i
c
s
2
0
2
3
,
”
T
o
u
r
i
sm
I
n
f
o
r
ma
t
i
o
n
Te
c
h
n
o
l
o
g
y
C
e
n
t
e
r
.
A
c
c
e
ss
e
d
:
A
u
g
.
1
2
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
v
i
e
t
n
a
mt
o
u
r
i
sm.
g
o
v
.
v
n
/
e
n
/
st
a
t
i
st
i
c
/
i
n
t
e
r
n
a
t
i
o
n
a
l
[
1
0
]
M
i
n
i
s
t
r
y
o
f
C
u
l
t
u
r
e
,
S
p
o
r
t
s
a
n
d
T
o
u
r
i
sm,
“
S
y
m
p
o
s
i
u
m
‘
d
i
g
i
t
a
l
t
r
a
n
sf
o
r
ma
t
i
o
n
i
n
t
h
e
f
i
e
l
d
o
f
c
u
l
t
u
r
e
’
(
i
n
V
i
e
t
n
a
mese
:
h
ộ
i
t
h
ả
o
c
h
u
y
ê
n
đ
ề
‘
c
h
u
y
ể
n
đ
ổ
i
s
ố
t
r
o
n
g
l
ĩ
n
h
v
ự
c
v
ă
n
h
ó
a
’
)
,
”
M
i
n
i
s
t
r
y
o
f
C
u
l
t
u
r
e
,
S
p
o
r
t
s
a
n
d
To
u
r
i
sm
.
A
c
c
e
sse
d
:
M
a
r
.
1
0
,
2
0
2
5
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
b
v
h
t
t
d
l
.
g
o
v
.
v
n
/
h
o
i
-
t
h
a
o
-
c
h
u
y
e
n
-
de
-
c
h
u
y
e
n
-
d
o
i
-
so
-
t
r
o
n
g
-
l
i
n
h
-
v
u
c
-
v
a
n
-
h
o
a
-
2
0
2
5
0
6
0
4
0
9
3
7
0
9
4
1
8
.
h
t
m
[
1
1
]
Ng
.
D
.
T
h
a
n
g
,
“
C
u
l
t
u
r
a
l
r
e
s
o
u
r
c
e
s
p
r
o
mo
t
e
t
o
u
r
i
sm
d
e
v
e
l
o
p
m
e
n
t
i
n
V
i
e
t
n
a
m,”
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
En
g
i
n
e
e
ri
n
g
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
1
0
,
n
o
.
4
7
s
,
p
p
.
2
0
6
–
2
1
4
,
M
a
y
2
0
2
5
,
d
o
i
:
1
0
.
5
2
7
8
3
/
j
i
se
m.v
1
0
i
4
7
s
.
9
2
4
8
.
[
1
2
]
H
.
D
.
T.
A
n
h
,
H
.
N
.
K
.
G
i
a
o
,
a
n
d
H
.
T.
H
.
L
a
n
,
“
Th
e
i
mp
a
c
t
o
f
s
mart
t
o
u
r
i
sm
e
c
o
s
y
st
e
m
o
n
t
o
u
r
i
st
s’
r
e
t
u
r
n
i
n
t
e
n
t
i
o
n
:
t
h
e
c
a
s
e
o
f
H
o
c
h
i
M
i
n
h
C
i
t
y
,
V
i
e
t
n
a
m
,
”
i
n
Th
e
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
r
e
n
c
e
o
n
H
o
sp
i
t
a
l
i
t
y
a
n
d
T
o
u
r
i
sm
:
T
ra
n
sf
o
rm
a
t
i
v
e
T
re
n
d
s
S
h
a
p
i
n
g
t
h
e
Fu
t
u
r
e
o
f
S
u
st
a
i
n
a
b
l
e
T
o
u
r
i
sm
,
N
h
a
Tr
a
n
g
,
V
i
e
t
n
a
m:
I
n
t
e
r
n
a
t
i
o
n
a
l
Jo
i
n
t
C
o
n
f
e
r
e
n
c
e
o
n
H
o
s
p
i
t
a
l
i
t
y
a
n
d
T
o
u
r
i
sm
2
0
2
4
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
r
e
s
e
a
r
c
h
g
a
t
e
.
n
e
t
/
p
u
b
l
i
c
a
t
i
o
n
/
3
8
6
2
4
4
5
8
9
_
T
h
e
_
i
mp
a
c
t
_
o
f
_
sm
a
r
t
_
t
o
u
r
i
sm
_
e
c
o
sy
s
t
e
m
_
o
n
_
t
o
u
r
i
s
t
s%
2
7
_
r
e
t
u
r
n
_
i
n
t
e
n
t
i
o
n
_
Th
e
_
c
a
s
e
_
o
f
_
H
o
C
h
i
_
M
i
n
h
_
C
i
t
y
_
V
i
e
t
n
a
m
[
1
3
]
T.
H
o
e
t
a
l
.
,
“
A
n
e
w
m
o
d
e
l
f
o
r
c
o
l
l
e
c
t
i
n
g
,
st
o
r
i
n
g
,
a
n
d
a
n
a
l
y
z
i
n
g
b
i
g
d
a
t
a
o
n
c
u
s
t
o
m
e
r
f
e
e
d
b
a
c
k
i
n
t
h
e
t
o
u
r
i
s
m
i
n
d
u
st
r
y
,
”
I
n
t
e
r
d
i
sci
p
l
i
n
a
r
y
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
,
K
n
o
w
l
e
d
g
e
,
a
n
d
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
1
8
,
p
p
.
2
2
5
–
2
4
9
,
2
0
2
3
,
d
o
i
:
1
0
.
2
8
9
4
5
/
5
1
0
7
.
[
1
4
]
H
.
T.
H
o
i
,
“
A
d
v
e
r
t
i
si
n
g
V
i
e
t
n
a
m’
s
t
o
u
r
i
sm
p
r
o
d
u
c
t
s
i
n
t
h
e
t
e
c
h
n
o
l
o
g
y
a
g
e
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Ma
n
a
g
e
m
e
n
t
o
f
e
-
C
o
m
m
e
r
c
e
a
n
d
e
-
G
o
v
e
r
n
m
e
n
t
,
N
e
w
Y
o
r
k
,
N
Y
,
U
S
A
:
A
C
M
,
Ju
l
.
2
0
2
0
,
p
p
.
1
1
–
1
5
.
d
o
i
:
1
0
.
1
1
4
5
/
3
4
0
9
8
9
1
.
3
4
0
9
8
9
2
.
[
1
5
]
P
.
D
o
,
T.
H
.
V
.
P
h
a
n
,
a
n
d
B
.
B
.
G
u
p
t
a
,
“
D
e
v
e
l
o
p
i
n
g
a
V
i
e
t
n
a
mes
e
t
o
u
r
i
sm
q
u
e
s
t
i
o
n
a
n
sw
e
r
i
n
g
sy
s
t
e
m
u
s
i
n
g
k
n
o
w
l
e
d
g
e
g
r
a
p
h
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
A
C
M
T
r
a
n
s
a
c
t
i
o
n
s
o
n
As
i
a
n
a
n
d
L
o
w
-
Re
so
u
rc
e
L
a
n
g
u
a
g
e
I
n
f
o
rm
a
t
i
o
n
Pr
o
c
e
ss
i
n
g
,
v
o
l
.
2
0
,
n
o
.
5
,
p
p
.
1
–
1
8
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
5
3
6
5
1
.
[
1
6
]
Z.
A
.
-
M
o
u
d
,
H
.
V
.
-
N
e
j
a
d
,
a
n
d
J.
S
a
d
r
i
,
“
To
u
r
i
sm
r
e
c
o
mm
e
n
d
a
t
i
o
n
sy
st
e
m
b
a
s
e
d
o
n
s
e
ma
n
t
i
c
c
l
u
s
t
e
r
i
n
g
a
n
d
se
n
t
i
m
e
n
t
a
n
a
l
y
si
s,
”
Ex
p
e
rt
S
y
st
e
m
s w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
6
7
,
p
.
1
1
4
3
2
4
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
0
.
1
1
4
3
2
4
.
[
1
7
]
A
.
B
a
n
e
r
j
e
e
,
A
.
S
a
t
i
s
h
,
F
.
N
.
A
i
s
y
a
h
,
W
.
W
ö
r
n
d
l
,
a
n
d
Y
.
D
e
l
d
j
o
o
,
“
S
y
n
t
h
TR
I
P
s:
a
k
n
o
w
l
e
d
g
e
-
g
r
o
u
n
d
e
d
f
r
a
mew
o
r
k
f
o
r
b
e
n
c
h
mar
k
d
a
t
a
g
e
n
e
r
a
t
i
o
n
f
o
r
p
e
r
s
o
n
a
l
i
z
e
d
t
o
u
r
i
sm
r
e
c
o
mm
e
n
d
e
r
s,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
4
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
A
C
M
S
I
G
I
R
C
o
n
f
e
re
n
c
e
o
n
Re
se
a
r
c
h
a
n
d
D
e
v
e
l
o
p
m
e
n
t
i
n
I
n
f
o
rm
a
t
i
o
n
Re
t
ri
e
v
a
l
,
N
e
w
Y
o
r
k
,
N
Y
,
U
S
A
:
A
C
M
,
J
u
l
.
2
0
2
5
,
p
p
.
3
7
4
3
–
3
7
5
2
.
d
o
i
:
1
0
.
1
1
4
5
/
3
7
2
6
3
0
2
.
3
7
3
0
3
2
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
meth
o
d
cla
s
s
ifyin
g
th
e
d
o
me
s
tic
to
u
r
is
t d
esti
n
a
tio
n
b
a
s
e
s
imila
r
ity
mea
s
u
r
in
g
(
N
g
u
ye
n
Th
i H
o
i
)
749
[
1
8
]
M
.
B
a
d
o
u
c
h
a
n
d
M
.
B
o
u
t
a
o
u
n
t
e
,
“
P
e
r
so
n
a
l
i
z
e
d
t
r
a
v
e
l
r
e
c
o
mm
e
n
d
a
t
i
o
n
sy
st
e
ms:
a
st
u
d
y
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
i
n
t
o
u
r
i
sm
,
”
Jo
u
r
n
a
l
o
f
A
rt
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
a
n
d
N
e
u
ra
l
N
e
t
w
o
rk
,
v
o
l
.
3
,
n
o
.
3
,
p
p
.
3
5
–
4
5
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
5
5
5
2
9
/
j
a
i
ml
n
n
.
3
3
.
3
5
.
4
5
.
[
1
9
]
A
.
P
r
a
mar
t
a
a
n
d
A
.
B
a
i
z
a
l
,
“
H
y
b
r
i
d
r
e
c
o
mm
e
n
d
e
r
s
y
s
t
e
m
u
s
i
n
g
si
n
g
u
l
a
r
v
a
l
u
e
d
e
c
o
m
p
o
s
i
t
i
o
n
a
n
d
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
i
n
B
a
l
i
t
o
u
r
i
sm
,
”
J
u
r
n
a
l
I
l
m
i
a
h
Pe
n
e
l
i
t
i
a
n
d
a
n
P
e
m
b
e
l
a
j
a
r
a
n
I
n
f
o
rm
a
t
i
k
a
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
4
0
8
–
4
1
8
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
2
9
1
0
0
/
j
i
p
i
.
v
7
i
2
.
2
7
7
0
.
[
2
0
]
I
.
F
a
t
h
i
m
a
a
n
d
B
.
K
o
t
a
i
a
h
,
“
D
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
t
o
u
r
i
sm
r
e
c
o
mm
e
n
d
a
t
i
o
n
sy
s
t
e
m
,
”
S
S
RN
El
e
c
t
r
o
n
i
c
J
o
u
r
n
a
l
,
2
0
2
2
,
d
o
i
:
1
0
.
2
1
3
9
/
s
sr
n
.
4
2
8
6
5
7
5
.
[
2
1
]
B
.
H
.
C
,
V
i
j
a
y
,
S
.
M
,
Y
.
V
,
a
n
d
S
.
H
.
G
,
“
P
e
r
so
n
a
l
i
z
e
d
t
r
a
v
e
l
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
s
t
e
m
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
Re
s
e
a
r
c
h
a
n
d
I
n
n
o
v
a
t
i
v
e
I
d
e
a
s
i
n
Ed
u
c
a
t
i
o
n
,
v
o
l
.
9
,
n
o
.
3
,
2
0
2
3
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
i
j
a
r
i
i
e
.
c
o
m/
A
d
mi
n
U
p
l
o
a
d
P
d
f
/
P
e
r
so
n
a
l
i
z
e
d
_
Tr
a
v
e
l
_
R
e
c
o
mm
e
n
d
a
t
i
o
n
_
S
y
s
t
e
m
_
U
si
n
g
_
M
a
c
h
i
n
e
_
Le
a
r
n
i
n
g
_
i
j
a
r
i
i
e
2
0
3
5
3
.
p
d
f
?
sr
sl
t
i
d
=
A
f
mBO
o
o
d
-
mS
K
Zi
p
a
JT3
q
T
G
4
A
EFP
C
2
M
U
i
h
S
2
V
F
2
c
z
g
j
a
D
EO
g
7
K
s
5
mT
p
9
k
[
2
2
]
J.
K
a
r
t
h
i
y
a
y
i
n
i
a
n
d
R
.
J.
A
n
a
n
d
h
i
,
“
P
e
r
so
n
a
l
i
z
e
d
t
r
a
v
e
l
r
e
c
o
m
me
n
d
a
t
i
o
n
s
s
y
st
e
m
u
s
i
n
g
h
y
b
r
i
d
f
i
l
t
e
r
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
.
”
R
e
se
a
r
c
h
S
q
u
a
r
e
,
N
o
v
.
2
7
,
2
0
2
4
.
d
o
i
:
1
0
.
2
1
2
0
3
/
r
s
.
3
.
r
s
-
5
4
0
8
4
4
2
/
v
1
.
[
2
3
]
X
.
X
i
a
o
,
C
.
Li
,
X
.
W
a
n
g
,
a
n
d
A
.
Ze
n
g
,
“
P
e
r
s
o
n
a
l
i
z
e
d
t
o
u
r
i
s
m
r
e
c
o
mm
e
n
d
a
t
i
o
n
m
o
d
e
l
b
a
se
d
o
n
t
e
m
p
o
r
a
l
m
u
l
t
i
l
a
y
e
r
se
q
u
e
n
t
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
5
,
n
o
.
1
,
J
a
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
4
-
8
4
5
8
1
-
z.
[
2
4
]
Y
.
M
o
s
h
f
e
g
h
i
,
B
.
P
i
w
o
w
a
r
sk
i
,
a
n
d
J.
M
.
Jo
s
e
,
“
H
a
n
d
l
i
n
g
d
a
t
a
sp
a
r
si
t
y
i
n
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
u
s
i
n
g
e
m
o
t
i
o
n
a
n
d
sem
a
n
t
i
c
b
a
s
e
d
f
e
a
t
u
r
e
s,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
3
4
t
h
i
n
t
e
rn
a
t
i
o
n
a
l
AC
M
S
I
G
I
R
c
o
n
f
e
r
e
n
c
e
o
n
R
e
se
a
rc
h
a
n
d
d
e
v
e
l
o
p
m
e
n
t
i
n
I
n
f
o
rm
a
t
i
o
n
Re
t
r
i
e
v
a
l
,
N
e
w
Y
o
r
k
,
N
Y
,
U
S
A
:
A
C
M
,
J
u
l
.
2
0
1
1
,
p
p
.
6
2
5
–
6
3
4
.
d
o
i
:
1
0
.
1
1
4
5
/
2
0
0
9
9
1
6
.
2
0
1
0
0
0
1
.
[
2
5
]
N
.
L.
H
o
,
R
.
K
.
-
W
.
L
e
e
,
a
n
d
K
.
H
.
Li
m,
“
S
B
T
R
E
C
-
a
t
r
a
n
sf
o
r
mer
f
r
a
m
e
w
o
r
k
f
o
r
p
e
r
so
n
a
l
i
z
e
d
t
o
u
r
r
e
c
o
mm
e
n
d
a
t
i
o
n
p
r
o
b
l
e
m
w
i
t
h
se
n
t
i
me
n
t
a
n
a
l
y
si
s,
”
i
n
2
0
2
3
I
EEE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Bi
g
D
a
t
a
(
B
i
g
D
a
t
a
)
,
I
EEE,
D
e
c
.
2
0
2
3
,
p
p
.
5
7
9
0
–
5
7
9
8
.
d
o
i
:
1
0
.
1
1
0
9
/
B
i
g
D
a
t
a
5
9
0
4
4
.
2
0
2
3
.
1
0
3
8
6
4
8
6
.
[
2
6
]
M
.
H
.
N
g
u
y
e
n
,
T
.
T.
N
g
u
y
e
n
,
M
.
N
.
Ta
,
T.
M
.
N
g
u
y
e
n
,
a
n
d
K
.
V
.
N
g
u
y
e
n
,
“
R
R
S
:
r
e
v
i
e
w
-
b
a
se
d
r
e
c
o
mm
e
n
d
a
t
i
o
n
sy
s
t
e
m
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
V
i
e
t
n
a
m
e
se
,”
S
N
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
5
,
n
o
.
5
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
9
7
9
-
024
-
0
2
8
1
2
-
6.
[
2
7
]
T.
H
.
N
g
u
y
e
n
,
D
.
Q
.
Tr
a
n
,
G
.
M
.
D
a
m,
a
n
d
M
.
H
.
N
g
u
y
e
n
,
“
Es
t
i
m
a
t
i
n
g
t
h
e
s
i
mi
l
a
r
i
t
y
o
f
s
o
c
i
a
l
n
e
t
w
o
r
k
u
sers
b
a
s
e
d
o
n
b
e
h
a
v
i
o
r
s,
”
V
i
e
t
n
a
m
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
5
,
n
o
.
2
,
p
p
.
1
6
5
–
1
7
5
,
M
a
y
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
5
9
5
-
018
-
0
1
1
2
-
1.
[
2
8
]
N
.
P
.
H
u
n
g
a
n
d
B
.
T.
K
h
o
a
,
“
A
p
p
l
y
i
n
g
smar
t
t
o
u
r
i
sm ma
n
a
g
e
m
e
n
t
i
n
V
i
e
t
n
a
m a
f
t
e
r
C
O
V
I
D
-
1
9
p
a
n
d
e
m
i
c
:
a
q
u
a
l
i
t
a
t
i
v
e
r
e
sea
r
c
h
,
”
Q
u
a
l
i
t
y
-
Ac
c
e
ss
t
o
S
u
c
c
e
s
s
,
v
o
l
.
2
4
,
n
o
.
1
9
4
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
4
7
7
5
0
/
Q
A
S
/
2
4
.
1
9
4
.
0
1
.
[
2
9
]
G
.
K
.
M
u
r
u
g
a
n
a
n
d
a
,
T.
S
.
S
.
A
n
g
e
l
,
S
.
K
u
m
a
r
,
N
.
S
n
e
h
a
l
a
t
h
a
,
a
n
d
S
.
S
.
M
a
n
i
p
a
u
l
,
“
A
r
e
a
l
-
t
i
m
e
t
o
u
r
i
s
m
r
e
c
o
mm
e
n
d
e
r
s
y
st
e
m
u
si
n
g
K
N
N
a
n
d
R
B
M
a
p
p
r
o
a
c
h
,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
a
t
a
S
c
i
e
n
c
e
,
A
g
e
n
t
s
and
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
I
EEE
,
D
e
c
.
2
0
2
3
,
p
p
.
1
–
5
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
S
A
A
I
5
9
3
1
3
.
2
0
2
3
.
1
0
4
5
2
5
5
8
.
[
3
0
]
S
.
K
o
n
g
p
e
n
g
a
n
d
A
.
H
a
n
s
k
u
n
a
t
a
i
,
“
To
u
r
i
s
t
d
e
st
i
n
a
t
i
o
n
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
s
t
e
m
b
a
se
d
o
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
4
9
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Bi
g
D
a
t
a
a
n
d
C
o
m
p
u
t
i
n
g
,
N
e
w
Y
o
r
k
,
N
Y
,
U
S
A
:
A
C
M
,
M
a
y
2
0
2
4
,
p
p
.
5
8
–
6
7
.
d
o
i
:
1
0
.
1
1
4
5
/
3
6
9
5
2
2
0
.
3
6
9
5
2
2
9
.
[
3
1
]
T.
A
.
W
.
Ty
a
s,
Z
.
K
.
A
.
B
a
i
z
a
l
,
a
n
d
R
.
D
h
a
r
a
y
a
n
i
,
“
T
o
u
r
i
st
p
l
a
c
e
s
r
e
c
o
mm
e
n
d
e
r
s
y
s
t
e
m
u
si
n
g
c
o
s
i
n
e
s
i
m
i
l
a
r
i
t
y
a
n
d
si
n
g
u
l
a
r
v
a
l
u
e
d
e
c
o
m
p
o
si
t
i
o
n
me
t
h
o
d
s,
”
J
u
r
n
a
l
Me
d
i
a
I
n
f
o
rm
a
t
i
k
a
B
u
d
i
d
a
rm
a
,
v
o
l
.
5
,
n
o
.
4
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
3
0
8
6
5
/
m
i
b
.
v
5
i
4
.
3
1
5
1
.
[
3
2
]
P
.
Zh
a
n
g
,
J.
W
a
n
g
,
a
n
d
R
.
Li
,
“
T
o
u
r
i
sm
-
t
y
p
e
o
n
t
o
l
o
g
y
f
r
a
mew
o
r
k
f
o
r
t
o
u
r
i
sm
-
t
y
p
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
n
a
m
i
n
g
,
a
n
d
k
n
o
w
l
e
d
g
e
o
r
g
a
n
i
z
a
t
i
o
n
,
”
H
e
l
i
y
o
n
,
v
o
l
.
9
,
n
o
.
4
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
3
.
e
1
5
1
9
2
.
[
3
3
]
D
.
S
h
r
e
st
h
a
,
T.
W
e
n
a
n
,
D
.
S
h
r
e
st
h
a
,
N
.
R
a
j
k
a
r
n
i
k
a
r
,
a
n
d
S
.
-
R
.
J
e
o
n
g
,
“
P
e
r
so
n
a
l
i
z
e
d
t
o
u
r
i
s
t
r
e
c
o
mm
e
n
d
e
r
s
y
st
e
m:
a
d
a
t
a
-
d
r
i
v
e
n
a
n
d
m
a
c
h
i
n
e
-
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
1
2
,
n
o
.
3
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
mp
u
t
a
t
i
o
n
1
2
0
3
0
0
5
9
.
[
3
4
]
G
.
Ö
z
d
e
m
i
r
a
n
d
V
.
A
.
A
r
z
ı
k
,
“
S
e
g
men
t
a
t
i
o
n
o
f
so
c
i
a
l
me
d
i
a
u
sers
f
o
r
d
e
st
i
n
a
t
i
o
n
s,
”
T
o
u
r
i
sm
,
v
o
l
.
7
0
,
n
o
.
1
,
p
p
.
5
3
–
6
6
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
3
7
7
4
1
/
t
.
7
0
.
1
.
4
.
[
3
5
]
J.
Y
o
o
n
a
n
d
C
.
C
h
o
i
,
“
R
e
a
l
-
t
i
me
c
o
n
t
e
x
t
-
a
w
a
r
e
r
e
c
o
mm
e
n
d
a
t
i
o
n
sy
st
e
m
f
o
r
t
o
u
r
i
sm
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
3
,
n
o
.
7
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
0
7
3
6
7
9
.
[
3
6
]
Y
.
S
u
i
,
“
Q
u
e
s
t
i
o
n
a
n
sw
e
r
i
n
g
s
y
s
t
e
m
b
a
se
d
o
n
t
o
u
r
i
sm
k
n
o
w
l
e
d
g
e
g
r
a
p
h
,
”
J
o
u
r
n
a
l
o
f
Ph
y
si
c
s:
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s
,
v
o
l
.
1
8
8
3
,
n
o
.
1
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
8
8
3
/
1
/
0
1
2
0
6
4
.
[
3
7
]
J.
C
.
C
u
i
z
o
n
a
n
d
C
.
G
.
A
g
r
a
v
a
n
t
e
,
“
S
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
f
o
r
r
e
v
i
e
w
r
a
t
i
n
g
p
r
e
d
i
c
t
i
o
n
i
n
a
t
r
a
v
e
l
j
o
u
r
n
a
l
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
N
a
t
u
r
a
l
L
a
n
g
u
a
g
e
Pr
o
c
e
ss
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
o
n
Re
t
r
i
e
v
a
l
,
N
e
w
Y
o
r
k
,
N
Y
,
U
S
A
:
A
C
M
,
D
e
c
.
2
0
2
0
,
p
p
.
7
0
–
7
4
.
d
o
i
:
1
0
.
1
1
4
5
/
3
4
4
3
2
7
9
.
3
4
4
3
2
8
2
.
[
3
8
]
N
.
M
a
l
i
k
a
n
d
M
.
B
i
l
a
l
,
“
N
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
f
o
r
a
n
a
l
y
z
i
n
g
o
n
l
i
n
e
c
u
st
o
m
e
r
r
e
v
i
e
w
s:
a
s
u
r
v
e
y
,
t
a
x
o
n
o
m
y
,
a
n
d
o
p
e
n
r
e
sea
r
c
h
c
h
a
l
l
e
n
g
e
s,
”
Pe
e
r
J
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
0
,
J
u
l
.
2
0
2
4
,
d
o
i
:
1
0
.
7
7
1
7
/
p
e
e
r
j
-
c
s.
2
2
0
3
.
[
3
9
]
M
.
Á
.
Á
.
-
C
a
r
mo
n
a
e
t
a
l
.
,
“
N
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
a
p
p
l
i
e
d
t
o
t
o
u
r
i
s
m
r
e
sea
r
c
h
:
a
sy
s
t
e
m
a
t
i
c
r
e
v
i
e
w
a
n
d
f
u
t
u
r
e
r
e
se
a
r
c
h
d
i
r
e
c
t
i
o
n
s,
”
J
o
u
rn
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rsi
t
y
-
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
4
,
n
o
.
1
0
,
p
p
.
1
0
1
2
5
–
1
0
1
4
4
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
s
u
c
i
.
2
0
2
2
.
1
0
.
0
1
0
.
[
4
0
]
S
.
Q
a
i
s
e
r
a
n
d
R
.
A
l
i
,
“
Te
x
t
mi
n
i
n
g
:
u
se
o
f
TF
-
I
D
F
t
o
e
x
a
mi
n
e
t
h
e
r
e
l
e
v
a
n
c
e
o
f
w
o
r
d
s
t
o
d
o
c
u
me
n
t
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
8
1
,
n
o
.
1
,
p
p
.
2
5
–
2
9
,
J
u
l
.
2
0
1
8
,
d
o
i
:
1
0
.
5
1
2
0
/
i
j
c
a
2
0
1
8
9
1
7
3
9
5
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ng
u
y
e
n
Th
i
H
o
i
is
re
c
e
iv
e
d
a
P
h
.
D
.
i
n
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
fro
m
th
e
P
o
sta
l
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
(P
TIT
)
i
n
2
0
2
1
.
Cu
rre
n
tl
y
a
lec
tu
re
r
a
t
t
h
e
F
a
c
u
lt
y
o
f
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
a
n
d
Eco
n
o
m
ics
,
T
h
u
o
n
g
m
a
i
Un
i
v
e
rsity
(TM
U)
,
Vie
tn
a
m
.
Are
a
s
o
f
in
tere
st:
e
c
o
n
o
m
ic
i
n
fo
rm
a
ti
o
n
sy
ste
m
s
,
e
-
c
o
m
m
e
rc
e
sy
ste
m
s
,
a
n
d
so
c
i
a
l
c
o
m
p
u
ti
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
o
in
t@tmu
.
e
d
u
.
v
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.