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.
11
,
No
.
3
,
J
u
n
e
2
0
2
1
,
p
p
.
2
2
2
9
~
2
2
3
7
I
SS
N:
2
0
8
8
-
8708
,
DO
I
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
1
i
3
.
p
p
2
2
2
9
-
2
2
3
7
2229
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Inv
estig
a
ting the
Pag
eRa
nk
a
nd se
quence
predic
tion
bas
ed
a
ppro
a
ches for ne
x
t
pa
g
e predic
tion
Ng
uy
en
T
ho
n Da
1
,
T
a
n H
a
n
h
2
1
F
a
c
u
lt
y
o
f
In
f
o
r
m
a
ti
o
n
S
y
ste
m
s,
Un
iv
e
rsit
y
o
f
Eco
n
o
m
ics
a
n
d
L
a
w
,
V
NU
-
HCM,
V
iet
n
a
m
2
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
P
o
sts a
n
d
T
e
lec
o
m
m
u
n
ic
a
ti
o
n
s I
n
stit
u
te o
f
T
e
c
h
n
o
lo
g
y
,
V
i
e
tn
a
m
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l 2
5
,
2
0
2
0
R
ev
i
s
ed
D
ec
10
,
2
0
2
0
A
cc
ep
ted
D
ec
1
7
,
2
0
2
0
Disc
o
v
e
rin
g
u
n
se
e
n
p
a
tt
e
rn
s
f
ro
m
we
b
c
li
c
k
stre
a
m
i
s
a
n
u
p
c
o
m
in
g
re
se
a
rc
h
a
re
a
.
On
e
o
f
th
e
m
e
a
n
in
g
f
u
l
a
p
p
ro
a
c
h
e
s
f
o
r
m
a
k
in
g
p
re
d
ictio
n
s
is
u
sin
g
se
q
u
e
n
c
e
p
re
d
icti
o
n
t
h
a
t
is
ty
p
ica
ll
y
th
e
i
m
p
ro
v
e
d
c
o
m
p
a
c
t
p
re
d
i
c
ti
o
n
tree
(
CP
T
+
).
Ho
w
e
v
e
r,
to
in
c
re
a
se
th
i
s
m
e
t
h
o
d
'
s
e
ffe
c
ti
v
e
n
e
s
s,
c
o
m
b
in
in
g
it
w
it
h
a
t
lea
st
o
th
e
r
m
e
th
o
d
s
is
n
e
c
e
ss
a
ry
.
T
h
is
w
o
rk
in
v
e
stig
a
tes
su
c
h
P
a
g
e
Ra
n
k
-
b
a
se
d
m
e
th
o
d
s
re
late
d
to
se
q
u
e
n
c
e
p
re
d
ictio
n
a
s
A
ll
-
K
-
M
a
rk
o
v
,
D
G
,
M
a
r
k
o
v
1
st,
C
P
T
,
C
P
T
+
.
T
h
e
e
x
p
e
rime
n
tal
re
su
lt
s
p
ro
v
e
d
th
a
t
t
h
e
i
n
teg
ra
ti
o
n
o
f
CP
T
+
a
n
d
P
a
g
e
Ra
n
k
is
th
e
rig
h
t
so
lu
ti
o
n
f
o
r
n
e
x
t
p
a
g
e
p
re
d
ictio
n
in
term
s
o
f
a
c
c
u
ra
c
y
,
w
h
ich
is
m
o
re
th
a
n
a
s
tan
d
a
rd
m
e
th
o
d
o
f
a
p
p
ro
x
im
a
t
e
l
y
0
.
0
6
2
1
%
.
S
ti
ll
,
t
h
e
siz
e
o
f
th
e
n
e
w
l
y
c
re
a
te
d
se
q
u
e
n
c
e
d
a
tab
a
se
is
re
d
u
c
e
d
u
p
to
3
5
%
.
F
u
rth
e
rm
o
re
,
o
u
r
p
r
o
p
o
se
d
s
o
lu
ti
o
n
h
a
s
a
n
a
c
c
u
ra
c
y
th
a
t
is
m
u
c
h
h
ig
h
e
r
th
a
n
o
th
e
r
o
n
e
s.
It
is
in
tr
ig
u
in
g
f
o
r
th
e
n
e
x
t
p
h
a
se
(tes
ti
n
g
o
n
e
)
to
m
a
k
e
th
e
n
e
x
t
p
a
g
e
p
re
d
ictio
n
in
term
s o
f
ti
m
e
p
e
rf
o
r
m
a
n
c
e
.
K
ey
w
o
r
d
s
:
C
P
T
+
Ma
r
k
o
v
P
ag
eRan
k
Seq
u
en
ce
p
r
ed
ictio
n
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Ng
u
y
e
n
T
h
o
n
Da
Facu
lt
y
o
f
I
n
f
o
r
m
a
tio
n
S
y
s
te
m
s
Un
i
v
er
s
it
y
o
f
E
co
n
o
m
ics a
n
d
L
a
w
,
VNU
-
H
C
M
Qu
ar
ter
3
,
L
in
h
X
u
an
W
ar
d
,
T
h
u
D
u
c
Di
s
tr
ict,
Ho
C
h
i M
in
h
C
it
y
,
V
ietn
a
m
E
m
ail:
d
an
t@
u
el.
ed
u
.
v
n
1.
I
NT
RO
D
UCT
I
O
N
Seq
u
en
ce
lear
n
i
n
g
i
s
a
s
i
g
n
i
f
i
ca
n
t
co
m
p
o
n
en
t
o
f
lear
n
i
n
g
i
n
n
u
m
er
o
u
s
ar
ea
s
o
f
in
tel
lig
e
n
t
s
y
s
te
m
s
,
DN
A
s
eq
u
e
n
ci
n
g
[
1
]
an
d
w
e
b
p
ag
e
p
r
ed
ictio
n
.
W
ith
th
e
in
cr
ea
s
e
in
i
n
f
o
r
m
atio
n
an
d
c
o
m
m
u
n
icatio
n
,
t
h
e
s
tu
d
y
o
f
w
eb
p
ag
e
p
r
ed
ictio
n
b
ec
o
m
es
o
n
e
o
f
th
e
m
ea
n
in
g
f
u
l
an
d
ch
alle
n
g
i
n
g
ta
s
k
s
.
M
o
r
eo
v
er
,
Seq
u
en
tial
p
atter
n
m
i
n
in
g
is
a
v
er
y
ac
t
iv
e
r
esear
c
h
to
p
ic,
w
h
er
e
h
u
n
d
r
ed
s
o
f
p
ap
er
s
p
r
ese
n
t
n
e
w
alg
o
r
it
h
m
s
an
d
ap
p
licatio
n
s
ea
ch
y
ea
r
[
2
]
.
T
h
e
y
h
av
e
n
u
m
er
o
u
s
r
ea
l
-
li
f
e
ap
p
licatio
n
s
s
i
n
ce
d
ata
is
n
at
u
r
all
y
e
n
co
d
ed
as
s
eq
u
en
ce
s
o
f
s
y
m
b
o
l
s
i
n
m
a
n
y
f
ield
s
s
u
c
h
a
s
b
io
in
f
o
r
m
a
ti
cs,
m
ar
k
et
b
as
k
et
a
n
al
y
s
i
s
,
te
x
t
a
n
al
y
s
i
s
,
en
er
g
y
r
ed
u
ctio
n
in
s
m
ar
t
h
o
m
es,
w
e
b
p
ag
e
click
s
tr
ea
m
a
n
al
y
s
i
s
,
an
d
e
-
lear
n
i
n
g
[
2
]
.
On
e
o
f
th
e
cr
u
cial
b
r
an
ch
e
s
o
f
s
eq
u
en
tial
p
atter
n
m
i
n
i
n
g
is
s
eq
u
en
ce
p
r
ed
ictio
n
.
Gi
v
e
n
a
s
et
o
f
tr
ai
n
in
g
s
eq
u
e
n
ce
s
,
t
h
e
p
r
o
b
lem
o
f
s
eq
u
en
ce
p
r
ed
ictio
n
in
v
o
l
v
es
h
o
w
to
f
i
n
d
th
e
n
e
x
t
ite
m
o
f
a
tar
g
et
s
eq
u
en
ce
b
y
o
n
l
y
o
b
s
er
v
in
g
its
p
r
ev
io
u
s
ite
m
s
[
3
]
.
Nu
m
er
o
u
s
m
o
d
el
s
h
av
e
b
ee
n
p
r
o
p
o
s
ed
b
y
r
esear
ch
er
s
to
ad
d
r
ess
th
is
s
eq
u
e
n
ce
p
r
ed
ictio
n
is
s
u
e.
So
m
e
o
f
th
e
m
u
s
e,
f
o
r
ex
a
m
p
le,
n
e
u
r
al
n
et
w
o
r
k
s
,
p
atter
n
m
in
in
g
,
an
d
a
p
r
o
b
ab
ilis
tic
ap
p
r
o
ac
h
.
Ho
w
e
v
er
,
Ma
r
k
o
v
C
h
ai
n
s
a
r
e
also
p
r
ev
ailin
g
l
y
u
s
ed
f
o
r
th
is
.
As
an
e
s
s
e
n
tial
p
ar
t
o
f
d
ata
m
i
n
in
g
,
n
ex
t
p
ag
e
p
r
ed
ictio
n
h
as
b
ec
o
m
e
m
o
r
e
co
m
m
o
n
in
t
h
e
r
ea
l
w
o
r
ld
.
An
ex
a
m
p
le
o
f
th
i
s
is
click
s
tr
ea
m
an
a
l
y
s
is
t
h
at
o
n
e
o
f
its
s
ig
n
i
f
ica
n
t
tas
k
s
is
to
f
i
n
d
ess
e
n
tial
ite
m
s
an
d
is
also
o
n
e
o
f
t
h
e
h
o
t
to
p
ics
t
h
ese
d
a
y
s
.
T
h
e
p
r
in
cip
al
ai
m
o
f
th
is
ar
ticle
is
to
i
n
v
esti
g
at
e
v
ar
io
u
s
m
e
th
o
d
s
u
s
i
n
g
t
h
e
P
ag
eRa
n
k
an
d
s
eq
u
e
n
ce
f
o
r
n
ex
t
p
ag
e
p
r
ed
ictio
n
o
n
r
ea
l
clic
k
s
tr
ea
m
d
ataset
s
.
I
n
th
is
p
ap
er
'
s
s
co
p
e,
w
e
f
o
cu
s
o
n
tech
n
iq
u
e
s
r
elate
d
to
s
eq
u
en
ce
p
r
ed
ictio
n
f
o
r
n
ex
t
p
ag
e
p
r
ed
ictio
n
.
T
h
is
p
a
p
er
is
o
r
g
an
ized
as
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.
11
,
No
.
3
,
J
u
n
e
2
0
2
1
:
2
2
2
9
-
2237
2230
f
o
llo
w
s
.
Sectio
n
2
i
n
t
r
o
d
u
ce
s
th
e
b
ac
k
g
r
o
u
n
d
.
Sectio
n
3
d
escr
ib
es
r
elate
d
w
o
r
k
.
I
n
t
h
e
n
e
x
t
s
ec
tio
n
,
w
e
p
r
esen
t o
u
r
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
.
I
n
s
ec
tio
n
5
,
w
e
o
f
f
er
r
e
s
u
lt
s
an
d
d
is
cu
s
s
io
n
.
Fi
n
all
y
,
s
ec
ti
o
n
6
co
n
clu
d
es.
2.
B
ACK
G
RO
UND
2
.
1
.
Nex
t
pa
g
e
predict
io
n
T
h
e
n
ex
t
p
ag
e
p
r
ed
ictio
n
tas
k
co
n
s
i
s
ts
o
f
p
r
ed
ictin
g
t
h
e
n
ex
t
p
a
g
e
o
f
a
s
eq
u
en
ce
b
as
ed
o
n
th
e
p
r
ev
io
u
s
l
y
o
b
s
er
v
ed
p
ag
e
s
.
Fo
r
in
s
ta
n
ce
,
i
f
a
u
s
er
h
as
v
i
s
ited
s
o
m
e
w
eb
p
ag
e
s
X,
Y,
Z
,
in
t
h
at
o
r
d
er
,
o
n
e
m
a
y
w
a
n
t
to
p
r
ed
ict
w
h
at
is
t
h
e
n
ex
t
w
eb
p
ag
e
t
h
at
w
i
ll
b
e
v
is
i
ted
b
y
t
h
at
u
s
er
.
T
h
er
e
ar
e
tw
o
m
aj
o
r
s
tep
s
f
o
r
m
ak
in
g
t
h
e
n
e
x
t p
ag
e
p
r
ed
ictio
n
s
h
o
w
n
b
elo
w
.
Step
1
: T
r
ain
in
g
s
eq
u
e
n
ce
s
→
b
u
ild
in
g
a
s
eq
u
e
n
ce
p
r
ed
ictio
n
m
o
d
el
→
p
r
ed
ictio
n
m
o
d
el
Step
2
: (
p
r
e
d
ictio
n
m
o
d
el,
a
s
p
ec
if
ic
s
eq
u
en
ce
)
→
p
r
ed
ictio
n
alg
o
r
ith
m
→
p
r
ed
ictio
n
.
2
.
2
.
Co
mm
o
n seq
uence
pre
dict
io
n
m
o
dels
On
e
o
f
t
h
e
t
y
p
ical
m
o
d
els
ar
e
p
r
o
p
o
s
ed
f
o
r
W
eb
p
ag
e
p
r
e
d
ictio
n
is
a
r
u
les
-
b
ased
m
o
d
el
[
4
-
9
]
.
T
h
e
d
ep
en
d
en
c
y
g
r
ap
h
(
DG
)
s
eq
u
e
n
ce
p
r
ed
ictio
n
m
o
d
el
w
as p
r
o
p
o
s
ed
in
w
o
r
k
[
1
0
]
.
T
h
e
au
th
o
r
s
u
s
ed
a
p
r
ed
ictio
n
alg
o
r
ith
m
p
atter
n
ed
af
ter
t
h
at
p
r
o
p
o
s
ed
b
y
J
am
e
s
Gr
if
f
io
e
n
an
d
R
an
d
y
A
p
p
leto
n
[
1
1
]
.
T
h
e
y
h
a
v
e
p
r
esen
ted
a
p
r
ef
etch
i
n
g
s
ch
e
m
e
f
o
r
th
e
W
o
r
ld
W
id
e
W
eb
aim
ed
at
r
ed
u
cin
g
th
e
late
n
c
y
p
er
ce
iv
e
d
b
y
u
s
er
s
.
A
l
s
o
,
th
e
p
r
ed
ictio
n
alg
o
r
it
h
m
co
n
s
tr
u
c
ts
a
d
ep
en
d
e
n
c
y
g
r
ap
h
t
h
at
d
ep
icts
th
e
p
atter
n
o
f
ac
ce
s
s
es
to
d
i
f
f
er
e
n
t
f
i
les
s
to
r
ed
at
th
e
s
er
v
er
[
1
0
]
-
u
s
i
n
g
th
e
f
ir
s
t
-
o
r
d
er
Ma
r
k
o
v
p
r
ed
ictio
n
m
et
h
o
d
d
escr
ib
ed
in
[
1
1
]
f
o
r
f
ile
p
r
ed
ictio
n
,
P
ad
m
an
ab
h
an
a
n
d
Mo
g
u
l
[1
2
]
co
n
s
tr
u
cted
a
d
ep
en
d
en
c
y
g
r
a
p
h
co
n
tain
i
n
g
n
o
d
es
f
o
r
all
f
il
es
ev
er
ac
ce
s
s
ed
at
a
p
ar
ticu
lar
W
W
W
s
er
v
er
.
T
o
ef
f
ec
ti
v
el
y
p
r
ed
ict,
[
1
3
]
es
ti
m
ated
f
r
o
m
n
-
g
r
a
m
s
to
y
ie
ld
th
e
co
n
d
itio
n
al
p
r
o
b
a
b
ilit
ies f
o
r
s
eq
u
e
n
ce
p
r
ed
ictio
n
.
T
h
e
p
a
p
er
[
1
4
]
d
escr
ib
es
h
o
w
t
h
e
co
n
f
lic
t
ca
n
b
e
r
eso
lv
ed
w
it
h
p
ar
tial
s
tr
in
g
m
a
tch
i
n
g
an
d
r
ep
o
r
ts
ex
p
er
i
m
e
n
tal
r
e
s
u
l
ts
s
h
o
w
in
g
th
at
m
i
x
ed
-
ca
s
e
E
n
g
lis
h
tex
t
c
an
b
e
co
d
ed
i
n
as
lit
tle
a
s
2
.
2
b
its
/ch
ar
ac
ter
s
w
it
h
n
o
p
r
io
r
k
n
o
w
led
g
e
o
f
th
e
s
o
u
r
ce
.
T
h
e
w
o
r
k
u
s
ed
t
h
e
c
o
n
ce
p
t
o
f
co
m
p
r
es
s
ib
il
it
y
s
h
o
w
n
to
p
la
y
a
r
o
le
an
alo
g
o
u
s
to
th
a
t
o
f
e
n
tr
o
p
y
i
n
clas
s
ical
i
n
f
o
r
m
atio
n
t
h
eo
r
y
,
w
h
er
e
o
n
e
d
ea
ls
w
it
h
p
r
o
b
ab
ilis
tic
e
n
s
e
m
b
les
o
f
s
eq
u
en
ce
s
.
[
1
5
]
is
a
m
o
d
el
f
o
r
m
ak
i
n
g
s
eq
u
en
ce
p
r
ed
ictio
n
u
s
i
n
g
th
e
tex
t
-
co
m
p
r
e
s
s
io
n
m
et
h
o
d
;
it
li
m
its
th
e
g
r
o
w
t
h
o
f
s
to
r
ag
e
b
y
r
etain
in
g
th
e
m
o
s
t
l
ik
el
y
p
r
ed
ictio
n
co
n
tex
ts
a
n
d
d
is
ca
r
d
in
g
(
f
o
r
g
etti
n
g
)
less
li
k
el
y
o
n
es.
A
r
o
b
u
s
t
m
o
d
el
is
C
P
T
th
at
is
d
escr
ib
ed
in
[
3
]
as b
elo
w
.
T
h
e
C
PT
'
s
ad
v
an
ta
g
e
is
th
at
i
t
co
u
ld
co
m
p
r
ess
th
e
tr
ai
n
i
n
g
d
ata
s
o
th
at
all
r
elev
an
t
i
n
f
o
r
m
atio
n
i
s
av
ailab
le
f
o
r
ea
ch
p
r
ed
ictio
n
.
I
t
also
o
f
f
er
s
a
lo
w
ti
m
e
co
m
p
le
x
it
y
f
o
r
its
tr
ai
n
i
n
g
p
h
ase
a
n
d
is
ea
s
il
y
ad
ap
tab
le
f
o
r
d
if
f
er
en
t
ap
p
licatio
n
s
a
n
d
co
n
tex
t
s
[
3
]
.
A
n
i
m
p
r
o
v
ed
m
o
d
el
o
f
C
P
T
is
C
P
T
+.
T
h
e
C
PT
+
ad
d
r
ess
th
i
s
i
s
s
u
e
b
y
p
r
o
p
o
s
in
g
t
h
r
ee
n
o
v
el
s
tr
ateg
ie
s
to
r
ed
u
ce
C
P
T
'
s
s
ize
a
n
d
p
r
ed
ictio
n
ti
m
e,
an
d
i
n
cr
ea
s
e
its
ac
cu
r
ac
y
.
E
x
p
er
i
m
e
n
tal
r
es
u
lts
o
f
C
P
T
+
o
n
s
ev
en
r
ea
l
-
life
d
atasets
s
h
o
w
t
h
at
t
h
e
r
esu
lt
in
g
m
o
d
el
(
C
P
T
+)
is
u
p
to
n
ea
r
l
y
1
0
0
ti
m
es
m
o
r
e
co
m
p
ac
t
a
n
d
n
ea
r
l
y
f
iv
e
ti
m
es
f
as
ter
th
a
n
C
P
T
,
an
d
h
as
th
e
b
etter
ac
cu
r
ac
y
th
an
o
t
h
er
m
o
d
els
s
u
ch
as
A
K
OM
[
1
3
]
,
C
PT
[
3
]
,
DG
[
1
0
]
,
L
z7
8
[
1
2
]
,
PP
M
[
1
4
]
,
an
d
T
D
A
G
[
1
5
].
T
h
is
w
o
r
k
ai
m
s
to
i
m
p
r
o
v
e
t
h
e
e
f
f
ec
ti
v
e
n
es
s
o
f
n
ex
t
p
ag
e
p
r
ed
ictio
n
b
y
u
s
i
n
g
th
e
in
te
g
r
atio
n
o
f
P
ag
e
R
an
k
w
it
h
a
s
tar
t
-
of
-
t
h
e
-
ar
t a
p
p
r
o
ac
h
ca
lled
C
PT
+
an
d
p
r
o
v
id
in
g
a
co
m
p
ar
is
o
n
o
f
t
h
is
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
w
ith
o
th
er
o
n
e
s
.
2
.
3
.
Usi
ng
P
a
g
eRa
nk
f
o
r
s
eq
uenc
e
predict
io
n
T
h
e
r
esear
ch
[
1
6
]
in
d
icate
s
th
at
P
ag
eRan
k
h
as
g
o
n
e
f
r
o
m
b
ein
g
u
s
ed
to
ev
al
u
ate
th
e
i
m
p
o
r
tan
ce
o
f
w
eb
p
ag
es
to
a
m
u
c
h
b
r
o
ad
er
s
et
o
f
ap
p
lica
tio
n
s
.
T
h
e
P
ag
eR
an
k
al
g
o
r
ith
m
s
u
p
p
o
r
tin
g
th
e
s
eq
u
en
ce
p
r
ed
ictio
n
is
d
escr
ib
ed
as
b
elo
w
.
L
et
S
Df
u
ll
b
e
th
e
o
r
ig
in
al
s
eq
u
en
c
e
d
atab
ase.
A
f
ter
th
e
P
ag
eRa
n
k
co
m
p
u
tatio
n
i
s
p
r
o
ce
s
s
ed
,
th
e
s
eq
u
en
ce
d
atab
ase
is
ar
r
an
g
ed
in
to
t
w
o
p
ar
ts
.
P
ar
t
1
:
SDh
ig
h
is
a
s
et
o
f
s
eq
u
en
t
ial
d
ata
s
er
ies
w
it
h
a
h
ig
h
a
v
er
ag
e
P
ag
eRa
n
k
in
d
e
x
an
d
t
h
e
s
ec
o
n
d
p
ar
t:
S
Dlo
w
i
s
a
s
et
o
f
s
eq
u
e
n
tial
d
at
a
s
er
ies
w
it
h
a
lo
w
av
er
ag
e
P
ag
eRa
n
k
.
T
h
e
r
elatio
n
s
h
ip
s
o
f
t
h
ese
d
ata
s
et
s
ar
e
d
eter
m
i
n
ed
b
y
t
h
e
f
o
r
m
u
la
(
1
)
:
=
ℎ
ℎ
∪
(
1
)
C
o
n
s
id
er
ℎ
ℎ
is
a
d
ata
s
et
c
o
n
tai
n
in
g
s
tr
in
g
s
o
f
th
e
f
o
r
m
*
P
PR
,
w
h
er
e
*
i
s
an
y
s
eq
u
e
n
ce
o
f
d
ata
an
d
p
r
ed
ictab
le
PP
R
p
ag
e
(
P
P
R
al
w
a
y
s
f
o
llo
w
s
s
tr
i
n
g
s
*
)
.
I
t
is
co
n
s
id
er
i
n
g
t
h
e
w
eb
s
ite
s
t
h
a
t
v
is
i
t
th
e
P
PR
p
ag
e,
w
h
e
n
th
e
P
ag
e
R
a
n
k
i
n
d
ex
o
f
th
e
P
PR
p
ag
e
is
h
i
g
h
,
th
e
m
o
r
e
p
ag
es
th
at
w
i
ll
d
ir
ec
tl
y
v
is
i
t
th
e
P
PR
p
ag
e
(
ac
co
r
d
in
g
to
P
ag
eRan
k
's
n
at
u
r
e)
.
T
h
is
m
ea
n
s
th
at
t
h
e
n
u
m
b
er
o
f
s
eq
u
en
ce
s
t
h
at
s
u
cc
ess
f
u
ll
y
p
r
ed
ict
th
e
P
PR
p
ag
e
w
i
ll
in
cr
ea
s
e.
C
o
n
v
er
s
el
y
,
w
h
e
n
th
e
P
ag
eRa
n
k
o
f
a
P
PR
p
ag
e
is
lo
w
,
th
e
f
e
w
er
p
ag
e
s
w
i
ll
g
o
d
ir
ec
tl
y
to
th
e
P
PR
p
ag
e
a
n
d
is
t
h
e
n
u
m
b
e
r
o
f
s
tr
i
n
g
s
t
h
at
p
r
ed
ict
t
h
e
P
PR
p
ag
e
'
s
s
u
cc
e
s
s
w
ill
d
r
o
p
.
W
h
en
ca
lcu
la
tin
g
t
h
e
av
er
ag
e
o
f
th
e
P
ag
e
R
a
n
k
in
d
ic
es o
n
t
h
e
d
ata
s
eq
u
e
n
ce
,
t
h
e
h
i
g
h
er
t
h
e
a
v
er
ag
e
n
u
m
b
er
o
f
s
e
q
u
en
tial
s
er
ies,
t
h
e
m
o
r
e
s
tr
i
n
g
s
o
f
f
o
r
m
*
P
PR
w
i
ll
ap
p
ea
r
.
T
h
is
also
m
ea
n
s
t
h
a
t
th
e
n
u
m
b
er
o
f
p
r
ed
icted
s
u
cc
ess
s
eq
u
e
n
ce
s
w
il
l
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
I
n
ve
s
tig
a
tin
g
th
e
P
a
g
eR
a
n
k
a
n
d
s
eq
u
en
ce
p
r
ed
ictio
n
b
a
s
ed
a
p
p
r
o
a
c
h
es fo
r
…
(
N
g
u
ye
n
Th
o
n
Da
)
2231
b
e
m
o
r
e
an
d
w
ill
b
e
ad
d
ed
to
th
e
n
u
m
b
er
o
f
p
r
ed
icted
s
u
cc
ess
s
eq
u
e
n
ce
s
ac
co
r
d
in
g
to
th
e
C
P
T
+
alg
o
r
ith
m
.
T
h
er
ef
o
r
e,
th
e
in
teg
r
atio
n
o
f
P
ag
eRa
n
k
ca
lc
u
lat
io
n
i
n
to
C
P
T
+
is
s
i
g
n
i
f
ica
n
t
f
o
r
p
r
ed
ictin
g
W
eb
ac
ce
s
s
.
3.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
T
h
is
r
esear
ch
[
1
7
]
ai
m
s
to
p
r
ed
ict
th
e
u
s
er
'
s
b
eh
a
v
io
u
r
u
s
i
n
g
t
h
e
A
p
r
io
r
i
p
r
ef
ix
tr
ee
(
P
T
)
alg
o
r
ith
m
.
Usi
n
g
t
h
e
p
o
p
u
lar
it
y
v
al
u
e
o
f
p
ag
es,
th
e
a
u
t
h
o
r
s
o
f
t
h
e
w
o
r
k
[
1
8
]
b
ias
co
n
v
en
tio
n
al
P
ag
e
R
an
k
al
g
o
r
ith
m
a
n
d
m
o
d
el
a
n
e
x
t
p
ag
e
p
r
ed
ictio
n
s
y
s
te
m
th
a
t
p
r
o
d
u
ce
s
p
ag
e
p
r
ed
ictio
n
s
u
n
d
er
g
iv
e
n
to
p
-
n
v
al
u
e.
T
h
e
w
o
r
k
[
1
9
]
in
tr
o
d
u
ce
d
an
ap
p
r
o
ac
h
f
o
r
p
e
r
s
o
n
alize
d
p
ag
e
r
an
k
i
n
g
an
d
r
ec
o
m
m
e
n
d
atio
n
b
y
i
n
te
g
r
atin
g
ass
o
ciatio
n
m
in
i
n
g
an
d
P
ag
eRa
n
k
to
m
ee
t
u
s
er
's
s
ea
r
ch
g
o
als.
T
h
e
e
f
f
ec
ti
v
en
e
s
s
o
f
th
e
ir
p
r
o
p
o
s
ed
m
et
h
o
d
w
a
s
v
er
if
ied
th
r
o
u
g
h
a
f
e
w
ex
p
er
i
m
en
tal
ev
al
u
atio
n
s
.
T
h
e
w
o
r
k
[
2
0
]
p
r
o
p
o
s
ed
a
Pag
e
R
a
n
k
-
l
ik
e
alg
o
r
it
h
m
is
p
r
o
p
o
s
ed
f
o
r
co
n
d
u
ctin
g
w
eb
p
ag
e
ac
ce
s
s
p
r
ed
ictio
n
,
an
d
th
e
y
e
x
te
n
d
ed
th
e
u
s
e
o
f
P
ag
eR
a
n
k
al
g
o
r
ith
m
f
o
r
n
e
x
t
p
ag
e
p
r
ed
ictio
n
w
it
h
s
ev
er
al
n
av
i
g
atio
n
al
at
tr
ib
u
tes.
I
n
th
e
r
esear
ch
[
2
1
]
p
r
o
v
id
es
a
s
o
l
u
tio
n
to
w
eb
p
ag
e
ac
ce
s
s
p
r
ed
ictio
n
ai
m
i
n
g
to
in
cr
ea
s
e
ac
c
u
r
ac
y
a
n
d
ef
f
icie
n
c
y
b
y
r
ed
u
cin
g
th
e
s
eq
u
en
c
e
s
p
ac
e
w
it
h
th
e
i
n
teg
r
at
i
o
n
o
f
P
ag
eRa
n
k
i
n
t
o
C
P
T
+.
Mo
r
eo
v
er
,
th
e
w
o
r
k
[
2
2
]
p
r
o
p
o
s
ed
a
m
eth
o
d
in
wh
ich
a
n
a
m
b
i
g
u
o
u
s
p
r
ed
ictio
n
p
r
o
b
lem
ca
n
b
e
r
eso
lv
ed
u
s
i
n
g
w
eb
P
ag
eRa
n
k
an
d
Ma
r
k
o
v
m
o
d
el
.
I
ts
e
x
p
er
i
m
e
n
tal
r
es
u
lt
s
h
o
w
s
a
r
ed
u
ce
d
n
u
m
b
er
o
f
v
a
g
u
e
p
r
ed
ictio
n
s
af
ter
ap
p
l
y
i
n
g
t
h
e
P
ag
eRan
k
m
eth
o
d
.
A
s
s
u
m
i
n
g
a
s
et
o
f
s
u
cc
es
s
iv
e
p
ast
to
p
-
k
r
an
k
i
n
g
s
,
t
h
e
p
ap
er
[
2
3
]
in
tr
o
d
u
ce
d
a
m
et
h
o
d
f
o
r
p
r
ed
ictin
g
th
e
r
an
k
i
n
g
p
o
s
itio
n
o
f
a
w
eb
p
ag
e
b
y
r
an
k
i
n
g
tr
en
d
s
eq
u
en
ce
s
u
s
ed
f
o
r
Ma
r
k
o
v
m
o
d
els
tr
ai
n
i
n
g
.
Du
e
to
t
h
e
ac
cu
r
ac
y
o
f
th
e
lo
w
o
r
d
er
Ma
r
k
o
v
m
o
d
el
u
s
u
al
l
y
is
n
o
t
s
a
tis
f
ac
to
r
y
,
th
e
ar
ticle
[
2
4
]
u
tili
ze
d
p
o
p
u
l
a
r
it
y
an
d
s
i
m
ilar
it
y
-
b
ased
P
ag
eR
a
n
k
alg
o
r
it
h
m
to
m
a
k
e
p
r
ed
ictio
n
s
w
h
en
th
e
a
m
b
ig
u
o
u
s
r
es
u
lts
ar
e
f
o
u
n
d
.
T
h
e
w
o
r
k
[
2
5
]
p
r
o
p
o
s
ed
th
e
u
s
e
o
f
a
P
ag
eRa
n
k
-
b
ased
al
g
o
r
ith
m
f
o
r
th
e
w
eb
s
ite
'
s
g
r
ap
h
,
an
d
th
e
y
p
r
o
v
ed
,
th
r
o
u
g
h
ex
p
er
i
m
e
n
tatio
n
,
t
h
at
th
eir
ap
p
r
o
ac
h
r
esu
lts
i
n
m
o
r
e
ac
c
u
r
ate
an
d
r
ep
r
esen
tativ
e
p
r
ed
ictio
n
s
th
a
n
th
e
o
n
es p
r
o
d
u
ce
d
f
r
o
m
t
h
e
p
u
r
e
u
s
a
g
e
-
b
ased
ap
p
r
o
ac
h
es.
Ho
w
e
v
er
,
th
ese
Ma
r
k
o
v
b
as
ed
m
o
d
els
s
u
f
f
er
f
r
o
m
s
o
m
e
s
ig
n
i
f
ica
n
t
d
r
a
w
b
ac
k
s
,
m
o
s
t
o
f
th
e
m
ass
u
m
e
t
h
e
Ma
r
k
o
v
ian
h
y
p
o
t
h
esi
s
th
at
ea
c
h
ev
e
n
t
s
o
lel
y
d
ep
en
d
s
o
n
th
e
p
r
ev
io
u
s
cir
cu
m
s
ta
n
ce
s
,
a
n
d
th
u
s
,
p
r
ed
ictio
n
ac
cu
r
ac
y
u
s
in
g
t
h
es
e
m
o
d
els
ca
n
d
ec
r
ea
s
e
[
2
6
]
.
F
u
r
th
er
m
o
r
e,
b
o
th
r
u
le
s
-
b
ased
m
o
d
el
s
an
d
Ma
r
k
o
v
b
ased
m
o
d
els
d
o
n
o
t
u
s
e
all
t
h
e
i
n
f
o
r
m
at
io
n
co
n
tai
n
ed
in
tr
ain
i
n
g
s
eq
u
e
n
ce
s
to
p
er
f
o
r
m
p
r
ed
ictio
n
s
,
an
d
t
h
i
s
ca
n
s
e
v
er
el
y
r
ed
u
ce
t
h
eir
ac
cu
r
ac
y
[
2
6
]
.
A
l
s
o
,
th
e
r
esear
ch
[
2
7
]
in
v
esti
g
ated
r
elate
d
w
o
r
k
f
o
r
w
eb
p
ag
e
ac
ce
s
s
p
r
ed
ictio
n
.
T
h
e
r
esear
ch
in
d
ic
ates
t
h
at
t
h
e
co
m
b
i
n
atio
n
o
f
t
h
e
C
P
T
+
[
2
6
]
w
it
h
t
h
e
P
ag
e
R
an
k
is
a
m
ea
n
i
n
g
f
u
l
ch
o
ice
f
o
r
n
e
x
t
p
a
g
e
p
r
ed
ictio
n
.
T
h
e
s
co
p
e
o
f
th
i
s
r
esear
ch
i
s
th
at
it
d
ea
ls
w
i
th
i
s
s
u
es
r
e
g
a
r
d
in
g
p
r
ed
ictin
g
t
h
e
n
ex
t
ite
m
s
e
f
f
ec
ti
v
el
y
i
n
click
s
tr
ea
m
o
r
w
eb
ac
ce
s
s
co
n
te
x
t
th
at
is
b
ein
g
u
s
ed
in
v
ar
io
u
s
ar
ea
s
in
r
ea
l
lif
e.
F
o
r
in
s
ta
n
ce
,
t
h
e
r
esu
l
t
o
f
t
h
is
w
o
r
k
ca
n
b
e
a
p
p
l
i
e
d
t
o
p
r
e
d
i
c
t
i
n
g
b
e
h
a
v
i
o
u
r
i
n
t
h
e
e
-
c
o
m
m
e
r
c
e
c
o
n
t
e
x
t
o
r
p
r
e
d
i
c
t
i
n
g
u
s
e
r
s
'
t
r
e
n
d
s
w
h
i
l
e
v
i
s
i
t
i
n
g
v
a
r
i
o
u
s
w
e
b
s
i
t
e
s
.
4.
RE
S
E
ARCH
M
E
T
H
O
D
I
n
th
is
s
ec
tio
n
,
w
e
f
ir
s
t
u
tili
ze
K
-
f
o
ld
cr
o
s
s
v
a
lid
atio
n
to
d
i
v
id
e
ea
ch
r
ea
l
d
ataset
i
n
to
te
n
e
q
u
al
p
ar
ts
an
d
p
er
f
o
r
m
t
h
e
w
o
r
k
[
2
1
]
o
n
tr
ai
n
in
g
d
atase
ts
.
Seco
n
d
l
y
,
w
e
e
v
al
u
ate
v
ar
io
u
s
s
eq
u
e
n
c
e
p
r
ed
ictio
n
b
ased
m
et
h
o
d
s
b
y
u
s
in
g
[
2
8
]
f
o
r
s
m
a
ller
d
atasets
w
it
h
th
e
ir
s
ize
s
h
o
r
ten
b
y
t
h
e
ap
p
r
o
ac
h
[
2
1
]
.
4
.
1
.
I
nte
g
ra
t
ing
K
-
f
o
ld
cr
o
s
s
v
a
lid
a
t
io
n
m
et
ho
d
t
o
i
m
pro
v
e
da
t
a
m
ini
ng
a
cc
ura
cy
f
o
r
w
eb
a
cc
ess
predict
io
n
T
h
e
o
b
j
ec
tiv
e
o
f
cr
o
s
s
-
v
alid
at
io
n
i
s
to
te
s
t
th
e
m
o
d
el
's
ab
ilit
y
to
p
r
ed
ict
n
e
w
d
ata
[
2
9
]
.
I
n
p
ar
ticu
lar
,
th
e
K
-
f
o
l
d
cr
o
s
s
v
al
id
atio
n
m
eth
o
d
[
3
0
]
d
iv
id
es
th
e
s
e
t
o
f
o
b
s
er
v
atio
n
s
in
to
K
g
r
o
u
p
s
,
a
p
p
r
o
x
im
a
tel
y
w
it
h
eq
u
al
s
ize
[
3
1
]
.
K
is
u
s
u
all
y
c
h
o
s
en
a
s
5
o
r
1
0
,
an
d
as
K
b
e
co
m
e
s
ex
te
n
s
iv
e,
t
h
e
s
ize
d
if
f
er
en
ce
b
et
w
ee
n
th
e
tr
ain
i
n
g
s
et
an
d
t
h
e
s
u
b
s
a
m
p
les
w
il
l
b
e
s
m
al
ler
ag
ai
n
,
a
s
th
i
s
d
i
f
f
er
e
n
ce
d
ec
r
ea
s
es,
t
h
e
d
ev
iatio
n
o
f
th
e
tech
n
iq
u
e
th
e
lo
w
er
t
h
e
[
3
2
]
.
T
h
e
d
ata
is
tr
ai
n
ed
a
n
d
test
ed
K
ti
m
es,
ea
c
h
ti
m
e
t,
tr
ai
n
ed
o
n
t
h
e
s
e
t
D
\
D
t
a
n
d
test
ed
o
n
Dt
(
D
is
th
e
o
r
i
g
in
al
d
ata
s
et,
an
d
Dt
is
th
e
s
et
test
d
ata)
[
3
0
]
.
T
h
e
esti
m
ate
o
f
cr
o
s
s
-
v
alid
atio
n
ac
cu
r
ac
y
is
t
h
e
s
u
m
o
f
th
e
co
r
r
ec
t
class
if
ica
tio
n
s
d
iv
id
ed
b
y
th
e
n
u
m
b
er
o
f
en
ti
ties
in
t
h
e
o
r
ig
in
a
l
d
ataset.
T
h
e
p
u
r
p
o
s
e
o
f
K
-
f
o
ld
cr
o
s
s
v
alid
atio
n
is
m
ai
n
l
y
u
s
ed
to
esti
m
ate
th
e
ab
ilit
y
o
f
t
h
e
m
ac
h
i
n
e
lear
n
in
g
m
o
d
el
o
n
in
v
is
ib
le
d
ata.
4
.
2
.
Dev
elo
p t
ra
ini
ng
da
t
a
s
et
s
a
nd
i
m
pro
v
e
a
cc
ura
cy
4
.
2
.
1
.
Da
t
a
W
e
ch
an
g
ed
t
h
e
d
ataset
K
OS
A
R
AK
(
co
llected
f
r
o
m
h
ttp
://f
i
m
i.
u
a.
ac
.
b
e/d
ata)
in
to
a
s
eq
u
en
c
e
d
atab
ase
(
in
clu
d
i
n
g
1
0
0
,
0
0
0
s
eq
u
en
ce
s
)
in
a
f
o
r
m
at
t
h
at
i
s
d
ef
in
ed
as
f
o
llo
w
s
.
T
h
er
e
is
a
tex
t
f
ile
w
h
ich
r
ep
r
esen
ts
a
s
eq
u
e
n
ce
f
r
o
m
a
s
eq
u
en
ce
d
atab
ase.
A
s
i
n
g
le
s
p
ac
e
an
d
a
-
1
s
ep
ar
ate
ea
ch
ite
m
f
r
o
m
a
s
eq
u
e
n
ce
.
T
h
e
v
alu
e
"
-
2
"
s
h
o
w
s
t
h
e
e
n
d
o
f
a
s
eq
u
e
n
ce
.
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.
11
,
No
.
3
,
J
u
n
e
2
0
2
1
:
2
2
2
9
-
2237
2232
4
.
2
.
2
.
M
et
ho
d
W
e
p
r
o
p
o
s
e
a
co
m
b
i
n
atio
n
a
m
o
n
g
n
u
m
er
o
u
s
tec
h
n
iq
u
es
s
u
ch
as
K
-
f
o
ld
er
-
v
a
lid
ati
o
n
ch
ec
k
,
P
ag
eRan
k
alg
o
r
it
h
m
o
n
s
eq
u
en
ce
d
atab
ase,
an
al
y
s
i
n
g
s
e
q
u
en
ce
s
to
p
r
ed
ict
n
ex
t
p
ag
es
ef
f
ec
tiv
e
l
y
.
T
h
e
p
r
o
p
o
s
ed
p
r
o
ce
d
u
r
e
in
clu
d
es 4
m
ain
p
h
ases
i
n
tr
o
d
u
ce
d
b
elo
w
.
P
h
ase
1
:
w
e
r
u
n
r
an
d
o
m
l
y
all
s
eq
u
e
n
ce
s
in
s
id
e
th
e
co
n
s
id
er
ed
d
atasets
(
also
t
h
e
i
n
p
u
t
s
eq
u
e
n
ce
d
atab
ase)
.
T
h
en
w
e
s
p
lit
th
e
r
an
d
o
m
ized
d
ataset
i
n
t
o
1
0
eq
u
al
p
ar
ts
.
T
h
e
f
ir
s
t
p
ar
t
i
s
u
s
ed
as
a
test
i
n
g
d
ataset
ca
lled
DB
T
est1
,
9
r
em
ain
i
n
g
p
ar
ts
b
ec
o
m
e
an
o
t
h
er
d
ataset
f
o
r
a
tr
ain
in
g
d
atase
t c
alled
DB
T
r
ain
1
.
P
h
ase
2
:
W
e
ca
lcu
late
th
e
P
ag
e
R
an
k
v
alu
e
f
o
r
all
s
eq
u
e
n
ce
s
i
n
t
h
e
d
ataset
DB
T
r
ain
1
.
T
h
an
k
s
to
t
h
e
[
2
1
]
w
e
r
ed
u
ce
d
r
ed
u
n
d
an
t seq
u
e
n
ce
s
.
P
h
ase
3
:
W
e
an
al
y
s
e
s
eq
u
en
ce
s
a
n
d
u
s
e
an
e
f
f
ec
tiv
e
s
eq
u
e
n
ce
p
r
ed
ictio
n
to
p
r
ed
ict
n
ex
t
p
ag
e
s
o
n
th
e
te
s
ti
n
g
d
ataset
(
DB
T
est1
)
.
W
e
r
ep
ea
t
th
e
m
en
tio
n
ed
p
h
ases
f
o
r
9
r
em
ai
n
i
n
g
p
ar
ts
a
cc
o
r
d
in
g
to
th
e
t
h
eo
r
y
o
f
K
-
Fo
ld
C
r
o
s
s
Valid
atio
n
.
P
h
ase
4
: W
e
ev
alu
ate
t
h
e
ac
cu
r
ac
y
o
f
s
eq
u
en
ce
-
p
r
ed
ictio
n
-
b
ased
m
o
d
els,
an
al
y
s
e
an
d
d
r
a
w
co
n
clu
s
io
n
s
.
4
.
2
.
3
.
E
v
a
lua
t
io
n
f
ra
m
ew
o
rk
W
e
u
s
ed
th
e
ev
al
u
atio
n
Fra
m
e
w
o
r
k
i
n
tr
o
d
u
ce
d
in
t
h
e
ar
ticle
[
2
6
]
to
ev
alu
ate
p
r
ed
ictio
n
m
o
d
el
s
.
A
p
r
ed
ictio
n
ca
n
b
e
eit
h
er
a
s
u
c
ce
s
s
i
f
th
e
p
r
ed
ictio
n
is
ac
cu
r
ate,
a
f
a
ilu
r
e
if
th
e
p
r
ed
ictio
n
is
i
n
ac
c
u
r
ate,
o
r
a
n
o
n
e
-
m
atch
i
f
th
e
m
o
d
el
is
u
n
ab
le
to
p
er
f
o
r
m
a
p
r
ed
ictio
n
.
B
esid
es,
co
v
er
ag
e
is
th
e
r
atio
o
f
s
eq
u
en
ce
s
w
it
h
o
u
t
p
r
ed
ictio
n
a
g
ai
n
s
t
th
e
to
tal
n
u
m
b
er
o
f
te
s
t
s
eq
u
e
n
ce
s
,
a
n
d
ac
c
u
r
ac
y
i
s
t
h
e
n
u
m
b
er
o
f
s
u
cc
e
s
s
f
u
l
p
r
ed
ictio
n
s
ag
ai
n
s
t t
h
e
to
tal
n
u
m
b
er
o
f
te
s
t seq
u
en
ce
s
[
2
6
]
.
5.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
NS
Af
ter
cr
ea
ti
n
g
1
0
d
ata
s
et
s
ac
co
r
d
in
g
to
th
e
ab
o
v
e
m
et
h
o
d
,
w
e
p
r
o
ce
ed
ed
to
tak
e
ten
tr
ain
i
n
g
s
et
s
(
w
it
h
th
e
s
ize
o
f
9
0
,
0
0
0
lin
es
)
o
f
th
ese
1
0
d
ata
s
ets
to
im
p
l
e
m
en
t
th
e
s
o
l
u
tio
n
to
s
h
o
r
ten
th
e
d
ata
s
er
ies.
B
y
u
s
i
n
g
t
h
e
P
ag
e
R
a
n
k
alg
o
r
it
h
m
,
s
eq
u
e
n
tial
d
atab
ases
w
i
th
co
r
r
esp
o
n
d
in
g
p
r
ec
is
io
n
ar
e
cr
ea
t
ed
,
as ill
u
s
tr
ated
in
T
ab
le
1
.
I
n
w
h
ich
R
i
i
s
t
h
e
ac
cu
r
ac
y
o
f
t
h
e
co
llap
s
ed
s
e
q
u
en
tial
d
atab
ases
d
u
r
in
g
th
e
i
th
K
-
Fo
ld
C
h
ec
k
Valid
atio
n
.
A
cc
o
r
d
in
g
to
T
ab
le
1
,
th
e
v
alu
es
1
0
0
,
9
8
,
9
6
d
o
w
n
to
5
8
,
5
6
ar
e
th
e
s
ize
(
in
p
er
ce
n
t)
o
f
th
e
co
llap
s
ed
d
atab
ase,
r
esp
ec
tiv
el
y
,
co
m
p
ar
ed
to
th
e
tr
ain
i
n
g
d
a
tab
ase
.
E
x
p
er
i
m
e
n
tal
r
esu
lts
s
h
o
w
t
h
at
w
h
en
ap
p
l
y
i
n
g
th
e
P
ag
eRa
n
k
s
o
l
u
tio
n
to
r
ed
u
ce
th
e
tr
ain
in
g
d
ata,
g
r
ad
u
all
y
s
et
s
ize
f
r
o
m
2
%,
4
%,
6
%,
u
p
to
3
4
%
(
c
o
r
r
esp
o
n
d
in
g
to
th
e
co
m
p
ac
t
d
ata
s
et
is
9
8
%,
9
6
%,
9
4
%,
d
o
w
n
to
6
6
%),
ac
cu
r
ac
y
is
h
i
g
h
er
th
a
n
t
h
at
o
f
t
h
e
i
n
iti
a
l
tr
ain
i
n
g
d
atab
ase.
T
h
e
co
m
p
ac
t
tr
ain
i
n
g
s
eq
u
en
ce
d
atab
ase'
s
co
n
s
tr
u
ctio
n
to
o
k
a
lo
n
g
ti
m
e
d
u
e
to
t
h
e
lar
g
e
d
ata
s
et
(
1
0
0
,
0
0
0
lin
es),
an
d
t
h
e
n
u
m
b
er
o
f
n
o
d
es
i
n
th
e
d
ir
ec
ted
g
r
ap
h
is
m
an
y
(
2
3
,
4
9
6
n
o
d
es).
A
cc
o
r
d
in
g
to
t
h
e
test
r
e
s
u
l
ts
illu
s
tr
ated
in
Fig
u
r
e
1
,
th
e
a
v
er
ag
e
p
r
ed
ictiv
e
ac
cu
r
ac
y
o
f
th
e
i
n
itia
l
tr
ain
i
n
g
d
atab
ase
(
s
ized
9
0
,
0
0
0
)
is
9
9
.
9
3
6
%,
w
h
e
n
r
e
m
o
v
in
g
th
e
r
ed
u
n
d
an
t
d
ata
s
er
ies
to
th
e
d
atab
ase
I
f
th
e
co
llap
s
ed
d
ata
r
ea
ch
es
a
s
ize
o
f
6
6
%
(
5
9
,
4
0
0
lin
es),
th
e
av
er
ag
e
p
r
ed
icted
ac
cu
r
ac
y
i
s
1
0
0
%
(
an
in
cr
ea
s
e
o
f
0
.
0
6
2
1
%).
Fig
u
r
e
1
illu
s
tr
ate
s
a
ch
ar
t
co
m
p
ar
in
g
th
e
a
v
er
ag
e
o
f
th
e
p
r
ed
icted
ac
cu
r
ac
y
o
n
th
e
co
llap
s
ed
d
atasets
in
s
ize
w
it
h
o
u
t lo
s
in
g
th
e
p
r
ed
ictiv
e
ac
cu
r
ac
y
b
y
P
ag
eRan
k
an
d
C
P
T
+.
No
te
th
at,
w
h
en
t
h
e
s
ize
is
r
ed
u
ce
d
to
6
6
%,
th
e
p
ea
k
ac
cu
r
ac
y
i
s
1
0
0
%,
an
d
a
p
r
o
ce
s
s
o
f
d
e
g
r
ad
atio
n
o
f
ac
cu
r
ac
y
is
r
ea
ch
ed
w
h
en
t
h
e
s
ize
is
6
2
%
o
r
less
.
Fro
m
t
h
e
ab
o
v
e
ex
p
er
i
m
e
n
tal
r
esu
lts
,
w
e
h
a
v
e
th
e
b
asi
s
to
co
n
f
ir
m
t
h
at
w
h
e
n
u
s
i
n
g
t
h
e
r
ed
u
ce
d
tr
ain
in
g
d
ata
s
et
o
f
s
ize,
6
6
%
(
5
9
,
4
0
0
)
to
co
n
tin
u
e
f
o
r
th
e
n
ex
t
s
tag
e
is
th
e
test
p
h
ase
(
p
r
ed
ictiv
e)
is
v
er
y
f
ea
s
ib
le.
C
o
m
p
ar
i
s
o
n
o
f
w
eb
ac
ce
s
s
p
r
ed
ictio
n
m
o
d
els
b
y
i
n
te
g
r
atin
g
P
ag
eRan
k
:
T
h
e
e
m
p
ir
ical
r
e
s
u
lts
d
etailed
i
n
T
ab
le
1
an
d
Fi
g
u
r
e
2
s
h
o
w
th
a
t
t
h
e
s
o
lu
tio
n
o
f
in
te
g
r
ati
n
g
P
ag
eRan
k
w
i
th
C
P
T
+
an
d
D
G
is
s
u
i
tab
le
w
it
h
t
h
e
p
r
ed
icte
d
ac
cu
r
ac
y
o
f
w
eb
ac
ce
s
s
i
s
a
p
p
r
o
x
im
a
tel
y
1
0
0
%
f
o
r
C
P
T
+
an
d
o
v
er
8
0
%
f
o
r
DG.
I
n
co
n
tr
ast,
t
h
e
s
o
lu
tio
n
o
f
in
te
g
r
ati
n
g
P
ag
e
R
an
k
w
it
h
C
P
T
(
an
o
ld
v
er
s
io
n
o
f
C
P
T
+)
is
n
o
t su
itab
le
b
ec
au
s
e
th
e
ac
c
u
r
ac
y
o
f
w
eb
ac
ce
s
s
p
r
ed
ictio
n
,
in
th
i
s
ca
s
e,
h
a
s
n
o
t r
ea
ch
ed
5
0
%.
Fu
r
t
h
er
m
o
r
e,
Fi
g
u
r
e
2
also
s
h
o
w
s
th
a
t
i
n
te
g
r
atin
g
P
ag
e
R
an
k
w
it
h
C
P
T
+
is
m
o
r
e
e
f
f
ec
tiv
e
th
a
n
a
l
l
th
e
o
t
h
er
m
et
h
o
d
s
(
DG,
Ma
r
k
o
v
1
,
A
KOM
,
L
Z
7
8
,
C
P
T
)
(
s
ee
A
p
p
en
d
i
x
f
r
o
m
1
to
6
)
.
I
t
ca
n
b
e
ea
s
il
y
u
n
d
er
s
to
o
d
th
at
th
e
p
atter
n
o
f
DG
s
tan
d
s
i
n
s
ec
o
n
d
p
lace
w
i
th
ac
cu
r
ac
y
f
r
o
m
8
0
%
to
9
3
%.
T
h
er
e
is
a
s
tead
y
in
cr
ea
s
e
f
r
o
m
8
0
%
(
ac
cu
r
ac
y
)
at
a
s
ize
o
f
1
0
0
%
to
9
3
%
at
5
6
%
(
r
ed
u
ce
d
s
eq
u
en
ce
d
atab
ase)
.
B
esid
es,
Ma
r
k
o
v
1
is
th
e
t
h
ir
d
p
lace
w
i
th
ac
cu
r
ac
y
f
r
o
m
6
5
%
to
8
3
%
.
T
h
e
f
ig
u
r
es
f
o
r
A
KOM
an
d
L
Z
7
8
s
h
o
w
s
i
m
ilar
tr
en
d
s
.
I
n
co
n
tr
a
s
t,
t
h
e
ac
c
u
r
a
c
y
o
f
C
P
T
is
b
elo
w
5
0
%
i
n
m
o
s
t
ca
s
es.
T
h
e
f
ig
u
r
e
f
o
r
C
P
T
in
d
icate
s
a
s
tead
y
f
all
f
r
o
m
ab
o
u
t
4
8
%
to
ab
o
u
t
3
8
%
(
ac
cu
r
ac
y
)
w
h
en
r
ed
u
ci
n
g
th
e
s
i
ze
o
f
t
h
e
s
eq
u
en
ce
d
atab
ase
u
s
i
n
g
t
h
e
P
ag
eRan
k
alg
o
r
it
h
m
.
T
h
e
p
atter
n
o
f
C
P
T
+
is
r
elativ
el
y
s
tab
le,
w
it
h
th
e
ac
cu
r
ac
y
r
ea
ch
ed
ap
p
r
o
x
im
a
tel
y
1
0
0
%
in
m
o
s
t
ca
s
es.
T
h
er
ef
o
r
e
,
o
u
r
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
t
o
in
te
g
r
atin
g
P
ag
e
R
an
k
w
it
h
C
PT
+
is
an
ef
f
ec
ti
v
e
s
o
lu
tio
n
f
o
r
p
r
ed
ictin
g
w
eb
ac
ce
s
s
.
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
I
n
ve
s
tig
a
tin
g
th
e
P
a
g
eR
a
n
k
a
n
d
s
eq
u
en
ce
p
r
ed
ictio
n
b
a
s
ed
a
p
p
r
o
a
c
h
es fo
r
…
(
N
g
u
ye
n
Th
o
n
Da
)
2233
T
ab
le
1
.
T
h
e
co
m
p
ar
is
o
n
o
f
t
h
e
ac
cu
r
ac
y
o
f
s
eq
u
en
ce
p
r
ed
ict
io
n
m
o
d
els
S
i
z
e
(
%)
A
v
e
r
a
g
e
o
f
a
c
c
u
r
a
c
y
DG
C
P
T
M
a
r
k
o
v
1
A
K
O
M
L
Z
7
8
C
P
T
+
1
0
0
8
0
.
1
1
6
4
8
.
0
8
8
6
5
.
9
3
2
5
9
.
4
5
1
5
9
.
9
4
5
9
9
.
9
3
6
98
8
0
.
5
8
5
4
8
.
0
3
1
6
6
.
3
3
8
5
9
.
7
7
3
6
0
.
3
1
9
9
9
.
9
4
1
96
8
1
.
0
6
0
4
8
.
0
0
7
6
6
.
7
9
9
6
0
.
1
7
1
6
0
.
6
3
0
9
9
.
9
4
8
94
8
1
.
4
8
6
4
7
.
9
4
6
6
7
.
3
1
2
6
0
.
5
9
1
6
0
.
9
2
2
9
9
.
9
5
5
92
8
1
.
9
9
6
4
7
.
9
5
5
6
7
.
9
8
6
6
1
.
1
4
5
6
1
.
4
1
5
9
9
.
9
6
0
90
8
2
.
4
9
9
4
7
.
9
2
4
6
8
.
5
8
0
6
1
.
5
7
7
6
1
.
8
1
1
9
9
.
9
6
4
88
8
3
.
0
4
4
4
7
.
6
3
1
7
0
.
2
8
2
6
2
.
1
2
3
6
2
.
2
6
7
9
9
.
9
6
8
86
8
3
.
5
1
7
4
6
.
9
9
4
7
0
.
0
7
6
6
2
.
7
0
2
6
2
.
7
0
7
9
9
.
9
7
1
84
8
4
.
0
8
7
4
6
.
3
3
2
7
0
.
9
2
5
6
3
.
3
5
3
6
3
.
2
6
5
9
9
.
9
7
2
82
8
4
.
6
7
8
4
5
.
7
4
1
7
1
.
7
2
8
6
4
.
0
8
3
6
4
.
0
0
2
9
9
.
9
7
6
80
8
5
.
2
9
2
4
4
.
8
7
7
7
2
.
5
9
2
6
4
.
8
2
9
6
4
.
5
0
2
9
9
.
9
6
6
78
8
5
.
9
3
1
4
4
.
0
9
1
7
3
.
4
9
5
6
5
.
7
8
0
6
5
.
0
9
5
9
9
.
9
8
2
76
8
6
.
8
2
8
4
3
.
2
9
5
7
4
.
5
0
1
6
6
.
4
7
8
6
5
.
8
9
7
9
9
.
9
8
5
74
8
7
.
8
3
4
4
2
.
3
9
7
7
5
.
4
6
6
6
7
.
2
8
3
6
6
.
4
8
6
9
9
.
9
9
0
72
8
8
.
4
9
7
4
1
.
7
0
0
7
6
.
3
6
2
6
8
.
1
4
6
6
7
.
2
6
0
9
9
.
9
9
3
70
8
9
.
3
1
1
4
1
.
1
0
5
7
7
.
2
7
8
6
9
.
7
3
3
6
8
.
0
3
7
9
9
.
9
9
7
68
8
9
.
9
3
1
4
0
.
6
1
1
7
8
.
0
8
0
6
8
.
8
8
7
6
8
.
7
7
3
9
9
.
9
9
8
66
9
0
.
3
0
7
4
0
.
2
8
1
7
8
.
9
1
8
7
0
.
2
9
3
6
9
.
4
4
3
9
9
.
9
9
8
64
9
0
.
7
8
1
3
9
.
9
3
2
7
9
.
2
9
9
7
0
.
9
8
6
7
0
.
4
0
7
9
9
.
9
8
5
62
8
9
.
6
1
3
3
9
.
1
2
4
8
0
.
7
7
1
7
1
.
8
7
9
7
1
.
1
9
5
9
9
.
9
7
9
60
9
0
.
7
3
1
3
9
.
0
8
4
8
1
.
8
6
8
7
2
.
8
7
3
7
2
.
5
3
4
9
9
.
8
6
2
58
9
2
.
0
8
6
3
8
.
1
2
5
8
3
.
1
2
7
7
3
.
9
5
9
7
3
.
3
1
7
9
9
.
6
9
0
56
9
3
.
3
0
4
3
7
.
9
7
0
8
2
.
8
8
7
7
4
.
9
3
1
7
3
.
9
5
8
9
9
.
6
8
3
Fig
u
r
e
1
.
Seq
u
en
ce
d
atab
ases
ar
e
s
h
o
r
ten
ed
b
y
P
ag
eRan
k
al
g
o
r
ith
m
Fig
u
r
e
2
.
T
h
e
co
m
p
ar
is
o
n
o
f
P
ag
eRa
n
k
alg
o
r
it
h
m
s
eq
u
en
ce
p
r
ed
ictio
n
b
ased
m
o
d
el
f
o
r
n
ex
t p
ag
e
p
r
ed
ictio
n
6.
CO
NCLU
SI
O
N
I
n
th
i
s
p
ap
er
,
w
e
p
r
esen
ted
an
in
v
est
ig
at
io
n
ab
o
u
t
th
e
s
eq
u
en
ce
p
r
ed
ictio
n
u
s
ed
to
p
r
ed
i
ct
th
e
n
e
x
t
p
ag
e.
E
x
p
er
i
m
en
ta
l
r
es
u
lt
s
o
n
th
e
r
ea
l
d
ataset
Ko
s
ar
a
k
s
h
o
w
s
t
h
at
th
e
i
n
teg
r
atio
n
o
f
C
P
T
+
w
it
h
P
ag
e
R
an
k
i
s
a
b
it h
i
g
h
er
th
a
n
a
n
y
s
eq
u
e
n
ce
p
r
ed
ictio
n
b
ased
m
o
d
els.
B
esi
d
es,
th
e
s
ize
o
f
th
e
s
h
o
r
ten
i
n
g
s
eq
u
en
ce
d
atab
ase
is
r
ed
u
ce
d
d
o
w
n
to
n
ea
r
l
y
3
5
%.
T
h
is
c
u
tti
n
g
i
n
ter
m
s
o
f
th
e
s
ize
o
f
s
eq
u
e
n
ce
d
atab
ases
ta
k
es a
d
v
an
tag
e
o
f
th
e
test
i
n
g
p
h
a
s
e
(
p
r
ed
ictio
n
p
h
as
e)
.
T
h
u
s
,
t
h
e
co
m
b
in
a
tio
n
o
f
P
ag
eRa
n
k
w
it
h
s
eq
u
e
n
ce
p
r
o
ce
s
s
i
n
g
s
u
p
p
o
r
t
to
th
e
C
P
T
+
f
o
r
n
ex
t
p
ag
e
p
r
ed
icti
o
n
.
I
n
p
ar
tic
u
lar
,
r
ed
u
n
d
an
t
s
eq
u
en
ce
s
ar
e
r
e
m
o
v
ed
f
r
o
m
d
atasets
(
s
eq
u
e
n
ce
d
atab
ases
)
.
T
h
e
p
r
ed
ictio
n
s
p
ac
e
is
s
h
o
r
ten
d
ep
en
d
in
g
o
n
t
h
e
n
u
m
b
er
o
f
r
e
m
o
v
ed
s
eq
u
e
n
ce
s
.
B
esid
es,
af
ter
r
e
m
o
v
i
n
g
n
ec
ce
s
s
ar
y
d
ata,
t
h
e
ac
c
u
r
ac
y
is
s
til
l
n
o
t
c
h
an
g
ed
ev
e
n
b
etter
.
Fro
m
p
r
ese
n
t
t
i
m
e
co
n
ti
n
u
i
n
g
f
o
r
w
ar
d
s
i
n
ti
m
e,
w
e
ar
e
g
o
i
n
t
to
d
ev
elo
p
a
n
o
v
el
al
g
o
r
ith
m
s
o
r
co
n
ti
n
u
e
i
m
p
r
o
v
i
n
g
t
h
e
a
v
ailab
le
al
g
o
r
ith
m
s
s
u
c
h
as
C
P
T
+,
P
ag
eRan
k
to
s
o
lv
e
th
e
n
ex
t
p
a
g
e
p
r
ed
ictio
n
is
s
u
e
m
o
r
e
ef
f
ec
ti
v
e.
A
p
ar
t
f
r
o
m
t
h
at,
a
s
o
l
u
tio
n
u
s
i
n
g
b
ig
d
ata
to
o
ls
is
also
co
n
s
id
er
ed
to
escalate
th
e
p
er
f
o
r
m
an
ce
i
n
ter
m
s
o
f
ti
m
e
ex
ec
u
tio
n
f
o
r
d
ea
l
w
it
h
th
is
i
s
s
u
e.
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.
11
,
No
.
3
,
J
u
n
e
2
0
2
1
:
2
2
2
9
-
2237
2234
AP
P
E
NDI
X
A
p
p
en
d
i
x
1
.
T
h
e
ac
cu
r
ac
y
o
f
m
o
d
el
D
G
o
n
r
ed
u
ce
d
d
atasets
N
o
.
l
%
R1
R2
R3
R4
R5
R6
R7
R8
R9
R
1
0
1
1
0
0
8
0
.
0
6
5
7
9
.
9
9
5
8
0
.
0
7
6
8
0
.
0
8
5
8
0
.
2
3
7
8
0
.
1
5
7
7
9
.
9
2
8
0
.
0
7
8
0
.
2
1
2
8
0
.
3
4
4
2
98
8
0
.
6
3
8
0
.
4
2
9
8
0
.
5
9
8
0
.
5
2
8
0
.
7
4
7
8
0
.
5
2
8
0
.
2
5
1
8
0
.
7
4
3
8
0
.
7
0
7
8
0
.
7
1
3
3
96
8
1
.
1
8
8
0
.
9
3
4
8
1
.
0
7
8
8
0
.
9
7
3
8
1
.
2
6
7
8
0
.
8
8
2
8
0
.
8
3
8
8
1
.
1
9
7
8
1
.
0
2
8
8
1
.
2
1
8
4
94
8
1
.
6
7
4
8
1
.
2
0
1
8
1
.
5
3
8
1
.
3
7
4
8
1
.
5
0
8
8
1
.
3
6
8
1
.
3
6
5
8
1
.
6
8
9
8
1
.
5
0
8
8
1
.
6
5
4
5
92
8
2
.
1
3
2
8
1
.
7
7
9
8
2
.
0
1
8
8
1
.
9
0
9
8
2
.
0
3
2
8
1
.
9
1
8
1
.
9
5
3
8
2
.
0
5
9
8
2
.
0
9
1
8
2
.
0
7
5
6
90
8
2
.
7
4
8
2
.
0
9
2
8
2
.
5
4
9
8
2
.
4
5
3
8
2
.
5
3
7
8
2
.
5
2
5
8
2
.
4
3
8
2
.
5
9
4
8
2
.
4
3
3
8
2
.
6
3
9
7
88
8
3
.
2
4
8
8
2
.
8
5
5
8
2
.
8
5
7
8
3
.
0
8
8
3
.
0
7
2
8
3
.
1
4
2
8
3
.
0
3
8
8
3
.
0
2
6
8
3
.
0
0
5
8
3
.
1
1
9
8
86
8
3
.
5
5
5
8
3
.
3
8
9
8
3
.
3
8
3
8
3
.
5
2
5
8
3
.
3
3
1
8
3
.
5
6
5
8
3
.
5
5
8
8
3
.
6
2
8
3
.
6
4
9
8
3
.
5
9
4
9
84
8
4
.
1
6
5
8
3
.
8
1
9
8
3
.
9
7
9
8
4
.
2
6
8
8
3
.
8
7
9
8
4
.
1
5
1
8
4
.
2
7
2
8
4
.
1
6
1
8
3
.
9
4
1
8
4
.
2
3
6
10
82
8
4
.
6
4
9
8
4
.
7
0
1
8
4
.
5
5
4
8
4
.
7
4
9
8
4
.
4
6
6
8
4
.
7
3
9
8
4
.
7
3
8
8
4
.
7
5
1
8
4
.
4
8
7
8
4
.
9
4
4
11
80
8
5
.
2
0
8
8
5
.
4
0
4
8
5
.
1
4
7
8
5
.
5
0
9
8
5
.
2
5
4
8
5
.
3
0
3
8
5
.
1
9
4
8
5
.
1
1
9
8
5
.
2
5
8
5
.
5
2
8
12
78
8
5
.
8
1
1
8
5
.
9
9
6
8
5
.
9
2
8
6
.
0
3
8
5
.
8
4
9
8
5
.
9
8
5
.
7
6
6
8
5
.
9
1
5
8
5
.
8
7
9
8
6
.
2
4
5
13
76
8
6
.
2
8
9
8
6
.
8
9
9
8
6
.
8
6
1
8
6
.
8
6
8
6
.
7
2
4
8
6
.
9
1
3
8
6
.
8
0
6
8
6
.
8
0
9
8
6
.
9
2
8
7
.
1
9
8
14
74
8
7
.
1
3
8
8
7
.
8
0
3
8
8
.
1
4
6
8
8
.
0
3
9
8
7
.
7
3
2
8
7
.
9
2
6
8
7
.
7
6
6
8
7
.
8
9
6
8
7
.
8
7
1
8
8
.
0
2
7
15
72
8
8
.
0
0
3
8
8
.
5
2
7
8
8
.
6
5
8
8
8
.
4
9
6
8
8
.
5
7
4
8
8
.
4
1
7
8
8
.
5
5
3
8
8
.
7
0
5
8
8
.
5
7
4
8
8
.
4
6
3
16
70
8
8
.
9
7
8
8
9
.
2
9
9
8
9
.
0
9
6
8
9
.
7
5
7
8
9
.
5
3
1
8
9
.
0
6
9
8
9
.
6
5
5
8
9
.
0
6
6
8
9
.
6
7
6
8
8
.
9
8
17
68
8
9
.
8
7
8
9
0
.
2
2
5
8
9
.
5
2
5
9
0
.
2
1
3
9
0
.
1
9
6
8
9
.
5
5
8
9
0
.
2
3
8
9
.
7
3
6
9
0
.
2
8
7
8
9
.
4
5
8
18
66
9
0
.
4
8
1
9
0
.
2
6
8
8
9
.
9
3
4
9
0
.
2
6
7
9
0
.
3
2
4
9
0
.
5
2
6
9
0
.
3
1
7
9
0
.
5
8
1
9
0
.
3
5
3
9
0
.
0
2
2
19
64
9
0
.
4
5
8
9
0
.
6
1
9
91
9
0
.
5
9
7
9
0
.
1
9
9
9
1
.
2
6
2
9
0
.
6
8
9
9
1
.
4
2
8
9
.
8
7
6
9
1
.
2
2
3
20
62
8
8
.
9
1
3
8
9
.
5
0
1
9
0
.
1
9
8
9
.
2
4
4
8
9
.
2
8
1
9
0
.
1
4
3
8
9
.
3
0
1
9
0
.
3
3
1
8
9
.
2
9
9
0
.
0
0
6
21
60
9
0
.
1
6
1
9
0
.
3
4
5
9
1
.
4
0
6
9
0
.
2
5
9
9
0
.
2
1
8
9
1
.
5
6
9
0
.
4
4
9
9
1
.
4
4
7
9
0
.
2
1
4
9
1
.
3
7
22
58
9
0
.
8
9
6
9
1
.
4
9
1
9
3
.
2
1
3
9
1
.
5
8
1
9
1
.
2
8
6
9
3
.
4
4
8
9
1
.
6
6
1
9
3
.
1
0
9
9
1
.
5
9
8
9
3
.
2
7
8
23
56
9
2
.
5
0
4
9
2
.
6
3
3
9
4
.
1
8
6
9
2
.
9
0
7
9
2
.
9
9
2
9
4
.
0
4
8
9
3
.
0
0
6
9
4
.
1
5
3
9
2
.
8
8
7
9
3
.
9
0
3
A
p
p
en
d
i
x
2
.
T
h
e
ac
cu
r
ac
y
o
f
m
o
d
el
C
P
T
o
n
r
ed
u
ce
d
d
atasets
N
o
.
%
R1
R2
R3
R4
R5
R6
R7
R8
R9
R
1
0
1
1
0
0
4
7
.
9
7
1
4
8
.
0
6
4
8
.
0
0
4
4
7
.
9
1
1
4
7
.
8
0
7
4
8
.
0
3
3
4
7
.
8
7
3
4
8
.
1
6
5
4
9
.
0
0
9
4
8
.
0
5
2
2
98
4
8
.
1
3
6
4
8
.
0
8
6
4
7
.
9
5
4
7
.
8
8
9
4
7
.
8
6
2
4
8
.
1
1
9
4
8
.
0
0
7
4
8
.
1
5
5
4
8
.
0
6
1
4
8
.
0
4
9
3
96
4
8
.
1
0
3
4
8
.
0
3
7
4
7
.
9
8
8
4
7
.
8
1
9
4
7
.
8
5
7
4
8
.
0
8
2
4
7
.
9
8
3
4
8
.
1
4
7
4
7
.
9
7
2
4
8
.
0
8
1
4
94
4
8
.
0
1
7
4
7
.
9
7
9
4
7
.
9
1
5
4
7
.
8
0
8
4
7
.
8
0
7
4
7
.
9
7
6
4
7
.
9
3
3
4
8
.
1
3
1
4
7
.
8
8
4
4
8
.
0
1
5
92
4
8
.
0
5
4
7
.
8
7
3
4
7
.
8
8
5
4
7
.
8
1
6
4
7
.
7
9
8
4
8
.
0
5
4
4
7
.
9
1
5
4
8
.
1
1
6
4
7
.
9
9
8
4
8
.
0
4
6
90
4
8
.
0
0
7
4
7
.
8
9
7
4
7
.
9
1
3
4
7
.
7
8
3
4
7
.
7
8
4
4
8
.
0
0
5
4
7
.
8
1
3
4
8
.
0
7
1
4
7
.
9
6
5
4
7
.
9
9
9
7
88
4
7
.
9
4
1
4
7
.
6
5
6
4
7
.
5
7
7
4
7
.
5
6
9
4
7
.
4
7
7
4
7
.
6
2
5
4
7
.
5
0
8
4
7
.
7
6
5
4
7
.
6
7
7
4
7
.
5
1
1
8
86
4
7
.
4
0
1
4
7
.
1
4
3
4
6
.
7
7
4
4
6
.
9
3
7
4
6
.
9
3
8
4
6
.
8
5
3
4
6
.
9
6
4
4
6
.
9
8
6
4
7
.
1
4
1
4
6
.
8
0
6
9
84
4
6
.
9
7
1
4
6
.
5
9
4
4
5
.
9
0
2
4
6
.
4
4
4
4
6
.
2
8
2
4
6
.
0
3
2
4
6
.
4
3
4
6
.
1
4
8
4
6
.
6
0
2
4
5
.
9
1
4
10
82
4
6
.
2
6
4
5
.
9
9
2
4
5
.
0
6
5
4
5
.
8
1
2
4
5
.
6
4
4
5
.
2
4
4
4
5
.
8
1
3
4
5
.
3
9
5
4
7
.
1
4
1
4
5
.
0
4
8
11
80
4
5
.
7
4
3
4
5
.
3
1
3
4
4
.
2
0
4
4
5
.
1
9
8
4
4
.
9
2
4
4
4
.
2
9
1
4
5
.
1
4
6
4
4
.
4
4
1
4
5
.
3
2
8
4
4
.
1
7
9
12
78
4
5
.
1
6
8
4
4
.
5
3
4
3
.
1
6
7
4
4
.
3
7
7
4
4
.
3
2
5
4
3
.
3
4
4
.
5
8
1
4
3
.
4
6
4
4
.
6
5
1
4
3
.
3
5
2
13
76
4
4
.
4
5
5
4
3
.
9
6
1
4
2
.
2
0
2
4
3
.
7
2
9
4
3
.
6
0
7
4
2
.
4
2
6
4
3
.
8
2
6
4
2
.
4
2
7
4
3
.
9
3
4
2
.
3
8
3
14
74
4
3
.
7
5
7
4
3
.
1
8
4
4
1
.
2
4
3
4
2
.
9
8
1
4
2
.
6
5
9
4
1
.
3
5
8
4
3
.
1
1
1
4
1
.
2
7
6
4
3
.
1
0
7
4
1
.
2
8
9
15
72
4
2
.
9
3
9
4
2
.
4
4
8
4
0
.
5
7
6
4
2
.
2
0
5
4
2
.
1
1
4
4
0
.
6
7
6
4
2
.
2
3
7
4
0
.
6
1
9
4
2
.
5
7
1
4
0
.
6
1
4
16
70
4
2
.
2
1
7
4
1
.
6
4
5
4
0
.
2
1
9
4
1
.
4
4
2
4
1
.
4
9
7
4
0
.
4
2
5
4
1
.
3
6
7
4
0
.
2
4
4
4
1
.
6
4
3
4
0
.
3
5
4
17
68
4
1
.
2
8
1
4
1
.
0
7
5
3
9
.
7
9
2
4
0
.
9
9
9
4
0
.
9
5
8
4
0
.
0
5
1
4
0
.
8
0
4
3
9
.
8
5
7
4
1
.
2
3
6
4
0
.
0
5
7
18
66
4
0
.
9
1
3
4
0
.
8
8
5
3
9
.
4
7
4
0
.
6
2
8
4
0
.
6
3
4
3
9
.
7
7
2
4
0
.
4
3
7
3
9
.
5
5
4
4
0
.
7
9
5
3
9
.
7
2
6
19
64
4
0
.
4
7
9
4
0
.
3
6
5
3
9
.
1
8
4
0
.
2
6
6
4
0
.
2
7
6
3
9
.
4
6
7
4
0
.
1
1
9
3
9
.
3
0
2
4
0
.
4
9
8
3
9
.
2
2
5
20
62
3
9
.
9
5
3
9
.
9
1
3
3
8
.
7
8
9
3
9
.
9
9
4
3
9
.
7
3
1
3
9
.
0
8
8
3
6
.
6
2
8
3
8
.
9
0
2
4
0
.
0
1
3
3
8
.
8
8
3
21
60
3
9
.
5
4
3
3
9
.
5
6
3
8
.
3
8
5
3
9
.
4
0
4
3
9
.
2
7
9
3
8
.
6
4
5
3
9
.
3
4
3
3
8
.
5
1
3
3
9
.
5
5
3
3
8
.
6
2
2
22
58
3
9
.
1
5
6
3
8
.
9
4
2
3
7
.
9
4
4
3
8
.
9
4
7
3
4
.
8
4
8
3
8
.
1
3
3
3
8
.
8
3
3
3
8
.
1
9
4
3
9
.
0
1
4
3
8
.
0
4
5
23
56
3
8
.
3
3
7
3
8
.
5
0
3
3
7
.
1
1
3
3
8
.
3
9
7
3
8
.
3
6
3
3
7
.
3
7
3
3
8
.
3
5
9
3
7
.
3
1
3
3
8
.
5
6
1
3
7
.
3
9
5
A
p
p
en
d
i
x
3
.
T
h
e
ac
cu
r
ac
y
o
f
m
o
d
el
Ma
r
k
o
v
1
o
n
r
ed
u
ce
d
d
atasets
N
o
.
%
R1
R2
R3
R4
R5
R6
R7
R8
R9
R
1
0
1
1
0
0
6
5
.
9
2
4
6
5
.
9
3
4
6
6
.
0
0
4
6
5
.
7
3
7
6
6
.
0
4
6
6
.
1
1
5
6
5
.
7
7
6
5
.
8
6
4
6
5
.
9
9
7
6
5
.
9
3
2
98
6
6
.
1
8
9
6
6
.
2
4
3
6
6
.
5
3
8
6
6
.
2
6
3
6
6
.
4
1
7
6
6
.
5
0
2
6
6
.
2
2
9
6
6
.
2
3
6
6
6
.
4
2
8
6
6
.
3
3
5
3
96
6
6
.
8
4
1
6
6
.
7
4
4
6
7
.
0
6
1
6
6
.
7
1
4
6
6
.
8
0
3
6
7
.
0
3
1
6
6
.
5
8
7
6
6
.
6
7
1
6
6
.
8
1
1
6
6
.
7
2
2
4
94
6
7
.
2
8
2
6
7
.
0
3
7
6
7
.
4
4
2
6
7
.
2
4
8
6
7
.
2
6
2
6
7
.
4
6
3
6
7
.
2
5
2
6
7
.
2
9
2
6
7
.
3
7
9
6
7
.
4
6
6
5
92
6
7
.
9
0
5
6
7
.
8
9
2
6
8
.
0
0
2
6
8
.
0
0
7
6
7
.
9
4
1
6
8
.
0
8
2
6
7
.
9
0
3
6
7
.
7
9
4
6
8
.
2
8
3
6
8
.
0
4
6
6
90
6
8
.
6
2
3
6
8
.
3
8
1
6
8
.
7
0
4
6
8
.
5
5
6
6
8
.
5
8
2
6
8
.
5
8
7
6
8
.
7
3
6
6
8
.
3
8
7
6
8
.
6
7
6
8
.
5
7
6
7
88
6
9
.
2
3
6
9
.
1
8
6
9
.
1
6
1
6
9
.
2
6
4
6
9
.
2
4
4
6
9
.
3
7
9
7
9
.
2
8
9
6
9
.
7
0
4
6
9
.
1
9
8
6
9
.
1
6
7
8
86
6
9
.
8
8
8
6
9
.
9
5
2
6
9
.
8
4
9
7
0
.
2
7
8
6
9
.
8
0
4
7
0
.
2
2
8
7
0
.
0
9
3
7
0
.
2
7
6
7
0
.
6
1
9
6
9
.
7
7
7
9
84
7
0
.
6
8
7
0
.
9
3
1
7
2
.
0
2
7
0
.
9
6
6
7
0
.
3
2
4
7
1
.
0
3
4
7
0
.
9
6
9
7
0
.
8
3
6
7
0
.
8
8
4
7
0
.
6
0
9
10
82
7
1
.
8
4
8
7
1
.
8
8
5
7
1
.
8
7
1
.
9
1
1
7
1
.
7
0
4
7
1
.
6
5
9
7
1
.
7
2
9
7
1
.
6
2
5
7
1
.
7
5
2
7
1
.
3
6
7
11
80
7
2
.
8
2
2
7
2
.
6
9
6
7
2
.
5
9
8
7
2
.
7
5
4
7
2
.
4
4
8
7
2
.
6
7
4
7
2
.
4
9
9
7
2
.
4
8
3
7
2
.
6
3
5
7
2
.
3
0
7
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
I
n
ve
s
tig
a
tin
g
th
e
P
a
g
eR
a
n
k
a
n
d
s
eq
u
en
ce
p
r
ed
ictio
n
b
a
s
ed
a
p
p
r
o
a
c
h
es fo
r
…
(
N
g
u
ye
n
Th
o
n
Da
)
2235
A
p
p
en
d
i
x
3
.
T
h
e
ac
cu
r
ac
y
o
f
m
o
d
el
Ma
r
k
o
v
1
o
n
r
ed
u
ce
d
d
atasets
(c
o
n
tin
u
e)
N
o
.
%
R1
R2
R3
R4
R5
R6
R7
R8
R9
R
1
0
12
78
7
3
.
3
9
9
7
3
.
6
0
3
7
3
.
3
2
7
3
.
6
5
4
7
3
.
5
6
5
7
3
.
4
7
8
7
3
.
3
2
8
7
3
.
6
2
5
7
3
.
6
5
4
7
3
.
3
2
2
13
76
7
4
.
1
4
6
7
4
.
5
4
8
7
4
.
3
3
1
7
4
.
6
4
1
7
4
.
5
7
7
7
4
.
3
9
7
4
.
4
6
3
7
4
.
6
4
8
7
4
.
7
9
9
7
4
.
4
6
8
14
74
7
5
.
1
8
8
7
5
.
6
9
4
7
5
.
2
4
3
7
5
.
5
2
1
7
5
.
4
7
2
7
5
.
3
6
1
7
5
.
5
6
2
7
5
.
4
6
2
7
5
.
7
9
4
7
5
.
3
6
4
15
72
7
6
.
1
2
4
7
6
.
8
4
7
5
.
8
7
3
7
6
.
4
7
7
7
6
.
5
9
3
7
6
.
1
5
6
7
6
.
5
7
4
7
6
.
1
6
5
7
6
.
8
1
1
7
6
.
0
0
2
16
70
7
7
.
1
0
4
7
7
.
6
5
7
6
.
7
4
7
7
7
.
7
7
1
7
7
.
5
3
6
7
6
.
9
9
8
7
7
.
4
7
6
7
6
.
8
8
7
7
7
.
7
7
7
6
.
8
4
4
17
68
7
7
.
8
4
8
7
8
.
5
7
9
7
7
.
5
5
4
7
8
.
3
7
5
7
8
.
3
2
9
7
7
.
7
1
8
7
8
.
2
9
2
7
7
.
8
5
6
7
8
.
6
4
6
7
7
.
5
9
9
18
66
7
8
.
7
2
7
7
9
.
2
5
8
7
8
.
4
5
7
7
9
.
1
1
2
7
8
.
9
9
1
7
8
.
9
4
7
8
.
9
2
4
7
8
.
8
0
4
7
9
.
3
4
6
7
8
.
6
2
19
64
7
5
.
5
8
7
7
9
.
8
3
1
7
9
.
6
9
7
9
.
7
4
3
7
9
.
7
8
4
8
0
.
0
1
6
7
9
.
8
6
1
7
9
.
8
7
6
7
1
.
2
4
1
7
9
.
6
0
8
20
62
8
0
.
5
2
3
8
0
.
5
6
1
8
1
.
0
5
2
8
0
.
6
3
7
8
0
.
5
4
8
8
1
.
1
8
5
8
0
.
6
1
9
8
1
.
0
4
2
8
0
.
7
8
2
8
0
.
8
3
4
21
60
8
1
.
4
5
7
8
1
.
4
6
7
8
2
.
3
7
2
8
1
.
6
5
6
8
1
.
4
4
7
8
2
.
4
0
8
8
1
.
6
0
6
8
2
.
5
3
8
1
.
6
4
5
8
2
.
4
22
58
8
2
.
5
8
8
8
2
.
5
0
6
8
3
.
9
2
1
8
2
.
5
9
6
8
2
.
4
8
6
8
4
.
1
8
8
8
2
.
6
6
9
8
4
.
0
6
5
7
3
.
7
0
8
8
4
.
0
1
9
23
56
8
3
.
5
3
4
8
3
.
4
8
5
7
5
.
6
8
1
8
3
.
6
3
9
8
3
.
8
4
4
8
4
.
4
8
3
8
3
.
8
4
8
8
4
.
5
7
8
8
3
.
7
7
4
8
4
.
4
6
1
A
p
p
en
d
i
x
4
.
T
h
e
ac
cu
r
ac
y
o
f
m
o
d
el
AKOM
o
n
r
ed
u
ce
d
d
atasets
N
o
.
%
R1
R2
R3
R4
R5
R6
R7
R8
R9
R
1
0
1
1
0
0
5
9
.
1
8
5
5
9
.
3
4
6
5
9
.
5
3
8
5
9
.
3
5
7
5
9
.
6
1
2
5
9
.
5
4
2
5
9
.
3
9
7
5
9
.
5
4
6
5
9
.
4
1
5
5
9
.
5
6
8
2
98
5
9
.
6
0
4
5
9
.
6
4
8
5
9
.
8
8
2
5
9
.
7
5
3
5
9
.
9
2
2
5
9
.
7
5
4
5
9
.
7
2
9
5
9
.
9
6
2
5
9
.
7
3
9
5
9
.
7
3
3
3
96
6
0
.
0
7
1
6
0
.
0
9
4
6
0
.
3
9
9
6
0
.
0
9
7
6
0
.
2
0
5
6
0
.
3
4
6
6
0
.
0
4
8
6
0
.
1
5
1
6
0
.
0
7
6
6
0
.
2
2
4
94
6
0
.
3
7
5
6
0
.
2
9
9
6
0
.
7
0
7
6
0
.
5
8
3
6
0
.
6
6
5
6
0
.
5
9
2
6
0
.
5
1
3
6
0
.
8
0
8
6
0
.
6
8
9
6
0
.
6
7
8
5
92
6
1
.
0
6
4
6
1
.
0
8
9
6
1
.
1
2
3
6
1
.
1
6
7
6
1
.
1
2
2
6
1
.
1
5
7
6
1
.
0
9
2
6
1
.
1
9
9
6
1
.
2
7
4
6
1
.
1
5
8
6
90
6
1
.
6
6
1
.
4
4
2
6
1
.
7
1
6
6
1
.
5
5
3
6
1
.
6
8
6
6
1
.
5
7
1
6
1
.
5
6
8
6
1
.
5
1
4
6
1
.
6
1
7
6
1
.
5
0
2
7
88
6
2
.
0
8
2
6
2
.
0
6
6
6
2
.
1
0
8
6
2
.
1
8
1
6
2
.
1
6
5
6
2
.
1
5
3
6
1
.
9
7
4
6
2
.
3
1
7
6
1
.
9
4
4
6
2
.
2
3
9
8
86
6
2
.
4
8
5
6
2
.
6
4
9
6
2
.
6
4
2
6
2
.
8
1
5
6
2
.
7
2
2
6
2
.
8
3
2
6
2
.
8
2
2
6
2
.
9
7
7
6
2
.
5
8
6
2
.
5
9
84
6
3
.
4
1
3
6
3
.
4
6
3
.
3
7
6
3
.
4
2
9
6
3
.
1
5
7
6
3
.
4
1
1
6
3
.
4
4
1
6
3
.
5
2
9
6
3
.
1
1
4
6
3
.
2
6
6
10
82
6
4
.
0
9
2
6
4
.
2
0
6
6
4
.
0
8
1
6
3
.
9
6
9
6
4
.
1
4
7
6
3
.
9
6
8
6
4
.
0
7
6
4
.
2
6
7
6
4
.
1
8
4
6
3
.
8
4
2
11
80
6
4
.
8
0
8
6
5
.
0
1
3
6
4
.
7
5
4
6
4
.
7
0
8
6
4
.
7
1
1
6
4
.
8
8
2
6
4
.
8
6
2
6
4
.
8
8
5
6
4
.
9
4
2
6
4
.
7
2
9
12
78
6
5
.
4
1
4
6
7
.
7
1
3
6
5
.
5
9
1
6
5
.
5
0
7
6
5
.
4
8
9
6
5
.
5
6
5
6
5
.
5
6
7
6
5
.
8
3
7
6
5
.
5
3
5
6
5
.
5
8
6
13
76
6
6
.
0
1
1
6
6
.
4
8
9
6
6
.
2
9
5
6
6
.
5
2
8
6
6
.
3
5
6
6
6
.
4
3
6
6
.
5
5
3
6
6
.
7
3
3
6
6
.
7
7
7
6
6
.
6
1
14
74
6
6
.
8
9
5
6
7
.
2
1
1
6
7
.
3
1
1
6
7
.
3
0
6
6
7
.
2
3
4
6
7
.
2
0
2
6
7
.
3
7
4
6
7
.
3
9
1
6
7
.
4
8
6
6
7
.
4
1
8
15
72
6
7
.
7
7
8
6
8
.
4
7
7
6
8
.
0
2
1
6
8
.
2
1
3
6
8
.
2
7
8
6
7
.
8
2
3
6
8
.
3
1
6
6
8
.
0
5
6
6
8
.
4
5
6
6
8
.
0
4
6
16
70
6
8
.
4
6
5
6
9
.
2
2
2
6
8
.
6
0
9
6
9
.
3
5
2
6
9
.
2
4
2
6
8
.
3
2
3
6
9
.
1
3
2
7
6
.
8
8
7
6
9
.
3
7
6
8
.
7
2
5
17
68
6
9
.
3
0
4
6
9
.
8
6
6
2
.
2
6
2
6
9
.
8
9
1
6
9
.
8
8
5
6
9
.
0
4
7
6
9
.
8
5
2
6
9
.
3
9
7
7
0
.
0
8
2
6
9
.
2
9
3
18
66
7
0
.
0
4
2
7
0
.
3
9
2
6
9
.
9
4
3
7
0
.
6
0
3
7
0
.
3
7
6
7
0
.
1
8
7
7
0
.
4
2
3
7
0
.
1
7
9
7
0
.
7
0
5
7
0
.
0
7
5
19
64
7
0
.
7
2
7
7
0
.
9
6
4
7
1
.
0
0
4
7
0
.
9
1
6
7
1
.
2
3
8
7
0
.
8
6
9
7
0
.
9
4
2
7
1
.
2
2
5
7
1
.
2
1
4
7
1
.
1
0
6
20
62
7
1
.
4
9
6
7
1
.
5
4
4
7
2
.
2
6
1
7
1
.
9
1
7
1
.
7
1
9
7
2
.
0
2
2
7
1
.
7
5
1
7
2
.
3
3
7
2
.
0
0
1
7
2
.
0
6
21
60
7
2
.
3
6
3
7
2
.
3
7
9
7
3
.
4
1
2
7
2
.
7
2
4
7
2
.
6
2
4
7
3
.
4
5
9
7
2
.
4
6
4
7
3
.
5
5
7
7
2
.
6
9
1
7
3
.
5
3
22
58
7
3
.
3
3
1
7
3
.
7
6
7
7
4
.
0
0
1
7
3
.
6
5
8
7
3
.
5
1
5
7
5
.
0
0
5
7
3
.
4
9
5
7
4
.
9
0
1
7
3
.
7
0
8
7
5
.
0
3
9
23
56
7
4
.
3
3
4
7
4
.
2
8
9
7
5
.
5
0
2
7
4
.
8
0
8
7
4
.
7
6
1
7
5
.
5
7
9
7
4
.
6
0
1
7
5
.
5
7
2
7
4
.
7
1
3
7
5
.
6
9
9
A
p
p
en
d
i
x
5
.
T
h
e
ac
cu
r
ac
y
o
f
m
o
d
el
L
Z
7
8
o
n
r
ed
u
ce
d
d
atasets
N
o
.
%
R1
R2
R3
R4
R5
R6
R7
R8
R9
R
1
0
1
1
0
0
5
9
.
8
0
5
5
9
.
8
9
6
0
.
1
4
5
9
.
7
4
4
6
0
.
0
2
7
5
9
.
7
4
5
6
0
.
1
3
4
5
9
.
7
3
9
5
9
.
9
6
2
6
0
.
2
6
6
2
98
6
0
.
1
6
6
6
0
.
3
5
6
0
.
4
2
4
6
0
.
2
5
9
6
0
.
2
4
3
6
0
.
4
6
6
6
0
.
3
8
6
6
0
.
2
3
5
6
0
.
4
3
1
6
0
.
2
3
3
96
6
0
.
3
8
6
6
0
.
4
9
1
6
0
.
7
2
6
0
.
5
4
6
6
0
.
6
6
5
6
0
.
8
3
4
6
0
.
4
0
3
6
0
.
5
0
2
6
0
.
9
4
9
6
0
.
7
9
9
4
94
6
0
.
9
8
9
6
0
.
6
1
8
6
0
.
6
8
2
6
1
.
0
2
6
0
.
9
0
1
6
1
.
1
5
1
6
0
.
9
5
9
6
1
.
0
6
6
0
.
8
1
2
6
1
.
0
2
6
5
92
6
1
.
3
0
6
6
1
.
3
6
4
6
1
.
5
6
6
6
1
.
4
7
4
6
1
.
2
0
1
6
1
.
4
7
2
6
1
.
2
7
2
6
1
.
4
3
3
6
1
.
6
1
9
6
1
.
4
3
9
6
90
6
1
.
7
7
7
6
1
.
8
5
4
6
1
.
7
1
6
1
.
8
0
3
6
1
.
9
3
1
6
1
.
6
9
2
6
1
.
8
7
3
6
1
.
8
7
8
6
1
.
6
1
7
6
1
.
9
7
2
7
88
6
2
.
4
2
4
6
1
.
9
3
1
6
2
.
4
1
2
6
2
.
3
0
8
6
2
.
2
9
1
6
2
.
5
9
9
6
1
.
7
8
3
6
2
.
2
0
1
6
2
.
2
9
3
6
2
.
4
2
5
8
86
6
2
.
6
4
6
6
2
.
6
4
9
6
2
.
6
0
9
6
2
.
4
6
3
6
2
.
8
2
4
6
2
.
8
8
9
6
2
.
7
0
2
6
2
.
8
5
6
6
2
.
8
8
1
6
2
.
5
5
4
9
84
6
3
.
6
7
4
6
3
.
3
7
1
6
3
.
1
0
1
6
3
.
6
8
7
6
3
.
4
1
3
6
2
.
9
6
2
6
3
.
2
9
5
6
2
.
8
1
5
6
3
.
1
1
4
6
3
.
2
2
10
82
6
4
.
4
3
9
6
4
.
2
5
6
6
3
.
4
8
6
4
.
1
1
7
6
4
.
0
4
3
6
3
.
7
7
4
6
4
.
2
1
8
6
3
.
9
4
7
6
3
.
9
8
6
3
.
7
6
3
11
80
6
4
.
7
2
4
6
4
.
8
9
6
4
.
3
3
2
6
4
.
6
3
4
6
4
.
6
6
4
.
3
5
6
6
4
.
4
7
5
6
3
.
9
4
7
6
4
.
8
1
1
6
4
.
2
5
5
12
78
6
5
.
2
3
9
6
5
.
5
5
6
6
4
.
8
3
6
6
5
.
2
8
1
6
5
.
2
9
5
6
4
.
4
5
9
6
5
.
1
9
7
6
4
.
7
7
6
5
.
5
6
7
6
4
.
7
4
5
13
76
6
6
.
1
5
6
6
6
.
3
5
4
6
5
.
6
3
4
6
6
.
0
8
3
6
6
.
1
8
4
6
5
.
1
7
9
6
6
.
2
5
6
5
.
3
6
7
6
6
.
4
5
7
6
5
.
3
0
1
14
74
6
6
.
5
6
6
6
6
.
9
8
6
6
6
.
0
1
1
6
6
.
8
4
3
6
6
.
7
3
5
6
6
.
1
1
5
6
6
.
7
8
5
6
5
.
9
3
6
6
7
.
0
5
6
6
5
.
8
2
6
15
72
6
7
.
5
2
6
6
8
.
0
0
8
6
6
.
4
0
9
6
7
.
6
6
8
6
7
.
6
8
5
6
6
.
5
3
4
6
7
.
8
0
6
6
6
.
4
0
8
6
7
.
7
7
1
6
6
.
7
8
5
16
70
6
8
.
1
3
4
6
8
.
2
7
2
6
7
.
4
2
6
8
.
7
6
8
.
7
4
6
7
.
5
3
3
6
8
.
1
1
3
6
7
.
2
2
1
6
8
.
7
9
6
6
7
.
4
3
6
17
68
6
8
.
7
8
6
9
.
1
6
8
6
8
.
1
3
2
6
9
.
2
4
1
6
9
.
3
6
3
6
8
.
2
6
3
6
9
.
2
7
8
6
8
.
0
6
1
6
9
.
2
9
2
6
8
.
1
4
9
18
66
6
9
.
3
4
2
6
9
.
9
4
1
6
8
.
8
9
6
6
9
.
8
2
1
6
9
.
5
5
8
6
9
.
2
6
3
6
9
.
4
6
3
6
8
.
9
4
8
7
0
.
0
5
6
9
.
1
4
3
19
64
7
0
.
1
9
1
7
0
.
6
4
9
7
0
.
2
7
7
0
.
6
3
7
0
.
5
2
4
7
0
.
3
4
9
7
0
.
3
8
8
7
0
.
2
5
5
7
0
.
4
7
8
7
0
.
3
7
6
20
62
7
0
.
9
8
8
7
1
.
2
8
6
7
1
.
2
5
9
7
1
.
2
8
8
7
0
.
8
3
7
1
.
3
6
7
7
1
.
2
0
8
7
1
.
3
3
7
1
.
3
3
4
7
1
.
2
9
7
21
60
7
1
.
6
7
8
7
1
.
9
9
2
7
2
.
7
0
5
7
2
.
1
6
8
7
1
.
7
2
2
7
5
.
5
7
2
7
1
.
8
1
4
7
2
.
6
2
3
7
2
.
3
0
1
7
2
.
7
7
1
22
58
7
2
.
4
4
9
7
2
.
7
6
7
7
4
.
8
3
2
7
3
.
0
4
8
7
2
.
6
4
5
7
4
.
1
0
4
7
2
.
7
4
6
7
3
.
9
4
3
7
3
.
0
2
5
7
4
.
1
6
23
56
7
3
.
5
7
1
7
3
.
4
5
4
7
4
.
6
8
7
3
.
8
0
8
7
3
.
9
5
2
7
4
.
2
4
5
7
3
.
7
2
9
7
4
.
2
2
1
7
3
.
7
5
7
7
4
.
5
7
3
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.
11
,
No
.
3
,
J
u
n
e
2
0
2
1
:
2
2
2
9
-
2237
2236
A
p
p
en
d
i
x
6
.
T
h
e
ac
cu
r
ac
y
o
f
m
o
d
el
C
P
T
+
o
n
r
ed
u
ce
d
d
atasets
N
o
.
%
R1
R2
R3
R4
R5
R6
R7
R8
R9
R
1
0
1
1
0
0
9
9
.
9
2
7
9
9
.
9
4
1
9
9
.
9
3
6
9
9
.
9
2
4
9
9
.
9
3
8
9
9
.
9
3
8
9
9
.
9
4
1
9
9
.
9
3
4
9
9
.
9
3
6
9
9
.
9
4
7
2
98
9
9
.
9
2
1
9
9
.
9
5
8
9
9
.
9
3
7
9
9
.
9
2
5
9
9
.
9
4
1
9
9
.
9
5
1
9
9
.
9
5
1
9
9
.
9
4
2
9
9
.
9
3
5
9
9
.
9
4
6
3
96
9
9
.
9
3
1
9
9
.
9
7
9
9
.
9
4
4
9
9
.
9
3
3
9
9
.
9
4
6
9
9
.
9
5
4
9
9
.
9
5
2
9
9
.
9
5
6
9
9
.
9
4
9
9
9
.
9
4
7
4
94
9
9
.
9
3
7
9
9
.
9
6
4
9
9
.
9
4
9
9
9
.
9
4
3
9
9
.
9
5
4
9
9
.
9
6
6
9
9
.
9
5
9
9
9
.
9
5
7
9
9
.
9
5
9
9
9
.
9
5
7
5
92
9
9
.
9
4
9
9
.
9
7
7
9
9
.
9
5
5
9
9
.
9
5
9
9
9
.
9
6
6
9
9
.
9
6
6
9
9
.
9
5
9
9
9
.
9
6
6
9
9
.
9
5
7
9
9
.
9
5
9
6
90
9
9
.
9
5
6
9
9
.
9
7
6
9
9
.
9
6
7
9
9
.
9
6
2
9
9
.
9
6
4
9
9
.
9
6
7
9
9
.
9
5
6
9
9
.
9
6
4
9
9
.
9
6
2
9
9
.
9
6
4
7
88
9
9
.
9
5
4
9
9
.
9
7
8
9
9
.
9
6
9
9
9
.
9
6
9
9
9
.
9
6
3
9
9
.
9
7
4
9
9
.
9
6
9
9
9
.
9
7
1
9
9
.
9
6
5
9
9
.
9
7
2
8
86
9
9
.
9
6
9
9
.
9
7
9
9
9
.
9
7
4
9
9
.
9
7
9
9
.
9
6
6
9
9
.
9
7
9
9
9
.
9
8
1
9
9
.
9
6
2
9
9
.
9
7
9
9
.
9
6
6
9
84
9
9
.
9
6
7
9
9
.
9
7
9
9
9
.
9
7
9
9
9
.
9
7
5
9
9
.
9
6
9
9
9
.
9
7
7
9
9
.
9
7
9
9
9
.
9
6
1
9
9
.
9
6
7
9
9
.
9
7
1
10
82
9
9
.
9
7
6
9
9
.
9
8
9
9
.
9
7
4
9
9
.
9
8
2
9
9
.
9
7
4
9
9
.
9
7
8
9
9
.
9
8
6
9
9
.
9
6
6
9
9
.
9
7
2
9
9
.
9
7
11
80
9
9
.
9
7
3
9
9
.
9
8
4
9
9
.
9
8
2
9
9
.
9
7
7
9
9
.
9
9
7
9
9
.
9
7
8
9
9
.
9
8
8
9
9
.
9
6
9
9
9
.
9
7
3
9
9
.
8
4
12
78
9
9
.
9
7
7
9
9
.
9
8
9
9
9
.
9
8
5
9
9
.
9
8
1
9
9
.
9
8
1
9
9
.
9
9
9
9
.
9
8
5
9
9
.
9
8
3
9
9
.
9
6
8
9
9
.
9
8
1
13
76
9
9
.
9
8
1
9
9
.
9
8
5
9
9
.
9
8
7
9
9
.
9
8
7
9
9
.
9
7
4
9
9
.
9
9
6
9
9
.
9
8
3
9
9
.
9
8
7
9
9
.
9
7
8
9
9
.
9
8
7
14
74
9
9
.
9
8
2
9
9
.
9
9
8
9
9
.
9
9
8
9
9
.
9
9
1
9
9
.
9
8
4
9
9
.
9
9
8
9
9
.
9
8
9
9
9
.
9
9
1
9
9
.
9
7
8
9
9
.
9
9
3
15
72
9
9
.
9
8
6
9
9
.
9
9
3
1
0
0
9
9
.
9
9
1
9
9
.
9
9
1
9
9
.
9
9
8
9
9
.
9
8
8
1
0
0
9
9
.
9
8
4
1
0
0
16
70
9
9
.
9
8
8
9
9
.
9
9
8
9
9
.
9
9
8
9
9
.
9
9
8
9
9
.
9
9
8
9
9
.
9
9
8
9
9
.
9
9
8
9
9
.
9
9
8
9
9
.
9
9
5
1
0
0
17
68
9
9
.
9
9
8
1
0
0
9
9
.
9
9
8
9
9
.
9
9
8
1
0
0
9
9
.
9
9
5
9
9
.
9
9
8
9
9
.
9
9
3
9
9
.
9
9
8
1
0
0
18
66
1
0
0
1
0
0
9
9
.
9
9
5
9
9
.
9
9
7
1
0
0
9
9
.
9
9
7
1
0
0
9
9
.
9
9
7
9
9
.
9
9
7
1
0
0
19
64
9
9
.
9
9
7
1
0
0
9
9
.
9
5
4
9
9
.
9
9
7
1
0
0
9
9
.
9
3
8
1
0
0
9
9
.
9
9
7
9
9
.
9
9
7
9
9
.
9
5
7
20
62
1
0
0
9
9
.
9
9
7
9
9
.
9
4
1
9
9
.
9
9
7
9
9
.
9
9
7
9
9
.
9
5
5
1
0
0
9
9
.
9
4
7
9
9
.
9
9
7
9
9
.
9
3
21
60
9
9
.
9
9
7
9
9
.
8
6
6
9
9
.
7
4
8
9
9
.
9
9
4
9
9
.
8
2
4
9
9
.
7
5
1
9
9
.
9
9
7
9
9
.
7
1
8
9
9
.
6
7
5
9
9
.
7
6
22
58
9
9
.
6
3
6
9
9
.
6
1
3
9
9
.
8
4
9
9
.
5
8
1
9
9
.
5
4
3
9
9
.
8
9
2
9
9
.
6
9
3
9
9
.
7
1
8
9
9
.
5
1
5
9
9
.
8
4
4
23
56
9
9
.
6
3
4
9
9
.
6
1
9
9
.
8
1
9
9
.
5
7
1
9
9
.
5
4
2
9
9
.
8
9
9
9
.
6
9
3
9
9
.
7
1
6
9
9
.
5
1
1
9
9
.
8
3
5
ACK
NO
WL
E
D
G
E
M
E
NT
T
h
is
r
esear
ch
is
f
u
n
d
ed
b
y
Vietn
a
m
Natio
n
al
U
n
i
v
er
s
it
y
Ho
C
h
i
Mi
n
h
C
it
y
(
VN
U
-
H
C
M)
u
n
d
er
g
r
an
t
n
u
m
b
er
C
2
0
1
9
-
34
-
06.
RE
F
E
R
E
NC
E
S
[1
]
R.
S
u
n
a
n
d
C.
L
.
G
il
e
s,
"
S
e
q
u
e
n
c
e
lea
rn
in
g
:
F
r
o
m
re
c
o
g
n
it
io
n
a
n
d
p
re
d
ictio
n
t
o
se
q
u
e
n
ti
a
l
d
e
c
isio
n
m
a
k
in
g
,
"
IEE
E
In
telli
g
e
n
t
S
y
ste
ms
,
v
o
l.
1
6
,
n
o
.
4
,
p
p
.
6
7
-
7
0
,
2
0
0
1
.
[2
]
P
.
F
o
u
r
n
ier
-
V
ig
e
r,
J.
C.
-
W
.
L
in
,
R.
U.
Kira
n
,
Y.
S
.
Ko
h
,
a
n
d
R.
Th
o
m
a
s,
"
A
su
rv
e
y
o
f
se
q
u
e
n
ti
a
l
p
a
tt
e
rn
m
in
in
g
,
"
Da
ta
S
c
ien
c
e
a
n
d
P
a
tt
e
rn
Rec
o
g
n
it
io
n
,
v
o
l.
1
,
n
o
.
1
,
p
p
.
5
4
-
7
7
,
2
0
1
7
.
[3
]
T
.
G
u
e
n
ich
e
,
P
.
F
o
u
rn
ier
-
V
ig
e
r,
a
n
d
V
.
S
.
T
se
n
g
,
"
Co
m
p
a
c
t
p
re
d
ictio
n
tree
:
A
lo
ss
les
s
m
o
d
e
l
f
o
r
a
c
c
u
ra
te
se
q
u
e
n
c
e
p
re
d
ictio
n
,
"
in
In
ter
n
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
d
D
a
ta
M
i
n
in
g
a
n
d
A
p
p
li
c
a
ti
o
n
s
,
v
o
l
.
8
3
4
7
,
p
p
.
1
7
7
-
1
8
8
,
2
0
1
3
[4
]
R.
A
g
r
a
w
a
l
a
n
d
R.
S
rik
a
n
t,
"
F
a
st
a
lg
o
rit
h
m
s
f
o
r
m
in
in
g
a
ss
o
c
ia
ti
o
n
r
u
l
e
s,"
VL
DB
'
9
4
:
Pro
c
e
e
d
i
n
g
s
o
f
th
e
2
0
t
h
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Ver
y
L
a
rg
e
D
a
ta
Ba
se
s
,
v
o
l.
1
2
1
5
,
1
9
9
4
,
p
p
.
4
8
7
-
4
9
9
.
[5
]
P
.
F
o
u
rn
ier
-
V
ig
e
r,
T
.
G
u
e
n
ich
e
,
S
.
Zi
d
a
,
a
n
d
V
.
S
.
T
se
n
g
,
"
ERM
in
e
r:
se
q
u
e
n
ti
a
l
ru
le
m
in
in
g
u
s
in
g
e
q
u
iv
a
len
c
e
c
las
se
s,
"
in
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m o
n
In
telli
g
e
n
t
Da
t
a
A
n
a
lys
is
,
v
o
l.
8
8
1
9
,
p
p
.
1
0
8
-
1
1
9
,
2
0
1
4
.
[6
]
P
.
F
o
u
rn
ier
-
V
ig
e
r,
R.
Nk
a
m
b
o
u
,
a
n
d
V
.
S
.
-
M
.
T
se
n
g
,
"
Ru
le
G
ro
w
th
:
m
in
in
g
se
q
u
e
n
ti
a
l
ru
les
c
o
m
m
o
n
to
se
v
e
ra
l
s
e
q
u
e
n
c
e
s
b
y
p
a
t
t
e
r
n
-
g
r
o
w
t
h
,
"
i
n
P
r
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
1
A
C
M
s
y
m
p
o
s
i
u
m
o
n
a
p
p
l
i
e
d
c
o
m
p
u
t
i
n
g
,
2
0
1
1
,
p
p
.
9
5
6
-
961
.
[7
]
P
.
F
o
u
r
n
ier
-
V
ig
e
r,
U.
F
a
g
h
ih
i,
R.
Nk
a
m
b
o
u
,
a
n
d
E.
M
.
Ng
u
if
o
,
"
CM
Ru
les
:
M
in
in
g
se
q
u
e
n
ti
a
l
ru
les
c
o
m
m
o
n
to
se
v
e
r
a
l
se
q
u
e
n
c
e
s,"
Kn
o
wled
g
e
-
B
a
se
d
S
y
ste
ms
,
v
o
l.
2
5
,
n
o
.
1
,
p
p
.
6
3
-
7
6
,
2
0
1
2
.
[8
]
M
.
J.
Zak
i,
"
S
P
A
DE:
A
n
e
ff
icie
n
t
a
lg
o
rit
h
m
f
o
r
m
in
in
g
f
r
e
q
u
e
n
t
se
q
u
e
n
c
e
s,"
M
a
c
h
in
e
lea
rn
i
n
g
,
v
o
l.
4
2
,
n
o
.
1
-
2
,
p
p
.
3
1
-
6
0
,
2
0
0
1
.
[9
]
P
.
F
o
u
r
n
i
e
r
-
Vi
g
e
r
,
C
.
-
W
.
W
u
,
V.
S
.
T
se
n
g
,
a
n
d
R
.
N
k
a
m
b
o
u
,
"
M
i
n
in
g
s
e
q
u
e
n
t
i
a
l
r
u
le
s
c
o
m
m
o
n
t
o
s
e
v
e
ra
l
se
q
u
e
n
c
e
s
w
i
t
h
t
h
e
w
i
n
d
o
w
s
i
z
e
c
o
n
s
t
ra
i
n
t
,
"
in
C
a
n
a
d
i
a
n
C
o
n
f
e
r
e
n
c
e
o
n
A
r
t
i
f
i
c
ia
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
7
3
1
0
,
2
0
1
2
,
p
p
.
2
9
9
-
3
0
4
.
[1
0
]
V
.
N.
P
a
d
m
a
n
a
b
h
a
n
a
n
d
J.
C.
M
o
g
u
l,
"
Us
in
g
p
re
d
ictiv
e
p
re
f
e
tch
in
g
to
im
p
ro
v
e
W
o
rld
W
id
e
W
e
b
late
n
c
y
,
"
AC
M
S
IGCO
M
M
Co
mp
u
ter
Co
mm
u
n
ic
a
ti
o
n
Rev
iew
,
v
o
l.
2
6
,
n
o
.
3
,
p
p
.
2
2
-
3
6
,
1
9
9
6
.
[1
1
]
J.
G
ri
ff
io
e
n
a
n
d
R.
A
p
p
leto
n
,
"
Re
d
u
c
in
g
F
il
e
S
y
ste
m
L
a
ten
c
y
u
sin
g
a
P
re
d
ictiv
e
A
p
p
ro
a
c
h
,
"
US
T
C
'
9
4
:
Pro
c
e
e
d
in
g
s
o
f
t
h
e
US
ENIX
S
u
mm
e
r
1
9
9
4
T
e
c
h
n
ica
l
Co
n
fer
e
n
c
e
o
n
US
ENIX
S
u
mm
e
r
1
9
9
4
T
e
c
h
n
ica
l
Co
n
fer
e
n
c
e
,
v
o
l.
1
,
1
9
9
4
,
p
p
.
1
9
7
-
2
0
7
.
[1
2
]
J.
Zi
v
a
n
d
A
.
L
e
m
p
e
l,
"
Co
m
p
re
ss
io
n
o
f
in
d
iv
id
u
a
l
se
q
u
e
n
c
e
s
v
ia
v
a
riab
le
-
ra
te
c
o
d
in
g
,
"
IEE
E
tra
n
sa
c
ti
o
n
s
o
n
In
fo
rm
a
t
io
n
T
h
e
o
ry
,
v
o
l.
2
4
,
n
o
.
5
,
p
p
.
5
3
0
-
5
3
6
,
1
9
7
8
.
[1
3
]
J.
P
it
k
o
w
a
n
d
P
.
P
iro
ll
i,
"
M
i
n
in
g
lo
n
g
e
stre
p
e
a
ti
n
g
su
b
se
q
u
e
n
c
e
sto
p
re
d
ict
w
o
rld
w
id
e
we
b
su
rf
in
g
,
"
Pro
c
e
e
d
in
g
s
o
f
US
IT
S
'
9
9
:
T
h
e
2
n
d
US
ENIX
S
y
mp
o
siu
m
o
n
In
ter
n
e
t
T
e
c
h
n
o
lo
g
ies
&
S
y
ste
m
s
,
1
9
9
9
,
p
p
. 1
-
13
.
[1
4
]
J.
Clea
r
y
a
n
d
I.
W
it
ten
,
"
Da
ta
c
o
m
p
re
ss
io
n
u
sin
g
a
d
a
p
ti
v
e
c
o
d
i
n
g
a
n
d
p
a
rti
a
l
strin
g
m
a
tch
in
g
,
"
IEE
E
tra
n
sa
c
ti
o
n
s
o
n
C
o
mm
u
n
ica
ti
o
n
s
,
v
o
l.
3
2
,
n
o
.
4
,
p
p
.
3
9
6
-
4
0
2
,
1
9
8
4
.
[1
5
]
P
.
L
a
ird
a
n
d
R
.
S
a
u
l,
"
Disc
re
te
se
q
u
e
n
c
e
p
re
d
icti
o
n
a
n
d
it
s
a
p
p
li
c
a
ti
o
n
s,"
M
a
c
h
in
e
lea
r
n
in
g
,
v
o
l.
1
5
,
n
o
.
1
,
p
p
.
4
3
-
6
8
,
1
9
9
4
.
[1
6
]
D.
F
.
G
leic
h
,
"
P
a
g
e
Ra
n
k
b
e
y
o
n
d
t
h
e
W
e
b
,
"
S
ia
m R
e
v
iew
,
v
o
l.
5
7
,
n
o
.
3
,
p
p
.
3
2
1
-
3
6
3
,
2
0
1
5
.
[1
7
]
R.
G
e
e
th
a
ra
m
a
n
i,
P
.
Re
v
a
th
y
,
a
n
d
S
.
G
.
J
a
c
o
b
,
"
P
re
d
icti
o
n
o
f
u
se
rs
w
e
b
p
a
g
e
a
c
c
e
ss
b
e
h
a
v
io
u
r
u
sin
g
a
ss
o
c
iatio
n
ru
le m
in
in
g
,
"
S
a
d
h
a
n
a
,
v
o
l.
4
0
,
n
o
.
8
,
p
p
.
2
3
5
3
-
2
3
6
5
,
2
0
1
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
I
n
ve
s
tig
a
tin
g
th
e
P
a
g
eR
a
n
k
a
n
d
s
eq
u
en
ce
p
r
ed
ictio
n
b
a
s
ed
a
p
p
r
o
a
c
h
es fo
r
…
(
N
g
u
ye
n
Th
o
n
Da
)
2237
[1
8
]
B.
D.
G
u
n
e
l
a
n
d
P
.
S
e
n
k
u
l,
"
In
v
e
stig
a
ti
n
g
th
e
e
ffe
c
t
o
f
d
u
ra
ti
o
n
p
a
g
e
siz
e
a
n
d
f
re
q
u
e
n
c
y
o
n
n
e
x
t
p
a
g
e
re
c
o
m
m
e
n
d
a
ti
o
n
w
it
h
p
a
g
e
ra
n
k
a
lg
o
rit
h
m
,
"
in
Pro
c
e
e
d
in
g
s
o
f
th
e
Fi
ft
h
ACM
W
e
b
S
e
a
rc
h
a
n
d
Da
t
a
M
in
i
n
g
Co
n
fer
e
n
c
e
,
2
0
1
2
.
[1
9
]
J.
-
H.
S
u
,
B.
-
W
.
W
a
n
g
,
a
n
d
V
.
S
.
T
se
n
g
,
"
Eff
e
c
ti
v
e
ra
n
k
in
g
a
n
d
re
c
o
m
m
e
n
d
a
ti
o
n
o
n
w
e
b
p
a
g
e
re
tri
e
v
a
l
b
y
in
teg
ra
ti
n
g
a
ss
o
c
iatio
n
m
in
in
g
a
n
d
P
a
g
e
Ra
n
k
,
"
2
0
0
8
IE
EE
/
W
IC
/A
CM
In
ter
n
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
o
n
W
e
b
In
telli
g
e
n
c
e
a
n
d
I
n
telli
g
e
n
t
A
g
e
n
t
T
e
c
h
n
o
lo
g
y
,
S
y
d
n
e
y
,
NSW
,
2
0
0
8
,
p
p
.
4
5
5
-
4
5
8
.
[2
0
]
P
.
T
h
w
e
,
"
P
ro
p
o
se
d
a
p
p
r
o
a
c
h
f
o
r
w
e
b
p
a
g
e
a
c
c
e
ss
p
re
d
ictio
n
u
sin
g
p
o
p
u
larity
a
n
d
sim
il
a
rit
y
b
a
se
d
p
a
g
e
ra
n
k
a
lg
o
rit
h
m
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
S
c
ien
ti
fi
c
&
T
e
c
h
n
o
lo
g
y
Res
e
a
rc
h
,
v
o
l.
2
,
n
o
.
3
,
p
p
.
2
4
0
-
2
4
6
,
2
0
1
3
.
[2
1
]
N.
T
.
Da
,
T
.
H
a
n
h
,
a
n
d
P
.
H.
D
u
y
,
"
I
m
p
ro
v
in
g
Web
p
a
g
e
A
c
c
e
ss
P
re
d
icti
o
n
s
Ba
se
d
o
n
S
e
q
u
e
n
c
e
P
re
d
ictio
n
a
n
d
P
a
g
e
ra
n
k
A
lg
o
rit
h
m
,
"
In
ter
d
isc
ip
li
n
a
ry
J
o
u
rn
a
l
o
f
In
fo
rm
a
t
io
n
,
K
n
o
wled
g
e
&
M
a
n
a
g
e
me
n
t
,
v
o
l
.
1
4
,
2
0
1
9
.
[2
2
]
B.
Nig
a
m
,
S
.
T
o
k
e
k
a
r,
a
n
d
S
.
Ja
i
n
,
"
P
re
d
icti
n
g
th
e
n
e
x
t
a
c
c
e
ss
e
d
w
e
b
p
a
g
e
u
sin
g
M
a
rk
o
v
m
o
d
e
l
a
n
d
P
a
g
e
Ra
n
k
,
"
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
D
a
ta
M
i
n
in
g
a
n
d
Eme
rg
in
g
T
e
c
h
n
o
l
o
g
ies
,
v
o
l.
3
,
n
o
.
2
,
p
p
.
7
3
-
8
0
,
2
0
1
3
.
[2
3
]
M
.
V
a
z
irg
ian
n
is,
D.
Dro
s
o
s,
P
.
S
e
n
e
ll
a
rt,
a
n
d
A
.
Vla
c
h
o
u
,
"
W
e
b
p
a
g
e
ra
n
k
p
re
d
ictio
n
w
it
h
M
a
rk
o
v
m
o
d
e
ls,"
in
W
W
W
'
0
8
:
Pr
o
c
e
e
d
in
g
s
o
f
t
h
e
1
7
t
h
in
ter
n
a
ti
o
n
a
l
c
o
n
fer
e
n
c
e
o
n
W
o
rld
W
id
e
W
e
b
,
2
0
0
8
,
p
p
.
1
0
7
5
-
1
0
7
6
.
[2
4
]
P
.
T
h
w
e
,
"
Us
in
g
M
a
rk
o
v
M
o
d
e
l
a
n
d
P
o
p
u
larity
a
n
d
S
im
il
a
rit
y
B
a
se
d
P
a
g
e
Ra
n
k
A
l
g
o
rit
h
m
f
o
r
W
e
b
P
a
g
e
A
c
c
e
ss
P
re
d
ictio
n
,
"
in
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
s in
En
g
in
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(
ICAT
E)
,
2
0
1
4
.
[2
5
]
M
.
Ei
ri
n
a
k
i,
M
.
V
a
z
irg
ian
n
is,
a
n
d
D.
Ka
p
o
g
ian
n
is,
"
W
e
b
p
a
th
re
c
o
m
m
e
n
d
a
ti
o
n
s b
a
se
d
o
n
p
a
g
e
ra
n
k
in
g
a
n
d
m
a
rk
o
v
m
o
d
e
ls,"
in
Pro
c
e
e
d
in
g
s
o
f
th
e
7
th
a
n
n
u
a
l
ACM
in
ter
n
a
ti
o
n
a
l
w
o
rk
sh
o
p
o
n
W
e
b
in
f
o
rm
a
ti
o
n
a
n
d
d
a
t
a
ma
n
a
g
e
me
n
t
,
2
0
0
5
,
p
p
.
2
-
9.
[2
6
]
T
.
G
u
e
n
ich
e
,
P
.
F
o
u
rn
ier
-
V
ig
e
r,
R.
Ra
m
a
n
,
a
n
d
V
.
S
.
T
se
n
g
,
"
CP
T
+
:
De
c
r
e
a
sin
g
th
e
ti
m
e
/sp
a
c
e
c
o
m
p
lex
it
y
o
f
th
e
Co
m
p
a
c
t
P
re
d
icti
o
n
T
re
e
,
"
in
Pa
c
if
ic
-
Asia
C
o
n
f
e
r
e
n
c
e
o
n
K
n
o
w
l
e
d
g
e
D
i
s
c
o
v
e
r
y
a
n
d
D
a
t
a
M
i
n
i
n
g
,
2
0
1
5
,
p
p
.
6
2
5
-
6
3
6
.
[2
7
]
N.
T
.
Da
,
T
.
Ha
n
h
,
a
n
d
P
.
H.
D
u
y
,
"
A
S
u
rv
e
y
o
f
W
e
b
p
a
g
e
A
c
c
e
s
s
P
re
d
ictio
n
,
"
2
0
1
8
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
d
T
e
c
h
n
o
lo
g
ies
fo
r
Co
m
mu
n
ica
t
io
n
s (
AT
C)
,
Ho
C
h
i
M
i
n
h
Cit
y
,
2
0
1
8
,
p
p
.
3
1
5
-
3
2
0
.
[2
8
]
S
.
Da
s,
“
T
i
m
e
se
ries
a
n
a
l
y
sis.
P
ri
n
c
e
to
n
u
n
iv
e
rsity
p
re
ss
,”
Prin
c
e
to
n
,
NJ
,
1
9
9
4
.
[2
9
]
G
.
C.
Ca
w
l
e
y
a
n
d
N.
L
.
T
a
lb
o
t,
"
On
o
v
e
r
-
f
it
ti
n
g
in
m
o
d
e
l
se
lec
ti
o
n
a
n
d
su
b
se
q
u
e
n
t
se
lec
ti
o
n
b
ias
in
p
e
rf
o
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
,
"
J
o
u
rn
a
l
o
f
M
a
c
h
in
e
L
e
a
rn
in
g
Res
e
a
rc
h
,
v
o
l.
1
1
,
p
p
.
2
0
7
9
-
2
1
0
7
,
2
0
1
0
.
[3
0
]
R.
Ko
h
a
v
i,
"
A
stu
d
y
o
f
c
ro
ss
-
v
a
li
d
a
ti
o
n
a
n
d
b
o
o
tstrap
f
o
r
a
c
c
u
r
a
c
y
e
sti
m
a
ti
o
n
a
n
d
m
o
d
e
l
s
e
lec
ti
o
n
,
"
IJ
CAI'
9
5
:
Pro
c
e
e
d
in
g
s
o
f
t
h
e
1
4
t
h
in
ter
n
a
ti
o
n
a
l
j
o
in
t
c
o
n
fer
e
n
c
e
o
n
Arti
fi
c
ia
l
in
telli
g
e
n
c
e
,
v
o
l.
2
,
1
9
9
5
,
p
p
.
1
1
3
7
-
1
1
4
5
.
[3
1
]
G
.
Ja
m
e
s,
D.
W
it
ten
,
T
.
Ha
stie,
a
n
d
R.
T
ib
sh
iran
i
,
“
A
n
in
tr
o
d
u
c
ti
o
n
to
sta
ti
stica
l
lea
rn
in
g
,
”
S
p
ri
n
g
e
r
,
2
0
1
3
.
[3
2
]
M
.
Ku
h
n
a
n
d
K.
Jo
h
n
so
n
,
“
A
p
p
li
e
d
p
re
d
ictiv
e
m
o
d
e
li
n
g
,
”
S
p
rin
g
e
r
,
2
0
1
3
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Ng
u
y
e
n
T
h
o
n
D
a
is
a
f
in
a
l
-
y
e
a
r
P
h
.
D.
stu
d
e
n
t
i
n
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
a
t
P
o
sts
a
n
d
T
e
le
c
o
m
m
u
n
ica
ti
o
n
s
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
V
ietn
a
m
,
in
th
e
y
e
a
r
2
0
2
0
.
He
is
c
u
rre
n
tl
y
a
lec
tu
re
r
in
th
e
F
a
c
u
lt
y
o
f
In
f
o
r
m
a
ti
o
n
S
y
ste
m
s,
Un
iv
e
rsit
y
o
f
Eco
n
o
m
ics
a
n
d
La
w
,
V
NU
-
HCM,
V
ietn
a
m
.
H
is
re
se
a
r
c
h
in
tere
sts
a
re
Da
ta
M
in
in
g
,
Da
ta
A
n
a
l
y
t
ics
,
Big
Da
ta,
a
n
d
S
e
q
u
e
n
c
e
P
re
d
ictio
n
.
h
tt
p
s://
o
rc
i
d
.
o
rg
/
0
0
0
0
-
0
0
0
2
-
2
6
6
0
-
5
0
1
1
(ORCID
ID)
Ta
n
H
a
n
h
re
c
e
iv
e
d
a
P
h
D d
e
g
re
e
in
In
f
o
rm
a
ti
c
s
f
ro
m
G
re
n
o
b
le INP
,
F
ra
n
c
e
,
in
2
0
0
9
.
Cu
rre
n
t
ly
,
h
e
is
v
ice
p
re
sid
e
n
t
o
f
th
e
P
o
sts
a
n
d
T
e
lec
o
m
m
u
n
ica
ti
o
n
s
In
stit
u
t
e
o
f
T
e
c
h
n
o
lo
g
y
.
His
r
e
se
a
r
c
h
in
tere
sts
a
re
Distrib
u
ted
S
y
ste
m
s
,
M
a
c
h
in
e
L
e
a
rn
in
g
,
In
f
o
rm
a
ti
o
n
Re
tri
e
v
a
l,
a
n
d
Da
ta
M
in
in
g
.
h
tt
p
s:/
/o
rc
id
.
o
rg
/0
0
0
0
-
0
0
0
2
-
8
2
4
4
-
7
0
4
6
(ORCID
ID)
Evaluation Warning : The document was created with Spire.PDF for Python.