T
E
L
K
O
M
N
I
K
A
T
elec
o
m
m
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
,
p
p
.
317
~
32
6
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Kem
en
r
is
tek
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/TE
L
KOM
NI
K
A.
v
1
9
i1
.
1
6
2
0
5
317
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
WEI
DJ
:
Dev
elo
p
ment of
a new
alg
o
rithm f
o
r s
emi
-
s
truct
u
red
web data
e
x
t
ra
cti
o
n
I
ly
Am
a
lin
a
Ahm
a
d Sa
bri
,
M
us
t
a
f
a
M
a
n
F
a
c
u
lt
y
o
f
Oc
e
a
n
En
g
i
n
e
e
rin
g
Tec
h
n
o
l
o
g
y
a
n
d
I
n
fo
rm
a
ti
c
s,
Un
i
v
e
r
siti
M
a
lay
sia
Tere
n
g
g
a
n
u
,
Tere
n
g
g
a
n
u
,
M
a
lay
sia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
2
9
,
2
0
2
0
R
ev
is
ed
Au
g
9
,
2
0
2
0
Acc
ep
ted
Au
g
2
9
,
2
0
2
0
In
t
h
e
e
ra
o
f
i
n
d
u
strial
d
ig
it
a
li
z
a
ti
o
n
,
p
e
o
p
le
a
re
in
c
re
a
sin
g
l
y
in
v
e
stin
g
i
n
so
lu
ti
o
n
s
t
h
a
t
a
ll
o
w
th
e
ir
p
ro
c
e
ss
fo
r
d
a
ta
c
o
ll
e
c
ti
o
n
,
d
a
ta
a
n
a
ly
sis
a
n
d
p
e
rfo
rm
a
n
c
e
imp
ro
v
e
m
e
n
t.
In
t
h
is
p
a
p
e
r,
a
d
v
a
n
c
in
g
we
b
sc
a
le
k
n
o
wle
d
g
e
e
x
trac
ti
o
n
a
n
d
a
li
g
n
m
e
n
t
b
y
in
teg
ra
ti
n
g
fe
w
so
u
rc
e
s
b
y
e
x
p
lo
r
in
g
d
iffere
n
t
m
e
th
o
d
s
o
f
a
g
g
re
g
a
ti
o
n
a
n
d
a
tt
e
n
ti
o
n
is
c
o
n
si
d
e
re
d
i
n
o
rd
e
r
f
o
c
u
sin
g
o
n
ima
g
e
in
fo
rm
a
ti
o
n
.
Th
e
m
a
in
a
i
m
o
f
d
a
ta
e
x
trac
ti
o
n
wit
h
re
g
a
rd
s
to
se
m
i
-
stru
c
tu
re
d
d
a
ta
is
to
re
tri
e
v
e
b
e
n
e
ficia
l
in
fo
rm
a
ti
o
n
fro
m
th
e
we
b
.
Th
e
d
a
ta
fro
m
we
b
a
lso
k
n
o
wn
a
s
d
e
e
p
we
b
is
re
tri
e
v
a
b
le
b
u
t
it
re
q
u
ir
e
s
re
q
u
e
st
th
ro
u
g
h
fo
rm
s
u
b
m
issio
n
b
e
c
a
u
se
it
c
a
n
n
o
t
b
e
p
e
rf
o
rm
e
d
b
y
a
n
y
se
a
rc
h
e
n
g
in
e
s.
A
s
t
h
e
HTM
L
d
o
c
u
m
e
n
t
s
sta
rt
to
g
ro
w
larg
e
r,
it
h
a
s
b
e
e
n
fo
u
n
d
th
a
t
th
e
p
r
o
c
e
ss
o
f
d
a
ta
e
x
trac
ti
o
n
h
a
s
b
e
e
n
p
lag
u
e
d
wi
th
le
n
g
t
h
y
p
ro
c
e
s
sin
g
ti
m
e
.
In
th
is
re
se
a
rc
h
wo
rk
,
we
p
ro
p
o
se
a
n
imp
ro
v
e
d
m
o
d
e
l
n
a
m
e
l
y
wra
p
p
e
r
e
x
trac
ti
o
n
o
f
ima
g
e
u
si
n
g
d
o
c
u
m
e
n
t
o
b
jec
t
m
o
d
e
l
(DO
M
)
a
n
d
J
a
v
a
S
c
rip
t
o
b
jec
t
n
o
tati
o
n
d
a
ta
(JSON)
(
WE
IDJ
)
in
re
sp
o
n
se
to
t
h
e
p
r
o
m
isin
g
re
su
lt
s
o
f
m
in
in
g
i
n
a
h
ig
h
e
r
v
o
l
u
m
e
o
f
i
m
a
g
e
fro
m
a
v
a
rio
u
s
ty
p
e
o
f
f
o
rm
a
t
.
T
o
o
b
se
rv
e
t
h
e
e
fficie
n
c
y
o
f
WE
I
DJ
,
we
c
o
m
p
a
re
th
e
p
e
rfo
rm
a
n
c
e
o
f
d
a
ta
e
x
trac
ti
o
n
b
y
d
iffere
n
t
lev
e
l
o
f
p
a
g
e
e
x
trac
ti
o
n
with
VIBS,
M
D
R,
DEP
TA
a
n
d
VID
E.
It
h
a
s
y
ield
e
d
th
e
b
e
st
re
su
lt
s
in
P
re
c
isio
n
wit
h
1
0
0
,
R
e
c
a
ll
with
9
7
.
9
3
1
0
3
a
n
d
F
-
m
e
a
su
re
with
9
8
.
9
5
4
7
.
K
ey
w
o
r
d
s
:
Do
cu
m
en
t o
b
ject
m
o
d
el
J
av
aS
cr
ip
t o
b
ject
n
o
tatio
n
W
eb
d
ata
ex
tr
ac
tio
n
W
r
ap
p
er
ex
tr
ac
tio
n
o
f
im
a
g
e
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
:
I
ly
Am
alin
a
Ah
m
ad
Sab
r
i
Facu
lty
o
f
Oce
an
E
n
g
in
ee
r
i
n
g
T
ec
h
n
o
lo
g
y
an
d
I
n
f
o
r
m
atics
Un
iv
er
s
iti Ma
lay
s
ia
T
er
en
g
g
a
n
u
Ku
ala
Ner
u
s
,
T
er
en
g
g
an
u
,
Ma
lay
s
ia
E
m
ail: ily
lin
a@
u
m
t.e
d
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
n
u
m
b
er
s
o
f
d
e
v
ices
an
d
g
ad
g
ets
co
n
n
ec
tio
n
to
th
e
I
n
ter
n
et
is
o
n
th
e
r
is
e.
T
h
is
in
cr
ea
s
e
in
in
ter
n
et’
s
co
n
n
ec
tio
n
m
ak
es
th
e
web
as
th
e
lar
g
est
s
o
u
r
ce
o
f
in
f
o
r
m
atio
n
wo
r
ld
wid
e
.
W
ith
th
e
lar
g
e
am
o
u
n
t
o
f
d
ata
r
esid
in
g
in
th
e
web
,
an
d
co
m
p
lem
en
ted
b
y
a
d
v
a
n
c
ed
tech
n
o
lo
g
ies
in
d
ata
b
ase
p
r
o
ce
s
s
in
g
,
it
is
th
er
ef
o
r
e
a
s
ea
m
less
ef
f
o
r
t
to
g
ath
er
,
co
llect
an
d
p
r
o
ce
s
s
th
e
d
ata.
As
th
e
co
n
s
eq
u
en
ce
o
f
t
h
e
ex
p
o
n
en
tial
d
ata
g
r
o
wth
,
it
is
m
o
s
t
im
p
o
r
tan
t
f
o
r
u
s
er
s
to
ad
o
p
t
ad
v
an
ce
d
d
a
ta
an
aly
tics
tech
n
o
lo
g
ies
f
o
r
a
n
ef
f
ici
en
t
s
to
r
ag
e
,
r
etr
iev
al
an
d
an
aly
s
is
o
f
th
e
d
ata.
T
h
e
m
ai
n
aim
is
to
u
s
ef
u
lly
u
tili
ze
th
is
d
ata,
to
lear
n
ab
o
u
t
p
atter
n
s
an
d
tr
en
d
s
th
at
ca
n
b
e
u
s
ed
t
o
m
a
k
e
a
p
o
s
itiv
e
im
p
ac
t
o
n
o
u
r
li
f
esty
le.
Ho
wev
er
,
th
e
d
ata
its
elf
d
o
esn
’
t
p
r
o
d
u
ce
th
ese
o
b
jectiv
es,
b
u
t
r
ath
er
it’
s
s
o
lu
tio
n
s
th
at
ar
is
e
f
r
o
m
an
aly
zin
g
it
an
d
f
in
d
in
g
t
h
e
an
s
wer
s
we
n
ee
d
.
T
h
is
ac
cu
m
u
latio
n
o
f
d
ata
in
ter
m
s
o
f
v
o
lu
m
e,
tech
n
o
lo
g
y
an
d
te
ch
n
iq
u
es
a
r
e
o
f
ten
b
ein
g
d
is
cu
s
s
ed
in
r
elatio
n
t
o
m
in
e
d
ata
f
r
o
m
wo
r
ld
wid
e
web
.
Fig
u
r
e
1
s
h
o
ws
th
e
n
u
m
b
er
o
f
s
ch
o
lar
ly
wo
r
k
s
o
v
er
tim
e
b
y
th
ei
r
p
u
b
licatio
n
ty
p
e
s
u
c
h
as
b
o
o
k
,
d
is
s
er
tatio
n
,
jo
u
r
n
al
ar
ticle
,
r
ep
o
r
t,
co
n
f
er
e
n
ce
p
r
o
ce
e
d
i
n
g
an
d
s
o
f
o
r
th
v
ia
len
s
.
o
r
g
.
Fro
m
th
is
g
r
ap
h
,
it c
a
n
b
e
ea
s
ily
s
ee
n
th
e
tr
e
n
d
in
t
h
is
r
esear
ch
f
ield
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
3
1
7
-
32
6
318
Fig
u
r
e
1
.
Nu
m
b
er
o
f
s
ch
o
l
ar
l
y
wo
r
k
s
f
r
o
m
1
9
7
0
till
2
0
2
0
Min
in
g
d
ata
u
n
c
o
v
er
n
ew
f
ac
ts
an
d
r
elatio
n
s
h
ip
s
u
s
in
g
u
s
ef
u
l
p
atter
n
s
an
d
tech
n
iq
u
es
i
n
o
r
d
er
t
o
g
iv
e
a
s
o
lu
tio
n
f
o
r
h
an
d
lin
g
b
ig
d
ata
[
1
]
.
Data
m
in
in
g
tech
n
iq
u
es
ar
e
im
p
lem
en
te
d
to
f
in
d
u
s
ef
u
l
p
atter
n
s
in
lar
g
e
d
atab
ase
s
u
c
h
as
My
SQ
L
an
d
O
r
ac
le.
I
t
is
th
e
p
r
o
ce
s
s
th
at
tr
ies
to
d
is
co
v
er
p
atter
n
s
o
r
tech
n
i
q
u
es
th
at
ca
n
b
e
ap
p
lied
in
lar
g
e
d
ataset
[
2
]
.
T
h
e
m
ain
g
o
al
o
f
d
ata
m
in
in
g
is
to
ex
tr
ac
t
in
f
o
r
m
atio
n
f
r
o
m
lar
g
e
d
ataset.
E
n
o
u
g
h
d
ata
an
d
s
u
p
p
o
r
ted
t
o
o
ls
ar
e
im
p
o
r
tan
t
a
n
d
n
ee
d
t
o
co
m
p
lem
e
n
t
ea
ch
o
th
e
r
’
s
in
d
ea
lin
g
with
lar
g
e
d
ata
s
et.
I
t
m
ay
b
e
lev
er
ag
in
g
o
n
to
th
e
im
p
lem
en
tatio
n
o
f
th
e
b
ig
d
ata
th
at
p
r
o
v
i
d
es
g
r
ea
t
o
p
p
o
r
tu
n
ities
f
o
r
v
ar
io
u
s
o
f
f
ield
s
s
u
ch
as
e
-
c
o
m
m
er
ce
,
i
n
d
u
s
tr
ial
c
o
n
tr
o
ls
a
n
d
s
m
ar
t m
ed
icals
[
3
]
.
H
o
wev
e
r
,
th
e
ch
ar
ac
te
r
is
tic
s
o
f
lar
g
e
v
o
lu
m
es,
lar
g
e
v
ar
ieties,
lar
g
e
v
elo
cities
an
d
lar
g
e
v
er
ac
ities
o
f
in
f
o
r
m
atio
n
n
ee
d
to
b
e
co
n
s
id
er
ed
i
n
o
r
d
er
to
h
an
d
le
th
e
c
h
allen
g
i
n
g
f
o
r
d
ata
m
in
in
g
[
4
]
.
Fin
ally
,
th
e
ex
tr
ac
ted
i
n
f
o
r
m
atio
n
will
b
e
tr
an
s
f
o
r
m
ed
in
to
a
s
tr
u
ctu
r
ed
way
f
o
r
f
u
r
t
h
er
u
s
e.
W
eb
m
in
in
g
is
th
e
a
p
p
licatio
n
o
f
d
ata
m
in
in
g
tec
h
n
iq
u
es
to
d
is
co
v
er
p
o
ten
tial in
f
o
r
m
atio
n
a
u
to
m
ati
ca
lly
f
r
o
m
t
h
e
web
.
I
n
r
elatio
n
to
Fig
u
r
e
2
,
web
m
in
in
g
is
d
iv
id
ed
in
to
th
r
e
e
ca
teg
o
r
ies;
web
c
o
n
ten
t
m
in
in
g
,
web
s
tr
u
ctu
r
e
m
in
in
g
an
d
web
u
s
ag
e
m
in
in
g
.
W
eb
co
n
ten
t
m
in
i
n
g
is
all
ab
o
u
t
d
is
co
v
e
r
in
g
u
s
ef
u
l
co
n
te
n
t
o
n
th
e
wo
r
ld
wid
e
web
(
W
W
W
)
b
y
u
s
in
g
d
ata
in
teg
r
atio
n
an
d
d
ata
e
x
tr
ac
tio
n
.
W
eb
s
tr
u
ctu
r
e
m
in
i
n
g
p
lace
s
web
s
ites
an
d
web
p
ag
es
th
at
c
o
n
tain
in
a
n
etwo
r
k
o
f
co
n
n
ec
ted
web
s
ites
b
y
u
s
in
g
h
y
p
er
lin
k
s
.
A
h
y
p
er
lin
k
is
an
elem
en
t
in
HT
ML
d
o
cu
m
e
n
ts
th
at
lin
k
s
an
o
b
ject
s
u
ch
as
te
x
t,
im
ag
e,
a
n
d
v
id
eo
.
to
an
o
th
er
HT
ML
d
o
c
u
m
en
t
alt
o
g
eth
er
.
I
n
o
th
er
h
a
n
d
,
web
u
s
ag
e
m
in
in
g
f
o
cu
s
es
o
n
b
r
o
wsi
n
g
b
eh
av
i
o
r
eith
e
r
u
s
i
n
g
p
atter
n
tr
ac
k
o
r
p
er
s
o
n
alize
u
s
ag
es tr
ac
k
.
T
h
is
p
ap
er
f
o
cu
s
es o
n
web
m
u
ltime
d
ia
m
in
in
g
f
o
cu
s
es o
n
im
a
g
es.
Fig
u
r
e
2
.
W
eb
m
in
i
n
g
ca
teg
o
r
ies
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
WEI
DJ:
Dev
elo
p
men
t o
f a
n
e
w
a
lg
o
r
ith
m
fo
r
s
emi
-
s
t
r
u
ctu
r
ed
w
eb
d
a
ta
.
.
.
(
I
ly
A
m
a
lin
a
A
h
ma
d
S
a
b
r
i
)
319
Min
in
g
d
ata
o
r
ex
tr
ac
tin
g
d
at
a
f
r
o
m
web
p
ag
es
is
a
m
ajo
r
f
ea
tu
r
e
f
o
r
h
u
m
an
to
lead
an
d
g
et
h
u
g
e
b
en
ef
its
.
W
eb
s
ites
ar
e
d
esig
n
ed
f
o
r
v
ar
io
u
s
p
eo
p
le
an
d
th
e
y
ar
e
k
n
o
wn
as
s
em
i
-
s
tr
u
ctu
r
ed
d
ata.
T
h
e
s
tr
u
ctu
r
e
o
f
ea
ch
web
p
ag
e
is
d
if
f
er
e
n
t
f
o
r
ea
ch
p
ag
e
.
T
h
u
s
,
it
is
n
o
t
ea
s
y
to
ca
p
tu
r
e
all
th
e
d
ata
in
d
if
f
er
en
t
s
tr
u
ctu
r
e
[
5
]
a
n
d
m
an
y
s
tu
d
ie
s
d
is
cu
s
s
ab
o
u
t
e
x
tr
ac
tin
g
d
at
a
f
r
o
m
web
s
ites
an
d
v
a
r
io
u
s
m
eth
o
d
s
h
a
v
e
b
ee
n
d
ev
elo
p
e
d
.
T
h
e
lar
g
e
v
o
lu
m
e
o
f
im
ag
es
an
d
t
h
eir
in
f
o
r
m
ati
o
n
r
eq
u
ir
es
n
ew
s
o
lu
tio
n
s
to
m
an
ag
e
an
d
an
aly
ze
th
em
.
W
e
h
av
e
p
r
o
p
o
s
ed
wr
a
p
p
er
ex
tr
ac
tio
n
o
f
im
a
g
e
u
s
in
g
d
o
cu
m
en
t
o
b
ject
m
o
d
el
(
D
OM
)
an
d
J
av
aS
cr
ip
t
o
b
ject
n
o
tatio
n
d
ata
(
J
SON)
(
W
E
I
DJ)
in
o
r
d
er
to
a
d
d
r
ess
th
is
co
n
ce
r
n
.
T
h
e
m
ai
n
m
o
tiv
ati
o
n
f
o
r
th
is
r
esear
ch
is
im
ag
e’
s
ex
tr
ac
tio
n
,
m
in
in
g
o
f
im
ag
e’
s
d
etails
an
d
its
s
to
r
ag
e
in
s
in
g
le
m
u
ltime
d
ia
d
atab
ase.
I
n
id
ea
l
s
ce
n
ar
io
,
if
im
ag
e
n
ee
d
to
b
e
s
av
ed
,
it
s
h
o
u
ld
b
e
m
a
n
u
ally
ex
tr
ac
ted
.
E
x
t
r
ac
tio
n
an
d
s
av
i
n
g
o
f
r
eq
u
ir
ed
f
iles
o
r
im
a
g
es
is
im
p
o
r
tan
t
s
in
ce
th
ese
d
o
cu
m
en
ts
ca
n
b
e
b
e
n
e
f
icial
f
o
r
f
u
r
th
er
p
u
r
p
o
s
e.
Ho
wev
er
,
p
r
o
b
lem
s
in
lo
ad
in
g
tim
es
ex
is
t
wh
en
th
e
s
ize
o
f
th
e
im
ag
es
to
b
e
ex
tr
a
cted
ar
e
to
o
b
ig
.
T
h
er
e
f
o
r
e,
a
n
o
th
er
s
o
lu
tio
n
m
u
s
t
b
e
d
ev
elo
p
ed
to
a
u
to
m
atica
ll
y
ex
tr
ac
t
th
e
im
a
g
es
to
r
ed
u
ce
th
e
co
n
s
u
m
e
d
tim
e.
A
d
at
a
ex
tr
ac
tio
n
en
g
in
e
s
h
o
u
ld
b
e
b
e
ab
le
to
ex
tr
ac
t
al
l
th
e
r
eq
u
ir
e
d
f
r
o
m
web
p
ag
e.
T
h
e
in
itial
s
tep
in
ex
tr
ac
tin
g
d
ata
f
r
o
m
a
s
p
ec
if
ic
web
p
ag
e
is
to
d
e
f
in
e
th
e
u
n
if
o
r
m
r
eso
u
r
ce
lo
ca
to
r
(
UR
L
)
o
f
th
e
web
p
a
g
e,
wh
er
e
t
h
e
d
ata
is
lo
ca
ted
.
2.
DATA
E
XT
RACT
I
O
N
Data
ex
tr
ac
tio
n
is
wh
er
e
d
ata
is
b
ee
n
an
aly
s
ed
an
d
cr
awle
d
th
r
o
u
g
h
f
r
o
m
d
ata
s
o
u
r
ce
s
s
u
ch
as
web
o
r
d
ata
b
ases
.
I
t
d
ep
e
n
d
s
o
n
s
p
ec
if
ic
p
atter
n
s
o
f
u
s
er
r
e
q
u
ir
em
en
ts
.
T
h
e
g
o
al
o
f
d
ata
ex
tr
ac
tio
n
is
to
r
etr
iev
e
r
elev
an
t
in
f
o
r
m
atio
n
.
I
t
o
r
g
a
n
izes
d
ata
in
to
u
s
ab
le
an
d
v
alu
ab
le
r
eso
u
r
ce
s
o
th
at
we
ca
n
u
s
e
f
o
r
f
u
r
th
e
r
pu
r
p
o
s
es.
T
h
e
ex
tr
ac
tio
n
p
r
o
c
ess
m
ay
in
v
o
lv
e
d
if
f
er
en
t d
ata
ty
p
es.
Prio
r
to
ex
tr
ac
tio
n
p
r
o
c
ess
es,
d
ata
n
ee
d
s
to
b
e
well
o
r
g
an
ized
.
I
f
th
e
d
ata
is
in
a
s
tr
u
ctu
r
ed
f
o
r
m
at,
it
will
b
e
m
o
r
e
ap
p
licab
le.
T
h
er
e
ar
e
th
r
ee
ty
p
es
o
f
d
ata;
s
tr
u
ctu
r
ed
d
ata,
s
em
i
-
s
tr
u
ctu
r
ed
d
ata
an
d
u
n
s
tr
u
ctu
r
ed
d
ata.
T
h
e
r
e
ar
e
m
an
y
way
s
t
o
d
ea
l
with
all
t
h
ese
ty
p
es
o
f
d
ata.
T
h
is
r
esear
ch
f
o
cu
s
ed
o
n
t
h
e
ex
tr
ac
tio
n
o
f
s
e
m
i
-
s
tr
u
ctu
r
ed
d
ata.
T
h
er
e
a
r
e
th
r
ee
b
asic
s
tep
s
in
d
ata
ex
tr
ac
tio
n
p
r
o
ce
s
s
as sh
o
wn
in
Fig
u
r
e
3
.
T
h
e
ad
v
an
tag
es
o
f
d
ata
e
x
tr
ac
t
io
n
f
r
o
m
s
em
i
-
s
tr
u
ctu
r
ed
d
ata
is
th
at
it
ca
n
b
e
a
p
p
lied
i
n
v
a
r
i
o
u
s
f
ield
s
s
u
ch
as
in
ed
u
ca
tio
n
[
6
]
,
ad
v
e
r
tis
em
en
ts
[
7
]
,
h
o
u
s
in
g
m
an
a
g
em
en
ts
[
8
]
.
I
n
f
o
r
m
er
wo
r
k
s
,
th
e
d
is
cu
s
s
ed
d
ata
ex
tr
ac
tio
n
s
h
av
e
b
ee
n
m
o
d
ell
ed
u
s
in
g
a
s
in
g
le
m
o
d
el
o
r
co
m
b
in
atio
n
o
f
s
ev
er
al
m
o
d
e
ls
f
o
r
an
o
p
tim
u
m
ass
es
s
m
en
t
[
9
]
W
h
ile
web
h
as
d
ev
elo
p
e
d
in
to
a
lar
g
e
s
o
u
r
ce
o
f
in
f
o
r
m
atio
n
,
t
h
er
e
ar
e
d
i
f
f
er
en
t
d
ata
ty
p
es
o
f
in
f
o
r
m
atio
n
th
at
will
b
e
d
is
c
u
s
s
ed
in
n
ex
t
s
ec
tio
n
.
T
h
is
p
ap
er
aim
s
to
ad
v
o
ca
te
th
e
p
o
ten
tial
o
f
two
-
p
h
ase
q
u
er
y
p
ar
ad
i
g
m
f
o
r
web
m
i
n
in
g
.
Ou
r
e
x
ten
s
iv
e
ex
p
e
r
im
en
ts
in
d
icate
b
y
f
o
llo
win
g
c
r
iter
ia:
-
Hav
in
g
an
e
x
p
licit tar
g
et
f
o
r
t
h
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
.
-
Usi
n
g
a
lar
g
e
s
et
o
f
in
f
o
r
m
atio
n
f
r
o
m
s
ev
er
al
web
s
ite
wh
ich
also
h
as d
if
f
er
en
t stru
ctu
r
e.
T
h
is
ap
p
r
o
ac
h
t
u
r
n
s
o
u
t
t
o
b
e
h
ig
h
ly
ef
f
ec
tiv
e
in
p
r
ac
tice.
I
n
o
u
r
v
iew,
th
ese
r
esu
lts
h
in
t
th
at
a
f
u
lly
au
t
o
m
atic
s
o
lu
tio
n
f
o
r
q
u
er
y
in
g
th
e
s
tr
u
ctu
r
ed
im
a
g
es
an
d
r
elate
d
in
f
o
r
m
atio
n
,
n
o
n
-
h
id
d
en
im
ag
es
r
ef
er
to
Fig
u
r
e
4
in
clu
d
in
g
asp
ec
ts
o
f
th
e
s
tr
u
ct
u
r
e
f
o
r
ea
ch
web
an
d
t
h
e
r
ed
u
n
d
an
cy
o
f
th
e
im
ag
es Fig
u
r
e
5
.
Fig
u
r
e
3
.
Data
ex
t
r
ac
tio
n
p
r
o
c
ess
Fig
u
r
e
4
.
I
m
ag
es c
an
n
o
t b
e
r
etr
iev
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
3
1
7
-
32
6
320
Fig
u
r
e
5
.
R
ed
u
n
d
an
c
y
o
f
im
ag
es
3
WE
B
DATA
E
X
T
RAC
T
I
O
N
(
WDE
)
T
h
e
im
p
o
r
tan
c
e
o
f
web
d
ata
ex
tr
ac
tio
n
(
W
DE
)
d
ep
en
d
s
o
n
th
e
f
ac
t
th
at
lar
g
e
am
o
u
n
ts
o
f
d
ata
ar
e
co
n
tin
u
o
u
s
ly
b
ee
n
g
en
er
ate
d
,
s
h
ar
ed
an
d
u
tili
ze
d
in
e
v
er
y
s
ec
o
n
d
.
W
DE
tech
n
i
q
u
es
ar
e
im
p
lem
en
ted
to
r
ed
u
ce
lab
o
r
in
te
n
s
iv
e
task
s
an
d
p
lay
im
p
o
r
tan
t
r
o
les
in
r
aisi
n
g
th
e
ac
cu
r
ac
ies
in
d
ata
ex
tr
ac
tio
n
.
Ma
n
y
f
ac
to
r
s
s
h
o
u
ld
b
e
c
o
n
s
id
er
ed
in
d
esig
n
in
g
W
DE
in
clu
d
in
g
th
e
tech
n
iq
u
es.
On
e
o
f
th
e
c
r
itical
f
ac
to
r
s
is
th
e
ab
ilit
y
o
f
th
e
d
ev
elo
p
ed
tech
n
iq
u
es in
p
r
o
ce
s
s
in
g
a
lar
g
e
am
o
u
n
t o
f
d
ata
in
a
s
h
o
r
t tim
e.
W
eb
d
ata
ex
tr
ac
tio
n
s
y
s
tem
is
a
s
o
f
twar
e
ap
p
licatio
n
th
at
ca
n
ex
tr
ac
t
d
ata
f
r
o
m
web
s
o
u
r
ce
s
[
1
0
]
.
T
h
is
ap
p
licatio
n
u
s
u
ally
i
n
ter
ac
ts
with
a
web
s
o
u
r
ce
an
d
ex
tr
ac
t
s
th
e
s
to
r
ed
d
ata.
T
h
e
ex
tr
ac
ted
co
n
ten
ts
co
n
s
is
t
o
f
elem
en
ts
in
th
e
HT
ML
web
p
ag
es
an
d
ca
n
b
e
p
o
s
t
-
p
r
o
ce
s
s
ed
,
co
n
v
e
r
ted
to
th
e
m
o
s
t
ap
p
r
o
p
r
iate
s
tr
u
ctu
r
ed
f
o
r
m
at
an
d
s
to
r
ed
f
o
r
f
u
r
th
e
r
u
s
ag
e.
T
ab
le
1
s
h
o
ws
web
d
ata
ex
tr
ac
tio
n
to
o
ls
th
at
ar
e
u
s
in
g
d
if
f
er
en
t te
ch
n
iq
u
es.
T
ab
le
1
.
W
eb
d
ata
e
x
tr
ac
tio
n
t
o
o
ls
(
A
u
t
h
o
r
,
y
e
a
r
)
To
o
l
s
M
o
d
e
l
F
a
n
g
,
X
i
e
[
1
1
]
S
TEM
S
u
f
f
i
x
Tr
e
e
B
a
se
d
M
e
t
h
o
d
P
o
u
r
a
mi
n
i
,
K
h
a
j
e
H
a
ss
a
n
i
[
1
2
]
H
a
n
d
l
e
-
b
a
s
e
d
W
r
a
p
p
e
r
D
O
M
Tr
e
e
Ji
mé
n
e
z
a
n
d
C
o
r
c
h
u
e
l
o
[
1
3
]
TA
N
G
O
DOM
C
h
i
t
r
a
a
n
d
A
y
s
h
a
B
a
n
u
[
1
4
]
D
W
D
E
Ta
g
b
a
se
d
F
e
a
t
u
r
e
Tr
i
p
a
t
h
y
,
J
o
s
h
i
[
1
5
]
V
ED
D
D
O
M
Tr
e
e
B
r
e
a
d
t
h
F
i
r
st
S
e
a
r
c
h
(
B
F
S
)
D
e
r
o
u
i
c
h
e
,
C
a
u
t
i
s [1
6
]
O
b
j
e
c
t
R
u
n
n
e
r
Li
u
,
P
u
[
1
7
]
X
W
R
A
P
D
O
M
Tr
e
e
C
h
a
n
g
a
n
d
K
u
o
[
1
8
]
O
LER
A
Li
u
,
G
r
o
s
sma
n
[
1
9
]
M
D
R
C
a
i
,
Y
u
[
2
0
]
V
I
P
S
D
O
M
Tr
e
e
V
i
s
u
a
l
C
u
e
s
C
r
e
sc
e
n
z
i
,
M
e
c
c
a
[
2
1]
R
o
a
d
R
u
n
n
e
r
-
C
h
a
n
g
a
n
d
Lu
i
[
2
2
]
I
EPA
D
P
a
t
t
e
r
n
D
i
sc
o
v
e
r
y
H
su
a
n
d
D
u
n
g
[
2
3
]
S
o
f
t
M
e
a
l
y
-
H
a
mm
e
r
,
G
a
r
c
i
a
-
M
o
l
i
n
a
[
2
4
]
TSI
M
M
I
S
O
b
j
e
c
t
E
x
c
h
a
n
g
e
M
o
d
e
l
(
O
E
M
)
4
RE
S
E
ARCH
M
E
T
H
O
D
Prio
r
to
ex
tr
ac
tio
n
p
r
o
ce
s
s
es,
d
ata
n
ee
d
s
to
b
e
well
o
r
g
an
ize
d
.
I
f
th
e
d
ata
is
in
a
s
tr
u
ctu
r
ed
f
o
r
m
at,
it
will
b
e
m
o
r
e
ap
p
licab
le.
T
h
er
e
ar
e
th
r
ee
ty
p
es
o
f
d
ata;
s
tr
u
c
tu
r
ed
d
ata,
s
em
i
-
s
tr
u
ctu
r
ed
d
a
ta
an
d
u
n
s
tr
u
ctu
r
e
d
d
ata.
T
h
er
e
a
r
e
m
an
y
way
s
t
o
d
ea
l
with
all
th
ese
ty
p
es
o
f
d
ata.
T
h
is
r
esear
ch
f
o
cu
s
ed
o
n
th
e
e
x
tr
ac
tio
n
o
f
s
em
i
-
s
tr
u
ctu
r
ed
d
ata.
T
h
er
e
a
r
e
th
r
ee
b
asic
s
tep
s
in
d
ata
e
x
tr
ac
tio
n
p
r
o
ce
s
s
;
s
elec
tio
n
,
tr
an
s
f
o
r
m
atio
n
an
d
k
n
o
wled
g
e
[
2
5
]
.
W
eb
wr
ap
p
er
is
a
p
r
o
ce
d
u
r
e
w
h
ich
is
im
p
lem
en
ted
b
ased
o
n
a
n
y
o
f
th
e
s
p
ec
if
ied
alg
o
r
ith
m
s
.
T
h
e
g
o
al
is
to
s
ee
k
an
d
f
in
d
d
ata
r
eq
u
ir
ed
b
y
h
u
m
an
u
s
er
s
f
r
o
m
th
e
web
s
o
u
r
ce
s
,
wh
ich
in
clu
d
es
u
n
s
tr
u
ctu
r
ed
o
r
s
em
i
-
s
tr
u
ctu
r
ed
d
ata.
T
h
e
ex
tr
ac
ted
d
ata
will
b
e
tr
an
s
f
o
r
m
ed
in
to
s
tr
u
ctu
r
e
d
r
ep
r
es
en
tatio
n
f
o
r
f
u
r
th
er
u
s
ag
e.
L
ately
,
th
e
p
r
o
b
lem
s
o
f
e
x
tr
ac
tin
g
in
f
o
r
m
atio
n
f
r
o
m
u
n
k
n
o
w
n
s
ites
,
f
o
c
u
s
in
g
o
n
u
n
s
tr
u
ctu
r
e
d
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
WEI
DJ:
Dev
elo
p
men
t o
f a
n
e
w
a
lg
o
r
ith
m
fo
r
s
emi
-
s
t
r
u
ctu
r
ed
w
eb
d
a
ta
.
.
.
(
I
ly
A
m
a
lin
a
A
h
ma
d
S
a
b
r
i
)
321
s
em
i
-
s
tr
u
ctu
r
ed
d
ata
a
r
e
g
ettin
g
m
u
ch
atten
tio
n
f
r
o
m
th
e
r
es
ea
r
ch
er
s
.
T
h
e
wo
r
k
s
o
n
W
DE
h
as
lo
ts
o
f
r
ev
iews.
T
h
is
s
ec
tio
n
d
is
cu
s
s
es
ab
o
u
t o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
,
W
E
I
DJ.
W
E
I
DJ
i
s
d
ev
elo
p
ed
to
ass
is
t
u
s
er
in
ex
tr
ac
tin
g
s
em
i
-
s
tr
u
ctu
r
ed
d
ata
f
r
o
m
web
p
a
g
e.
A
web
p
ag
e
ca
n
b
e
r
ep
r
esen
te
d
b
y
a
tr
ee
s
tr
u
ctu
r
e
DOM
.
I
t
co
n
v
er
ts
an
d
s
to
r
e
a
g
iv
en
web
a
d
d
r
ess
o
f
web
p
ag
e
f
r
o
m
a
s
ea
r
ch
en
g
in
e
in
t
o
a
DOM
tr
e
e
[
2
6
]
.
R
ec
en
tly
,
th
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
is
f
o
cu
s
ed
o
n
im
ag
e
[
2
7
,
2
8
]
.
W
h
en
u
s
er
in
p
u
t
th
e
u
n
i
f
o
r
m
r
eso
u
r
ce
lo
ca
to
r
(
UR
L
)
an
d
th
e
q
u
er
y
is
s
u
b
m
itted
to
a
s
ea
r
ch
en
g
in
e
,
th
e
s
ea
r
ch
en
g
in
e
will
d
y
n
am
ically
g
e
n
er
ated
r
e
s
u
lt
p
ag
e
co
n
tain
in
g
t
h
e
r
esu
lt
r
ec
o
r
d
s
.
T
h
e
r
esu
lts
co
n
s
is
t
a
lin
k
p
at
h
f
o
r
ea
ch
elem
en
t
o
f
im
ag
e,
im
a
g
e,
s
iz
e
o
f
im
a
g
e
an
d
tim
e
p
r
o
ce
s
s
in
g
to
lo
a
d
ea
ch
im
ag
e
[
2
9
]
.
W
E
I
DJ
u
s
ed
alp
h
a
jet
ex
p
er
im
en
t
(
AJAX
)
tech
n
o
l
o
g
y
to
ex
tr
ac
t
d
ata
f
r
o
m
web
s
o
u
r
ce
s
.
AJAX,
i
s
th
e
ab
b
r
ev
iatio
n
o
f
Asy
n
ch
r
o
n
o
u
s
J
av
aScr
ip
t
an
d
XM
L
,
is
a
s
et
o
f
web
d
e
v
elo
p
m
en
t
tech
n
i
q
u
es
th
at
allo
ws
a
w
eb
p
ag
e
to
u
p
d
ate
p
o
r
tio
n
s
o
f
co
n
ten
ts
with
o
u
t
h
av
in
g
to
r
ef
r
esh
th
e
p
a
g
e.
AJAX
r
ep
r
esen
ts
a
s
im
il
ar
co
n
ce
p
t
to
th
e
clien
t
-
s
er
v
er
d
e
v
elo
p
m
e
n
t.
Du
r
in
g
clien
t
-
s
er
v
er
p
h
ase,
th
e
a
m
o
u
n
t
o
f
d
ata
tr
a
n
s
f
er
r
ed
is
v
er
y
m
in
im
al
o
v
e
r
a
ter
m
in
al
ap
p
licatio
n
b
y
tr
an
s
f
er
r
in
g
o
n
ly
th
e
n
ec
ess
ar
y
d
ata
b
ac
k
an
d
f
o
r
th
.
Similar
ly
,
wi
th
AJAX,
o
n
ly
th
e
n
ec
ess
ar
y
d
ata
is
tr
an
s
f
er
r
ed
b
ac
k
an
d
f
o
r
t
h
b
etwe
en
th
e
clien
t
an
d
th
e
web
s
er
v
er
.
T
h
is
m
in
im
izes
th
e
n
etwo
r
k
u
tili
za
tio
n
a
n
d
p
r
o
ce
s
s
in
g
o
n
th
e
clien
t.
T
h
e
tim
e
f
o
r
ex
tr
ac
tio
n
p
r
o
ce
s
s
h
as
b
ee
n
r
ed
u
ce
d
.
Fig
u
r
e
6
s
h
o
ws an
o
v
er
v
iew
o
f
W
E
I
DJ u
s
in
g
AJAX a
n
d
J
SON
d
ata.
Fig
u
r
e
6.
Ov
e
r
v
iew
o
f
W
E
I
DJ m
o
d
el
I
t
ca
n
b
e
d
if
f
i
c
u
lt
to
p
r
o
p
e
r
l
y
cr
ea
t
e
ex
tr
ac
t
io
n
r
u
l
es
d
es
cr
i
b
i
n
g
r
e
q
u
i
r
e
d
d
a
ta
.
I
n
t
h
is
p
ap
er
,
we
p
r
o
p
o
s
e
W
E
I
DJ
[
3
0
]
m
o
d
el
t
o
ex
tr
ac
t
im
a
g
es
f
r
o
m
a
w
e
b
p
a
g
e
.
T
h
e
wo
r
k
d
es
cr
ib
ed
i
n
th
is
s
ec
ti
o
n
u
s
es
a
co
m
b
i
n
ati
o
n
o
f
b
o
t
h
tech
n
iq
u
es
,
DOM
a
n
d
J
SON
[
3
1
]
.
I
n
ad
d
it
io
n
,
w
e
als
o
d
o
t
h
e
c
h
e
c
k
i
n
g
o
f
i
m
a
g
es
b
y
b
l
o
c
k
s
i
n
t
h
e
H
T
M
L
d
o
cu
m
e
n
ts
.
I
t
als
o
f
o
cu
s
s
es
o
n
ar
r
a
n
g
in
g
t
h
e
ex
tr
ac
t
ed
d
ata
in
a
ta
b
u
la
r
f
o
r
m
at
.
L
o
ts
o
f
ap
p
li
ca
ti
o
n
s
f
o
c
u
s
es
o
n
e
x
t
r
ac
t
in
g
i
n
f
o
r
m
ati
o
n
a
n
d
t
h
e
n
h
a
v
e
it a
r
r
a
n
g
e
d
ac
co
r
d
in
g
ly
[
3
2
,
3
3
]
.
E
v
er
y
we
b
p
a
g
e
h
as
t
h
e
ir
o
w
n
s
tr
u
c
tu
r
e
i
n
cl
u
d
es
m
ai
n
t
o
p
ic
,
r
e
lat
ed
t
o
p
i
c
s
,
ad
d
i
ti
o
n
al
i
n
f
o
r
m
ati
o
n
,
ad
v
er
t
is
e
m
e
n
t
,
c
o
n
tac
t
in
f
o
r
m
at
io
n
,
im
ag
es,
a
u
d
i
o
a
n
d
v
i
d
eo
f
il
e.
T
h
e
p
r
o
b
l
em
t
h
a
t
we
wa
n
t
t
o
s
o
l
v
e
is
w
h
a
t
is
t
h
e
b
est
te
c
h
n
iq
u
e
ca
n
b
e
ap
p
l
ie
d
i
n
o
r
d
er
to
e
x
t
r
ac
t
i
m
a
g
es
au
to
m
a
tic
all
y
[
3
4
,
3
5
]
.
Min
in
g
i
n
f
o
r
m
a
ti
o
n
r
e
c
o
r
d
s
i
n
d
a
ta
r
e
g
i
o
n
s
p
la
y
s
im
p
o
r
t
an
t
r
o
le
i
n
d
ef
in
in
g
ta
g
s
o
f
s
e
m
i
-
s
t
r
u
c
t
u
r
e
d
d
at
a.
I
t
is
ea
s
y
t
o
ex
tr
ac
t
d
at
a
f
r
o
m
d
at
a
r
eg
io
n
s
b
ec
a
u
s
e
it
co
n
t
ai
n
s
u
s
e
f
u
l
d
ata
.
I
t
is
r
e
c
o
g
n
iz
ed
as
d
at
a
a
r
e
a
.
A
te
ch
n
iq
u
e
is
r
e
q
u
is
i
te
i
n
o
r
d
er
t
o
m
i
n
e
d
at
a
ar
ea
.
I
n
t
h
e
ea
r
lie
r
s
ta
g
e,
t
h
is
m
o
d
el
p
r
o
p
o
s
ed
DO
M
t
r
e
e
as
b
ase
d
tec
h
n
i
q
u
e
t
o
m
i
n
e
d
at
a
r
e
g
i
o
n
s
in
w
e
b
p
ag
e.
4
.
1
.
WE
I
DJ
a
lg
o
rit
hm
T
h
e
in
d
u
s
tr
ial
o
f
b
i
g
d
ata
c
o
m
p
letes
th
e
in
d
e
x
f
u
n
ctio
n
o
f
b
ig
v
o
lu
m
es
o
f
d
ata
es
p
ec
ially
in
ex
tr
ac
tin
g
im
ag
e
as
th
e
d
ata
o
f
p
r
e
f
er
en
ce
.
T
h
er
e
ar
e
m
a
n
y
o
th
er
r
esear
ch
er
s
wh
o
wo
r
k
o
n
d
ata
ex
tr
ac
tio
n
f
r
o
m
d
if
f
er
e
n
t
s
ites
in
o
r
d
er
t
o
test
th
e
p
e
r
f
o
r
m
an
ce
s
o
f
ex
t
r
ac
tio
n
.
I
n
th
is
r
esear
c
h
wo
r
k
,
we
r
etr
iev
e
im
ag
es
an
d
th
eir
in
f
o
r
m
atio
n
f
r
o
m
web
s
o
u
r
ce
s
to
b
e
an
al
y
s
ed
f
o
r
f
u
r
th
er
u
s
ag
e.
A
m
ed
iato
r
to
o
l
ca
ll
W
E
I
DJ
ap
p
r
o
ac
h
h
as
b
ee
n
p
r
o
p
o
s
ed
.
T
h
is
to
o
l
aim
s
to
ex
tr
ac
t
im
ag
es
ac
co
r
d
in
g
to
u
n
if
o
r
m
r
es
o
u
r
ce
lo
ca
to
r
UR
L
.
T
h
e
im
ag
e’
s
d
etails
will
b
e
m
in
ed
an
d
p
r
esen
ted
in
a
s
tr
u
ctu
r
ed
f
o
r
m
at
b
ef
o
r
e
s
to
r
in
g
th
e
m
in
to
m
u
ltime
d
ia
d
atab
ase.
I
n
th
is
r
esear
ch
,
we
p
r
o
p
o
s
e
a
m
e
d
iato
r
t
o
o
l
ca
ll
W
E
I
DJ
ap
p
r
o
ac
h
.
T
h
is
to
o
l
ai
m
s
to
ex
tr
ac
t
im
ag
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
3
1
7
-
32
6
322
ac
co
r
d
in
g
to
u
n
if
o
r
m
r
eso
u
r
ce
lo
ca
to
r
UR
L
an
d
m
in
e
im
a
g
e
d
etails
th
en
p
r
esen
t
im
a
g
es
in
s
tr
u
ctu
r
ed
f
o
r
m
at
b
ef
o
r
e
s
to
r
i
n
g
th
em
in
to
m
u
ltime
d
ia
d
atab
ase.
I
n
W
DE
,
a
web
-
b
ased
m
et
h
o
d
b
ased
o
n
DOM
is
ap
p
lie
d
.
DOM
p
r
o
v
id
es
a
s
tr
u
ctu
r
ed
way
to
d
escr
ib
e
d
o
cu
m
e
n
ts
.
T
h
e
HT
ML
d
o
c
u
m
en
ts
will
b
e
c
o
n
v
er
ted
in
to
DOM
tr
ee
s
tr
u
ctu
r
e.
E
ac
h
elem
en
t
in
th
e
tr
ee
s
tr
u
ctu
r
e
is
k
n
o
wn
as
n
o
d
e.
T
h
e
m
ain
task
o
f
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
in
web
d
ata
ex
t
r
a
ctio
n
in
clu
d
es
p
r
e
-
b
u
ilt
th
e
DOM
tr
ee
o
f
th
e
we
b
p
ag
e.
T
h
is
wr
ap
p
e
r
will
an
a
ly
s
e
th
e
s
p
ec
if
ic
tar
g
ets
in
th
e
s
o
u
r
ce
s
o
f
I
n
t
er
n
et
wo
r
ld
,
web
s
ites
.
First,
it
o
b
tain
s
th
e
r
elativ
e
o
f
UR
L
f
r
o
m
a
web
s
ite.
E
ac
h
UR
L
m
ay
co
n
tain
s
a
f
ew,
h
u
n
d
r
ed
s
o
r
th
o
u
s
an
d
im
ag
es.
I
n
f
o
r
m
atio
n
will
b
e
ex
tr
ac
ted
f
r
o
m
f
r
o
m
d
if
f
er
e
n
t
lev
els
o
f
web
p
ag
es
s
u
c
h
as
s
in
g
le
web
,
d
if
f
er
en
t
s
o
u
r
ce
s
o
f
web
p
ag
es
an
d
d
ee
p
web
.
T
h
e
ex
tr
ac
tio
n
o
f
in
f
o
r
m
atio
n
n
ee
d
to
d
ea
l
with
p
ag
e
r
ef
in
em
e
n
t to
clea
n
an
d
e
x
tr
ac
t u
s
ef
u
l in
f
o
r
m
atio
n
s
u
ch
as im
ag
es,
p
ath
o
f
im
ag
es,
s
iz
e
o
f
im
ag
es a
n
d
s
o
f
o
r
th
in
th
e
r
u
le
of
ex
tr
ac
tio
n
.
T
h
is
wr
ap
p
er
is
p
r
o
p
o
s
ed
to
ex
tr
ac
t
im
a
g
es
f
r
o
m
web
.
I
n
th
is
way
,
th
e
p
r
o
ce
s
s
in
g
o
f
im
a
g
es
will
b
e
co
n
v
er
te
d
in
to
a
f
o
r
m
o
f
co
m
p
u
ter
p
r
o
ce
s
s
in
g
;
wh
ich
is
r
ep
r
esen
ted
b
y
th
e
ex
tr
ac
tio
n
o
f
d
ata
in
tab
u
lar
f
o
r
m
at.
T
h
is
r
ep
r
esen
tatio
n
is
im
p
o
r
tan
t
in
o
r
d
e
r
f
o
r
p
r
o
v
id
in
g
r
esear
ch
an
aly
s
is
o
f
d
ata
ex
t
r
ac
tio
n
.
Fi
g
u
r
e
7
d
e
s
cr
ib
es th
e
wh
o
le
p
r
o
ce
s
s
o
f
th
e
r
ea
lizatio
n
o
f
W
DE
.
F
i
g
u
r
e
7
.
T
h
e
p
r
o
c
e
s
s
o
f
t
h
e
i
m
a
g
e
’
s
e
x
t
r
a
ct
i
o
n
5.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
I
n
th
is
r
esear
ch
wo
r
k
,
web
d
at
a
ex
tr
ac
tio
n
ex
p
e
r
im
en
ts
h
ad
b
ee
n
s
et
u
p
to
co
m
p
ar
e
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
W
E
I
DJ
with
ex
is
tin
g
m
eth
o
d
.
T
h
e
s
o
f
twar
e
c
o
n
f
ig
u
r
atio
n
th
at
h
as
b
ee
n
u
s
ed
in
th
is
e
x
p
er
im
en
tatio
n
ca
n
b
e
r
ef
er
r
ed
in
t
h
e
p
r
e
v
io
u
s
wo
r
k
[
3
5
]
.
T
h
e
f
in
d
in
g
s
o
f
ex
p
e
r
i
m
en
ts
tab
u
lated
in
Fig
u
r
e
8
s
h
o
ws
th
at
wh
en
th
e
am
o
u
n
t
o
f
ex
tr
ac
ted
im
a
g
es
in
cr
ea
s
e,
th
e
tim
e
o
f
th
e
two
r
etr
iev
al
m
eth
o
d
s
;
DOM
an
d
W
HDJ
ar
e
in
cr
ea
s
ed
b
u
t
th
e
tim
e
o
f
W
E
I
DJ
o
n
im
ag
es
ex
tr
ac
tio
n
is
s
ig
n
if
ican
tly
lo
wer
th
an
o
th
e
r
ap
p
r
o
a
ch
es.
Fiv
e
d
if
f
er
en
t
web
s
ites
f
r
o
m
b
io
d
iv
er
s
ity
f
ie
ld
h
as
b
ee
n
s
elec
ted
t
o
test
th
e
p
er
f
o
r
m
an
ce
o
f
web
d
ata
e
x
tr
ac
tio
n
as
s
h
o
wn
in
T
ab
le
2
.
E
ac
h
web
s
ite
h
as
d
if
f
er
en
t
d
ata
v
o
lu
m
e
a
n
d
d
if
f
er
en
t
d
ata
s
ize.
Fo
r
a
we
b
d
ata
ex
tr
ac
tio
n
ex
p
er
im
en
t,
d
if
f
er
e
n
t d
ata
v
o
l
u
m
e
an
d
d
ata
s
ize
ar
e
b
ee
n
test
ed
b
y
f
o
u
r
d
if
f
er
e
n
t e
x
tr
ac
tio
n
m
eth
o
d
s.
T
h
is
p
ap
er
also
s
elec
t
s
th
e
w
eb
s
ite
o
f
Fan
g
J
ia
wh
ich
i
s
h
tt
p
://s
h
.
Fan
g
J
ia.
co
m
as
s
h
o
w
i
n
Fig
u
r
e
9
.
T
h
e
r
ea
s
o
n
wh
y
th
is
web
s
ite
is
s
elec
ted
a
s
a
g
u
id
elin
e
b
ec
au
s
e
th
er
e
is
a
d
is
cu
s
s
io
n
o
f
f
in
d
in
g
s
f
o
r
im
ag
e
ex
tr
ac
tio
n
th
at
h
as
b
ee
n
co
n
s
tr
u
cted
[
2
7
]
.
Fo
u
r
ty
p
ical
d
ata
ex
tr
ac
tio
n
alg
o
r
ith
m
VI
B
S,
MD
R
,
DE
PTA
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
WEI
DJ:
Dev
elo
p
men
t o
f a
n
e
w
a
lg
o
r
ith
m
fo
r
s
emi
-
s
t
r
u
ctu
r
ed
w
eb
d
a
ta
.
.
.
(
I
ly
A
m
a
lin
a
A
h
ma
d
S
a
b
r
i
)
323
VI
DE
wer
e
s
elec
ted
as
co
m
p
ar
in
g
tar
g
et.
T
h
e
ex
p
er
im
en
ts
wer
e
co
n
d
u
cted
o
n
th
e
p
r
o
to
ty
p
e
s
y
s
tem
o
f
th
e
ab
o
v
e
alg
o
r
ith
m
.
T
h
er
e
ar
e
t
wo
ty
p
es
o
f
p
er
f
o
r
m
a
n
ce
m
e
asu
r
em
en
t
th
at
h
av
e
b
ee
n
co
n
d
u
cted
d
u
r
in
g
th
is
ex
p
er
im
en
t.
T
h
e
f
ir
s
t m
ea
s
u
r
e
m
en
t is ex
ec
u
tio
n
tim
e
a
n
aly
s
is
an
d
s
ec
o
n
d
is
p
r
ec
is
io
n
,
r
ec
a
ll a
n
d
F
-
m
ea
s
u
r
e.
Fig
u
r
e
8.
Per
f
o
r
m
an
c
e
o
f
im
a
g
e
ex
tr
ac
tio
n
f
o
r
d
ee
p
web
T
ab
le
2
.
C
h
ar
ac
ter
is
tics
o
f
in
s
tan
t d
ataset
U
R
L
U
n
i
f
o
r
m
R
e
so
u
r
c
e
L
o
c
a
t
o
r
(
U
R
L)
D
o
ma
i
n
G
e
n
e
r
a
l
B
i
o
d
i
v
e
r
s
i
t
y
a
n
d
E
n
d
a
n
g
e
r
e
d
S
p
e
c
i
e
s
I
n
f
o
r
mat
i
o
n
1
h
t
t
p
:
/
/
w
w
w
.
a
m
n
h
.
o
r
g
/
A
meric
a
n
M
u
se
u
m
o
f
N
a
t
u
r
a
l
H
i
s
t
o
r
y
(
A
M
N
H
)
H
a
l
l
o
f
B
i
o
d
i
v
e
r
si
t
y
2
h
t
t
p
:
/
/
o
c
e
a
n
.
si
.
e
d
u
/
O
c
e
a
n
P
o
r
t
a
l
:
S
mi
t
h
s
o
n
i
a
n
I
n
st
i
t
u
t
i
o
n
3
h
t
t
p
:
/
/
w
w
w
.
i
u
c
n
.
o
r
g
/
I
n
t
e
r
n
a
t
i
o
n
a
l
U
n
i
o
n
f
o
r
C
o
n
ser
v
a
t
i
o
n
o
f
N
a
t
u
r
e
4
h
t
t
p
:
/
/
w
w
w
.
e
n
d
a
n
g
e
r
e
d
s
p
e
c
i
e
si
n
t
e
r
n
a
t
i
o
n
a
l
.
o
r
g
En
d
a
n
g
e
r
e
d
S
p
e
c
i
e
s
I
n
t
e
r
n
a
t
i
o
n
a
l
5
h
t
t
p
:
/
/
w
w
w
.
w
w
f
.
my
W
o
r
l
d
W
i
d
e
F
u
n
d
f
o
r
N
a
t
u
r
e
Fig
u
r
e
9.
Stru
ctu
r
ed
p
ag
es f
r
o
m
Fan
g
J
ia.
co
m
5
.
1
.
T
im
e
e
x
t
ra
c
t
io
n a
na
ly
s
is
I
n
th
is
ex
p
er
im
en
tal
wo
r
k
,
4
0
p
ag
es
f
r
o
m
th
e
s
am
e
web
s
ite
Fan
g
J
ia
(
h
ttp
s
://fa
n
g
jia.
f
an
g
.
co
m
/
b
j/)
ha
ve
b
ee
n
s
elec
ted
r
an
d
o
m
ly
.
T
h
en
,
t
h
e
ex
t
r
ac
tio
n
tim
e
will b
e
ca
lcu
lated
f
r
o
m
th
e
b
e
g
in
n
i
n
g
o
f
th
e
ex
tr
ac
te
d
p
ag
e
to
th
e
n
e
x
t
p
a
g
e.
Fig
u
r
e
1
0
s
h
o
w
s
th
e
s
am
p
le
o
u
tp
u
t f
o
r
e
x
tr
ac
tin
g
4
0
p
ag
es
b
y
co
r
r
e
s
p
o
n
d
in
g
p
a
g
e.
T
h
e
d
u
r
atio
n
o
f
th
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
is
s
h
o
wn
in
d
etails
in
T
ab
le
3
.
Fro
m
th
e
p
er
f
o
r
m
a
n
ce
an
aly
s
is
,
in
th
e
p
r
elim
in
ar
y
f
o
r
5
an
d
1
0
p
ag
es
VI
B
S
it
is
ex
ce
l
len
t
in
ex
t
r
ac
tin
g
im
ag
es
b
u
t
wh
en
th
e
HT
ML
d
o
cu
m
en
ts
b
ec
o
m
e
lar
g
e
r
,
we
f
o
u
n
d
th
at
W
E
I
DJ cle
ar
ly
o
u
tp
er
f
o
r
m
s
e
x
is
tin
g
to
o
ls
.
5
.
2
.
P
re
cisi
o
n,
re
ca
ll
a
nd
F
-
m
ea
s
ure
Acc
o
r
d
in
g
to
[
27
]
,
th
e
in
ter
f
er
en
ce
o
f
web
p
ag
e
n
o
is
e
to
d
ata
ex
tr
ac
tio
n
is
im
p
o
r
t
an
t
to
b
e
co
n
s
id
er
ed
b
esid
es
ef
f
icien
cy
an
d
ac
cu
r
ac
y
o
f
d
if
f
er
en
t
d
ee
p
web
p
ag
e
h
eter
o
g
en
eity
.
T
h
is
is
s
u
e
m
o
tiv
ates
u
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
3
1
7
-
32
6
324
to
im
p
r
o
v
is
e
ex
is
tin
g
alg
o
r
ith
m
o
n
n
o
is
y
in
f
o
r
m
atio
n
.
S
o
,
b
esid
es
f
o
cu
s
in
g
o
n
th
e
p
er
f
o
r
m
a
n
ce
o
f
tim
e
ex
tr
ac
tio
n
f
o
r
ex
tr
ac
tin
g
in
f
o
r
m
atio
n
,
we
also
wan
t
to
e
x
tr
ac
t
th
e
s
ig
n
if
ican
t
in
f
o
r
m
at
io
n
o
f
im
a
g
e
an
d
r
em
o
v
e
th
e
n
o
is
y
in
f
o
r
m
atio
n
.
T
ab
le
4
s
h
o
ws
th
e
r
esu
lt
o
f
th
e
ex
p
er
im
en
tal
e
v
alu
atio
n
f
o
r
W
E
I
DJ
u
s
in
g
Fan
g
J
ia
web
p
ag
e
as
test
ed
UR
L
.
Fig
u
r
e
1
1
s
h
o
ws
th
e
co
m
p
ar
is
o
n
o
f
t
h
e
f
iv
e
alg
o
r
ith
m
o
f
th
e
ex
p
er
im
en
ts
.
Ou
r
m
o
d
el,
W
E
I
DJ
h
as
p
r
o
v
e
n
th
at
its
ab
ilit
y
to
ex
tr
ac
t
d
ata
as
ac
cu
r
ate
as
VI
B
S.
T
h
is
ac
c
u
r
ac
y
in
e
x
tr
ac
tio
n
is
ac
h
iev
ed
b
ec
a
u
s
e
o
f
two
f
a
cto
r
s
th
at
we
in
clu
d
e
in
th
is
r
e
s
ea
r
ch
,
wh
ich
a
r
e
n
o
is
es
f
ilter
atio
n
an
d
th
e
u
s
e
o
f
J
SON
wh
ich
h
elp
s
to
tr
an
s
f
o
r
m
th
e
d
ata
f
aster
.
=
+
(
1
)
=
(
2
)
=
2
•
+
(
3
)
Fig
u
r
e
1
0.
E
x
tr
ac
tin
g
4
0
p
ag
e
s
T
ab
le
3
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
d
ata
e
x
tr
ac
tio
n
M
e
t
h
o
d
Ti
me
E
x
t
r
a
c
t
i
o
n
5
p
a
g
e
s
1
0
p
a
g
e
s
1
5
p
a
g
e
s
2
0
p
a
g
e
s
2
5
p
a
g
e
s
3
0
p
a
g
e
s
3
5
p
a
g
e
s
4
0
p
a
g
e
s
W
EI
D
J
1
2
.
6
9
7
2
1
8
.
6
3
9
2
2
.
1
8
2
9
.
1
4
6
8
2
9
.
5
0
7
9
3
5
.
2
6
5
1
3
7
.
9
7
7
4
8
.
8
4
9
8
V
I
B
S
7
.
2
5
1
2
.
7
2
3
.
7
4
30
3
5
.
0
1
4
4
.
3
7
4
9
.
7
6
6
2
.
6
9
M
D
R
1
9
.
2
9
4
0
.
1
1
6
1
.
1
8
8
3
.
7
8
1
0
1
.
0
7
1
2
2
.
6
3
1
4
8
.
3
3
1
6
4
.
1
6
D
EPTA
2
0
.
9
8
4
3
.
7
9
6
6
.
6
6
9
0
.
6
3
1
1
4
.
0
4
1
3
5
.
7
2
1
5
3
.
5
5
1
8
0
.
7
1
V
I
D
E
5
3
.
1
3
9
4
.
3
7
1
4
4
.
3
3
1
9
5
.
2
3
2
4
6
.
2
9
2
9
1
.
0
8
3
4
1
.
1
8
3
8
9
.
5
2
Fig
u
r
e
1
1
.
C
o
m
p
ar
is
o
n
p
er
f
o
r
m
an
ce
ex
is
tin
g
m
eth
o
d
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
WEI
DJ:
Dev
elo
p
men
t o
f a
n
e
w
a
lg
o
r
ith
m
fo
r
s
emi
-
s
t
r
u
ctu
r
ed
w
eb
d
a
ta
.
.
.
(
I
ly
A
m
a
lin
a
A
h
ma
d
S
a
b
r
i
)
325
T
ab
le
4.
R
esu
lt o
f
th
e
e
x
p
er
im
en
tal
ev
alu
atio
n
f
o
r
W
E
I
DJ
To
t
a
l
i
m
g
D
a
t
a
r
e
t
r
i
e
v
e
d
D
a
t
a
(
F
a
l
s
e
)
U
n
k
n
o
w
n
D
a
t
a
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
1
4
5
1
4
2
0
3
1
0
0
9
7
.
9
3
1
0
3
9
8
.
9
5
4
7
6.
CO
NCLU
SI
O
N
All
th
e
W
o
r
ld
W
id
e
W
eb
h
as
b
ec
o
m
e
a
v
ast
in
f
o
r
m
atio
n
s
to
r
e
th
at
is
g
r
o
win
g
at
a
r
ap
i
d
r
ate,
eith
er
in
n
u
m
b
er
o
f
s
ites
o
r
in
v
o
lu
m
e
o
f
u
s
ef
u
l
in
f
o
r
m
atio
n
.
W
DE
is
t
im
e
co
n
s
u
m
in
g
wh
en
th
e
h
tm
l
d
o
cu
m
en
ts
b
ec
o
m
es
lar
g
er
.
Sin
g
le
DOM
d
id
n
o
t
p
er
f
o
r
m
v
e
r
y
well
in
ex
tr
ac
tin
g
m
u
ltime
d
ia
d
ata
s
u
ch
as
im
ag
e
if
th
e
v
o
lu
m
e
o
f
d
ata
b
ec
o
m
e
i
n
cr
ea
s
ed
.
Ho
wev
er
,
wh
en
a
n
o
th
er
tech
n
iq
u
e
J
av
a
S
cr
ip
t
o
b
ject
n
o
tatio
n
is
im
p
lem
en
ted
in
e
n
h
an
ce
d
m
o
d
el
n
am
ely
as
wr
ap
p
er
h
y
b
r
id
DOM
an
d
J
SON
(
W
HD
J
)
,
th
e
tim
e
ex
ec
u
tio
n
in
ex
tr
ac
tin
g
im
ag
e
a
n
d
its
in
f
o
r
m
atio
n
h
as
b
ee
n
r
e
d
u
ce
d
t
o
5
0
%
g
r
ea
ter
th
an
DOM
tech
n
i
q
u
e.
E
v
e
n
th
e
tim
e
ex
ec
u
tio
n
h
as
im
p
r
o
v
ed
b
u
t
t
h
e
lim
itatio
n
o
f
th
is
m
o
d
el
i
s
th
e
r
ed
u
n
d
an
c
y
o
f
s
im
ilar
f
ilen
am
e
in
im
a
g
es
ex
tr
ac
tio
n
.
C
o
m
p
lem
en
tar
y
to
th
is
,
we
in
ten
d
to
co
m
b
in
e
b
o
th
ap
p
r
o
ac
h
es
an
d
ap
p
ly
v
is
u
al
s
eg
m
en
tatio
n
to
g
et
th
e
b
est
p
er
f
o
r
m
an
ce
an
d
ex
tr
ac
t
th
e
co
n
s
tr
u
ctiv
e
im
ag
es.
T
h
is
wr
ap
p
er
h
as
b
ee
n
d
ev
elo
p
e
d
b
ased
o
n
p
r
o
p
o
s
ed
m
o
d
el,
W
E
I
DJ.
T
h
e
f
in
d
in
g
s
r
esu
lt
o
f
tim
e
e
x
e
cu
ti
o
n
o
f
W
E
I
DJ
is
g
r
ea
ter
(
9
0
%)
th
an
ex
is
tin
g
to
o
ls
s
h
o
u
ld
b
e
in
ter
p
r
eted
b
ec
a
u
s
e
o
f
th
e
p
ag
e
lev
el
o
f
ex
tr
ac
ti
o
n
s
wh
ich
is
d
ee
p
web
,
u
s
ed
in
th
e
an
aly
s
is
o
f
ex
p
er
im
en
tatio
n
f
o
r
th
e
ex
ec
u
tio
n
tim
e.
I
n
th
is
s
tu
d
y
,
t
h
e
b
en
ch
m
ar
k
o
f
d
ataset
(
Fan
g
J
i
a)
an
d
b
io
d
iv
e
r
s
ity
web
s
ites
wer
e
h
eter
o
g
en
eo
u
s
with
r
esp
ec
t
to
im
ag
e,
p
ath
o
f
im
ag
es,
s
ize
o
f
im
ag
es
a
n
d
ex
ec
u
tio
n
tim
e.
B
esid
e
th
e
ex
ec
u
tio
n
tim
e
is
f
o
cu
s
ed
as
m
ain
g
u
id
elin
e,
th
e
ex
p
er
im
en
tatio
n
o
f
im
ag
es
ex
t
r
ac
tio
n
wo
u
ld
h
a
v
e
im
p
r
o
v
e
d
th
e
v
alid
it
y
o
f
s
ig
n
if
ican
t
in
f
o
r
m
atio
n
b
y
r
em
o
v
in
g
n
o
is
y
in
f
o
r
m
atio
n
o
f
im
ag
es.
I
n
f
u
tu
r
e
s
tu
d
ies
,
it
is
r
ec
o
m
m
en
d
ed
th
at
th
e
s
e
lectio
n
o
f
d
ataset
in
v
o
lv
es
v
a
r
iety
o
f
f
ield
s
wh
ic
h
in
clu
d
es
s
o
cial
n
etwo
r
k
s
o
r
o
th
er
p
latf
o
r
m
.
T
h
is
is
b
ec
au
s
e
th
e
s
tr
u
ctu
r
e
o
f
web
s
ite
h
av
e
b
ee
n
d
e
v
elo
p
e
d
in
d
if
f
er
en
t te
ch
n
o
lo
g
ies.
ACK
NO
WL
E
DG
E
M
E
NT
S
I
s
in
ce
r
ely
th
an
k
all
th
o
s
e
w
h
o
h
elp
e
d
m
e
in
co
m
p
letin
g
th
is
task
esp
ec
ially
B
ia
s
is
wa
Un
iv
er
s
iti
Ma
lay
s
ia
T
er
en
g
g
an
u
(
B
UM
T
)
.
RE
F
E
R
E
NC
E
S
[
1
]
R.
S
u
re
sh
,
e
t
a
l
.
,
“
Da
ta
m
in
in
g
a
n
d
tex
t
m
in
i
n
g
-
A
S
u
r
v
e
y
,
”
2
0
1
7
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
mp
u
ta
ti
o
n
o
f
Po
we
r,
En
e
rg
y
I
n
f
o
rm
a
ti
o
n
a
n
d
Co
mm
u
n
ica
ti
o
n
.
2
0
1
7
,
p
p
.
4
1
2
-
4
1
9
,
M
a
rc
h
2
0
1
7
.
[
2
]
A.
Ap
a
o
laz
a
,
M
.
Vig
o
,
“
As
siste
d
P
a
tt
e
rn
M
i
n
in
g
fo
r
Disc
o
v
e
rin
g
I
n
tera
c
ti
v
e
Be
h
a
v
io
u
rs o
n
Th
e
We
b
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Hu
ma
n
-
Co
m
p
u
ter
S
tu
d
ies
,
v
o
l.
1
3
0
,
p
p
.
1
9
6
-
2
0
8
,
Oc
to
b
e
r
2
0
1
9
.
[
3
]
Q.
Zh
a
n
g
,
e
t
a
l
.
,
“
A
su
rv
e
y
o
n
d
e
e
p
lea
rn
in
g
fo
r
b
i
g
d
a
ta
,
”
In
f
o
rm
a
ti
o
n
Fu
si
o
n
,
v
o
l.
4
2
,
p
p
.
1
4
6
-
1
5
7
,
Ju
ly
2
0
1
8
.
[
4
]
C.
S
.
S
a
ra
v
a
n
a
Ku
m
a
r
a
n
d
R.
S
a
n
th
o
s
h
,
“
Eff
e
c
ti
v
e
in
f
o
rm
a
ti
o
n
re
tri
e
v
a
l
a
n
d
fe
a
tu
re
m
in
imiz
a
ti
o
n
tec
h
n
i
q
u
e
fo
r
se
m
a
n
ti
c
we
b
d
a
ta
,”
Co
mp
u
ter
s &
El
e
c
trica
l
En
g
in
e
e
rin
g
,
v
o
l
.
8
1
,
Ja
n
u
a
ry
2
0
2
0
.
[
5
]
V.
Ka
y
se
r
a
n
d
E.
S
h
a
la,
“
S
c
e
n
a
ri
o
d
e
v
e
l
o
p
m
e
n
t
u
sin
g
we
b
m
i
n
in
g
fo
r
o
u
tl
i
n
i
n
g
tec
h
n
o
l
o
g
y
f
u
tu
re
s
,”
T
e
c
h
n
o
l
o
g
ic
a
l
Fo
re
c
a
stin
g
a
n
d
S
o
c
ia
l
C
h
a
n
g
e
,
v
o
l.
1
5
6
,
Ju
l
y
2
0
2
0
.
[
6
]
K.
Wi
ll
iam
s,
e
t
a
l
.
,
“
S
c
h
o
larly
b
i
g
d
a
ta
i
n
fo
rm
a
ti
o
n
e
x
trac
ti
o
n
a
n
d
in
teg
ra
ti
o
n
in
t
h
e
c
it
e
se
e
r
χ
d
ig
i
t
a
l
li
b
ra
r
y
,
”
D
a
ta
En
g
i
n
e
e
rin
g
W
o
rk
sh
o
p
s (ICDEW
),
M
a
rc
h
2
0
1
4
.
[
7
]
M
.
S
.
P
e
ra
,
e
t
a
l
.
,
“
Web
-
b
a
se
d
c
l
o
se
d
-
d
o
m
a
in
d
a
ta
e
x
trac
ti
o
n
o
n
o
n
li
n
e
a
d
v
e
rti
se
m
e
n
ts
,”
In
fo
rm
a
ti
o
n
S
y
ste
ms
,
v
o
l.
3
8
,
n
o
.
2
,
p
p
.
1
8
3
-
1
9
7
,
Ap
ri
l
2
0
1
3
.
[
8
]
De
wa
e
lh
e
y
n
s,
V.,
I.
Lo
ris,
a
n
d
T.
S
tee
n
b
e
r
g
h
e
n
,
“
Web
d
a
ta
e
x
t
ra
c
ti
o
n
sy
ste
m
s
v
e
rsu
s
re
se
a
rc
h
c
o
ll
a
b
o
ra
ti
o
n
in
su
sta
in
a
b
le p
lan
n
i
n
g
fo
r
h
o
u
sin
g
:
sm
a
rt
g
o
v
e
rn
a
n
c
e
tak
e
s it
a
ll
,”
R
E
AL
CORP
2
0
1
6
Pro
c
e
e
d
in
g
,
2
0
1
6
.
[
9
]
N.
V.
Ka
m
a
n
wa
r,
S
.
Ka
,
“
We
b
d
a
ta
e
x
trac
ti
o
n
tec
h
n
i
q
u
e
s
:
A
Re
v
iew
,
”
Fu
tu
ristic
T
re
n
d
s
in
Res
e
a
rc
h
a
n
d
In
n
o
v
a
ti
o
n
f
o
r S
o
c
ia
l
W
e
lf
a
re
(S
t
a
rtu
p
Co
n
c
la
v
e
),
M
a
rc
h
2
0
1
6
.
[
1
0
]
Lae
n
d
e
r,
A.
H
.
,
e
t
a
l
.,
“
A
b
rief
su
rv
e
y
o
f
we
b
d
a
ta
e
x
trac
ti
o
n
to
o
ls
.
ACM
si
g
m
o
d
re
c
o
rd
,
”
DBL
P
,
v
o
l.
3
1
,
n
o
.
2
,
p
p
.
8
4
-
9
3
,
Ju
n
e
2
0
0
2
.
[
1
1
]
F
a
n
g
,
Y.
X.,
e
t
a
l
.,
“
S
TE
M
:
A
su
ffix
tree
-
b
a
se
d
m
e
th
o
d
f
o
r
we
b
d
a
ta
re
c
o
rd
s
e
x
trac
ti
o
n
,”
Kn
o
wled
g
e
a
n
d
In
fo
rm
a
t
io
n
S
y
ste
ms
,
v
o
l.
5
5
,
n
o
.
1
0
,
p
p
.
1
-
2
7
,
M
a
y
2
0
1
7
.
[
1
2
]
A.
P
o
u
ra
m
in
i
,
e
t
a
l.
,
“
Da
ta
e
x
trac
ti
o
n
u
si
n
g
c
o
n
ten
t
-
b
a
se
d
h
a
n
d
les
,”
J
o
u
rn
a
l
o
f
AI
a
n
d
Da
t
a
M
in
in
g
,
Ja
n
u
a
ry
2
0
1
8
.
[
1
3
]
P.
Jim
é
n
e
z
a
n
d
R
.
C
o
rc
h
u
e
lo
,
“
On
lea
rn
i
n
g
we
b
in
f
o
rm
a
ti
o
n
e
x
t
ra
c
ti
o
n
r
u
les
wit
h
TANG
O
,”
In
fo
rm
a
ti
o
n
S
y
ste
ms
,
v
o
l.
6
2
,
p
p
.
7
4
-
1
0
3
,
De
c
e
m
b
e
r
2
0
1
6
.
[
1
4
]
M.
Ch
it
ra
,
B.
Ay
s
h
a
Ba
n
u
,
“
De
e
p
we
b
d
a
ta
e
x
trac
ti
o
n
b
a
se
d
o
n
u
r
l
a
n
d
d
o
m
a
in
c
las
sifica
ti
o
n
,”
IS
A
ACA
J
OU
RNA
L
,
p
p
.
1
-
4
,
Ju
l
y
2
0
1
5
.
[
1
5
]
A.
K.
Tri
p
a
th
y
,
e
t
a
l
.
, “
Ve
d
d
-
A
v
i
su
a
l
wra
p
p
e
r
fo
r
e
x
trac
ti
o
n
o
f
d
a
t
a
u
sin
g
DO
M
tree
,”
Co
mm
u
n
ica
t
i
o
n
,
I
n
fo
rm
a
ti
o
n
&
Co
mp
u
t
in
g
T
e
c
h
n
o
l
o
g
y
(ICCIC
T
),
Oc
to
b
e
r
2
0
1
2
.
[
1
6
]
N.
De
ro
u
ich
e
,
e
t
a
l
.
,
“
Au
t
o
m
a
ti
c
e
x
trac
ti
o
n
o
f
stru
c
t
u
re
d
we
b
d
a
ta
wit
h
d
o
m
a
in
k
n
o
wle
d
g
e
,”
IEE
E
2
8
th
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
D
a
ta
En
g
in
e
e
rin
g
,
Ap
ri
l
2
0
1
2
.
[
1
7
]
L.
Li
u
,
e
t
a
l
.
,
“
XWRAP:
A
n
XML
-
e
n
a
b
led
wra
p
p
e
r
c
o
n
str
u
c
t
io
n
s
y
ste
m
fo
r
we
b
i
n
fo
rm
a
ti
o
n
so
u
rc
e
s
,”
Da
ta
En
g
i
n
e
e
rin
g
,
2
0
0
0
.
Pr
o
c
e
e
d
in
g
s
.
1
6
t
h
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
.
2
0
0
0
,
F
e
b
r
u
a
ry
2
0
0
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
3
1
7
-
32
6
326
[
1
8
]
C.
H.
Ch
a
n
g
a
n
d
S
.
C.
K
u
o
,
“
OLERA:
se
m
isu
p
e
rv
ise
d
we
b
-
d
a
ta
e
x
trac
ti
o
n
wit
h
v
isu
a
l
su
p
p
o
rt
,”
IEE
E
In
tell
ig
e
n
t
S
y
ste
ms
,
v
o
l.
1
9
,
n
o
.
6
,
p
p
.
5
6
-
6
4
,
De
c
e
m
b
e
r
2
0
0
4
.
[
1
9
]
B.
Li
u
,
e
t
a
l
.
,
“
M
i
n
in
g
d
a
ta
r
e
c
o
rd
s
in
we
b
p
a
g
e
s
,”
Pro
c
e
e
d
in
g
s
o
f
th
e
n
i
n
t
h
ACM
S
IGKD
D
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Kn
o
wled
g
e
Disc
o
v
e
ry
a
n
d
D
a
ta
M
i
n
in
g
,
2
0
0
3
.
[
2
0
]
D.
Ca
i,
e
t
a
l
.,
“
VIPS
:
A Visio
n
-
B
a
se
d
P
a
g
e
S
e
g
m
e
n
tatio
n
Al
g
o
ri
th
m
,”
M
icr
o
so
ft
tec
h
n
ica
l
re
p
o
rt
,
2
0
0
3
.
[
2
1
]
V.
Cre
sc
e
n
z
i,
e
t
a
l
.,
“
Ro
a
d
r
u
n
n
e
r:
to
wa
rd
s a
u
t
o
m
a
ti
c
d
a
ta ex
trac
ti
o
n
fro
m
lar
g
e
we
b
sites
,”
VL
DB
,
S
e
p
tem
b
e
r
2
0
0
1
.
[
2
2
]
Ch
a
n
g
,
C
.
-
H.
a
n
d
S
.
-
C.
Lu
i
,
“
IE
P
AD
:
in
fo
rm
a
ti
o
n
e
x
trac
ti
o
n
b
a
s
e
d
o
n
p
a
t
tern
d
isc
o
v
e
ry
,”
Pro
c
e
e
d
in
g
s
o
f
t
h
e
1
0
t
h
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
W
o
rl
d
W
id
e
W
e
b
,
Ja
n
u
a
ry
2
0
0
1
.
[
2
3
]
C.
N.
Hs
u
,
M
.
T.
Du
n
g
,
“
G
e
n
e
ra
ti
n
g
f
in
it
e
-
sta
te
tran
s
d
u
c
e
rs
fo
r
se
m
i
-
stru
c
tu
re
d
d
a
ta
e
x
trac
ti
o
n
fro
m
th
e
we
b
,
”
In
fo
rm
a
t
io
n
S
y
ste
ms
,
v
o
l.
8
,
n
o
.
8
,
p
p
.
5
2
1
-
5
3
8
,
De
c
e
m
b
e
r
1
9
9
8
.
[
2
4
]
J.
Ha
m
m
e
r,
e
t
a
l
.,
“
Ex
trac
ti
n
g
se
m
istru
c
tu
re
d
i
n
fo
rm
a
ti
o
n
fr
o
m
th
e
we
b
,”
S
e
p
tem
b
e
r
2
0
0
2
.
[
2
5
]
A.
G
u
p
ta
,
An
a
n
d
S
h
a
n
k
a
r
S.
,
a
n
d
C
.
M
a
n
ju
n
a
th
,
“
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
o
n
d
a
ta
e
x
trac
ti
o
n
a
n
d
it
s
p
r
o
c
e
ss
e
s
,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
A
p
p
li
e
d
En
g
i
n
e
e
rin
g
Res
e
a
rc
h
,
v
o
l.
1
2
,
n
o
.
1
8
,
p
p
.
7
1
9
4
-
7
2
0
1
,
2
0
1
7
.
[
2
6
]
Ily
Am
a
li
n
a
A.
S
.
,
a
n
d
M
.
M
a
n
,
“
M
u
lt
ip
le
ty
p
e
s
o
f
se
m
i
-
stru
c
tu
re
d
d
a
ta
e
x
trac
ti
o
n
u
si
n
g
wra
p
p
e
r
f
o
r
e
x
trac
ti
o
n
o
f
i
m
a
g
e
u
s
i
n
g
D
O
M
(
W
E
I
D
)
,
”
R
e
g
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
c
i
e
n
c
e
,
T
e
c
h
n
o
l
o
g
y
a
n
d
S
o
c
i
a
l
S
c
i
e
n
c
e
s
(
R
C
S
T
S
S
2
0
1
6
)
,
2018.
[
2
7
]
J.
Li
u
,
e
t
a
l
.
,
“
De
e
p
we
b
d
a
ta
e
x
trac
ti
o
n
b
a
se
d
o
n
v
isu
a
l
i
n
fo
rm
a
t
io
n
p
r
o
c
e
ss
in
g
,”
J
o
u
rn
a
l
o
f
Amb
i
e
n
t
In
telli
g
e
n
c
e
a
n
d
Hu
ma
n
ize
d
C
o
mp
u
ti
n
g
,
Oc
t
o
b
e
r
2
0
1
7
.
[
2
8
]
A.
Bh
a
rd
wa
j
a
n
d
V.
M
a
n
g
a
t,
“
An
imp
ro
v
ise
d
a
l
g
o
rit
h
m
fo
r
re
lev
a
n
t
c
o
n
te
n
t
e
x
trac
ti
o
n
fro
m
we
b
p
a
g
e
s
,”
J
o
u
rn
a
l
o
f
Eme
rg
in
g
T
e
c
h
n
o
lo
g
ies
in
W
e
b
I
n
telli
g
e
n
c
e
,
v
o
l.
6
,
n
o
.
2
,
M
a
y
2
0
1
4
.
[
2
9
]
I
l
y
A
m
a
l
i
n
a
A
.
S
.
,
a
n
d
M
.
M
a
n
,
“
T
h
e
p
r
o
p
o
s
e
d
a
l
g
o
r
i
t
h
m
f
o
r
s
e
m
i
-
s
t
r
u
c
t
u
r
e
d
d
a
t
a
i
n
t
e
g
r
a
t
i
o
n
:
c
a
s
e
s
t
u
d
y
o
f
s
e
t
i
u
w
e
t
l
a
n
d
d
a
t
a
s
e
t
,
”
J
o
u
r
n
a
l
o
f
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
E
l
e
c
t
r
o
n
i
c
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
9
,
n
o
.
3
-
3
,
p
p
.
7
9
-
8
4
,
2
0
1
7
.
[
3
0
]
Ily
Am
a
li
n
a
A.
S
.
,
a
n
d
M
.
M
a
n
,
“
WE
IDJ
:
An
imp
ro
v
ise
d
a
lg
o
r
it
h
m
fo
r
ima
g
e
e
x
trac
ti
o
n
fro
m
we
b
p
a
g
e
s
,”
T
h
e
8
t
h
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
I
n
fo
r
ma
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
M
a
y
2
0
1
7
.
[
3
1
]
Ily
Am
a
li
n
a
A.
S
.
,
a
n
d
M
.
M
a
n
,
“
Im
p
ro
v
i
n
g
p
e
rfo
rm
a
n
c
e
o
f
DO
M
in
se
m
i
-
stru
c
tu
re
d
d
a
ta
e
x
trac
t
io
n
u
sin
g
WE
IDJ
m
o
d
e
l
,”
In
d
o
n
e
sia
n
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
C
o
mp
u
t
e
r S
c
ien
c
e
,
v
o
l
.
9
,
n
o
.
3
,
p
p
.
7
5
2
-
7
6
3
,
2
0
1
8
.
[
3
2
]
J.
Wan
g
a
n
d
F
.
H.
L
o
c
h
o
v
sk
y
,
“
Da
ta
e
x
trac
ti
o
n
a
n
d
lab
e
l
a
ss
ig
n
m
e
n
t
fo
r
we
b
d
a
tab
a
se
s
,”
Pro
c
e
e
d
in
g
s
o
f
t
h
e
1
2
t
h
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
W
o
rl
d
W
id
e
W
e
b
,
Ja
n
u
a
ry
2
0
0
3
.
[
3
3
]
Y.
Zh
a
i
a
n
d
B
.
L
iu
,
“
Web
d
a
ta
e
x
trac
ti
o
n
b
a
se
d
o
n
p
a
rti
a
l
tree
a
li
g
n
m
e
n
t
,”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
1
4
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
W
o
rld
W
i
d
e
W
e
b
,
Ja
n
u
a
ry
2
0
0
5
.
[
3
4
]
I
l
y
A
m
a
l
i
n
a
A
.
S
.
,
a
n
d
M
.
M
a
n
,
“
T
h
e
p
r
o
p
o
s
e
d
a
l
g
o
r
i
t
h
m
f
o
r
s
e
m
i
-
s
t
r
u
c
t
u
r
e
d
d
a
t
a
i
n
t
e
g
r
a
t
i
o
n
:
c
a
s
e
s
t
u
d
y
o
f
s
e
t
i
u
w
e
t
l
a
n
d
d
a
t
a
s
e
t
,”
J
o
u
r
n
a
l
o
f
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
E
l
e
c
t
r
o
n
i
c
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
9
,
n
o
.
3
-
3
,
p
p
.
7
9
-
8
4
,
2
0
1
7
.
[
3
5
]
Ily
Am
a
li
n
a
A.
S
.
,
M
.
M
a
n
,
e
t
a
l
.,
“
Web
d
a
ta
e
x
trac
ti
o
n
a
p
p
ro
a
c
h
fo
r
d
e
e
p
we
b
u
si
n
g
WE
IDJ
,”
Pro
c
e
d
ia
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
1
6
3
,
p
p
.
4
1
7
-
4
2
6
,
2
0
1
9
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Ily
Am
a
l
in
a
Ah
m
a
d
S
a
b
r
i
wa
s
b
o
r
n
o
n
2
0
t
h
M
a
rc
h
1
9
8
5
i
n
Ku
a
l
a
Tere
n
g
g
a
n
u
,
Tere
n
g
g
a
n
u
.
He
r
p
rima
ry
e
d
u
c
a
ti
o
n
sta
rte
d
a
t
S
e
k
o
lah
Ke
b
a
n
g
sa
a
n
Ru
s
il
a
(1
9
9
2
-
1
9
9
7
)
a
n
d
sh
e
a
c
c
o
m
p
li
sh
e
d
h
e
r
h
i
g
h
sc
h
o
o
l
a
t
Ko
lej
S
a
in
s
P
e
n
d
i
d
ik
a
n
Isla
m
Ne
g
e
ri
Tere
n
g
g
a
n
u
(KO
S
P
INT)
in
2
0
0
3
.
S
h
e
re
c
e
iv
e
d
h
e
r
Dip
lo
m
a
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
fro
m
P
o
l
y
tec
h
n
ic
o
f
S
u
lt
a
n
M
iza
n
Zain
a
l
Ab
i
d
in
(
P
S
M
ZA).
Afte
r
t
h
a
t,
s
h
e
e
n
ro
l
led
t
o
Un
iv
e
rsiti
M
a
lay
sia
Tere
n
g
g
a
n
u
t
o
fu
r
th
e
r
h
e
r
d
e
g
re
e
stu
d
ies
in
S
o
f
twa
re
En
g
i
n
e
e
ri
n
g
,
w
h
ich
wa
s
o
b
tain
e
d
i
n
2
0
0
9
.
S
h
e
c
o
n
ti
n
u
e
d
h
e
r
m
a
ste
r
d
e
g
re
e
in
M
a
ste
r
o
f
S
c
ien
c
e
(C
o
m
p
u
ter
S
c
ie
n
c
e
)
in
t
h
e
sa
m
e
u
n
i
v
e
rsity
a
n
d
g
ra
d
u
a
ted
i
n
2
0
1
4
.
Du
r
in
g
m
a
ste
rs’s
d
e
g
re
e
,
h
e
r
re
se
a
rc
h
wa
s
in
De
c
isio
n
S
u
p
p
o
rt
S
y
ste
m
,
fo
c
u
si
n
g
o
n
F
u
z
z
y
AH
P
in
d
e
c
isio
n
m
a
k
i
n
g
fo
r
to
u
rism
d
e
sti
n
a
ti
o
n
.
N
o
w,
sh
e
h
a
s
c
o
m
p
lete
d
h
e
r
Do
c
to
r
o
f
P
h
il
o
so
p
h
y
(C
o
m
p
u
ter
S
c
ien
c
e
),
a
lso
in
Un
i
v
e
rsiti
M
a
lay
sia
Tere
n
g
g
a
n
u
.
He
r
c
u
rre
n
t
a
re
a
o
f
i
n
tere
st i
s Da
ta M
in
i
n
g
fo
c
u
si
n
g
o
n
Web
Da
ta E
x
trac
ti
o
n
.
Mu
sta
fa
Ma
n
is
a
n
As
so
c
iate
P
ro
fe
ss
o
r
in
S
c
h
o
o
l
o
f
I
n
fo
rm
a
ti
c
s
a
n
d
Ap
p
l
ied
M
a
th
e
m
a
ti
c
s
a
n
d
a
l
so
a
s
a
De
p
u
ty
Dire
c
to
r
a
t
Re
se
a
rc
h
M
a
n
a
g
e
m
e
n
t
In
n
o
v
a
ti
o
n
Ce
n
tre
(RM
IC),
UMT
.
He
sta
rted
h
is
P
h
D
stu
d
ies
i
n
J
u
ly
2
0
0
9
a
n
d
fi
n
ish
e
d
h
is
stu
d
ies
i
n
C
o
m
p
u
ter
S
c
ien
c
e
fr
o
m
UT
M
in
2
0
1
2
.
He
h
a
s
re
c
e
iv
e
d
Co
m
p
u
ter
S
c
ien
c
e
Dip
lo
m
a
,
C
o
m
p
u
t
e
r
S
c
ien
c
e
De
g
re
e
,
M
a
ste
r
D
e
g
re
e
fro
m
UPM
.
In
2
0
1
2
,
h
e
h
a
s
b
e
e
n
a
wa
rd
e
d
a
“
M
Ie
c
M
OS
P
re
stig
io
u
s
Aw
a
rd
s”
fo
r
h
is
P
h
D
b
y
M
IM
OS
Be
rh
a
d
.
His
re
se
a
rc
h
is
fo
c
u
se
d
o
n
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
m
u
l
ti
p
le
ty
p
e
s
o
f
d
a
tab
a
se
s
in
teg
ra
ti
o
n
m
o
d
e
l
a
n
d
a
lso
in
Au
g
m
e
n
ted
Re
a
li
t
y
(A
R),
a
n
d
ro
i
d
b
a
se
d
,
a
n
d
IT
re
late
d
in
t
o
a
c
ro
ss
d
o
m
a
in
p
latfo
r
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.