T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t
2020
,
p
p
.
1
8
7
4
~
1
8
8
3
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Ke
m
e
n
r
is
te
k
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DO
I
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
KA
.
v
1
8
i4
.
1
5
0
0
1
1874
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
Se
m
a
n
tics
-
ba
sed
clustering
appro
a
ch f
o
r si
m
ila
r
resea
rch area
de
t
ection
M
a
rio
n O
luw
a
bu
n
m
i A
debi
y
i
1
,
E
mm
a
nu
e
l B
.
Adig
un
2
,
Ro
s
eline
O
luw
a
s
eun O
g
un
d
o
k
u
n
3
,
Abid
e
m
i
E
mm
a
nu
el
A
deniy
i
4
,
P
ea
ce
Ay
eg
ba
5
,
O
lufun
k
e
O
.
O
la
dip
up
o
6
1,
3,
4,
5
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Co
ll
e
g
e
o
f
P
u
re
a
n
d
A
p
p
li
e
d
S
c
ien
c
e
s,
L
a
n
d
m
a
rk
Un
iv
e
r
sit
y
,
Nig
e
ria
1,
2,
6
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Co
v
e
n
a
n
t
U
n
iv
e
rsity
Ot
a
,
Nig
e
ria
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
6
,
2019
R
ev
i
s
ed
J
an
22
,
2
0
2
0
A
cc
ep
ted
Mar
18
,
2
0
2
0
T
h
e
m
a
n
u
a
l
p
ro
c
e
ss
o
f
se
a
rc
h
i
n
g
o
u
t
in
d
iv
id
u
a
ls
i
n
a
n
a
lrea
d
y
e
x
isti
n
g
re
se
a
rc
h
f
ield
is
c
u
m
b
e
rso
m
e
a
n
d
ti
m
e
-
c
o
n
su
m
in
g
.
P
ro
m
in
e
n
t
a
n
d
r
o
o
k
ie
re
se
a
rc
h
e
rs
a
li
k
e
a
re
p
re
d
isp
o
se
d
to
se
e
k
e
x
isti
n
g
re
s
e
a
rc
h
p
u
b
l
ica
ti
o
n
s
i
n
a
re
se
a
r
c
h
f
i
e
ld
o
f
in
tere
st
b
e
f
o
re
c
o
m
in
g
u
p
w
it
h
a
th
e
sis.
F
ro
m
e
x
tan
t
li
tera
tu
re
,
a
u
t
o
m
a
ted
si
m
il
a
r
re
se
a
rc
h
a
re
a
d
e
tec
ti
o
n
sy
st
e
m
s
h
a
v
e
b
e
e
n
d
e
v
e
lo
p
e
d
t
o
so
lv
e
t
h
is
p
ro
b
lem
.
Ho
w
e
v
e
r,
m
o
st
o
f
th
e
m
u
se
k
e
y
w
o
rd
-
m
a
tch
in
g
tec
h
n
iq
u
e
s,
w
h
ich
d
o
n
o
t
su
f
f
icie
n
tl
y
c
a
p
tu
re
th
e
im
p
li
c
it
se
m
a
n
ti
c
s
o
f
k
e
y
w
o
rd
s
th
e
re
b
y
lea
v
in
g
o
u
t
so
m
e
re
se
a
rc
h
a
rti
c
les
.
In
t
h
is
stu
d
y
,
we
p
ro
p
o
se
th
e
u
se
o
f
o
n
t
o
lo
g
y
-
b
a
s
e
d
p
re
-
p
ro
c
e
ss
in
g
,
L
a
ten
t
S
e
m
a
n
ti
c
In
d
e
x
in
g
a
n
d
K
-
M
e
a
n
s
Cl
u
ste
rin
g
to
d
e
v
e
lo
p
a
p
r
o
to
ty
p
e
sim
il
a
r
re
s
e
a
rc
h
a
re
a
d
e
tec
ti
o
n
sy
ste
m
,
th
a
t
c
a
n
b
e
u
se
d
to
d
e
term
in
e
sim
il
a
r
re
se
a
r
c
h
d
o
m
a
in
p
u
b
li
c
a
ti
o
n
s.
O
u
r
p
ro
p
o
se
d
sy
ste
m
so
lv
e
s
th
e
c
h
a
ll
e
n
g
e
o
f
h
ig
h
d
i
m
e
n
sio
n
a
li
ty
a
n
d
d
a
ta
sp
a
rsity
fa
c
e
d
b
y
th
e
trad
it
io
n
a
l
d
o
c
u
m
e
n
t
c
lu
ste
r
in
g
tec
h
n
iq
u
e
.
Ou
r
s
y
ste
m
is
e
v
a
lu
a
ted
w
it
h
ra
n
d
o
m
l
y
se
le
c
ted
p
u
b
li
c
a
ti
o
n
s
f
ro
m
f
a
c
u
lt
ies
in
Nig
e
rian
u
n
iv
e
rsiti
e
s
a
n
d
re
su
lt
s
sh
o
w
th
a
t
th
e
i
n
teg
ra
ti
o
n
o
f
o
n
t
o
lo
g
ies
in
p
re
p
ro
c
e
ss
in
g
p
r
o
v
id
e
s m
o
re
a
c
c
u
ra
te clu
ste
rin
g
re
su
lt
s.
K
ey
w
o
r
d
s
:
K
-
m
ea
n
s
clu
s
ter
i
n
g
L
ate
n
t se
m
a
n
tic
i
n
d
ex
i
n
g
Nig
er
ia
U
n
iv
er
s
it
y
On
to
lo
g
y
-
b
a
s
ed
p
r
ep
r
o
ce
s
s
in
g
Se
m
a
n
tic
s
-
b
ased
cl
u
s
ter
i
n
g
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
:
R
o
s
eli
n
e
Olu
w
ase
u
n
O
g
u
n
d
o
k
u
n
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
L
a
n
d
m
ar
k
U
n
i
v
er
s
it
y
,
K
w
ar
a
Sta
te,
Nig
er
ia.
+2
3
4
7
0
3
6
2
6
1
5
0
4
E
m
ail:
o
g
u
n
d
o
k
u
n
.
r
o
s
eli
n
e@
l
m
u
.
ed
u
.
n
g
1.
I
NT
RO
D
UCT
I
O
N
B
ac
k
g
r
o
u
n
d
o
f
s
t
u
d
y
Fo
r
th
e
p
u
r
p
o
s
e
o
f
r
esear
c
h
,
to
p
ics
an
d
r
elev
a
n
t
ar
ticle
s
f
r
o
m
d
ig
ital
lib
r
ar
ies
a
n
d
o
n
li
n
e
d
at
ab
ases
ar
e
s
o
u
g
h
t
f
o
r
in
o
r
d
er
to
g
ai
n
a
b
etter
u
n
d
er
s
ta
n
d
i
n
g
.
T
h
ese
s
o
u
r
ce
s
ar
e
u
s
e
f
u
l
i
n
th
e
r
etr
ie
v
al
o
f
r
elev
a
n
t
ar
ticle
s
b
y
r
e
n
o
w
n
ed
r
esear
c
h
er
s
[
1
]
.
C
itatio
n
s
(
a
d
o
cu
m
en
t
cites
an
o
th
er
)
,
b
ib
lio
g
r
ap
h
ic
co
u
p
lin
g
(
d
o
cu
m
en
t
s
s
h
ar
i
n
g
a
r
ef
er
en
ce
in
t
h
eir
b
ib
lio
g
r
ap
h
y
)
an
d
co
-
w
o
r
d
lin
k
ag
e
s
(
d
o
cu
m
e
n
t
s
s
h
ar
e
ce
r
tai
n
w
o
r
d
s
)
ar
e
s
o
m
e
o
f
th
e
ex
i
s
ti
n
g
m
eth
o
d
s
t
h
at
h
a
v
e
b
ee
n
u
s
ed
to
id
en
tify
tex
tu
al
d
o
cu
m
e
n
t
s
th
at
ar
e
n
ec
e
s
s
ar
y
f
o
r
r
esear
ch
.
T
r
a
d
itio
n
al
d
o
cu
m
en
t
clu
s
t
er
in
g
ap
p
r
o
ac
h
es
d
o
n
o
t
s
u
f
f
icie
n
tl
y
ca
p
t
u
r
e
s
e
m
a
n
tic
r
elatio
n
s
b
et
w
ee
n
k
e
y
w
o
r
d
s
lead
in
g
to
a
m
b
i
g
u
it
y
a
n
d
h
i
g
h
d
i
m
e
n
s
io
n
alit
y
th
er
eb
y
r
ed
u
cin
g
t
h
e
ac
cu
r
ac
y
o
f
clu
s
ter
in
g
r
es
u
lt
s
[
2
,
3
]
.
T
r
a
d
itio
n
al
clu
s
ter
in
g
m
et
h
o
d
s
o
f
te
n
i
g
n
o
r
e
s
e
m
a
n
tic
r
elati
o
n
s
h
ip
s
o
r
co
n
n
ec
tio
n
s
b
et
w
e
en
w
o
r
d
s
an
d
th
er
e
p
r
o
d
u
ce
in
ac
cu
r
ate
r
ep
r
esen
ta
t
io
n
s
o
f
s
u
ch
ar
t
icles.
T
ex
t
d
ata
ca
r
r
y
h
i
g
h
lev
e
l
s
e
m
a
n
tic
i
n
f
o
r
m
atio
n
an
d
d
i
v
er
s
e
v
o
ca
b
u
lar
y
,
h
en
ce
t
h
e
n
ee
d
f
o
r
tex
t c
lu
s
ter
in
g
tec
h
n
iq
u
es to
i
m
p
r
o
v
e
q
u
alit
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
S
ema
n
tics
-
b
a
s
ed
clu
s
teri
n
g
a
p
p
r
o
a
ch
fo
r
s
imila
r
r
esea
r
ch
a
r
ea
d
etec
tio
n
(
Ma
r
io
n
Olu
w
a
b
u
n
mi
A
d
eb
iyi
)
1875
W
h
en
a
p
r
o
s
p
ec
tiv
e
r
esear
ch
er
em
b
ar
k
s
o
n
a
r
esear
ch
en
d
ea
v
o
r
,
th
e
r
esear
ch
er
m
u
s
t
co
n
d
u
c
t
a
r
ev
ie
w
o
f
r
elate
d
w
o
r
k
s
alr
ea
d
y
d
o
cu
m
en
ted
in
liter
atu
r
e
i
n
th
at
f
iel
d
f
o
r
a
r
o
b
u
s
t
r
esear
ch
p
u
b
licatio
n
.
T
h
e
r
esear
ch
er
w
o
u
ld
T
h
is
s
tu
d
y
u
tili
ze
s
a
d
at
aset
co
n
ta
in
i
n
g
b
ib
lio
g
r
ap
h
ic
i
n
f
o
r
m
atio
n
o
f
Nig
er
ia
n
r
esear
c
h
er
s
a
s
a
ca
s
e
s
tu
d
y
an
d
ap
p
lies
co
-
w
o
r
d
lin
k
a
g
es
to
d
eter
m
i
n
e
d
o
cu
m
e
n
ts
in
t
h
e
s
a
m
e
f
ield
.
T
h
e
g
o
al
o
f
t
h
is
s
tu
d
y
is
to
d
ev
elo
p
a
s
e
m
an
t
ics
-
b
ased
clu
s
ter
i
n
g
f
r
a
m
e
w
o
r
k
f
o
r
d
etec
tin
g
s
i
m
ilar
r
esear
ch
ar
ea
s
.
T
h
e
s
y
s
te
m
d
eter
m
i
n
e
s
th
e
s
u
itab
ilit
y
o
f
a
n
au
t
h
o
r
to
a
r
esear
ch
f
ield
b
ased
o
n
th
e
s
e
m
an
tic
s
i
m
ilar
it
y
b
et
w
ee
n
an
au
th
o
r
’
s
w
o
r
k
an
d
p
r
ev
io
u
s
w
o
r
k
s
.
T
h
is
w
o
u
ld
b
e
p
ar
ticu
lar
l
y
u
s
e
f
u
l
f
o
r
r
esear
ch
er
s
w
h
o
i
n
te
n
d
to
lo
ca
te
r
esear
ch
er
s
w
it
h
i
n
th
eir
r
esear
ch
f
ie
ld
an
d
s
i
m
ilar
r
esea
r
ch
f
ie
ld
.
T
h
e
d
etec
tio
n
o
f
s
i
m
i
lar
r
esear
ch
ar
ea
s
b
ased
o
n
k
e
y
w
o
r
d
s
co
u
ld
p
r
o
v
e
b
en
ef
icia
l
to
ter
tiar
y
in
s
tit
u
tio
n
s
o
f
lear
n
in
g
a
n
d
r
esear
ch
ce
n
ter
.
T
h
e
r
esear
ch
n
et
w
o
r
k
s
cr
ea
ted
is
in
ten
d
ed
to
en
h
a
n
ce
t
h
e
p
r
o
s
p
ec
t o
f
r
esear
ch
co
llab
o
r
atio
n
s
in
t
h
e
co
n
ti
n
en
t.
Ac
co
r
d
in
g
to
[
4
-
6
]
,
th
e
ex
is
ti
n
g
m
et
h
o
d
s
th
at
h
av
e
b
ee
n
u
s
ed
to
id
en
ti
f
y
tex
t
u
al
d
o
cu
m
e
n
t
s
th
a
t a
d
d
r
ess
a
p
ar
ticu
lar
s
u
b
j
ec
t m
atter
i
n
cl
u
d
e:
-
C
itatio
n
s
(
a
d
o
cu
m
e
n
t c
ite
s
an
o
th
er
)
-
B
ib
lio
g
r
ap
h
ic
co
u
p
lin
g
(
d
o
cu
m
en
ts
s
h
ar
i
n
g
a
r
ef
er
e
n
ce
in
t
h
eir
b
ib
lio
g
r
ap
h
y
)
-
Co
-
w
o
r
d
lin
k
ag
e
s
(
d
o
cu
m
e
n
t
s
s
h
ar
e
ce
r
tain
w
o
r
d
s
)
T
h
e
p
r
o
b
lem
T
r
a
d
itio
n
al
d
o
cu
m
en
t
cl
u
s
ter
i
n
g
ap
p
r
o
ac
h
es
d
o
n
o
t
s
u
f
f
ic
ie
n
tl
y
ca
p
t
u
r
e
s
e
m
a
n
tic
r
elatio
n
s
b
et
w
ee
n
k
e
y
w
o
r
d
s
lead
i
n
g
to
a
m
b
i
g
u
it
y
an
d
h
i
g
h
d
i
m
e
n
s
io
n
alit
y
t
h
er
eb
y
r
ed
u
ci
n
g
t
h
e
ac
c
u
r
ac
y
o
f
clu
s
ter
i
n
g
r
esu
lt
s
[
7
]
.
E
x
is
tin
g
k
e
y
w
o
r
d
m
atc
h
in
g
tec
h
n
iq
u
es
ca
n
b
e
s
i
g
n
i
f
ica
n
tl
y
i
m
p
r
o
v
ed
b
y
i
n
te
g
r
atin
g
s
e
m
a
n
tic
s
in
d
o
cu
m
en
t
s
i
m
i
lar
it
y
co
m
p
u
tat
io
n
.
T
h
e
d
etec
tio
n
o
f
s
i
m
i
lar
r
esear
ch
ar
ea
s
b
ased
o
n
k
e
y
w
o
r
d
s
co
u
ld
p
r
o
v
e
b
en
ef
icia
l
to
ter
tiar
y
i
n
s
ti
tu
t
i
o
n
s
o
f
lea
r
n
i
n
g
a
n
d
r
esear
ch
ce
n
tr
es.
T
h
is
s
tu
d
y
i
n
te
n
d
s
to
u
tili
ze
a
d
ataset
co
n
tain
i
n
g
b
ib
lio
g
r
ap
h
ic
in
f
o
r
m
atio
n
o
f
Ni
g
er
ia
n
r
esear
ch
er
s
as
a
ca
s
e
s
t
u
d
y
.
W
e
e
x
p
ec
t
th
e
r
esear
ch
n
e
t
w
o
r
k
s
cr
ea
ted
to
en
h
an
ce
t
h
e
p
r
o
s
p
ec
t o
f
r
esear
ch
co
llab
o
r
atio
n
s
in
th
e
co
n
ti
n
e
n
t
Th
e
p
r
o
p
o
s
ed
s
o
lu
tio
n
I
n
th
is
s
t
u
d
y
,
an
au
to
m
ated
s
i
m
ilar
r
esear
ch
ar
ea
d
etec
tio
n
s
y
s
te
m
i
s
p
r
o
p
o
s
ed
th
at
g
en
er
ates
s
i
m
ilar
r
esear
ch
ar
ea
s
an
d
p
u
b
licatio
n
s
to
th
at
o
f
a
p
r
o
s
p
ec
tiv
e
r
ese
ar
ch
er
.
B
ased
o
n
th
e
ex
p
er
tis
e
o
f
th
e
p
r
o
s
p
ec
tiv
e
r
esear
ch
er
,
th
e
s
y
s
te
m
au
to
m
at
icall
y
ass
i
g
n
s
p
r
o
s
p
ec
tiv
e
r
esear
ch
er
s
to
alr
ea
d
y
ex
is
ti
n
g
r
esear
ch
er
s
in
th
e
s
a
m
e
o
r
s
im
i
lar
r
esear
ch
f
ield
.
T
h
is
is
d
o
n
e
u
s
in
g
th
e
s
i
m
i
lar
it
y
s
co
r
e
o
b
tain
ed
u
s
in
g
th
e
L
S
A
m
o
d
el
an
d
co
s
in
e
s
i
m
i
lar
it
y
to
ca
lc
u
late
t
h
e
s
e
m
a
n
tic
s
i
m
ilar
it
y
b
et
w
ee
n
t
h
e
m
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
b
u
ilt
f
o
r
r
esear
ch
er
s
to
d
etec
t
s
i
m
ilar
r
esear
ch
ar
ea
s
d
ep
en
d
in
g
o
n
th
e
ir
r
esear
ch
p
r
ef
er
en
ce
s
.
T
h
e
s
y
s
te
m
is
ac
ce
s
s
ib
le
a
s
a
w
eb
ap
p
licatio
n
.
T
h
er
ef
o
r
e,
th
e
aim
o
f
th
e
r
ese
ar
ch
w
as
to
d
ev
elo
p
a
s
em
a
n
ti
cs
-
b
ased
clu
s
ter
in
g
m
et
h
o
d
f
o
r
d
etec
tin
g
s
i
m
i
lar
r
esear
ch
ar
ea
s
u
s
in
g
Nig
er
ia
n
p
u
b
licatio
n
s
as
a
ca
s
e
s
tu
d
y
an
d
t
o
ac
h
ie
v
e
th
i
s
ai
m
,
th
e
f
o
llo
w
i
n
g
o
b
j
ec
tiv
es
w
er
e
ca
r
r
ied
o
u
t
;
-
C
r
ea
tio
n
o
f
a
d
ataset
-
Dev
elo
p
a
f
r
a
m
e
w
o
r
k
f
o
r
s
i
m
i
lar
r
esear
ch
ar
ea
d
etec
tio
n
-
I
m
p
le
m
e
n
t a
p
r
o
to
ty
p
e
f
o
r
th
e
p
r
o
p
o
s
ed
f
r
a
m
e
w
o
r
k
-
Valid
atio
n
an
d
ev
a
lu
at
io
n
o
f
t
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
A
r
e
v
ie
w
o
f
e
x
i
s
ti
n
g
s
e
m
an
t
ic
clu
s
ter
in
g
tec
h
n
iq
u
es
alr
e
ad
y
d
o
cu
m
e
n
t
i
n
liter
at
u
r
e
i
s
o
u
tli
n
ed
b
elo
w
[
8
]
p
r
esen
ted
a
d
ee
p
h
y
p
er
g
r
ap
h
m
o
d
el
f
o
r
s
e
n
ti
m
en
t c
lass
i
f
icatio
n
an
d
o
n
l
in
e
r
e
v
ie
w
s
.
T
h
e
m
o
d
el
u
s
ed
a
h
ier
ar
ch
ical
cl
u
s
ter
i
n
g
alg
o
r
ith
m
to
d
is
co
v
er
s
e
m
an
tic
cli
q
u
es.
T
h
e
m
o
d
el,
test
ed
w
i
th
m
o
v
ie
r
e
v
ie
w
s
a
n
d
p
r
o
d
u
ct
r
ev
ie
w
s
(
b
o
o
k
s
,
DVD
,
elec
tr
o
n
ic
an
d
k
itc
h
e
n
)
w
a
s
co
m
p
ar
ed
w
it
h
s
e
v
en
o
t
h
er
m
eth
o
d
s
o
f
s
e
n
ti
m
e
n
t
class
i
f
icatio
n
a
n
d
r
esu
lts
s
h
o
wed
th
e
m
o
d
el
o
u
tp
er
f
o
r
m
ed
al
l
o
th
er
m
et
h
o
d
s
i
n
all
ca
s
e
s
.
A
ls
o
,
[
9
]
u
s
ed
s
e
m
a
n
ti
c
clu
s
ter
i
n
g
to
lo
ca
te
a
n
d
ac
ce
s
s
w
eb
d
o
cu
m
e
n
ts
.
T
h
e
te
x
t
co
r
p
u
s
i
s
p
r
e
-
p
r
o
ce
s
s
ed
,
s
te
m
m
i
n
g
is
p
er
f
o
r
m
ed
u
s
i
n
g
th
e
W
o
r
d
Net
o
n
to
lo
g
y
.
T
h
e
t
er
m
f
r
eq
u
en
c
y
-
i
n
v
er
s
e
d
o
cu
m
en
t
f
r
eq
u
en
c
y
al
g
o
r
ith
m
was
u
s
ed
to
co
n
s
tr
u
ct
a
f
ea
t
u
r
e
m
atr
ix
.
Hier
ar
ch
ical
ag
g
lo
m
er
ati
v
e
cl
u
s
ter
i
n
g
w
as
u
s
ed
to
p
er
f
o
r
m
clu
s
ter
i
n
g
o
n
th
e
f
ea
t
u
r
e
m
a
tr
ix
.
T
h
e
ap
p
r
o
ac
h
u
s
ed
,
i
m
p
r
o
v
e
d
th
e
ac
cu
r
ac
y
o
f
th
e
c
lu
s
ter
s
g
e
n
er
ated
.
T
h
e
d
r
a
w
b
ac
k
i
s
th
a
t
Hier
ar
ch
ical
ag
g
lo
m
er
ati
v
e
cl
u
s
ter
i
n
g
is
n
o
t
s
u
itab
le
f
o
r
lar
g
e
d
ataset
s
.
Si
m
ilar
l
y
,
[
1
0
]
p
er
f
o
r
m
ed
en
h
a
n
ce
d
s
e
m
a
n
tic
clu
s
ter
i
n
g
w
i
th
th
e
W
o
r
d
Net
o
n
to
lo
g
y
.
T
h
e
tex
t
co
r
p
u
s
w
as
p
r
e
-
p
r
o
ce
s
s
ed
w
i
th
W
o
r
d
Net
o
n
to
lo
g
y
to
p
er
f
o
r
m
w
o
r
d
s
en
s
e
d
is
a
m
b
i
g
u
atio
n
.
T
h
e
ter
m
f
r
eq
u
e
n
c
y
-
i
n
v
er
s
e
d
o
cu
m
en
t
f
r
eq
u
e
n
c
y
tech
n
iq
u
e
is
u
s
ed
to
d
er
iv
e
a
f
ea
tu
r
e
r
ep
r
esen
tatio
n
o
f
t
h
e
w
o
r
d
s
in
th
e
te
x
t
co
r
p
u
s
.
T
h
e
K
-
Me
a
n
s
clu
s
ter
i
n
g
al
g
o
r
ith
m
is
ap
p
lied
to
clu
s
ter
th
e
f
ea
t
u
r
e
v
ec
to
r
s
[
1
1
]
.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
m
e
th
o
d
u
s
ed
eli
m
i
n
ated
th
e
d
i
m
e
n
s
io
n
alit
y
p
r
o
b
lem
e
n
co
u
n
ter
ed
in
tr
ad
itio
n
al
d
o
cu
m
e
n
t
cl
u
s
t
er
in
g
.
T
h
e
li
m
itat
io
n
is
t
h
at
th
e
K
-
Me
a
n
s
clu
s
ter
in
g
alg
o
r
ith
m
s
u
f
f
er
s
f
r
o
m
th
e
lo
ca
l
o
p
ti
m
a
p
r
o
b
le
m
.
I
n
[
1
2
]
as
w
ell
u
s
ed
Se
m
a
n
t
ic
clu
s
ter
in
g
to
s
o
lv
e
t
h
e
to
p
ic
d
r
if
t
p
r
o
b
le
m
in
i
n
f
o
r
m
atio
n
r
etr
ie
v
al
s
y
s
t
e
m
s
.
Sear
c
h
s
n
ip
p
ets
ar
e
p
r
ep
r
o
ce
s
s
ed
an
d
ex
tr
ac
t
th
e
lo
n
g
e
s
t
co
m
m
o
n
s
u
b
s
eq
u
en
ce
b
et
w
ee
n
t
w
o
s
n
ip
p
ets
b
y
GST
.
E
v
alu
a
te
W
o
r
d
s
i
m
ilar
it
y
u
s
i
n
g
Ho
w
Net
o
n
to
lo
g
y
a
n
d
co
n
s
tr
u
ct
a
lex
ic
al
c
h
ai
n
to
s
elec
t
f
ea
t
u
r
es
o
f
s
n
ip
p
ets.
A
f
ea
t
u
r
e
v
ec
to
r
is
co
n
s
tr
u
cted
a
n
d
ev
a
lu
ate
s
n
ip
p
et
s
i
m
ilar
ities
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
1
8
7
4
-
1
8
8
3
1876
T
h
e
I
m
p
r
o
v
ed
C
h
a
m
eleo
n
alg
o
r
ith
m
u
s
ed
f
o
r
clu
s
ter
i
n
g
t
h
e
f
ea
t
u
r
e
v
ec
to
r
s
i
m
p
r
o
v
ed
t
h
e
w
it
h
i
n
-
clas
s
d
en
s
it
y
an
d
b
et
w
ee
n
-
clas
s
v
ar
iat
io
n
o
f
th
e
cl
u
s
te
r
lab
els.
Ho
w
e
v
er
,
th
e
C
h
a
m
eleo
n
alg
o
r
it
h
m
h
a
s
a
h
ig
h
ti
m
e
an
d
s
p
ac
e
co
m
p
le
x
it
y
w
h
ich
d
o
es
n
o
t
m
a
k
e
it s
u
itab
le
f
o
r
h
ig
h
d
i
m
e
n
s
i
o
n
al
d
atasets
.
I
n
[
1
3
]
u
s
ed
s
em
a
n
tic
cl
u
s
ter
i
n
g
to
clu
s
ter
s
ea
r
ch
r
esu
lt
d
o
cu
m
en
ts
b
ased
o
n
th
e
s
e
m
an
tics
o
f
r
etr
iev
ed
d
o
cu
m
en
ts
.
A
s
ea
r
ch
e
n
g
in
e
w
as
q
u
er
ied
to
r
etr
iev
e
in
f
o
r
m
at
io
n
,
th
e
s
ea
r
c
h
en
g
i
n
e
r
esu
lts
w
er
e
th
e
n
p
r
e
-
p
r
o
ce
s
s
ed
,
an
d
ex
tr
ac
tio
n
o
f
f
ea
t
u
r
es
w
a
s
ca
r
r
ied
o
u
t.
T
h
e
f
ea
t
u
r
es
w
er
e
en
h
a
n
ce
d
u
s
in
g
co
n
ce
p
t
s
f
r
o
m
an
o
n
to
lo
g
y
a
n
d
s
e
m
a
n
tic
n
et
w
o
r
k
.
A
d
is
s
i
m
ilar
i
t
y
m
atr
i
x
o
f
th
e
d
o
cu
m
e
n
ts
w
a
s
cr
ea
ted
u
s
in
g
th
e
F
lo
y
d
-
W
ar
s
h
all
a
lg
o
r
it
h
m
[
1
4
]
.
T
h
e
Hier
ar
ch
ical
a
g
g
lo
m
er
ati
v
e
cl
u
s
ter
i
n
g
al
g
o
r
ith
m
is
u
s
ed
to
cl
u
s
ter
th
e
f
ea
t
u
r
e
v
ec
to
r
s
i
n
th
e
s
i
m
il
ar
it
y
m
atr
i
x
.
Hig
h
p
r
ec
i
s
io
n
r
e
s
u
lt
s
w
er
e
o
b
tain
ed
as
th
e
ap
p
r
o
ac
h
o
u
tp
er
f
o
r
m
ed
ex
is
t
in
g
ap
p
r
o
ac
h
es
f
o
r
w
e
b
s
ea
r
ch
r
es
u
lt
cl
u
s
ter
i
n
g
.
Hier
ar
ch
ical
a
g
g
lo
m
er
ati
v
e
clu
s
ter
i
n
g
ca
n
b
e
co
m
p
u
tatio
n
all
y
e
x
p
en
s
i
v
e
to
u
s
e
f
o
r
lar
g
e
d
atasets
.
I
n
[
1
5
]
also
p
r
o
p
o
s
ed
th
e
u
s
e
o
f
s
e
m
an
tic
clu
s
te
r
i
n
g
to
d
eter
m
in
e
s
i
m
ilar
tex
t d
o
cu
m
e
n
ts
.
T
h
e
tex
t c
o
r
p
u
s
is
ex
tr
ac
ted
an
d
p
r
e
-
p
r
o
ce
s
s
ed
.
T
h
e
ter
m
f
r
eq
u
en
c
y
-
i
n
v
er
s
e
d
o
cu
m
en
t
f
r
eq
u
en
c
y
al
g
o
r
ith
m
is
u
s
ed
to
id
en
ti
f
y
f
r
eq
u
e
n
tl
y
o
cc
u
r
r
in
g
ter
m
s
a
n
d
co
n
s
tr
u
ct
a
d
o
cu
m
e
n
t
m
atr
i
x
.
A
d
o
m
ai
n
o
n
to
lo
g
y
is
co
n
s
tr
u
ct
ed
f
r
o
m
th
e
te
x
t
co
r
p
u
s
to
p
r
o
v
id
e
a
v
o
ca
b
u
lar
y
f
o
r
f
ilter
i
n
g
r
elev
a
n
t
ter
m
s
.
A
F
u
zz
y
eq
u
iv
ale
n
ce
r
elatio
n
is
u
s
ed
to
d
eter
m
i
n
e
th
e
lev
el
o
f
m
e
m
b
er
s
h
ip
o
f
ter
m
s
i
n
th
e
tex
t
co
r
p
u
s
.
Sin
g
u
lar
v
al
u
e
d
ec
o
m
p
o
s
itio
n
is
u
s
ed
to
tr
an
s
f
o
r
m
th
e
d
o
cu
m
e
n
t
m
atr
ix
i
n
t
o
a
co
n
ce
p
t
s
p
ac
e.
B
is
ec
tin
g
K
-
m
ea
n
s
alg
o
r
it
h
m
i
s
u
s
ed
to
p
er
f
o
r
m
clu
s
ter
in
g
o
f
t
h
e
co
n
ce
p
t
s
p
ac
e.
T
h
e
u
s
e
o
f
a
d
o
m
a
in
o
n
to
lo
g
y
i
n
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
ta
g
e
i
m
p
r
o
v
es
clu
s
ter
in
g
r
esu
lt
s
.
T
h
e
li
m
ita
tio
n
o
f
t
h
e
m
et
h
o
d
is
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
et
h
o
d
is
en
t
ir
el
y
d
ep
en
d
en
t
o
n
th
e
q
u
alit
y
a
n
d
co
m
p
r
eh
en
s
i
v
en
e
s
s
o
f
t
h
e
o
n
to
lo
g
y
u
s
ed
.
I
n
[
1
6
]
as
w
el
l
u
s
ed
s
e
m
an
t
ic
clu
s
ter
in
g
to
class
i
f
y
c
u
s
to
m
er
r
ev
ie
w
s
.
T
h
e
tex
t
co
r
p
u
s
is
ex
tr
ac
ted
b
y
cr
a
w
li
n
g
c
u
s
to
m
er
r
ev
ie
w
w
eb
s
i
tes
an
d
th
e
n
it
is
p
r
e
-
p
r
o
ce
s
s
ed
.
On
to
lo
g
y
is
u
s
ed
to
g
en
er
ate
a
co
n
ce
p
t
m
ap
p
in
g
in
th
e
tex
t
co
r
p
u
s
.
E
u
clid
ea
n
d
is
ta
n
ce
m
etr
ics
ar
e
u
s
ed
to
ca
lcu
late
th
e
s
i
m
ilar
it
y
o
f
s
en
te
n
ce
s
i
n
th
e
b
ag
o
f
w
o
r
d
s
v
ec
to
r
s
p
ac
e
m
o
d
el.
T
h
e
m
o
d
if
ied
K
-
Me
an
s
alg
o
r
ith
m
is
u
s
ed
to
clu
s
ter
th
e
b
ag
o
f
w
o
r
d
s
.
E
x
p
er
i
m
e
n
tal
r
esu
l
t
s
r
ev
ea
led
th
a
t
th
e
ac
cu
r
ac
y
o
f
t
h
e
clu
s
ter
s
g
e
n
er
ated
is
in
cr
ea
s
ed
w
it
h
t
h
e
u
s
e
o
f
o
n
to
lo
g
y
i
n
th
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
s
tag
e.
Fu
r
t
h
er
m
et
h
o
d
s
f
o
r
id
en
ti
f
y
i
n
g
e
x
i
s
ti
n
g
co
llab
o
r
atio
n
s
b
et
w
ee
n
v
ar
io
u
s
r
esear
c
h
er
s
f
r
o
m
v
ar
io
u
s
p
u
b
licatio
n
d
atab
ases
ar
e
p
r
esen
ted
b
elo
w
[
1
7
]
d
ev
elo
p
ed
a
co
-
au
t
h
o
r
s
h
ip
n
et
w
o
r
k
to
r
ev
ea
l
th
e
in
ter
ac
tio
n
s
b
et
w
ee
n
r
esear
ch
er
s
.
A
s
y
s
te
m
f
o
r
s
elec
ti
n
g
a
co
llab
o
r
ato
r
w
i
th
s
i
m
ilar
r
esear
ch
i
n
ter
es
ts
f
o
r
j
o
in
t
r
esear
ch
w
a
s
m
o
d
eled
as
a
lin
k
p
r
ed
ictio
n
p
r
o
b
lem
.
Au
t
h
o
r
s
w
it
h
s
i
m
ila
r
k
n
o
w
n
f
ea
tu
r
e
s
w
er
e
d
eter
m
i
n
ed
u
s
i
n
g
C
o
s
i
n
e
s
i
m
ilar
it
y
co
m
p
u
ted
o
n
a
v
ec
t
o
r
co
n
s
tr
u
cted
to
m
o
d
el
th
e
d
escr
ip
tiv
e
s
tat
is
tic
s
o
f
v
ar
io
u
s
r
esear
ch
ac
tiv
itie
s
.
T
h
e
co
-
au
th
o
r
s
h
ip
n
et
w
o
r
k
was
d
eter
m
i
n
ed
u
s
in
g
th
e
h
ier
a
r
ch
ical
clu
s
ter
in
g
o
f
r
esear
ch
in
ter
est
s
in
v
ar
io
u
s
co
-
o
cc
u
r
r
en
ce
n
et
w
o
r
k
s
.
T
h
ey
also
u
s
ed
lo
g
is
tic
r
eg
r
es
s
io
n
w
it
h
la
s
s
o
r
e
g
u
lar
izat
io
n
o
n
n
o
r
m
alize
d
f
ea
t
u
r
e
v
ec
to
r
s
.
T
h
e
d
is
ad
v
a
n
tag
e
o
f
th
i
s
ap
p
r
o
ac
h
is
t
h
at
i
n
f
o
r
m
atio
n
r
etr
iev
al
w
as
u
s
ed
t
o
o
b
tain
d
ata
f
r
o
m
th
e
b
ib
lio
g
r
ap
h
y
d
atab
ase
a
n
d
th
e
s
e
m
a
n
tic
m
ea
n
i
n
g
o
f
t
h
e
te
r
m
s
w
as
n
o
t ta
k
e
n
i
n
to
co
n
s
id
er
atio
n
.
A
n
o
v
el
ar
ch
itect
u
r
e
w
as
p
r
o
p
o
s
ed
b
y
[
18
]
f
o
r
j
o
in
in
g
m
u
ltip
le
b
ib
lio
g
r
ap
h
ic
s
o
u
r
ce
s
to
id
en
tify
co
m
m
o
n
r
esear
ch
ar
ea
s
an
d
r
elatio
n
s
h
ip
s
b
et
w
ee
n
au
t
h
o
r
s
an
d
th
eir
p
u
b
licatio
n
s
.
T
h
e
s
cien
ti
f
ic
p
u
b
licati
o
n
s
w
er
e
r
etr
iev
ed
f
r
o
m
v
ar
io
u
s
b
ib
lio
g
r
ap
h
ic
s
o
u
r
ce
s
u
s
in
g
A
P
I
s
an
d
L
in
k
ed
d
ata
p
r
ac
tices,
t
h
e
d
ata
is
an
al
y
ze
d
to
p
r
o
v
id
e
a
s
tr
u
ctu
r
e
an
d
i
f
t
h
er
e
is
n
o
e
x
p
licit
s
tr
u
ct
u
r
e,
th
e
d
ata
m
o
d
el
is
p
r
o
d
u
ce
d
u
s
in
g
w
eb
s
cr
ap
in
g
.
An
o
n
to
lo
g
y
m
ap
p
in
g
m
o
d
el
is
u
s
ed
to
u
n
if
y
t
h
e
d
ata
f
r
o
m
d
if
f
er
en
t
b
ib
lio
g
r
ap
h
ic
s
o
u
r
ce
s
,
an
d
d
ata
d
is
a
m
b
i
g
u
at
io
n
is
p
er
f
o
r
m
ed
to
elim
in
ate
d
ata
in
co
n
s
is
te
n
cies
an
d
d
u
p
licatio
n
s
.
A
v
ec
t
o
r
s
p
ac
e
m
o
d
el
o
f
th
e
r
etr
iev
ed
in
f
o
r
m
atio
n
i
s
g
en
er
ated
u
s
in
g
t
h
e
T
F
-
I
D
F
al
g
o
r
ith
m
.
T
h
e
K
-
m
ea
n
s
cl
u
s
te
r
in
g
al
g
o
r
ith
m
u
s
i
n
g
th
e
C
o
s
i
n
e
Si
m
i
lar
it
y
m
ea
s
u
r
e
w
as
u
s
ed
to
au
to
m
atica
ll
y
d
i
s
co
v
er
s
i
m
ilar
itie
s
a
n
d
g
r
o
u
p
th
e
au
t
h
o
r
s
i
n
to
t
h
eir
r
esear
ch
ar
ea
s
.
T
h
e
in
f
o
r
m
atio
n
r
etr
ie
v
al
m
eth
o
d
u
s
ed
d
id
n
o
t
u
tili
ze
s
e
m
a
n
tics
i
n
r
etr
iev
in
g
th
e
i
n
f
o
r
m
atio
n
.
I
n
[
1
9
]
p
r
o
p
o
s
ed
a
m
eth
o
d
f
o
r
d
eter
m
in
i
n
g
co
llab
o
r
atio
n
s
b
et
w
ee
n
u
n
i
v
er
s
it
y
r
esear
ch
a
n
d
in
d
u
s
tr
y
r
esear
c
h
.
A
h
eter
o
g
e
n
eo
u
s
s
o
cial
n
et
w
o
r
k
[2
0
]
w
a
s
co
n
s
tr
u
cted
to
d
escr
ib
e
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
r
esear
ch
er
s
an
d
co
m
p
a
n
ies,
a
co
m
p
an
y
a
n
d
a
r
esear
ch
er
ar
e
d
ee
m
ed
to
h
av
e
a
r
elatio
n
s
h
ip
if
th
e
y
h
a
v
e
co
-
au
t
h
o
r
ed
ac
ad
e
m
ic
ar
ticles,
co
-
p
ar
ticip
ated
in
p
r
o
j
ec
ts
o
r
co
-
in
v
e
n
ted
p
aten
t
s
.
A
d
ataset
[2
1
,
2
2
]
is
cr
ea
ted
f
o
r
r
esear
ch
er
s
w
h
o
h
a
v
e
d
ir
ec
tl
y
co
llab
o
r
ated
w
it
h
co
m
p
an
ies
b
ef
o
r
e,
it
is
ass
u
m
ed
th
at
r
esear
ch
er
s
w
it
h
in
th
e
s
a
m
e
d
o
m
ain
a
s
th
e
r
esear
ch
er
s
in
t
h
is
d
atase
t
ca
n
co
llab
o
r
ate
w
ith
t
h
e
m
.
C
o
m
p
a
n
y
s
i
m
ilar
it
y
is
also
u
s
ed
to
d
eter
m
i
n
e
p
o
ten
tial
co
llab
o
r
atio
n
s
,
co
m
p
a
n
ies
t
h
at
h
a
v
e
w
o
r
k
ed
o
n
s
i
m
ilar
p
ate
n
ts
,
ar
t
icles,
an
d
p
r
o
j
ec
ts
.
Ke
y
w
o
r
d
s
ar
e
ex
tr
ac
ted
f
r
o
m
co
m
p
an
y
tec
h
n
o
lo
g
ica
l
d
o
cu
m
e
n
t
s
,
p
r
e
-
p
r
o
ce
s
s
i
n
g
i
s
t
h
e
n
p
er
f
o
r
m
ed
u
s
i
n
g
to
k
en
izat
io
n
,
s
to
p
w
o
r
d
s
r
e
m
o
v
al,
n
o
r
m
aliza
tio
n
an
d
s
te
m
m
i
n
g
,
t
h
e
v
ec
to
r
s
p
ac
e
m
o
d
e
l
is
u
s
ed
to
in
d
ex
th
e
e
x
tr
ac
ted
k
e
y
w
o
r
d
f
r
eq
u
e
n
cies.
T
h
e
co
s
i
n
e
s
i
m
ilar
it
y
m
ea
s
u
r
e
is
u
s
ed
to
d
eter
m
i
n
e
th
e
s
i
m
ilar
it
y
o
f
th
e
d
if
f
er
en
t
co
m
p
a
n
ies
u
s
i
n
g
th
eir
k
e
y
w
o
r
d
s
,
th
e
to
p
K
m
o
s
t
s
i
m
ilar
co
m
p
an
ie
s
ar
e
s
to
r
ed
as
n
eig
h
b
o
r
co
m
p
a
n
ies
a
n
d
r
esear
ch
er
s
with
co
n
n
ec
tio
n
s
to
a
n
eig
h
b
o
r
in
g
co
m
p
a
n
y
ar
e
p
o
ten
tial
c
o
llab
o
r
ato
r
s
o
f
its
n
eig
h
b
o
r
in
g
co
m
p
an
ie
s
.
T
h
e
ap
p
r
o
ac
h
u
s
ed
b
y
[2
3
]
to
p
r
ed
ict
p
o
ten
tial
r
esear
ch
co
llab
o
r
atio
n
s
in
v
o
l
v
es
th
e
u
s
e
o
f
t
h
e
o
n
li
n
e
s
o
cial
n
et
w
o
r
k
[2
0
]
to
d
eter
m
i
n
e
t
h
e
co
-
au
th
o
r
s
h
ip
n
et
w
o
r
k
.
T
h
e
late
n
t
d
ir
ich
let
allo
ca
tio
n
(
L
D
A
)
alg
o
r
it
h
m
i
s
u
s
ed
to
m
o
d
el
a
s
et
o
f
to
p
ics f
r
o
m
a
d
o
cu
m
e
n
t c
o
r
p
u
s
co
n
s
is
t
in
g
o
f
a
u
t
h
o
r
ed
p
ap
er
s
,
th
ese
ar
e
th
en
r
ep
r
esen
ted
i
n
a
K
-
d
i
m
en
s
io
n
al
v
ec
to
r
.
L
D
A
is
also
u
s
ed
to
d
eter
m
i
n
e
t
h
e
co
n
ten
t
s
i
m
ilar
it
y
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
S
ema
n
tics
-
b
a
s
ed
clu
s
teri
n
g
a
p
p
r
o
a
ch
fo
r
s
imila
r
r
esea
r
ch
a
r
ea
d
etec
tio
n
(
Ma
r
io
n
Olu
w
a
b
u
n
mi
A
d
eb
iyi
)
1877
th
e
p
ap
er
s
.
T
h
e
w
eig
h
ted
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
w
as
u
s
ed
to
p
er
f
o
r
m
li
n
k
p
r
ed
ictio
n
to
d
eter
m
in
e
p
o
ten
t
ial
co
llab
o
r
ato
r
s
.
T
h
e
d
r
aw
b
ac
k
o
f
th
is
m
eth
o
d
is
t
h
at
t
h
e
u
s
e
o
f
L
D
A
m
ak
e
s
it c
o
m
p
u
tatio
n
a
ll
y
ex
p
en
s
i
v
e.
2
.
1
.
Do
cum
e
nt
clus
t
er
ing
Do
cu
m
e
n
t
cl
u
s
ter
in
g
i
s
t
h
e
tas
k
o
f
g
r
o
u
p
i
n
g
a
s
et
o
f
te
x
t
d
o
cu
m
en
ts
i
n
to
g
r
o
u
p
s
o
r
clu
s
ter
s
.
Do
cu
m
e
n
t
s
b
elo
n
g
i
n
g
to
th
e
s
a
m
e
cl
u
s
ter
s
h
ar
e
t
h
e
s
a
m
e
f
ea
t
u
r
es
w
h
ile
d
o
cu
m
en
ts
i
n
a
n
o
th
er
cl
u
s
ter
d
o
n
o
t
s
h
ar
e
s
i
m
ilar
f
ea
t
u
r
es.
T
r
ad
itio
n
al
d
o
cu
m
e
n
t
clu
s
ter
in
g
tech
n
iq
u
e
s
u
s
e
a
b
ag
o
f
w
o
r
d
s
r
ep
r
ese
n
tatio
n
;
w
h
ic
h
d
o
n
o
t
tak
e
s
e
m
a
n
tic
s
in
to
co
n
s
id
er
atio
n
.
In
[
2
]
d
escr
ib
ed
th
e
ty
p
ical
p
r
o
ce
s
s
o
f
d
o
cu
m
en
t c
lu
s
ter
in
g
i
n
Fig
u
r
e
1.
Fig
u
r
e
1
.
Do
cu
m
e
n
t
cl
u
s
ter
i
n
g
p
r
o
ce
s
s
[
2]
2
.
2
.
F
ea
t
ure
re
presenta
t
io
n
2
.
2
.
1
.
Vec
t
o
r
s
pa
ce
m
o
del
T
h
e
v
ec
to
r
s
p
ac
e
m
o
d
el
(
VSM)
is
lar
g
el
y
co
n
s
id
er
ed
th
e
b
asic
m
o
d
el
f
o
r
f
ea
tu
r
e
r
ep
r
esen
tatio
n
a
n
d
h
as
b
ee
n
m
o
d
if
ied
s
e
v
er
el
y
to
ca
ter
f
o
r
its
in
ad
eq
u
ac
ies.
I
n
th
e
g
e
n
er
ic
VSM
m
o
d
el,
ea
c
h
tex
t
d
o
cu
m
e
n
t
is
r
ep
r
esen
ted
as f
o
llo
w
s
:
:
⟼
(
)
=
[
1
,
,
2
,
,
…
,
,
]
∈
(
1
)
T
h
e
ter
m
f
r
eq
u
e
n
c
y
-
in
v
er
s
e
d
o
cu
m
e
n
t
f
r
eq
u
e
n
c
y
tec
h
n
iq
u
e
h
as b
ee
n
w
id
el
y
u
s
ed
f
o
r
f
ea
tu
r
e
r
ep
r
esen
tatio
n
o
f
tex
t
d
o
cu
m
e
n
ts
,
w
h
er
e
is
th
e
T
F
-
I
DF
w
ei
g
h
t
o
f
ter
m
t
in
d
o
cu
m
en
t
d
.
T
d
en
o
tes
th
e
tr
an
s
p
o
s
e
o
p
e
r
ato
r
,
d
en
o
tes
th
e
d
o
cu
m
en
t
d
as
a
w
ei
g
h
te
d
ter
m
v
ec
to
r
i
n
th
e
m
-
d
i
m
e
n
s
io
n
al
s
p
ac
e
o
f
ter
m
s
.
T
h
i
s
f
u
n
ctio
n
co
u
ld
al
s
o
r
ep
r
esen
t
th
e
m
ap
p
in
g
o
f
a
d
o
cu
m
e
n
t
to
its
v
ec
to
r
s
p
ac
e
r
e
p
r
esen
tatio
n
.
T
h
e
d
o
cu
m
en
t
s
ar
e
th
en
w
e
ig
h
ted
b
y
th
eir
i
n
v
er
s
e
d
o
cu
m
en
t
f
r
eq
u
en
c
y
(
I
DF)
.
T
h
is
w
ei
g
h
ti
n
g
i
s
d
o
n
e
to
d
eter
m
in
e
ter
m
s
t
h
at
ap
p
ea
r
f
r
eq
u
en
t
l
y
ac
r
o
s
s
th
e
s
et
o
f
tex
t d
o
cu
m
e
n
ts
.
T
h
e
T
F
-
I
DF
m
atr
ix
i
s
r
ep
r
esen
ted
t
h
u
s
:
(
−
)
=
×
(
2
)
T
h
e
d
r
aw
b
ac
k
o
f
th
e
VSM
m
o
d
el
is
th
at
it
s
u
f
f
er
s
f
r
o
m
th
e
s
p
ar
s
it
y
p
r
o
b
le
m
an
d
d
o
es
n
o
t
p
er
f
o
r
m
w
ell
w
it
h
lar
g
e
d
o
cu
m
e
n
ts
[
2
4
].
2
.
2
.
2
.
N
-
g
r
a
m
m
o
del
T
h
e
N
-
g
r
a
m
m
o
d
el
tr
ad
itio
n
al
l
y
f
o
c
u
s
e
s
o
n
b
i
-
g
r
a
m
s
,
w
h
ich
ar
e
p
air
s
o
f
w
o
r
d
s
b
u
t
r
ec
en
tl
y
,
th
e
u
s
e
o
f
ch
ar
ac
ter
N
-
g
r
a
m
s
an
d
b
y
t
e
N
-
g
r
a
m
s
i
s
co
m
m
o
n
p
lace
.
C
h
ar
ac
ter
N
-
g
r
a
m
is
a
lan
g
u
ag
e
au
to
n
o
m
o
u
s
tex
t
r
ep
r
esen
tatio
n
m
e
th
o
d
.
T
ex
t
d
o
cu
m
e
n
ts
ar
e
tr
an
s
f
o
r
m
ed
in
to
h
ig
h
-
d
i
m
e
n
s
io
n
al
f
ea
t
u
r
e
v
ec
t
o
r
s
w
h
er
e
f
ea
tu
r
e
s
r
ep
r
esen
t
s
u
b
s
tr
in
g
s
.
N
-
g
r
a
m
s
ar
e
ty
p
ical
l
y
N
ad
j
ac
en
t
ch
ar
ac
ter
s
f
r
o
m
t
h
e
alp
h
ab
et.
T
h
e
d
i
m
en
s
io
n
ali
t
y
o
f
N
-
g
r
a
m
f
ea
tu
r
e
s
ca
n
b
e
as
h
ig
h
as
|
A|
N
ev
e
n
f
o
r
m
id
-
r
an
g
e
v
alu
e
s
o
f
N.
Gen
er
all
y
,
o
n
l
y
a
s
izea
b
le
p
o
r
tio
n
o
f
N
-
g
r
a
m
s
ar
e
a
v
ailab
le
i
n
a
g
i
v
en
s
e
t o
f
tex
t
d
o
cu
m
en
t
s
.
T
h
e
N
-
g
r
a
m
m
o
d
el
h
as
th
e
f
u
r
th
er
ad
v
an
ta
g
e
o
f
b
ein
g
r
o
b
u
s
t
an
d
to
ler
an
t
o
f
g
r
am
m
atica
l
an
d
ty
p
o
g
r
ap
h
ical
er
r
o
r
s
[2
5
]
.
T
h
e
lim
itat
io
n
o
f
th
e
n
-
g
r
a
m
m
o
d
el
is
th
at
th
e
s
e
m
a
n
tics
o
f
w
o
r
d
s
a
n
d
w
o
r
d
o
r
d
er
is
n
o
t ta
k
en
in
to
co
n
s
id
er
atio
n
.
2
.
2
.
3
.
L
a
t
ent
s
e
m
a
ntic
in
dex
ing
L
ate
n
t
s
e
m
a
n
tic
i
n
d
ex
i
n
g
i
s
an
alg
eb
r
aic
b
ased
alg
o
r
it
h
m
th
at
is
u
s
ed
f
o
r
f
ea
tu
r
e
r
ep
r
esen
tat
io
n
.
I
t
w
o
r
k
s
b
ased
o
n
a
p
r
i
m
ar
y
o
r
laten
t
s
tr
u
ct
u
r
e
to
t
h
e
w
o
r
d
p
atter
n
u
s
ag
e
in
a
tex
t
d
o
cu
m
e
n
t
an
d
u
tili
ze
s
s
tatis
t
ical
tech
n
iq
u
e
s
in
d
eter
m
in
i
n
g
t
h
is
s
tr
u
ctu
r
e.
I
t
co
n
s
id
er
s
laten
t
h
i
g
h
er
-
o
r
d
er
s
tr
u
ctu
r
es
in
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
ter
m
s
an
d
d
o
cu
m
e
n
t
s
.
T
h
i
s
tech
n
iq
u
e
ca
n
b
e
ap
p
lied
to
s
y
n
o
n
y
m
y
a
n
d
p
o
ly
s
e
m
y
p
r
o
b
le
m
s
.
L
a
ten
t
s
e
m
a
n
tic
in
d
e
x
i
n
g
is
also
u
s
ed
f
o
r
d
im
e
n
s
io
n
alit
y
r
ed
u
cti
o
n
u
s
i
n
g
s
i
n
g
u
lar
v
alu
e
d
ec
o
m
p
o
s
i
tio
n
(
SVD)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
1
8
7
4
-
1
8
8
3
1878
T
h
e
d
r
aw
b
ac
k
o
f
L
SI
is
th
at
it u
s
e
s
a
b
ag
-
of
-
w
o
r
d
s
ap
p
r
o
ac
h
w
h
ic
h
ca
n
lead
to
u
n
s
tr
u
ctu
r
ed
in
f
o
r
m
a
tio
n
an
d
it
o
n
l
y
w
o
r
k
s
o
n
s
i
n
g
u
lar
ter
m
s
[
2
6
].
2
.
2
.
4
.
P
ro
ba
bil
is
t
ic
la
t
ent
s
em
a
ntic
a
na
ly
s
i
s
(
P
L
SA)
P
r
o
b
ab
ilis
tic
L
S
A
is
a
s
tatis
ti
ca
l
tech
n
iq
u
e
f
o
r
co
-
o
cc
u
r
r
en
ce
d
ata.
P
L
SA
is
d
er
iv
ed
f
r
o
m
L
S
A
b
y
m
ak
in
g
it
a
p
r
o
b
ab
ilis
tic
m
o
d
el.
P
r
o
b
ab
ili
s
tic
L
S
A
is
b
as
ed
o
n
co
m
b
in
atio
n
d
ec
o
m
p
o
s
itio
n
d
er
iv
ed
f
r
o
m
a
laten
t
clas
s
m
o
d
el,
u
n
li
k
e
th
e
s
tan
d
ar
d
laten
t
s
e
m
a
n
tic
an
a
l
y
s
i
s
w
h
ich
i
s
f
r
o
m
li
n
ea
r
alg
e
b
r
a.
Do
cu
m
e
n
t
s
ar
e
m
o
d
eled
as
a
m
u
lt
in
o
m
ial
co
m
b
in
at
io
n
o
f
to
p
ics
w
h
ich
g
i
v
es
r
o
o
m
f
o
r
d
o
cu
m
e
n
t
-
d
o
cu
m
en
t
co
m
p
ar
is
o
n
.
T
h
is
m
ak
e
s
P
L
S
A
a
m
o
r
e
p
o
p
u
lar
tech
n
iq
u
e
f
o
r
a
n
al
y
s
is
o
f
co
-
o
cc
u
r
r
en
ce
d
ata.
P
L
SA
is
u
s
ed
to
m
o
d
el,
th
e
p
r
o
b
ab
ilit
y
o
f
ea
ch
co
-
o
cc
u
r
r
en
ce
as a
co
m
b
i
n
atio
n
o
f
in
d
ep
en
d
en
t
m
u
lti
n
o
m
ial
d
is
tr
ib
u
tio
n
s
.
P
(
w
,
d
)
=
∑
(
)
(
|
)
(
|
)
=
(
)
∑
(
|
)
(
|
)
(
3
)
P
(
w
,
d
)
is
t
h
e
s
y
m
m
etr
ic
f
o
r
m
u
latio
n
w
h
er
e
w
a
n
d
d
ar
e
co
m
p
u
ted
f
r
o
m
th
e
late
n
t
cla
s
s
i
n
s
i
m
ilar
w
a
y
s
u
s
in
g
th
e
co
n
d
itio
n
a
l p
r
o
b
ab
ilit
ies P(
d
|
c)
an
d
P
(
w
|
c)
,
f
o
r
ea
ch
d
o
cu
m
e
n
t
[2
7
].
3.
M
AT
E
RIAL
A
ND
M
E
T
H
O
DS
T
h
e
2
0
1
0
-
2
0
1
8
P
u
b
licatio
n
d
ata
f
r
o
m
r
an
d
o
m
l
y
s
elec
ted
Ni
g
er
ian
in
s
tit
u
tio
n
s
w
a
s
r
etr
ie
v
ed
th
r
o
u
g
h
th
e
Sco
p
u
s
A
P
I
lis
ted
in
th
e
S
co
p
u
s
d
atab
ase.
E
ac
h
p
u
b
licatio
n
r
etr
iev
ed
w
it
h
a
u
n
iq
u
e
E
ls
ev
ier
I
D
is
u
s
ed
to
r
etr
iev
e
its
ab
s
tr
ac
t
w
h
ic
h
b
u
il
d
s
a
d
atab
ase
o
f
9
8
0
0
p
u
b
licatio
n
d
ata.
T
h
e
ab
s
tr
ac
ts
ar
e
co
n
c
aten
ated
an
d
s
to
r
ed
in
a
d
atab
ase
an
d
th
e
f
ile
f
o
r
m
at
o
f
th
e
ab
s
tr
ac
ts
r
etr
iev
ed
is
in
J
av
aScr
ip
t O
b
j
ec
t
No
tatio
n
(
J
SON)
f
ile
f
o
r
m
at.
3
.
1
.
Da
t
a
prepro
ce
s
s
ing
T
h
e
d
atasets
w
er
e
o
b
tain
ed
i
n
th
eir
r
a
w
f
o
r
m
a
n
d
r
eq
u
ir
ed
tex
t
p
r
o
ce
s
s
i
n
g
a
n
d
f
o
r
m
a
tti
n
g
to
m
a
k
e
th
e
m
i
n
tel
lig
ib
le.
Sev
er
al
o
p
er
atio
n
s
w
er
e
ca
r
r
ied
o
u
t
o
n
th
e
d
ataset
s
to
ex
tr
ac
t
th
e
r
eq
u
ir
ed
tex
t
ar
e
d
is
cu
s
s
ed
b
elo
w
:
-
No
n
-
p
r
i
n
tab
le
ch
ar
ac
ter
s
:
R
e
g
u
lar
ex
p
r
es
s
io
n
s
w
er
e
u
s
ed
to
r
e
m
o
v
e
c
h
ar
ac
ter
s
t
h
at
d
id
n
o
t
co
n
f
o
r
m
to
th
e
U
n
ico
d
e
tex
t e
n
co
d
in
g
f
o
r
m
at.
-
T
o
k
en
izatio
n
:
T
h
e
n
atu
r
al
lan
g
u
a
g
e
to
o
lk
it
(
NL
T
K)
class
w
as
u
s
ed
to
p
er
f
o
r
m
to
k
en
iza
tio
n
an
d
th
e
co
n
v
er
s
io
n
o
f
ea
ch
w
o
r
d
to
lo
w
er
ca
s
e
ch
ar
ac
ter
s
.
-
Nu
m
b
er
r
e
m
o
v
a
l
:
T
h
e
b
u
ilt
-
in
p
y
t
h
o
n
m
o
d
u
le
w
as
u
s
ed
to
el
i
m
i
n
ate
n
u
m
b
er
s
b
u
t
n
o
t
w
o
r
d
s
r
ep
r
esen
tin
g
n
u
m
b
er
s
.
-
Sto
p
w
o
r
d
s
r
e
m
o
v
al
:
Usi
n
g
t
h
e
NL
T
K
to
o
lk
it,
s
to
p
w
o
r
d
s
li
s
t
w
as
u
s
ed
to
r
e
m
o
v
e
f
r
eq
u
e
n
tl
y
o
cc
u
r
r
i
n
g
E
n
g
l
is
h
w
o
r
d
s
s
u
c
h
as c
o
n
j
u
n
ctio
n
s
a
n
d
p
r
ep
o
s
itio
n
s
w
h
ic
h
d
o
n
o
t r
ef
lect
th
e
co
n
te
n
t o
f
t
h
e
tex
t c
o
r
p
u
s
.
-
L
e
m
m
atiza
tio
n
:
T
h
e
NL
T
K
w
o
r
d
n
et
an
d
th
e
W
o
r
d
Net
L
e
m
m
atize
r
w
as
u
s
e
d
to
o
b
tain
th
e
s
te
m
v
er
s
io
n
s
o
f
ea
ch
w
o
r
d
in
th
e
te
x
t c
o
r
p
u
s
.
4.
T
H
E
P
RO
P
O
SE
D
SYS
T
E
M
T
h
e
m
a
in
co
m
p
o
n
en
ts
i
n
cl
u
d
e
d
ataset
co
llatio
n
,
p
r
e
-
p
r
o
ce
s
s
i
n
g
&
d
atab
ase,
d
o
cu
m
en
t
r
ep
r
esen
tat
io
n
m
o
d
u
le,
an
d
th
e
P
atter
n
d
etec
tio
n
m
o
d
u
le.
T
h
e
s
y
s
te
m
ar
ch
itectu
r
e
is
laid
o
u
t
in
th
e
Fi
g
u
r
e
2
.
T
h
e
p
r
o
p
o
s
ed
f
r
a
m
e
w
o
r
k
co
n
s
is
t
s
o
f
t
h
e
p
r
esen
tat
io
n
la
y
er
,
b
u
s
in
e
s
s
lo
g
ic
la
y
er
a
n
d
t
h
e
d
ata
la
y
er
,
all
h
av
in
g
th
eir
r
o
les
i
n
th
e
to
tal
f
u
n
ctio
n
al
it
y
o
f
t
h
e
s
y
s
te
m
.
Fi
g
u
r
e
3
p
r
esen
t
s
th
e
th
r
ee
-
t
ier
s
h
o
w
i
n
g
t
h
e
d
if
f
er
en
t
la
y
er
s
an
d
t
h
eir
in
ter
ac
tio
n
s
.
-
P
r
esen
tatio
n
l
a
y
er
Fro
m
t
h
is
la
y
er
,
u
s
er
s
ca
n
i
n
p
u
t
a
q
u
er
y
a
n
d
r
ec
eiv
e
a
r
e
s
p
o
n
s
e
to
t
h
eir
q
u
er
y
.
T
h
is
la
y
er
c
an
n
o
t
ca
r
r
y
o
u
t
co
m
p
u
tatio
n
s
o
n
it
s
o
w
n
,
b
u
t
it
in
ter
ac
ts
w
i
th
t
h
e
b
u
s
i
n
e
s
s
lo
g
ic
la
y
er
th
r
o
u
g
h
t
h
e
Dj
an
g
o
w
eb
f
r
a
m
e
w
o
r
k
to
p
r
o
v
id
e
m
o
r
e
f
u
n
ct
io
n
alitie
s
.
-
B
u
s
i
n
ess
lo
g
ic
la
y
er
T
h
is
la
y
er
co
n
s
i
s
ts
o
f
t
h
e
P
y
t
h
o
n
ap
p
licatio
n
,
w
h
ich
p
r
o
v
id
es
t
h
e
f
u
n
ctio
n
alitie
s
to
t
h
e
p
r
esen
tat
io
n
la
y
er
.
I
t
also
in
t
er
ac
ts
w
it
h
th
e
d
ata
lay
er
th
r
o
u
g
h
p
y
t
h
o
n
SQ
L
ite
co
n
n
ec
to
r
to
p
r
o
ce
s
s
n
ec
ess
ar
y
d
ata
u
s
e
f
u
l
f
o
r
th
e
w
o
r
k
i
n
g
o
f
t
h
e
s
y
s
te
m
.
T
h
e
Gen
s
i
m
l
ib
r
ar
y
i
s
a
p
y
t
h
o
n
lib
r
ar
y
th
at
i
s
u
s
ed
f
o
r
d
o
cu
m
en
t
r
ep
r
esen
tatio
n
i
m
p
le
m
en
ta
tio
n
w
h
ile
t
h
e
n
at
u
r
al
lan
g
u
ag
e
to
o
l
k
it
h
a
n
d
les
n
atu
r
al
la
n
g
u
a
g
e
co
m
p
u
tatio
n
s
.
T
h
e
DB
p
ed
ia
an
d
W
o
r
d
Net
o
n
to
lo
g
y
i
s
u
s
ed
f
o
r
s
e
m
a
n
tical
l
y
a
n
n
o
tati
n
g
d
o
cu
m
en
ts
.
-
Data
la
y
er
T
h
is
is
th
e
la
y
er
w
h
er
e
all
th
e
in
f
o
r
m
atio
n
n
ee
d
s
o
f
th
e
s
y
s
te
m
ar
e
s
to
r
ed
.
SQL
ite
i
s
u
s
ed
as
th
e
d
atab
ase
m
a
n
a
g
e
m
e
n
t s
y
s
t
e
m
p
latf
o
r
m
f
o
r
s
to
r
in
g
an
d
m
an
ag
i
n
g
r
ec
o
r
d
s
o
f
in
d
iv
id
u
al
r
ev
ie
w
er
s
.
T
h
e
d
ata
la
y
er
co
m
m
u
n
icate
s
w
it
h
th
e
b
u
s
i
n
es
s
lo
g
ic
la
y
er
th
r
o
u
g
h
p
y
t
h
o
n
SQ
L
i
te
co
n
n
ec
to
r
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
S
ema
n
tics
-
b
a
s
ed
clu
s
teri
n
g
a
p
p
r
o
a
ch
fo
r
s
imila
r
r
esea
r
ch
a
r
ea
d
etec
tio
n
(
Ma
r
io
n
Olu
w
a
b
u
n
mi
A
d
eb
iyi
)
1879
D
a
t
a
D
a
ta
S
o
ur
c
e
s
D
oc
um
e
nt
R
e
pr
e
s
e
nt
a
t
i
on
K
no
w
l
e
dg
e
D
i
s
cov
e
r
y
F
i
nd
G
r
oup
s
La
be
l
Gr
oups
D
a
t
a
R
e
t
r
i
e
v
a
l
P
u
bl
i
ca
t
i
on
D
a
t
a
b
a
s
e
P
a
tt
e
r
n
D
e
t
e
c
ti
o
n
C
o
nc
e
p
t
W
e
i
g
ht
i
ng
D
a
t
a
E
x
t
r
a
ct
i
on
Fig
u
r
e
2
.
P
r
o
p
o
s
ed
f
r
am
e
w
o
r
k
U
s
e
r
i
nt
e
r
f
a
c
e
B
r
o
w
s
e
r
ap
pl
i
c
at
i
o
n
D
ja
n
g
o
F
r
am
e
wor
k
P
r
e
s
e
nt
a
t
i
o
n
La
y
e
r
B
us
i
n
e
s
s
Log
i
c
La
y
e
r
D
a
ta
L
a
y
e
r
S
Q
L
i
te
D
a
ta
ba
s
e
R
e
c
o
r
d
o
f
R
e
s
e
a
r
c
he
r
i
nf
o
r
m
a
ti
o
n
G
e
ns
i
m
l
i
br
ar
y
N
L
T
K
P
y
tho
n
S
Q
L
i
te
C
o
nn
e
c
to
r
P
y
thon
H
T
ML
,
C
S
S
D
bp
e
di
a
a
nd
W
or
d
N
e
t
O
nto
l
og
y
Fig
u
r
e
3
.
T
h
r
ee
-
tier
ar
ch
itectu
r
e
4.
1
.
Act
i
v
it
y
d
ia
g
r
a
m
I
n
Fi
g
u
r
e
4
,
th
e
f
lo
w
o
f
ac
tiv
i
ties
i
n
s
i
m
ilar
r
esear
c
h
ar
ea
d
etec
tio
n
is
s
h
o
w
n
.
T
h
e
d
iag
r
a
m
d
is
p
la
y
s
th
e
f
lo
w
o
f
ac
tiv
ities
b
et
w
ee
n
t
h
e
u
s
er
an
d
t
h
e
s
y
s
te
m
.
T
h
e
f
lo
w
o
f
ac
t
iv
i
ties
i
n
cl
u
d
es
:
r
eg
is
tr
at
io
n
,
lo
g
i
n
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
1
8
7
4
-
1
8
8
3
1880
u
p
lo
ad
in
g
a
n
e
x
is
ti
n
g
p
u
b
licat
io
n
,
th
e
s
y
s
te
m
r
ec
o
m
m
en
d
s
s
i
m
ilar
p
u
b
licat
io
n
s
,
t
h
e
u
s
er
c
h
ec
k
s
t
h
e
r
esear
ch
ar
ea
,
th
e
r
esu
lt
i
s
d
is
p
la
y
ed
,
i
f
th
e
u
s
er
is
n
o
t
p
leased
w
it
h
t
h
e
r
esu
lt,
th
e
u
s
er
w
ill
b
e
r
ed
ir
ec
ted
to
th
e
s
i
m
ilar
r
esear
ch
ar
ea
p
ag
e
to
ad
j
u
s
t th
e
u
p
lo
ad
ed
p
u
b
licatio
n
.
E
n
te
r
R
e
g
i
s
t
r
at
i
o
n
da
t
a
L
og
i
n
V
i
e
w
U
s
e
r
P
age
U
pl
o
a
d
pu
b
l
i
c
a
ti
o
n
U
pl
oa
d
pub
l
i
c
a
ti
o
n
f
o
r
s
i
m
i
l
a
r
i
ty
c
he
c
k
S
ta
r
t
N
e
w
U
s
e
r
D
i
s
p
l
a
y
R
e
s
ul
ts
D
i
s
p
l
a
y
R
e
s
ul
ts
C
h
e
c
k
f
o
r
s
i
m
i
l
a
r
pub
l
i
c
a
ti
ons
i
n
r
e
pos
i
to
r
y
C
h
e
c
k
f
o
r
s
i
m
i
l
a
r
pub
l
i
c
a
ti
ons
i
n
r
e
po
s
i
to
r
y
Y
e
s
No
Fig
u
r
e
4
.
A
cti
v
it
y
d
iag
r
a
m
4.
2
.
Sequ
ence
dia
g
ra
m
Seq
u
en
ce
d
iag
r
a
m
s
m
o
d
el
th
e
d
y
n
a
m
ic
b
e
h
av
io
u
r
o
f
a
s
y
s
te
m
;
t
h
e
y
ar
e
i
n
ter
ac
ti
v
e
d
ia
g
r
a
m
s
t
h
at
d
ep
ict
th
e
p
ass
in
g
o
f
m
e
s
s
a
g
es
b
et
w
ee
n
o
b
j
ec
ts
in
a
s
y
s
t
e
m
.
T
h
e
m
es
s
ag
e
s
ar
e
p
ass
ed
f
r
o
m
th
e
u
s
er
to
th
e
r
eg
is
tr
atio
n
m
o
d
u
le,
an
d
f
r
o
m
th
e
r
eg
is
tr
atio
n
m
o
d
u
le
to
th
e
d
atab
ase
an
d
b
ac
k
to
th
e
u
s
er
to
d
is
p
la
y
a
s
u
cc
ess
f
u
l
r
eg
is
tr
atio
n
.
Fig
u
r
e
5
s
h
o
w
s
th
e
s
eq
u
en
ce
d
iag
r
a
m
o
f
th
e
s
i
m
ilar
r
esear
ch
p
u
b
licatio
n
d
is
co
v
er
y
p
r
o
ce
s
s
an
d
h
o
w
m
e
s
s
a
g
es
ar
e
ex
ch
a
n
g
ed
b
et
w
ee
n
th
e
d
i
f
f
er
en
t
m
o
d
u
les
f
r
o
m
th
e
u
s
er
to
th
e
p
u
b
licat
io
n
r
ep
o
s
ito
r
y
an
d
b
ac
k
to
t
h
e
u
s
e
r
w
it
h
th
e
r
es
u
lt o
f
th
e
m
es
s
ag
e
p
ass
ed
ac
r
o
s
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
S
ema
n
tics
-
b
a
s
ed
clu
s
teri
n
g
a
p
p
r
o
a
ch
fo
r
s
imila
r
r
esea
r
ch
a
r
ea
d
etec
tio
n
(
Ma
r
io
n
Olu
w
a
b
u
n
mi
A
d
eb
iyi
)
1881
U
s
e
r
Si
m
i
l
a
r
i
t
y
C
o
m
p
u
t
a
t
i
o
n
R
e
t
r
i
e
va
l
P
u
b
l
i
ca
t
i
o
n
R
e
p
o
s
i
t
o
r
y
U
pl
oa
ds
publ
i
ca
t
i
o
n
S
i
m
i
l
a
r
i
t
y
C
om
pu
t
a
t
i
on
R
e
t
r
i
e
v
e
P
ub
l
i
c
a
t
i
ons
R
e
t
r
i
e
v
e
d
P
ub
l
i
ca
t
i
on
s
D
i
s
pl
a
y
S
I
m
i
l
a
r
pu
bl
i
ca
t
i
o
ns
Fig
u
r
e
5
.
Seq
u
en
ce
d
iag
r
a
m
f
o
r
s
i
m
ilar
p
u
b
licatio
n
d
is
co
v
er
y
5.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
5
.
1
.
E
x
peri
m
ent
a
l
r
esu
lt
s
T
h
e
elb
o
w
cu
r
v
e
w
a
s
u
s
ed
to
v
alid
ate
t
h
e
o
p
ti
m
a
l
n
u
m
b
er
o
f
cl
u
s
ter
s
b
ef
o
r
eh
a
n
d
,
w
e
u
s
ed
a
r
an
g
e
o
f
v
alu
e
s
o
f
K
an
d
s
elec
ted
th
e
o
p
tim
al
v
al
u
e
b
ased
o
n
th
e
elb
o
w
cu
r
v
e
o
f
th
e
clu
s
ter
s
.
T
h
e
ev
alu
atio
n
o
f
th
e
cl
u
s
ter
s
g
en
er
ated
w
a
s
p
er
f
o
r
m
ed
u
s
i
n
g
Sil
h
o
u
e
tte
a
n
al
y
s
is
,
w
h
ic
h
r
ev
ea
led
a
h
i
g
h
le
v
el
o
f
ac
c
u
r
ac
y
a
n
d
co
n
s
is
ten
c
y
as
ev
id
en
ce
d
b
y
an
av
er
ag
e
8
0
%
s
il
h
o
u
e
tte
s
c
o
r
e
f
o
r
all
th
e
d
ata
p
o
in
ts
as
s
h
o
w
n
in
Fi
g
u
r
e
6
.
T
h
e
f
ig
u
r
e
s
h
o
w
s
th
at
t
h
e
n
u
m
b
er
o
f
clu
s
ter
s
i
n
cr
ea
s
es
w
i
th
t
h
e
s
co
r
es.
Fig
u
r
e
6
.
E
v
alu
atio
n
r
esu
lt
s
6.
CO
NCLU
SI
O
N
I
n
th
i
s
w
o
r
k
,
a
p
r
o
to
t
y
p
e
s
y
s
t
e
m
w
as
d
ev
elo
p
ed
to
p
r
o
v
id
e
a
p
latf
o
r
m
f
o
r
en
h
an
c
in
g
co
ll
ab
o
r
atio
n
s
b
et
w
ee
n
r
esear
ch
er
s
i
n
a
r
esear
ch
f
ield
b
y
e
n
ab
li
n
g
a
r
esear
c
h
er
to
id
en
ti
f
y
o
th
er
r
esear
c
h
er
s
in
a
g
i
v
en
r
esear
ch
f
ield
.
A
r
ig
o
r
o
u
s
r
ev
ie
w
o
f
t
h
e
liter
atu
r
e
w
as
co
n
d
u
cted
t
o
ex
a
m
i
n
e
ex
i
s
ti
n
g
ap
p
r
o
ac
h
es
th
a
t
h
av
e
b
ee
n
u
tili
ze
d
in
d
is
co
v
er
i
n
g
s
i
m
i
lar
r
esear
ch
ar
ea
s
,
th
is
s
t
u
d
y
u
ti
lized
an
ap
p
r
o
ac
h
in
v
o
lv
in
g
th
e
u
s
e
o
f
p
u
b
licatio
n
d
o
cu
m
e
n
ts
s
h
ar
i
n
g
ce
r
ta
in
k
e
y
w
o
r
d
s
.
R
a
n
d
o
m
l
y
s
elec
ted
Nig
er
ia
n
U
n
i
v
er
s
it
y
p
u
b
licat
io
n
d
o
cu
m
e
n
ts
f
r
o
m
2
0
1
0
to
2
0
1
8
w
er
e
r
etr
iev
ed
an
d
u
s
ed
as
a
ca
s
e
s
tu
d
y
.
T
h
is
ap
p
r
o
ac
h
w
as
m
o
d
eled
as
a
clu
s
ter
in
g
p
r
o
b
lem
.
I
n
o
r
d
er
t
o
i
m
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
th
e
cl
u
s
ter
i
n
g
r
es
u
lt
s
,
th
e
DB
p
ed
ia
a
n
d
W
o
r
d
Net
o
n
to
lo
g
y
w
as
u
s
e
d
to
ca
p
tu
r
e
d
o
m
ain
ter
m
s
a
n
d
s
e
m
a
n
tical
l
y
r
ela
t
e
d
ter
m
s
in
th
e
p
u
b
licatio
n
d
at
aset
u
s
ed
.
L
SI
a
n
d
T
F
-
I
DF
wer
e
u
s
ed
to
m
o
d
el
th
e
te
x
t
d
o
cu
m
e
n
t
s
an
d
g
en
e
r
ate
f
ea
tu
r
e
v
ec
to
r
s
.
T
h
e
K
-
Me
an
s
cl
u
s
ter
in
g
al
g
o
r
ith
m
w
a
s
u
s
ed
to
clu
s
ter
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
1
8
7
4
-
1
8
8
3
1882
th
e
f
ea
t
u
r
e
v
ec
to
r
s
.
T
h
e
clu
s
ter
in
g
r
es
u
lts
w
er
e
ev
al
u
ated
u
s
in
g
th
e
s
i
lh
o
u
e
tte
an
al
y
s
i
s
tech
n
iq
u
e,
w
h
ic
h
r
ev
ea
led
a
h
ig
h
i
n
tr
a
-
c
lu
s
ter
s
i
m
ilar
it
y
o
f
0
.
8
o
n
th
e
a
v
er
ag
e
ac
r
o
s
s
all
th
e
d
ata
p
o
in
ts
.
A
p
r
o
to
ty
p
e
s
y
s
te
m
w
a
s
d
ev
elo
p
ed
u
s
in
g
P
y
th
o
n
p
r
o
g
r
a
m
m
in
g
lan
g
u
ag
e,
w
h
ile
SQ
L
ite
Data
b
ase
Ma
n
ag
e
m
e
n
t
S
y
s
te
m
w
as
u
s
ed
to
m
an
a
g
e
t
h
e
d
ata
b
ase.
Ou
r
r
es
u
lts
s
h
o
w
t
h
at
t
h
e
p
r
o
to
t
y
p
e
s
y
s
te
m
s
h
o
w
ed
h
i
g
h
cl
u
s
ter
i
n
g
ac
cu
r
ac
y
a
n
d
co
u
ld
b
e
d
ep
lo
y
ed
f
o
r
lar
g
e
s
ca
le
u
t
i
lizatio
n
.
7.
CO
NT
RIB
U
T
I
O
N
T
O
K
NO
WL
E
D
G
E
T
h
is
w
o
r
k
co
n
tr
ib
u
tes
to
t
h
e
ex
is
ti
n
g
b
o
d
y
o
f
k
n
o
w
led
g
e
b
y
d
ev
elo
p
i
n
g
a
p
r
o
to
t
y
p
e
s
y
s
te
m
t
h
at
in
te
g
r
ates
o
n
to
lo
g
y
-
b
a
s
ed
p
r
e
-
p
r
o
ce
s
s
i
n
g
,
L
aten
t
Se
m
a
n
tic
I
n
d
ex
in
g
an
d
K
-
Me
an
s
clu
s
ter
in
g
to
d
is
co
v
er
s
i
m
ilar
r
esear
ch
d
o
m
ai
n
p
u
b
li
ca
tio
n
s
.
T
h
e
s
y
s
te
m
d
eter
m
i
n
es
th
e
s
i
m
ilar
it
y
b
et
w
ee
n
p
u
b
licatio
n
d
o
cu
m
e
n
ts
u
s
i
n
g
s
e
m
an
t
ic
s
i
m
ilar
it
y
tec
h
n
iq
u
e
s
.
T
h
e
clu
s
ter
in
g
r
es
u
lts
s
h
o
w
an
i
m
p
r
o
v
e
m
en
t
t
h
r
o
u
g
h
th
e
u
s
e
o
f
o
n
to
lo
g
y
s
e
m
a
n
tic
s
i
n
p
r
e
-
p
r
o
ce
s
s
i
n
g
th
e
d
o
cu
m
e
n
ts
.
I
t
i
s
al
s
o
b
eliev
e
d
th
at
t
h
is
ap
p
r
o
ac
h
w
i
ll
b
e
u
s
ef
u
l
f
o
r
u
n
ea
r
t
h
i
n
g
h
id
d
en
an
d
i
m
p
licit p
atter
n
s
in
th
e
d
o
cu
m
e
n
t d
ataset.
8.
RE
CO
M
M
E
NDATI
O
N
S A
ND
F
UT
UR
E
WO
RK
Fo
r
th
e
s
y
s
te
m
to
b
e
co
n
tin
u
o
u
s
l
y
r
elev
a
n
t,
th
e
p
u
b
lica
tio
n
r
ep
o
s
ito
r
y
w
ill
h
av
e
to
u
n
d
er
g
o
r
eg
u
lar
u
p
d
ates
to
i
m
p
r
o
v
e
t
h
e
r
o
b
u
s
t
n
ess
o
f
t
h
e
s
y
s
te
m
.
He
n
ce
,
f
o
r
f
u
tu
r
e
i
m
p
r
o
v
e
m
en
ts
i
n
t
h
is
r
es
ea
r
ch
,
th
e
f
o
llo
w
in
g
r
ec
o
m
m
e
n
d
atio
n
s
ar
e
p
r
o
p
o
s
ed
:
-
T
h
e
s
y
s
te
m
ca
n
b
e
in
teg
r
ated
w
it
h
lo
ca
ll
y
av
ai
lab
le
co
n
f
er
en
ce
an
d
j
o
u
r
n
al
p
u
b
licatio
n
r
ep
o
s
ito
r
ies
to
p
r
o
v
id
e
s
i
m
ilar
r
esear
ch
ar
ea
d
etec
tio
n
s
er
v
ice
s
.
-
T
o
im
p
r
o
v
e
t
h
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
s
ta
g
e,
a
n
o
n
to
lo
g
y
lear
n
i
n
g
m
o
d
el
ca
n
b
e
i
n
co
r
p
o
r
ated
in
to
th
e
co
n
ce
p
t
o
f
w
ei
g
h
tin
g
a
n
d
co
n
ce
p
t
-
d
o
cu
m
e
n
t
co
n
s
tr
u
ctio
n
s
ta
g
e
to
p
r
o
d
u
ce
d
o
m
ai
n
o
n
to
lo
g
i
es
p
er
tin
e
n
t
to
th
e
p
u
b
licatio
n
tex
t c
o
r
p
u
s
.
-
Oth
er
d
o
cu
m
en
t
cl
u
s
ter
i
n
g
alg
o
r
ith
m
s
co
u
ld
b
e
u
ti
lized
,
s
u
c
h
as
B
i
s
ec
ti
n
g
K
-
m
ea
n
s
a
n
d
K
-
m
ed
o
id
s
alg
o
r
ith
m
.
-
T
h
e
u
s
e
o
f
s
o
m
e
o
t
h
er
d
o
cu
m
en
t
r
ep
r
esen
ta
tio
n
tec
h
n
iq
u
es
s
u
c
h
as
W
o
r
d
2
Vec
o
r
R
ec
u
r
r
en
t
Ne
u
r
al
Net
w
o
r
k
L
a
n
g
u
a
g
e
ca
n
b
e
u
s
ed
to
im
p
r
o
v
e
th
e
s
e
m
a
n
tic
s
i
m
ilar
it
y
co
m
p
u
tatio
n
a
n
d
f
u
r
t
h
er
ca
p
tu
r
e
th
e
i
m
p
l
icit se
m
a
n
tics
o
f
th
e
t
ex
t c
o
r
p
u
s
.
ACK
NO
WL
E
D
G
M
E
NT
S
T
h
is
r
esear
ch
is
f
u
ll
y
s
p
o
n
s
o
r
ed
b
y
L
a
n
d
m
ar
k
Un
i
v
er
s
i
t
y
C
en
tr
e
f
o
r
R
esear
ch
a
n
d
Dev
elo
p
m
e
n
t,
L
a
n
d
m
ar
k
Un
iv
er
s
it
y
,
O
m
u
-
Ar
an
,
Nig
er
ia
a
n
d
C
o
v
e
n
an
t
Un
iv
er
s
it
y
f
o
r
R
esear
c
h
a
n
d
Dis
co
v
er
y
(
C
U
C
R
I
D)
f
o
r
th
eir
i
m
m
e
n
s
e
s
u
p
p
o
r
t in
t
h
is
r
esear
c
h
.
RE
F
E
R
E
NC
E
S
[1
]
Ca
g
li
e
ro
L
.
,
Ch
iu
sa
n
o
S
.
,
G
a
rz
a
P
.
,
Bru
n
o
G
.
,
“
P
a
tt
e
r
n
se
t
m
in
in
g
w
it
h
sc
h
e
m
a
-
b
a
s
e
d
c
o
n
stra
in
t
,”
K
n
o
wled
g
e
-
Ba
se
d
S
y
ste
ms
,
v
o
l.
84
,
p
p
.
2
2
4
-
38
,
2
0
1
5
.
[2
]
Na
ik
M
.
P
.
,
P
ra
jap
a
ti
H
.
B
.
,
Da
b
h
i
V
.
K.
,
“
A
su
rv
e
y
o
n
se
m
a
n
ti
c
d
o
c
u
m
e
n
t
c
lu
ste
rin
g
,”
2
0
1
5
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
trica
l,
Co
mp
u
ter
a
n
d
Co
mm
u
n
ica
ti
o
n
T
e
c
h
n
o
l
o
g
ies
(
ICECCT
)
,
2
0
1
5
.
[3
]
S
z
c
z
u
k
a
M
.
,
Ja
n
u
sz
A
.
,
He
rb
a
K.
,
“
Clu
ste
rin
g
o
f
ro
u
g
h
se
t
re
late
d
d
o
c
u
m
e
n
ts
w
it
h
u
se
o
f
k
n
o
w
led
g
e
fro
m
DB
p
e
d
ia
,”
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
R
o
u
g
h
S
e
ts a
n
d
K
n
o
w
led
g
e
T
e
c
h
n
o
lo
g
y
,
2
0
1
1
.
[4
]
W
a
n
g
Y.,
S
o
n
g
S
.
,
Zh
o
u
F
.
,
Zh
e
n
g
X
.
,
“
Ch
in
e
se
W
e
Ch
a
t
a
n
d
Blo
g
Ho
t
W
o
rd
s
De
tec
ti
o
n
M
e
th
o
d
B
a
se
d
o
n
C
h
in
e
se
S
e
m
a
n
ti
c
Clu
ste
rin
g
,”
In
telli
g
e
n
t
Au
to
m
a
ti
o
n
a
n
d
S
o
ft
Co
mp
u
ti
n
g
,
v
o
l.
23
,
n
o
.
4
,
p
p
.
6
1
3
–
6
1
8
,
2
0
1
7
.
[5
]
V
e
ld
e
n
,
T
h
e
re
sa
,
Bo
y
a
c
k
,
Ke
v
in
,
G
las
e
r,
Jo
c
h
e
n
,
K
o
o
p
m
a
n
,
Ro
b
,
S
c
h
a
rn
h
o
rst,
A
n
d
re
a
,
W
a
n
g
,
S
h
e
n
g
h
u
i
,
“
Co
m
p
a
riso
n
o
f
to
p
ic ex
trac
ti
o
n
a
p
p
r
o
a
c
h
e
s a
n
d
t
h
e
ir
re
su
lt
s
,
”
S
c
ien
to
me
trics
,
v
o
l
.
1
1
1
,
p
p
.
1
1
6
9
-
1
2
2
1
,
2
0
1
7
.
[6
]
W
a
n
g
,
S
h
e
n
g
h
u
i
,
Ko
o
p
m
a
n
,
Ro
b
.
,
“
Cl
u
ste
rin
g
a
rti
c
les
b
a
se
d
o
n
se
m
a
n
ti
c
sim
il
a
rit
y
,
”
S
c
ien
to
me
trics
,
v
o
l.
1
1
1
,
p
p
.
1
0
1
7
-
3
1
,
2
0
1
7
.
[7
]
Na
ik
M
.
P
.
,
P
ra
jap
a
ti
H.
B.
,
Da
b
h
i
V
.
K.
,
“
A
su
rv
e
y
o
n
se
m
a
n
ti
c
d
o
c
u
m
e
n
t
c
lu
ste
rin
g
,
”
Pr
o
c
e
e
d
in
g
s
o
f
2
0
1
5
IEE
E
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
E
lec
trica
l,
Co
m
p
u
ter
a
n
d
Co
mm
u
n
ica
ti
o
n
T
e
c
h
n
o
lo
g
ies
,
2
0
1
5
.
[8
]
Yu
a
n
X
,
S
u
n
M
,
C
h
e
n
Z,
G
a
o
J,
L
i
P
.
,
“
S
e
m
a
n
ti
c
c
lu
ste
rin
g
-
b
a
se
d
d
e
e
p
h
y
p
e
rg
ra
p
h
m
o
d
e
l
f
o
r
o
n
li
n
e
r
e
v
ie
w
s
s
e
m
a
n
ti
c
c
las
si
f
ica
ti
o
n
in
c
y
b
e
r
-
p
h
y
sic
a
l
-
s
o
c
ial
sy
st
e
m
s,”
IEE
E
Acc
e
ss
,
v
o
l.
6
,
p
p
.
1
7
9
4
2
-
5
1
,
2
0
1
8
.
[9
]
F
a
h
a
d
S
.
A
.
,
Ya
f
o
o
z
W
.
M
.
,
“
De
sig
n
a
n
d
d
e
v
e
lo
p
se
m
a
n
ti
c
tex
tu
a
l
d
o
c
u
m
e
n
t
c
lu
ste
ri
n
g
m
o
d
e
l,
”
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
3
.
n
o
.
2
,
p
p
.
2
6
-
3
9
,
2
0
1
7
.
[1
0
]
M
a
h
a
jan
S
.
,
S
h
a
h
N.,
“
Ef
f
icie
n
t
p
re
-
p
ro
c
e
ss
in
g
f
o
r
e
n
h
a
n
c
e
d
se
m
a
n
ti
c
s b
a
se
d
d
istr
ib
u
ted
d
o
c
u
m
e
n
t
c
l
u
ste
rin
g
,
”
2
0
1
6
3
rd
I
n
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Co
mp
u
t
in
g
f
o
r S
u
sta
i
n
a
b
le Glo
b
a
l
De
v
e
lo
p
me
n
t,
2
0
1
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
S
ema
n
tics
-
b
a
s
ed
clu
s
teri
n
g
a
p
p
r
o
a
ch
fo
r
s
imila
r
r
esea
r
ch
a
r
ea
d
etec
tio
n
(
Ma
r
io
n
Olu
w
a
b
u
n
mi
A
d
eb
iyi
)
1883
[1
1
]
Ola
d
e
le
T
.
O.,
A
ro
T
.
O.,
A
d
e
g
u
n
A
.
A
.
,
O
g
u
n
d
o
k
u
n
R.
O.,
“
P
re
d
ictio
n
o
f
S
tu
d
e
n
t'
s
A
c
a
d
e
m
i
c
P
e
rf
o
r
m
a
n
c
e
u
sin
g
K
-
m
e
n
a
s
Clu
ste
rin
g
a
n
d
M
u
lt
i
p
le
L
in
e
a
r
Re
g
re
ss
io
n
s,”
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
Ap
p
li
e
d
S
c
ien
c
e
s
,
v
o
l.
1
4
,
n
o
.
2
2
,
p
p
.
8
2
5
4
-
8
2
6
0
,
2
0
1
9
.
[1
2
]
Zh
a
n
g
H.,
W
a
n
g
D.,
W
a
n
g
L
.
,
Zh
u
m
in
g
Bi.
,
Yo
n
g
Ch
e
n
,
“
A
se
m
a
n
ti
c
s
-
b
a
se
d
m
e
th
o
d
f
o
r
c
lu
ste
rin
g
o
f
Ch
in
e
se
w
e
b
se
a
rc
h
re
su
lt
s,”
En
ter
p
rise
In
f
o
rm
a
ti
o
n
S
y
ste
ms
,
v
o
l.
8
,
n
o
.
1
,
p
p
.
1
4
7
-
6
5
,
2
0
1
4
.
[1
3
]
S
o
li
m
a
n
S
.
S
.
,
El
-
S
a
y
e
d
M
.
F
.
,
Ha
ss
a
n
Y.
F
.
,
“
S
e
m
a
n
ti
c
c
lu
ste
rin
g
o
f
se
a
rc
h
e
n
g
in
e
re
su
lt
s,”
T
h
e
S
c
ien
ti
fi
c
W
o
rld
J
o
u
rn
a
l,
v
o
l
.
2
0
1
5
,
p
p
.
1
-
9
,
2
0
1
5
.
[1
4
]
Ola
d
e
le
T
.
,
A
d
e
g
u
n
A
.
,
Og
u
n
d
o
k
u
n
R.
O
.,
k
e
y
in
k
a
A
.
,
Ay
e
n
i
L
.
,
“
A
p
p
li
c
a
ti
o
n
o
f
F
l
o
y
d
-
Wars
h
a
ll
’s
A
l
g
o
rit
h
m
in
A
ir
F
re
ig
h
t
S
e
rv
ice
in
Nig
e
ria,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
in
e
e
rin
g
Res
e
a
rc
h
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
1
2
,
n
o
.
1
2
,
p
p
.
2
5
2
9
-
2
5
3
5
,
2
0
1
9
.
[1
5
]
Yu
e
L
.
,
Zu
o
W
.
,
P
e
n
g
T
.
,
W
a
n
g
Y.,
Ha
n
X
.
,
“
A
f
u
z
z
y
d
o
c
u
m
e
n
t
c
lu
ste
rin
g
a
p
p
r
o
a
c
h
b
a
se
d
o
n
d
o
m
a
in
-
sp
e
c
i
f
ied
o
n
t
o
lo
g
y
,
”
Da
ta
&
Kn
o
wled
g
e
En
g
in
e
e
rin
g
,
v
o
l
.
1
0
0
,
p
p
.
4
8
-
6
6
,
2
0
1
5
.
[1
6
]
S
u
lt
h
a
n
a
A
.
R.
,
S
u
b
b
u
ra
j
R.
,
“
A
n
i
m
p
ro
v
ise
d
o
n
to
l
o
g
y
-
b
a
s
e
d
K
-
m
e
a
n
s
c
lu
ste
rin
g
a
p
p
ro
a
c
h
f
o
r
c
las
si
f
ica
ti
o
n
o
f
c
u
sto
m
e
r
re
v
i
e
w
s,”
In
d
ia
n
J
o
u
r
n
a
l
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
9
,
n
o
.
1
5
,
p
p
.
1
-
6
,
2
0
1
6
.
[1
7
]
M
a
k
a
ro
v
I.
,
Bu
la
n
o
v
O.,
Z
h
u
k
o
v
L
.
E.
,
“
Co
-
a
u
th
o
r
re
c
o
m
m
e
n
d
e
r
sy
ste
m
,
”
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ne
two
rk
An
a
lys
is
NE
T
2
0
1
6
:
M
o
d
e
ls,
Al
g
o
rith
ms
,
a
n
d
T
e
c
h
n
o
lo
g
ies
fo
r
Ne
two
rk
An
a
lys
is
,
p
p
.
2
5
1
-
2
5
7
,
2
0
1
6
.
[
1
8
]
S
u
m
b
a
X
.
,
S
u
m
b
a
F
.
,
T
e
l
l
o
A
.
,
B
a
c
u
l
i
m
a
F
.
,
E
s
p
i
n
o
z
a
M
.
,
S
a
q
u
i
c
e
l
a
V
.
,
“
D
e
t
e
c
t
i
n
g
s
i
m
i
l
a
r
a
r
e
a
s
o
f
k
n
o
w
l
e
d
g
e
u
s
i
n
g
s
e
m
a
n
t
i
c
a
n
d
d
a
t
a
m
i
n
i
n
g
t
e
c
h
n
o
l
o
g
i
e
s
,
”
E
l
e
c
t
r
o
n
i
c
N
o
t
e
s
i
n
T
h
e
o
r
e
t
i
c
a
l
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
2
9
,
p
p
.
1
4
9
-
6
7
,
2
0
1
6
.
[1
9
]
A
ru
m
a
wa
d
u
H.
I.
,
Ra
th
n
a
y
a
k
a
R.
M
.
K.
T
.
,
Ill
a
n
g
a
ra
th
n
e
S
.
K.
,
“
M
i
n
in
g
p
r
o
f
it
a
b
il
it
y
o
f
tele
c
o
m
m
u
n
i
c
a
ti
o
n
c
u
sto
m
e
rs
u
sin
g
k
-
m
e
a
n
s c
lu
ste
rin
g
,
”
J
o
u
rn
a
l
o
f
Da
t
a
A
n
a
lys
is
a
n
d
In
fo
rm
a
t
i
o
n
Pr
o
c
e
ss
in
g
,
v
o
l.
3
,
n
o
.
3
,
p
p
.
6
3
–
7
1
,
2
0
1
5
.
[2
0
]
Aw
o
tu
n
d
e
J.
B.
,
Og
u
n
d
o
k
u
n
R.
O.,
Ay
o
F
.
,
A
ja
m
u
G
.
J.,
A
d
e
n
i
y
i
E.
,
Og
u
n
d
o
k
u
n
E.
O.,
“
S
o
c
ial
M
e
d
ia
Ac
c
e
p
tan
c
e
a
n
d
Us
e
Am
o
n
g
Un
iv
e
rsit
y
S
tu
d
e
n
ts
f
o
r
L
e
a
rn
in
g
P
u
r
p
o
se
Us
in
g
UTAU
T
M
o
d
e
l,
”
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
fo
rm
a
t
io
n
S
y
ste
ms
Arc
h
it
e
c
tu
re
a
n
d
T
e
c
h
n
o
l
o
g
y
,
2
0
1
9
[2
1
]
Og
u
n
d
o
k
u
n
R.
O.,
A
d
e
b
iy
i,
M
.
O
.,
A
b
ik
o
y
e
,
O.
C.
,
Ola
d
e
le,
T
.
O.,
L
u
k
m
a
n
A
.
F.,
A
d
e
n
iy
i
A.
E.,
A
d
e
g
u
n
A.
A
.
,
G
b
a
d
a
m
o
si
B.
,
A
k
a
n
d
e
N.
O
.
,
“
Ev
a
lu
a
ti
o
n
o
f
th
e
sc
h
o
las
ti
c
p
e
rf
o
rm
a
n
c
e
o
f
stu
d
e
n
ts
i
n
1
2
p
ro
g
ra
m
s
f
ro
m
a
p
riv
a
te
u
n
iv
e
rsity
in
th
e
so
u
th
-
w
e
st g
e
o
p
o
li
ti
c
a
l
z
o
n
e
in
Ni
g
e
ria
,”
p
p
.
1
5
4
,
2
0
1
9
.
F
1
0
0
0
Re
se
a
rc
h
8
[
v
e
rsio
n
1
]
.
[2
2
]
Og
u
n
d
o
k
u
n
R.
O.
,
A
d
e
b
iy
i
M
.
O.,
A
b
ik
o
y
e
O.
C.
,
Ola
d
e
le
T
.
O.,
L
u
k
m
a
n
A
.
F.,
A
d
e
n
iy
i
A
.
E.,
A
d
e
g
u
n
A
.
A
.
,
G
b
a
d
a
m
o
si
B.
,
A
k
a
n
d
e
N.
O.
,
“
Ev
a
lu
a
ti
o
n
o
f
th
e
sc
h
o
las
ti
c
p
e
rf
o
rm
a
n
c
e
o
f
stu
d
e
n
ts
i
n
1
2
p
ro
g
ra
m
s
f
ro
m
a
p
riv
a
te
u
n
iv
e
rsity
in
th
e
so
u
th
-
w
e
st g
e
o
p
o
li
ti
c
a
l
z
o
n
e
in
Nig
e
ria
,
”
2
0
1
9
.
F
1
0
0
0
Re
se
a
rc
h
8
[
v
e
rsio
n
2
].
[2
3
]
Ola
d
e
le
T
.
O.,
Og
u
n
d
o
k
u
n
R.
O.,
Ka
y
o
d
e
A
.
A
.
,
A
d
e
g
u
n
A
.
A
.
,
A
d
e
b
i
y
i
M
.
O.,
“
A
p
p
li
c
a
ti
o
n
o
f
Da
ta
M
in
in
g
A
l
g
o
rit
h
m
s
f
o
r
F
e
a
tu
re
S
e
lec
ti
o
n
a
n
d
P
re
d
ictio
n
o
f
Dia
b
e
ti
c
Re
ti
n
o
p
a
th
y
,
”
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
mp
u
t
a
ti
o
n
a
l
S
c
ien
c
e
a
n
d
Its
A
p
p
li
c
a
ti
o
n
s,
2
0
1
9
.
[2
4
]
W
a
n
g
Y.,
S
o
n
g
S
.
,
Zh
o
u
F
.
,
Zh
e
n
g
X
.
,
“
Ch
in
e
se
W
e
Ch
a
t
a
n
d
Blo
g
Ho
t
W
o
rd
s
De
tec
ti
o
n
M
e
th
o
d
B
a
se
d
o
n
C
h
in
e
se
S
e
m
a
n
ti
c
Clu
ste
rin
g
,
”
In
telli
g
e
n
t
Au
to
m
a
ti
o
n
&
S
o
ft
Co
m
p
u
ti
n
g
,
v
o
l.
2
3
,
n
o
.
4
,
p
p
.
6
1
3
-
8
,
2
0
1
7
.
[2
5
]
Ch
u
a
n
P
.
M
.
,
A
li
M
.
,
Kh
a
n
g
T
.
D.,
De
y
N.,
“
L
in
k
p
re
d
ic
ti
o
n
i
n
c
o
-
a
u
th
o
rsh
i
p
n
e
tw
o
rk
s
b
a
se
d
o
n
h
y
b
rid
c
o
n
te
n
t
sim
il
a
rit
y
m
e
tri
c
,
”
Ap
p
li
e
d
I
n
telli
g
e
n
c
e
,
v
o
l.
4
8
,
n
o
.
8
,
p
p
.
2
4
7
0
-
8
6
,
2
0
1
8
.
[2
6
]
De
sh
m
u
k
h
A
.
,
H
e
g
d
e
G
.
,
L
a
th
i
R.
,
G
o
v
ik
a
rn
S
.
,
“
A
li
tera
tu
re
su
rv
e
y
o
n
late
n
t
se
m
a
n
ti
c
in
d
e
x
in
g
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
I
n
v
e
n
ti
o
n
s,”
v
o
l.
1
,
n
o
.
4
,
p
p
.
2
2
7
8
-
7
4
6
1
,
2
0
1
2
.
[2
7
]
S
h
a
f
iei
M
.
,
W
a
n
g
S
.
,
Z
h
a
n
g
R.
,
M
il
io
s
E
.
,
T
a
n
g
B.
,
T
o
u
g
a
s
J.,
S
p
it
e
ri
R.
,
“
Do
c
u
m
e
n
t
re
p
re
se
n
tatio
n
a
n
d
d
im
e
n
sio
n
re
d
u
c
ti
o
n
f
o
r
tex
t
c
lu
ste
rin
g
,
”
2
0
0
7
IEE
E
2
3
rd
i
n
ter
n
a
ti
o
n
a
l
c
o
n
fer
e
n
c
e
o
n
d
a
t
a
e
n
g
i
n
e
e
rin
g
wo
rk
sh
o
p
,
2
0
0
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.