I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
11
,
No
.
2
,
A
p
r
il
2
0
2
1
,
p
p
.
1
6
7
5
~
1
6
8
8
I
SS
N:
2
088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/
ijece
.
v
1
1
i
2
.
pp
1
6
7
5
-
1
6
8
8
1675
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Intellig
ent
ma
chi
ne f
o
r on
tolo
g
ica
l represen
tatio
n of
ma
ss
iv
e
peda
g
o
g
ica
l knowledg
e bas
ed on ne
ura
l net
wo
rks
Abdella
dim
H
a
dio
ui,
Ya
s
s
i
n
e
B
enj
ello
un
T
o
uim
i,
No
ur
-
eddin
e
E
l F
a
dd
o
uli
,
Sa
m
ir
B
e
nn
a
ni
RIM
E
TE
AM
-
Ne
two
r
k
in
g
,
M
o
d
e
li
n
g
a
n
d
e
-
Lea
rn
in
g
-
LRIE
La
b
o
ra
to
ry
-
Re
se
a
rc
h
in
C
o
m
p
u
ter S
c
ien
c
e
a
n
d
Ed
u
c
a
ti
o
n
Lab
o
ra
to
r
y
,
M
o
h
a
m
m
a
d
ia S
c
h
o
o
l
En
g
in
e
e
rs (E
M
I)
-
M
o
h
a
m
m
e
d
V
Un
iv
e
rsity
i
n
Ra
b
a
t
,
M
o
ro
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
2
4
,
2
0
2
0
R
ev
is
ed
Au
g
7
,
2
0
2
0
Acc
ep
ted
No
v
1
2
,
2
0
2
0
Hig
h
e
r
e
d
u
c
a
ti
o
n
is
i
n
c
re
a
sin
g
ly
in
teg
ra
ti
n
g
fre
e
lea
rn
in
g
m
a
n
a
g
e
m
e
n
t
sy
ste
m
s
(
LM
S
).
T
h
e
m
a
in
o
b
jec
ti
v
e
u
n
d
e
rly
i
n
g
su
c
h
sy
ste
m
s
i
n
t
e
g
ra
ti
o
n
is
th
e
a
u
to
m
a
ti
z
a
ti
o
n
o
f
o
n
li
n
e
e
d
u
c
a
ti
o
n
a
l
p
r
o
c
e
ss
e
s
fo
r
th
e
b
e
n
e
fit
o
f
a
ll
t
h
e
in
v
o
lv
e
d
a
c
to
rs
w
h
o
u
se
th
e
se
s
y
ste
m
s.
Th
e
sa
id
p
r
o
c
e
ss
e
s
a
re
d
e
v
e
lo
p
e
d
th
ro
u
g
h
t
h
e
in
teg
ra
ti
o
n
a
n
d
imp
l
e
m
e
n
tatio
n
o
f
lea
rn
i
n
g
sc
e
n
a
rio
s
sim
il
a
r
to
trad
it
io
n
a
l
lea
rn
in
g
sy
ste
m
s.
LM
S
p
r
o
d
u
c
e
b
i
g
d
a
ta
trac
e
s
e
m
e
rg
in
g
fr
o
m
a
c
to
rs’
in
tera
c
ti
o
n
s
i
n
o
n
li
n
e
le
a
rn
in
g
.
Ho
we
v
e
r,
we
n
o
te
t
h
e
a
b
se
n
c
e
o
f
in
stru
m
e
n
ts
a
d
e
q
u
a
te
fo
r
re
p
re
se
n
ti
n
g
k
n
o
wle
d
g
e
e
x
trac
ted
fro
m
b
ig
trac
e
s.
In
th
is
c
o
n
tex
t,
t
h
e
re
se
a
rc
h
a
t
h
a
n
d
is
a
ime
d
a
t
tran
sfo
rm
in
g
t
h
e
b
ig
d
a
ta
p
ro
d
u
c
e
d
v
ia
in
tera
c
ti
o
n
s
i
n
to
b
ig
k
n
o
wle
d
g
e
t
h
a
t
c
a
n
b
e
u
se
d
in
M
OO
Cs
b
y
a
c
to
rs
fa
ll
in
g
wit
h
in
a
g
i
v
e
n
lea
rn
in
g
lev
e
l
with
i
n
a
g
i
v
e
n
lea
rn
i
n
g
d
o
m
a
in
,
b
e
it
f
o
rm
a
l
o
r
i
n
fo
rm
a
l.
In
o
rd
e
r
to
a
c
h
ie
v
e
su
c
h
a
n
o
b
jec
ti
v
e
,
o
n
to
l
o
g
ica
l
a
p
p
ro
a
c
h
e
s
a
re
tak
e
n
,
n
a
m
e
ly
:
m
a
p
p
in
g
,
lea
rn
in
g
a
n
d
e
n
rich
m
e
n
t,
in
a
d
d
it
i
o
n
to
a
rti
ficia
l
in
tell
ig
e
n
c
e
-
b
a
se
d
a
p
p
ro
a
c
h
e
s
wh
ic
h
a
re
re
lev
a
n
t
in
o
u
r
re
se
a
rc
h
c
o
n
tex
t.
In
t
h
is
p
a
p
e
r,
we
p
r
o
p
o
se
th
re
e
in
terc
o
n
n
e
c
ted
a
lg
o
rit
h
m
s fo
r
a
b
e
tt
e
r
o
n
t
o
lo
g
ica
l
re
p
re
se
n
tati
o
n
o
f
lea
rn
in
g
a
c
to
rs’
k
n
o
wle
d
g
e
,
wh
il
e
p
re
m
isin
g
h
e
a
v
il
y
o
n
a
rti
ficia
l
in
tell
ig
e
n
c
e
a
p
p
r
o
a
c
h
e
s
th
r
o
u
g
h
o
u
t
t
h
e
sta
g
e
s
o
f
t
h
is
wo
rk
.
F
o
r
v
e
rify
i
n
g
t
h
e
v
a
li
d
it
y
o
f
o
u
r
c
o
n
tri
b
u
t
io
n
,
we
will
imp
lem
e
n
t
a
n
e
x
p
e
rime
n
t
a
b
o
u
t
k
n
o
wle
d
g
e
so
u
r
c
e
s e
x
a
m
p
le
.
K
ey
w
o
r
d
s
:
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
B
ig
d
ata
E
-
lear
n
in
g
L
in
k
ed
d
ata
On
to
lo
g
y
e
n
g
in
ee
r
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
:
Ab
d
ellad
im
Had
io
u
i
R
I
ME
T
E
AM
-
Netwo
r
k
in
g
,
M
o
d
elin
g
a
n
d
e
-
L
ea
r
n
in
g
L
R
I
E
L
ab
o
r
ato
r
y
-
R
esear
ch
in
C
o
m
p
u
ter
Scien
ce
an
d
E
d
u
ca
t
io
n
L
ab
o
r
ato
r
y
Mo
h
am
m
ad
ia
Sch
o
o
l E
n
g
in
ee
r
s
(
E
MI
)
-
Mo
h
am
m
ed
V
U
n
iv
er
s
ity
in
R
ab
at
Ag
d
al
AV.
I
b
n
Sin
a
Ag
d
al
R
ab
at
B
P.
7
6
5
Mo
r
o
cc
o
E
m
ail:
ah
ad
io
u
i@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
C
lo
u
d
co
m
p
u
tin
g
is
an
im
m
en
s
e
in
f
r
astru
ctu
r
e
b
ased
o
n
d
if
f
er
en
t
m
o
d
els
f
o
r
p
r
o
v
id
in
g
v
ar
i
o
u
s
s
er
v
ices
f
o
r
s
o
f
twar
e
an
d
h
a
r
d
war
e.
C
l
o
u
d
co
m
p
u
tin
g
p
a
r
ad
ig
m
h
as
r
esu
lted
f
r
o
m
in
t
eg
r
atio
n
o
f
o
n
lin
e
s
y
s
tem
s
.
Ob
s
er
v
ab
le
is
th
at
ter
tiar
y
ed
u
ca
tio
n
is
cu
r
r
en
tly
in
co
r
p
o
r
atin
g
tech
n
o
lo
g
i
ca
l
s
o
lu
tio
n
s
(
L
MS)
i
n
t
o
ed
u
ca
tio
n
,
th
at
is
to
s
ay
,
co
m
p
u
ter
izatio
n
o
f
ed
u
ca
tio
n
al
p
r
o
ce
s
s
es
f
o
r
th
e
b
en
ef
it
o
f
th
e
cu
r
r
en
t
lear
n
er
s
an
d
th
e
o
th
er
co
m
in
g
lear
n
in
g
ac
t
o
r
s
alik
e.
R
ec
en
t
r
elev
an
t
r
ese
ar
ch
[
1
]
h
as
s
h
o
wn
th
e
v
ital
i
m
p
o
r
tan
ce
o
f
L
MS
in
m
an
y
ed
u
c
atio
n
al
estab
lis
h
m
en
ts
.
W
e
ca
n
in
co
r
p
o
r
ate
m
an
y
lear
n
i
n
g
ac
tiv
ities
in
th
e
f
o
r
m
o
f
lear
n
i
n
g
s
ce
n
ar
io
s
in
MO
OC
s
y
s
tem
s
,
wh
ich
ca
n
g
en
er
ate
m
ass
iv
e
tr
ac
es
th
r
o
u
g
h
ac
to
r
s
’
u
s
ag
e.
T
h
at
is
,
in
th
e
co
u
r
s
e
o
f
lear
n
in
g
,
s
u
ch
s
y
s
tem
s
p
r
o
d
u
ce
b
ig
d
ata
b
u
ild
in
g
o
n
th
e
lear
n
in
g
ac
to
r
s
’
in
ter
ac
tio
n
s
(
in
clu
d
in
g
th
eir
ef
f
ec
ts
an
d
p
r
o
d
u
ctio
n
s
)
.
T
h
e
s
e
b
ig
d
ata
wer
e
d
ea
lt
with
i
n
d
ep
t
h
in
o
u
r
b
ig
d
ata
p
r
ep
r
o
ce
s
s
in
g
wo
r
k
[
2
]
.
B
ased
o
n
th
e
m
ass
iv
e
d
ata
p
r
o
d
u
ce
d
v
ia
i
n
ter
ac
tio
n
s
,
we
p
r
o
p
o
s
ed
,
as
a
f
i
r
s
t
s
tep
,
a
m
ac
h
i
n
e
lear
n
i
n
g
s
y
s
tem
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
Ap
r
il 2
0
2
1
:
1
6
7
5
-
1688
1676
wh
ile
r
esp
ec
tin
g
th
e
r
u
les
an
d
o
b
jectiv
es
d
escr
ib
ed
in
[
2
]
.
T
h
e
s
ec
o
n
d
s
tep
co
n
ce
r
n
s
o
n
t
o
lo
g
ical
co
n
s
tr
u
ctio
n
b
ased
o
n
th
e
m
ass
iv
e
d
ata
p
r
e
p
r
o
ce
s
s
ed
b
y
t
h
e
o
p
e
r
atio
n
al
m
ass
iv
e
d
ata
lay
er
.
T
h
e
aim
is
to
p
r
o
d
u
ce
m
ass
iv
e
k
n
o
wled
g
e
u
s
in
g
o
n
to
lo
g
i
es
-
g
r
o
u
n
d
ed
ap
p
r
o
ac
h
es
as
well
as
th
e
co
n
ce
p
ts
o
f
ar
tific
ial
in
tellig
e
n
ce
(
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
)
.
T
h
e
lar
g
e
am
o
u
n
t
o
f
d
ata
p
r
o
d
u
ce
d
b
y
MO
OC
s
u
s
er
s
in
v
ites
r
esear
ch
er
s
in
th
is
f
ield
to
s
tu
d
y
th
e
b
est
m
eth
o
d
s
f
o
r
e
x
tr
ac
tin
g
an
d
r
ep
r
esen
tin
g
k
n
o
wled
g
e
in
th
e
f
ield
s
o
f
ed
u
ca
tio
n
.
Fo
llo
win
g
o
u
r
an
aly
s
is
o
f
tr
ac
es
p
r
o
d
u
ce
d
b
y
o
n
lin
e
lear
n
in
g
s
y
s
tem
s
(
MO
OC
s
)
[
3
]
,
we
n
o
tice
th
at,
c
u
r
r
e
n
tly
,
o
n
e
o
f
th
e
m
ain
o
b
s
tacle
s
h
am
p
er
i
n
g
th
e
ev
o
lu
tio
n
o
f
th
ese
s
y
s
tem
s
,
at
th
e
lev
el
o
f
teac
h
in
g
e
n
titi
es,
is
th
e
a
b
s
en
ce
o
f
ca
p
italizatio
n
an
d
r
e
p
r
esen
tatio
n
o
f
t
h
e
k
n
o
wled
g
e
r
es
u
ltin
g
f
r
o
m
ac
to
r
s
’
s
y
s
tem
ic
in
ter
ac
tio
n
s
.
T
o
clar
if
y
th
e
p
o
in
t,
th
e
e
x
tr
ac
tio
n
p
r
o
ce
s
s
o
f
k
n
o
wled
g
e
s
o
u
r
ce
s
is
h
ig
h
ly
co
m
p
lex
b
ec
au
s
e
o
f
th
e
s
aid
ab
s
en
ce
;
t
h
er
ef
o
r
e
,
th
e
lear
n
in
g
tr
ac
es
p
r
o
d
u
ce
d
ar
e
in
a
r
aw
f
o
r
m
at
th
at
ca
n
n
o
t
b
e
u
s
ed
.
Acc
o
r
d
in
g
ly
,
we
in
tr
o
d
u
ce
o
n
to
lo
g
y
-
b
ased
s
y
s
tem
.
On
lin
e
l
ea
r
n
in
g
s
y
s
tem
s
ar
e
ch
a
r
ac
ter
is
tic
o
f
lim
its
an
d
s
h
o
r
tco
m
in
g
s
n
o
twith
s
tan
d
in
g
th
e
f
ac
t
th
at
th
ese
s
y
s
tem
s
o
f
f
er
p
latf
o
r
m
s
,
wh
ich
ar
e
r
ich
with
ed
u
ca
tio
n
al
f
u
n
ctio
n
s
.
I
n
s
u
c
h
p
latf
o
r
m
s
we
n
o
ted
t
h
e
ex
is
ten
ce
o
f
s
o
m
e
lim
its
lin
k
ed
to
th
e
lack
o
f
m
ea
n
s
o
f
ex
tr
ac
ti
n
g
an
d
r
ep
r
esen
tin
g
th
e
k
n
o
wled
g
e
p
r
o
d
u
ce
d
b
y
lea
r
n
in
g
ac
to
r
s
.
I
n
th
is
s
en
s
e,
th
r
o
u
g
h
o
u
r
a
n
a
ly
s
is
o
f
th
e
wo
r
k
[
4
-
6
]
,
we
n
o
tice
th
at
it
p
r
o
p
o
s
es
s
o
m
e
s
o
lu
tio
n
s
f
o
r
ex
tr
ac
tin
g
an
d
r
ep
r
esen
tin
g
t
h
e
k
n
o
wled
g
e
p
r
o
d
u
ce
d
v
ia
MO
OC
s
.
Ho
wev
er
,
o
n
th
e
o
n
e
h
an
d
,
it
h
as
b
ee
n
n
o
ted
t
h
at
th
ese
s
y
s
tem
s
d
o
n
o
t
o
f
f
er
s
o
lu
tio
n
s
f
o
r
ca
p
italizin
g
th
e
k
n
o
wled
g
e
th
at
cir
cu
late
s
in
th
ese
s
y
s
tem
s
.
On
th
e
o
th
er
h
an
d
,
k
n
o
wled
g
e
ex
tr
ac
tio
n
a
n
d
r
ep
r
esen
tatio
n
s
y
s
tem
s
p
r
o
p
o
s
ed
b
y
th
e
s
aid
r
esear
ch
wo
r
k
h
av
e
s
o
m
e
p
r
o
ce
s
s
in
g
lim
its
d
u
e
t
o
th
e
ab
s
en
ce
o
f
a
g
e
n
er
ic
in
tel
lig
en
t
ap
p
r
o
ac
h
in
th
eir
o
p
er
at
io
n
s
.
Ho
wev
er
,
t
h
e
k
n
o
wled
g
e
p
r
o
d
u
ce
d
b
y
ac
to
r
s
is
g
en
er
ally
m
ad
e
u
p
o
f
m
ass
iv
e
tr
ac
es
(
lo
g
f
iles
,
d
ata
f
ile
s
,
etc.
)
,
w
h
ich
ta
k
e
in
m
o
s
t
ca
s
es
an
u
n
s
tr
u
ctu
r
ed
f
o
r
m
at.
T
h
e
r
ef
o
r
e,
th
e
y
d
o
n
o
t
h
av
e
th
e
s
em
an
tic
asp
ec
t;
t
h
at
is
,
th
ey
ar
e
in
a
n
o
is
y
f
o
r
m
at,
w
h
ich
ca
n
n
o
t
b
e
u
s
ed
,
an
d
wh
ich
m
ak
es
n
o
s
en
s
e
f
o
r
th
e
in
v
o
lv
ed
ac
to
r
s
.
I
n
ad
d
itio
n
,
i
n
MO
OC
s
y
s
tem
s
,
th
er
e
i
s
n
o
in
s
tr
u
m
en
t f
o
r
r
ep
r
esen
tin
g
th
e
ac
to
r
s
’
k
n
o
wled
g
e
.
Hen
ce
,
co
m
es th
e
n
ec
ess
ity
o
f
p
r
o
p
o
s
in
g
a
s
o
lu
tio
n
f
o
r
th
e
r
e
p
r
esen
tatio
n
o
f
lear
n
in
g
ac
to
r
s
’
k
n
o
wled
g
e.
I
n
th
is
ar
ticle,
we
s
tu
d
y
th
e
in
tellig
en
t
o
n
to
lo
g
ical
r
e
p
r
es
en
tatio
n
o
f
lear
n
in
g
ac
to
r
s
’
k
n
o
wled
g
e
b
ased
o
n
th
e
m
ass
iv
e
d
ata
p
r
ep
r
o
ce
s
s
ed
in
[
2
]
,
wh
ile
m
ak
i
n
g
u
s
e
o
f
th
e
o
n
to
lo
g
ically
b
ased
s
em
an
ti
c
web
ap
p
r
o
ac
h
es
as
well
as
ar
tific
i
al
in
tellig
en
ce
alg
o
r
ith
m
s
.
I
n
d
ee
d
,
t
h
is
s
tag
e
r
ep
r
esen
ts
th
e
co
n
tin
u
ity
o
f
th
e
r
ea
lizatio
n
o
f
o
u
r
f
r
am
ew
o
r
k
wh
o
s
e
ar
ch
itectu
r
e
f
o
r
ex
tr
ac
tin
g
k
n
o
wled
g
e
is
b
ased
o
n
th
e
r
esu
lts
o
f
in
ter
ac
tio
n
s
o
f
MO
OC
s
"
lear
n
in
g
ac
to
r
s
[
7
]
.
B
y
an
al
y
zin
g
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
m
eth
o
d
s
,
o
u
r
p
r
o
p
o
s
ed
s
y
s
tem
r
ed
u
ce
s
th
e
lim
its
ch
ar
ac
ter
izin
g
k
n
o
wled
g
e
ex
t
r
ac
ted
at
th
e
en
d
o
f
a
lear
n
in
g
s
ess
i
o
n
.
T
h
e
m
ain
o
b
jectiv
e
in
t
h
is
wo
r
k
is
th
e
co
n
s
tr
u
ctio
n
a
n
d
th
e
r
e
p
r
esen
tatio
n
o
f
lear
n
in
g
ac
to
r
s
’
kn
o
wled
g
e
r
esu
ltin
g
f
r
o
m
th
ei
r
in
ter
ac
tio
n
s
i
n
an
o
n
lin
e
lear
n
in
g
p
latf
o
r
m
b
ased
o
n
o
n
t
o
lo
g
ies
an
d
c
o
n
ce
p
ts
o
f
ar
tific
ial
in
tellig
en
ce
(
n
eu
r
al
n
etwo
r
k
s
)
.
I
n
th
is
ar
ticle,
we
p
r
esen
t
an
in
tellig
en
t
m
ac
h
in
e
f
o
r
r
e
p
r
esen
tin
g
s
u
ch
k
n
o
wled
g
e.
Acc
o
u
n
tin
g
f
o
r
s
u
ch
a
n
o
b
jectiv
e,
th
e
a
r
ticle
is
m
ad
e
u
p
o
f
6
s
ec
tio
n
s
:
in
t
h
e
f
ir
s
t
s
ec
tio
n
we
lay
o
u
t
th
e
g
en
e
r
al
co
n
tex
t
o
f
th
e
s
tu
d
y
.
I
n
th
e
s
ec
o
n
d
s
ec
tio
n
,
we
s
h
ed
lig
h
t
o
n
th
e
e
x
is
tin
g
r
esear
ch
r
elev
an
t
f
o
r
th
e
s
u
b
ject
m
atter
d
ea
lt
with
in
th
is
wo
r
k
.
T
h
e
th
ir
d
s
ec
tio
n
p
o
in
ts
o
u
t
th
e
th
eo
r
etica
l
f
o
u
n
d
atio
n
o
f
th
e
tak
en
ap
p
r
o
ac
h
.
T
h
e
f
o
u
r
th
o
n
e
p
r
esen
ts
o
u
r
s
y
s
tem
o
f
r
ep
r
esen
tin
g
lear
n
in
g
ac
to
r
s
’
k
n
o
wled
g
e.
I
n
th
e
f
if
th
s
ec
tio
n
,
we
tack
le
th
e
k
n
o
wle
d
g
e
r
e
p
r
esen
tatio
n
alg
o
r
ith
m
s
p
r
o
p
o
s
ed
in
th
is
wo
r
k
b
ased
o
n
ar
tific
ial
n
e
u
r
al
n
etwo
r
k
s
.
T
h
e
f
in
al
s
ec
tio
n
is
d
ev
o
ted
to
an
ev
alu
atio
n
o
f
th
e
s
y
s
tem
an
d
,
th
en
,
d
r
aw
s
a
co
n
clu
s
io
n
an
d
p
er
s
p
ec
tiv
es
.
T
h
e
ex
is
tin
g
k
n
o
wl
ed
g
e
r
ep
r
e
s
en
tatio
n
s
y
s
tem
s
co
v
er
m
an
y
is
s
u
es
[
8
-
1
0
]
;
th
e
m
o
s
t
co
m
m
o
n
o
n
es
ar
e
as f
o
llo
ws:
−
C
o
r
r
esp
o
n
d
en
ce
b
etwe
en
d
a
t
ab
ase
attr
ib
u
tes
an
d
o
n
to
l
o
g
ical
attr
ib
u
tes
f
o
r
estab
lis
h
in
g
co
n
n
ec
tio
n
b
etwe
en
th
e
elem
en
ts
o
f
a
d
at
ab
ase
an
d
th
o
s
e
o
f
o
n
to
lo
g
ies
−
Sem
an
ti
c
s
im
ilar
ity
o
f
ac
q
u
ir
ed
k
n
o
wled
g
e:
T
h
e
ca
lcu
latio
n
o
f
s
em
an
tic
s
im
ilar
ity
th
r
o
u
g
h
id
en
tif
y
in
g
k
n
o
wled
g
e
s
o
u
r
ce
s
wh
ic
h
ar
e
eq
u
al
weig
h
t
−
C
alcu
latio
n
o
f
th
e
d
is
tan
ce
s
b
e
twee
n
k
n
o
wled
g
e
s
o
u
r
ce
s
f
o
r
a
b
etter
ex
tr
ac
tio
n
−
C
las
s
if
icatio
n
o
f
co
llectio
n
m
e
asu
r
es
−
I
d
en
tific
atio
n
o
f
a
n
ew
k
n
o
wle
d
g
e
s
o
u
r
ce
.
C
o
n
s
id
er
in
g
th
e
p
r
o
g
r
ess
o
f
ap
p
r
o
ac
h
es
r
elatin
g
to
k
n
o
wl
ed
g
e
o
n
to
lo
g
ical
r
ep
r
e
s
en
tati
o
n
an
d
th
e
p
r
o
b
lem
s
s
o
lv
e
d
b
y
r
esear
ch
er
s
'
p
r
o
p
o
s
als,
we
will
s
tar
t
th
is
wo
r
k
with
a
liter
atu
r
e
r
e
v
iew
o
f
th
e
cu
r
r
en
t
p
r
o
b
lem
s
r
e
latin
g
t
o
th
e
co
n
te
x
t
o
f
th
e
p
r
esen
t
p
ap
e
r
.
Ou
r
s
t
u
d
y
d
ea
ls
with
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
s
y
s
tem
s
s
p
ec
if
ically
ad
ap
ted
t
o
e
-
lear
n
in
g
s
y
s
tem
,
b
ased
o
n
m
ass
iv
e
d
ata
alr
ea
d
y
p
r
e
-
p
r
o
ce
s
s
ed
b
y
o
u
r
wo
r
k
[
2
]
,
wh
ich
co
v
er
s
m
a
n
y
c
o
n
s
tr
ain
t
s
an
d
p
r
o
b
lem
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8
7
0
8
I
n
tellig
en
t m
a
ch
in
e
f
o
r
o
n
to
lo
g
ica
l rep
r
esen
ta
tio
n
o
f
…
(
A
b
d
ella
d
im
Ha
d
io
u
i
)
1677
2.
ST
A
T
E
O
F
AR
T
Ou
r
r
esear
ch
f
o
c
u
s
es
o
n
k
n
o
wled
g
e
ex
tr
ac
tio
n
f
r
o
m
m
ass
iv
e
d
ata
p
r
e
-
p
r
o
ce
s
s
ed
in
[
2
]
an
d
th
ei
r
o
n
to
lo
g
ical
r
ep
r
ese
n
tatio
n
s
.
T
h
er
ef
o
r
e,
em
p
h
asis
is
to
b
e
p
lace
d
o
n
th
e
b
ig
d
ata
g
r
o
u
n
d
ed
o
n
t
o
lo
g
y
(
NOSQL
)
.
I
t is n
o
tewo
r
th
y
th
at
k
n
o
wled
g
e
r
e
p
r
esen
tatio
n
r
em
ain
s
a
d
o
m
ain
wh
ich
is
s
till
k
n
o
win
g
e
x
p
an
s
io
n
b
y
th
e
c
o
n
ce
r
n
e
d
r
esear
ch
e
r
s
.
I
n
d
ee
d
,
o
u
r
s
tu
d
y
r
ev
ea
ls
th
at
n
u
m
er
o
u
s
r
esear
ch
p
r
o
ject
s
h
av
e
em
er
g
e
d
to
p
r
o
v
id
e
s
o
lu
tio
n
s
t
o
p
r
o
b
lem
s
lin
k
ed
to
t
h
e
d
e
v
elo
p
m
e
n
t
o
f
th
e
r
elatin
g
f
ield
s
[
1
1
]
.
T
h
at
is
,
it
h
as
b
e
en
u
s
ed
in
m
ed
icin
e
f
o
r
co
m
p
lex
p
r
o
c
ess
es
s
u
ch
as th
e
id
en
tific
atio
n
o
f
DNA,
in
th
e
s
atellite
f
ield
f
o
r
id
en
tific
atio
n
o
f
k
n
o
wled
g
e
[
1
2
]
,
in
ad
d
itio
n
to
o
u
r
f
ield
,
n
am
ely
,
e
d
u
ca
tio
n
in
wh
ich
n
u
m
er
o
u
s
r
esear
c
h
p
r
o
jects
h
av
e
b
ee
n
co
n
d
u
cte
d
[
4
]
.
T
h
ese
in
clu
d
e
p
r
o
jects
o
n
th
e
r
ep
r
esen
tatio
n
o
f
ac
to
r
s
’
k
n
o
wled
g
e
an
d
th
e
u
s
e
o
f
o
n
to
lo
g
ies
f
o
r
th
e
in
d
ex
in
g
o
f
n
u
m
e
r
ic
r
eso
u
r
ce
s
[
1
3
]
.
I
n
ac
c
o
u
n
tin
g
f
o
r
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
,
we
h
av
e
r
e
v
iewe
d
th
e
r
elev
an
t liter
atu
r
e,
f
o
cu
s
in
g
o
n
th
e
wo
r
k
s
r
ec
en
tly
p
r
o
p
o
s
ed
b
y
r
ese
ar
ch
er
s
in
th
e
f
ield
in
o
r
d
er
to
ar
r
iv
e
at
th
e
b
est
s
o
lu
tio
n
s
to
t
h
e
p
r
o
b
lem
s
d
ea
lt
with
in
o
u
r
r
esear
ch
.
I
n
th
is
v
ein
,
f
o
c
u
s
is
len
t
to
m
an
y
m
eth
o
d
s
r
elate
d
to
o
u
r
r
esear
ch
c
o
n
tex
t
.
2
.
1
.
O
nto
lo
g
ica
l e
ng
ineering
Kn
o
wled
g
e
m
ap
p
i
n
g
r
ep
r
esen
ts
an
im
p
o
r
tan
t
s
tag
e
in
ac
to
r
s
’
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
.
Giv
en
th
is
f
ac
t,
we
h
av
e
m
a
d
e
an
i
n
-
d
ep
th
an
aly
s
is
o
f
th
e
b
est
m
eth
o
d
s
u
s
ed
b
y
r
e
-
s
ea
r
ch
er
s
in
o
n
to
lo
g
ical
m
ap
p
i
n
g
.
T
h
e
m
ain
o
b
jectiv
e
o
f
th
is
s
tag
e
is
:
−
T
o
m
ak
e
c
o
r
r
esp
o
n
d
en
ce
b
etw
ee
n
th
e
d
atab
ase
elem
en
ts
an
d
o
n
to
lo
g
ical
elem
en
ts
,
o
n
th
e
o
n
e
h
a
n
d
,
a
n
d
b
etwe
en
o
n
to
l
o
g
y
s
o
u
r
ce
s
an
d
o
n
to
lo
g
ical
elem
en
ts
,
o
n
t
h
e
o
th
er
h
an
d
.
−
T
o
m
ak
e
c
o
r
r
esp
o
n
d
en
ce
b
et
wee
n
two
o
r
m
o
r
e
o
n
to
lo
g
y
a
s
s
o
ciate
d
with
o
u
r
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
s
y
s
tem
.
I
n
f
ac
t,
s
o
m
e
r
esear
ch
er
s
u
s
e
lin
k
ed
o
r
o
p
e
n
d
ata
f
o
r
th
e
r
ep
r
esen
tatio
n
o
f
k
n
o
w
-
le
d
g
e
b
ased
o
n
th
e
SP
AR
QL
lan
g
u
ag
e
[
1
4
]
,
wh
er
ea
s
o
th
er
s
u
s
e
th
e
o
n
to
l
o
g
ical
r
e
p
r
esen
tatio
n
[
1
5
]
as
a
s
o
lu
tio
n
to
p
r
o
b
lem
s
r
elatin
g
to
k
n
o
wled
g
e
m
ap
p
in
g
.
Kn
o
wled
g
e
id
en
tific
atio
n
is
ac
h
iev
ed
v
i
a
t
h
e
u
s
e
o
f
t
w
o
t
y
p
e
s
o
f
m
e
t
h
o
d
s
,
n
a
m
e
l
y
:
n
o
n
-
s
u
p
e
r
v
i
s
e
d
[
1
4
]
an
d
s
u
p
er
v
is
ed
W
eb
m
eth
o
d
s
p
r
o
ce
s
s
ed
b
y
ex
p
e
r
ts
in
th
e
f
ield
[
1
6
]
.
I
n
th
e
s
ec
o
n
d
ca
s
e,
th
er
e
ar
e
tech
n
ical
team
s
wo
r
k
in
g
o
n
t
h
e
e
x
tr
ac
tio
n
o
f
k
n
o
wled
g
e
p
r
o
d
u
ce
d
b
y
ac
to
r
s
in
th
e
f
ield
o
f
ed
u
ca
tio
n
.
C
u
r
r
e
n
tl
y
,
u
s
in
g
s
y
s
tem
s
wh
ich
ar
e
b
ased
o
n
w
eb
r
elate
d
tech
n
o
lo
g
ies,
th
e
W
eb
d
o
m
ai
n
p
r
o
d
u
ce
s
m
ass
iv
e
d
ata
r
esu
ltin
g
f
r
o
m
u
s
er
s
’
in
ter
ac
t
io
n
s
.
Nu
m
er
o
u
s
r
esear
ch
er
s
h
a
v
e
wo
r
k
ed
f
o
r
y
ea
r
s
o
n
th
e
in
teg
r
ate
d
web
'
m
eth
o
d
s
t
o
b
etter
m
an
ip
u
late
th
o
s
e
d
ata
[
1
7
]
.
B
u
ild
in
g
o
n
th
eir
an
al
y
s
is
,
we
h
av
e
c
o
m
e
to
g
r
ip
s
with
li
n
k
ed
a
n
d
o
p
en
d
ata
m
eth
o
d
s
f
ac
ilit
atin
g
d
ata
ac
ce
s
s
.
As
a
ca
s
e
in
p
o
in
t,
th
e
r
ese
ar
ch
er
in
[
1
8
]
h
as
u
s
ed
s
u
ch
m
eth
o
d
s
to
f
ac
ilit
ate
ac
ce
s
s
to
clo
u
d
d
ata.
L
in
k
ed
an
d
o
p
e
n
d
ata
ar
e
b
ased
o
n
a
s
tan
d
ar
d
SP
AR
QL
[
1
9
]
,
wh
ich
o
f
f
er
s
a
u
n
i
f
o
r
m
ap
p
r
o
ac
h
f
o
r
ac
ce
s
s
in
g
m
ass
iv
e
d
ata.
T
o
p
u
t
it
an
o
t
h
er
way
,
web
-
b
ased
m
eth
o
d
s
,
in
clu
d
in
g
lin
k
ed
an
d
o
p
en
d
ata,
in
teg
r
ate
d
ig
ital
r
eso
u
r
ce
s
o
r
m
ass
iv
e
d
ata
f
o
r
an
y
ar
ea
.
Sev
er
al
wo
r
k
s
h
a
v
e
b
ee
n
p
r
o
p
o
s
ed
in
o
n
to
lo
g
ical
m
ap
p
in
g
;
am
o
n
g
t
h
ese
wo
r
k
s
[
2
0
]
,
we
f
in
d
ar
ticles
wh
ich
p
r
o
p
o
s
e
s
o
lu
tio
n
s
r
elate
d
to
o
n
to
lo
g
ica
l
m
ap
p
in
g
b
etwe
en
Data
s
et
an
d
o
n
to
lo
g
y
,
o
n
th
e
o
n
e
h
an
d
,
a
n
d
m
ap
p
in
g
b
etwe
en
two
o
r
m
o
r
e
o
n
t
o
lo
g
ies
o
n
th
e
o
th
e
r
,
as
m
en
tio
n
e
d
a
b
o
v
e.
Acc
o
r
d
in
g
ly
,
th
e
m
ain
o
b
jectiv
e
o
f
m
ap
p
in
g
f
u
n
ctio
n
is
to
m
ak
e
co
r
r
esp
o
n
d
en
ce
/m
atch
in
g
b
et
wee
n
a
g
iv
en
o
p
er
atio
n
al
d
at
a
lay
er
an
d
o
n
to
lo
g
ical
k
n
o
w
led
g
e
r
ep
r
esen
tatio
n
f
o
r
an
y
g
i
v
en
f
ield
(
i.e
.
,
m
ed
i
cin
e,
ed
u
ca
tio
n
,
a
n
d
s
o
o
n
)
.
T
h
u
s
,
th
e
a
b
o
v
e
-
m
en
tio
n
e
d
co
r
r
esp
o
n
d
en
c
e
is
u
s
ed
to
cr
ea
te
a
n
o
n
to
lo
g
y
c
o
m
m
o
n
to
k
n
o
wled
g
e
e
x
tr
ac
tio
n
s
y
s
tem
s
f
o
r
t
h
e
b
e
n
ef
it
o
f
ac
to
r
s
in
v
o
lv
ed
in
o
n
lin
e
lear
n
in
g
[
7
]
.
Ho
wev
e
r
,
o
n
to
l
o
g
ical
m
ap
p
in
g
s
till
en
co
u
n
t
er
s
p
r
o
b
lem
s
r
elatin
g
,
f
o
r
i
n
s
tan
ce
,
to
s
im
ilar
ity
b
etwe
en
k
n
o
wled
g
es,
as
in
tr
o
d
u
ce
d
in
o
u
r
wo
r
k
[
2
]
,
wh
ich
r
ep
r
es
en
ts
a
p
r
ep
r
o
ce
s
s
in
g
m
ac
h
in
e
f
o
r
b
ig
d
ata
p
r
o
d
u
ce
d
b
y
in
ter
ac
tiv
e
ac
to
r
s
.
T
h
e
p
r
e
p
r
o
ce
s
s
ed
d
ata
o
u
t
p
u
t
o
f
o
u
r
m
ac
h
in
e
ar
e
r
e
p
r
e
s
e
n
ted
in
XM
L
an
d
R
DF
f
o
r
m
ats.
Hav
in
g
r
ev
iewe
d
s
o
m
e
s
tu
d
ies,
we
h
av
e
n
o
ted
th
at
o
n
to
lo
g
ical
m
ap
p
in
g
in
th
e
ca
s
e
o
f
co
r
r
esp
o
n
d
en
ce
s
b
etwe
e
n
o
n
t
o
lo
g
ies
is
p
er
f
o
r
m
e
d
b
y
a
g
iv
en
ty
p
e
o
f
m
eth
o
d
s
an
d
to
o
ls
,
wh
er
ea
s
in
th
e
ca
s
e
o
f
m
ap
p
i
n
g
b
etwe
en
d
ataset
an
d
o
n
t
o
lo
g
y
,
it
is
f
u
n
ctio
n
ed
b
y
an
o
t
h
er
ty
p
e
.
Giv
en
th
is
d
is
tin
ctio
n
,
we
h
av
e
i
n
v
e
s
t
i
g
a
t
e
d
t
h
e
b
e
s
t
m
e
t
h
o
d
s
f
o
r
m
a
p
p
i
n
g
w
h
a
t
e
v
e
r
t
y
p
e
o
f
i
n
p
u
t
k
n
o
w
l
e
d
g
e
s
o
u
r
c
e
s
.
T
h
e
T
a
b
l
e
1
s
h
o
w
s
i
n
d
e
t
a
il
t
h
e
c
o
r
r
e
s
p
o
n
d
e
n
c
e
b
e
t
w
e
e
n
k
n
o
w
l
e
d
g
e
s
o
u
r
c
e
s
(
D
a
t
a
s
e
t
a
n
d
o
n
t
o
l
o
g
i
e
s
)
a
n
d
o
n
t
o
l
o
g
i
e
s
o
u
tp
u
t:
T
ab
le
1
.
On
to
l
o
g
ical
m
ap
p
in
g
alg
o
r
ith
m
s
To
o
l
s
D
a
t
a
s
e
t
a
n
d
t
e
x
t
u
r
a
l
R
D
F
/
O
W
L
S
P
A
R
Q
L
Li
mi
t
s
O
N
TO
P
D
a
t
a
s
e
t
√
√
S
p
e
c
i
f
i
c
t
o
s
t
r
u
c
t
u
r
e
d
d
a
t
a
.
D
a
t
a
M
a
s
t
e
r
D
a
t
a
s
e
t
√
√
X
A
p
i
B
o
t
h
√
√
P
r
o
c
e
ss
a
l
l
t
y
p
e
s
o
f
t
e
x
t
s
W
o
r
d
2
V
e
c
B
o
t
h
√
√
On
to
lo
g
ical
lear
n
in
g
:
T
h
is
p
r
o
ce
s
s
aim
s
to
f
il
l
th
e
p
r
o
p
o
s
ed
o
u
tp
u
t
o
n
to
lo
g
y
[
7
]
with
k
n
o
wled
g
e
ex
tr
ac
ted
f
r
o
m
th
e
b
ig
d
ata
lay
er
[
2
]
.
On
to
lo
g
ical
lear
n
i
n
g
is
im
p
lem
en
te
d
b
y
s
o
m
e
r
es
ea
r
ch
er
s
wh
o
h
a
v
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
Ap
r
il 2
0
2
1
:
1
6
7
5
-
1688
1678
cr
ea
ted
alg
o
r
ith
m
s
in
th
ei
r
r
esear
ch
wo
r
k
s
[
2
1
]
,
wh
e
r
ea
s
o
t
h
er
r
esear
ch
er
s
u
s
e
ex
is
tin
g
a
lg
o
r
ith
m
s
p
r
o
p
o
s
ed
b
y
th
e
s
cien
tific
co
m
m
u
n
ity
.
I
n
t
h
e
T
a
b
le
2
,
we
s
h
o
w
th
e
ef
f
icien
c
y
o
f
s
o
m
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
s
b
y
r
esear
ch
er
s
wh
o
d
ea
lt with
o
n
t
o
lo
g
ical
lear
n
in
g
in
th
eir
s
cien
tific
p
r
o
p
o
s
als:
T
ab
le
2
.
L
ea
r
n
in
g
o
n
to
lo
g
y
al
g
o
r
ith
m
s
A
l
g
o
r
i
t
h
ms
a
n
d
M
e
t
h
o
d
s
i
n
p
u
t
o
u
t
p
u
t
Li
mi
t
s
O
n
t
o
4
K
D
D
O
n
t
o
K
D
D
Th
e
l
i
mi
t
s
o
f
t
h
e
se
a
p
p
r
o
a
c
h
e
s
a
p
p
e
a
r
e
i
t
h
e
r
o
n
t
h
e
p
r
o
c
e
ssi
n
g
t
i
me
o
r
b
y
t
h
e
f
l
e
x
i
b
i
l
i
t
y
w
i
t
h
t
h
e
so
u
r
c
e
s
o
f
k
n
o
w
l
e
d
g
e
.
K
D
D
4
O
n
t
o
K
D
D
O
n
t
o
O
n
t
o
K
D
D
4
O
n
t
o
O
n
t
o
K
D
D
O
n
t
o
O
n
t
o
4
O
n
t
o
K
D
D
O
n
t
o
O
n
t
o
K
D
D
O
n
t
o
4
O
n
t
o
O
n
t
o
O
n
t
o
In
th
is
s
tag
e,
r
esear
ch
e
r
s
[
1
8
,
21]
p
r
o
p
o
s
ed
s
o
m
e
o
n
to
lo
g
ical
lear
n
in
g
s
o
lu
tio
n
s
f
o
r
in
teg
r
a
tin
g
th
e
in
p
u
t
k
n
o
wled
g
e
s
o
u
r
ce
s
(
i.e
.
,
a
d
ata
s
et
an
d
a
n
o
n
to
lo
g
y
)
a
n
d
th
e
o
u
tp
u
t
o
n
to
lo
g
y
.
Fo
r
in
s
tan
ce
,
in
h
is
wo
r
k
,
th
e
au
th
o
r
u
n
d
er
to
o
k
an
in
-
d
ep
th
s
tu
d
y
o
n
o
n
to
lo
g
ical
m
atch
in
g
f
o
r
k
n
o
wled
g
e
ex
tr
ac
tio
n
.
Du
r
in
g
th
e
o
n
to
lo
g
ical
m
atch
in
g
s
tag
es,
h
e
ca
r
r
ied
o
u
t
th
e
o
n
to
lo
g
i
ca
l
alig
n
m
en
t
b
etwe
en
o
n
e
o
r
m
o
r
e
k
n
o
wled
g
e
s
o
u
r
ce
s
.
Hav
in
g
an
a
ly
ze
d
th
e
s
e
wo
r
k
s
,
we
n
o
ted
th
at
th
ey
ar
e
ch
ar
ac
ter
is
tic
o
f
s
h
o
r
tco
m
in
g
s
in
ter
m
s
o
f
th
e
u
s
ed
ap
p
r
o
ac
h
es.
Ou
r
an
aly
s
i
s
o
f
t
h
e
r
esu
lts
o
f
th
e
r
ec
en
tl
y
p
r
o
p
o
s
ed
wo
r
k
s
[
3
,
22]
r
e
v
ea
led
th
at
th
e
b
est
m
eth
o
d
s
o
f
o
n
to
l
o
g
ical
lear
n
i
n
g
ar
e
b
u
ilt
o
n
a
r
tific
ial
in
te
llig
en
ce
(
AI
)
a
p
p
r
o
ac
h
es
d
u
e
to
th
eir
co
n
tr
ib
u
tio
n
with
r
eg
ar
d
t
o
Kn
o
wled
g
e
ex
tr
ac
tio
n
.
On
to
lo
g
ical
en
r
ich
m
en
t:
As
th
e
liter
atu
r
e
d
em
o
n
s
tr
ates,
m
an
y
m
eth
o
d
s
o
f
o
n
to
lo
g
ical
e
n
r
ich
m
en
t
h
av
e
b
ee
n
i
n
tr
o
d
u
ce
d
b
y
r
es
ea
r
ch
er
s
.
T
h
e
m
ai
n
o
b
jectiv
e
o
f
th
eir
wo
r
k
s
is
to
id
en
tif
y
n
o
v
el
k
n
o
wled
g
e
s
o
u
r
ce
s
f
o
r
a
g
iv
en
f
ield
,
i
n
clu
d
in
g
th
e
k
n
o
wled
g
e
r
elev
a
n
t
f
o
r
ed
u
ca
tio
n
(
t
h
e
co
n
tex
t
o
f
o
u
r
s
tu
d
y
)
.
Oth
er
s
tu
d
ies
as
in
[
2
3
]
p
r
o
p
o
s
ed
m
eth
o
d
s
f
o
r
tack
lin
g
c
o
r
r
esp
o
n
d
en
ce
b
etwe
en
th
e
in
itially
cr
ea
ted
o
n
to
lo
g
ies
an
d
th
e
o
n
e
id
e
n
tifie
d
b
y
o
u
r
m
a
ch
in
e
in
o
r
d
er
t
o
en
r
ich
o
u
r
o
n
to
lo
g
ical
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
s
y
s
tem
f
o
r
ed
u
ca
tio
n
al
s
y
s
tem
s
.
T
h
e
f
iel
d
o
f
ed
u
ca
tio
n
p
r
o
d
u
ce
s
k
n
o
wled
g
e
th
r
o
u
g
h
e
-
lear
n
in
g
s
y
s
tem
s
th
at
f
all
in
to
d
if
f
er
en
t
k
n
o
wled
g
e
s
o
u
r
ce
s
c
ateg
o
r
ies
an
d
f
o
u
n
d
in
d
if
f
er
e
n
t
p
lace
s
.
R
esear
ch
er
s
a
r
e
wo
r
k
in
g
o
n
two
p
h
ases
o
f
s
u
ch
k
n
o
wled
g
e
id
e
n
tific
atio
n
:
th
e
f
ir
s
t
co
n
ce
r
n
s
lo
ca
lizatio
n
,
wh
ile
th
e
s
ec
o
n
d
s
u
g
g
ests
th
e
in
teg
r
atio
n
o
f
in
tellig
en
t
ag
en
ts
f
o
r
a
b
etter
id
en
tific
atio
n
o
f
d
elo
ca
lized
k
n
o
wled
g
e
[
2
4
]
.
Oth
er
r
esear
ch
er
s
h
av
e
o
f
f
er
e
d
web
s
er
v
ices to
id
en
tify
n
ew
d
is
tan
t k
n
o
wled
g
e
in
t
h
e
f
ield
.
2
.
2
.
K
no
wledg
e
ex
t
ra
ct
io
n ba
s
ed
o
n neura
l net
wo
rk
s
Ar
tific
ial
in
tellig
en
ce
(
AI
)
ap
p
r
o
ac
h
es:
s
u
ch
ap
p
r
o
ac
h
es
h
a
v
e
b
ee
n
in
tr
o
d
u
ce
d
in
t
o
m
a
n
y
ar
ea
s
o
f
s
cien
tific
r
esear
ch
.
I
t
s
h
o
u
ld
b
e
n
o
ted
th
at
s
cien
ce
s
s
u
b
s
u
m
ed
with
in
AI
r
ep
r
esen
t
th
e
tr
en
d
s
th
at
will
d
o
m
in
ate
t
h
e
s
ce
n
e
in
t
h
e
c
o
m
in
g
y
ea
r
s
d
u
e
to
th
eir
ef
f
ec
ti
v
en
ess
in
th
e
d
e
v
elo
p
m
e
n
t
o
f
m
an
y
s
ec
to
r
s
.
Mo
r
e
r
ec
en
tly
,
r
esear
ch
e
r
s
in
th
e
f
i
eld
h
av
e
p
r
o
p
o
s
ed
m
eth
o
d
s
f
o
r
ac
ce
n
tu
ated
h
an
d
lin
g
in
th
e
s
tag
es
o
f
ca
r
r
y
in
g
o
u
t
th
e
r
esear
ch
r
esu
lts
in
v
ar
i
o
u
s
f
ield
s
.
I
n
th
is
co
n
tex
t,
r
es
ea
r
ch
er
s
h
av
e
p
r
o
p
o
s
ed
m
eth
o
d
s
f
o
r
ac
ce
n
tu
ate
d
in
v
esti
g
atio
n
an
d
p
r
o
ce
s
s
in
g
i
n
th
e
p
h
ases
o
f
ca
r
r
y
in
g
o
u
t
th
eir
wo
r
k
i
n
v
a
r
io
u
s
f
ield
s
.
Am
o
n
g
th
ese
f
ield
s
we
m
ay
r
e
f
er
to
th
e
f
ield
o
f
r
o
b
o
ti
cs.
Fo
r
e
x
am
p
le,
th
e
au
th
o
r
in
[
2
5
,
2
6
]
h
as
m
ad
e
a
co
m
p
a
r
ativ
e
s
tu
d
y
o
f
wo
r
k
s
r
elatin
g
to
th
is
v
i
b
r
an
t
f
ield
an
d
its
o
u
tc
o
m
es
an
d
im
p
l
icatio
n
s
f
o
r
in
d
u
s
tr
y
.
An
o
th
er
ex
am
p
le
is
th
at
r
esear
ch
er
s
h
av
e
u
n
d
er
tak
en
co
m
p
ar
ativ
e
s
t
u
d
ies
to
m
ak
e
ag
en
t
-
b
ased
m
o
d
els.
Ma
jo
r
ity
o
f
th
e
p
in
p
o
in
ted
id
ea
s
an
d
co
n
ce
p
ts
h
a
v
e
an
au
to
m
atic
asp
ec
t
in
t
h
at
th
ey
tack
le
m
eth
o
d
s
wh
ich
h
av
e
b
ee
n
p
r
o
p
o
s
ed
f
o
r
d
ea
lin
g
with
m
ass
iv
e
d
ata
in
te
g
r
atio
n
i
n
a
g
iv
en
ar
ea
.
Am
o
n
g
th
ese
co
n
ce
p
ts
,
we
m
a
y
r
e
f
e
r
to
a
r
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANN)
an
d
th
e
r
elatin
g
ap
p
r
o
ac
h
es,
wh
ich
ca
n
b
e
i
n
co
r
p
o
r
ated
i
n
v
ar
i
o
u
s
f
ield
s
,
esp
ec
ially
th
e
f
ield
o
f
ed
u
ca
tio
n
,
wh
er
e
th
ey
ca
n
b
e
u
s
e
d
in
p
ar
allel
p
r
o
ce
s
s
in
g
o
f
b
ig
d
ata
as
an
in
p
u
t,
a
n
d
class
if
icatio
n
o
f
k
n
o
wled
g
e
as a
n
o
u
t
p
u
t
.
Am
o
n
g
th
ese
wo
r
k
s
we
cite
[
2
7
]
.
W
OR
D2
VE
C
:
I
t
r
ep
r
esen
ts
th
e
em
b
ed
d
in
g
o
f
lex
ical
wo
r
d
s
f
am
ilies
(
i.e
.
,
wo
r
d
em
b
e
d
d
in
g
)
,
wh
ic
h
allo
ws
v
ec
to
r
ial
r
ep
r
esen
tatio
n
b
a
s
ed
o
n
k
n
o
wled
g
e
s
o
u
r
ce
s
.
W
e
ca
n
u
s
e
wo
r
d
2
v
ec
i
n
t
wo
d
if
f
er
e
n
t
way
s
:
C
o
n
tin
u
o
u
s
b
ag
o
f
wo
r
d
s
m
o
d
el
(
C
B
O
W
)
an
d
Sk
ip
-
g
r
am
(
Gr
am
ju
m
p
)
.
O
n
th
e
o
n
e
h
an
d
,
th
e
r
ea
lizatio
n
o
f
th
e
wo
r
d
s
v
ec
to
r
ial
r
ep
r
esen
ta
tio
n
with
C
B
OW
is
o
b
tain
ed
b
y
p
r
ed
ictin
g
th
eir
co
n
ten
t
f
r
o
m
k
n
o
wled
g
e
o
f
th
e
n
eig
h
b
o
r
in
g
w
o
r
d
s
.
I
n
th
is
ca
s
e,
th
e
n
o
tio
n
o
f
"wo
r
d
s
b
a
g
"
d
o
es
n
o
t
im
p
ac
t
t
h
e
o
r
d
er
o
f
wo
r
d
s
.
On
th
e
o
th
er
h
an
d
,
t
h
e
s
ec
o
n
d
m
eth
o
d
,
Sk
i
p
-
g
r
am
,
is
b
ased
o
n
an
a
p
p
r
o
ac
h
o
f
p
r
ed
ictin
g
wo
r
d
s
b
ased
o
n
t
h
e
co
n
tex
t
o
f
th
eir
o
cc
u
r
r
e
n
ce
.
I
n
th
i
s
ca
s
e,
th
e
wo
r
d
s
with
h
ea
v
y
weig
h
t a
r
e
n
eig
h
b
o
r
in
g
o
n
es.
T
h
e
ca
l
cu
latio
n
o
f
th
e
w
o
r
d
ce
n
ter
s
is
m
ad
e
b
y
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
wh
ich
s
im
p
lify
th
e
d
ata
p
r
o
ce
s
s
in
g
.
Dr
awin
g
o
n
o
u
r
a
n
aly
s
is
o
f
th
e
wo
r
k
s
w
h
ich
in
te
g
r
ate
W
o
r
d
2
Vec
a
p
p
r
o
ac
h
es,
we
n
o
ted
th
at
W
o
r
d
2
Vec
h
as
a
n
im
p
lic
atio
n
f
o
r
th
e
ca
s
es
o
f
k
n
o
wled
g
e
ex
tr
ac
tio
n
f
r
o
m
tex
tu
al
d
o
cu
m
e
n
ts
[
1
3
,
2
8
]
.
I
n
o
th
er
w
o
r
k
s
,
it
was
u
s
ed
f
o
r
k
n
o
wled
g
e
ex
tr
ac
tio
n
f
r
o
m
s
tr
u
ctu
r
ed
d
o
c
u
m
en
ts
.
Ho
wev
er
,
we
eq
u
ally
n
o
ticed
th
at
s
u
ch
wo
r
k
s
h
av
e
s
o
m
e
s
h
o
r
tco
m
in
g
s
in
ter
m
s
o
f
th
eir
k
n
o
wled
g
e
s
o
u
r
ce
s
n
atu
r
e
a
n
d
ty
p
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8
7
0
8
I
n
tellig
en
t m
a
ch
in
e
f
o
r
o
n
to
lo
g
ica
l rep
r
esen
ta
tio
n
o
f
…
(
A
b
d
ella
d
im
Ha
d
io
u
i
)
1679
3.
T
H
E
M
E
T
H
O
DO
L
O
G
Y
I
n
o
r
d
er
to
ac
h
iev
e
o
u
r
m
ai
n
o
b
jectiv
e,
wh
ic
h
h
as
alr
ea
d
y
b
ee
n
laid
o
u
t
ab
o
v
e,
an
d
wh
ic
h
r
ev
o
lv
es
ar
o
u
n
d
th
e
r
ep
r
esen
tatio
n
o
f
m
ass
iv
e
k
n
o
wled
g
e
p
r
o
d
u
ce
d
b
y
lear
n
in
g
ac
to
r
s
,
th
e
p
r
esen
t
wo
r
k
ad
o
p
t
s
th
e
me
th
o
d
o
l
o
g
y
p
r
esen
ted
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
T
h
e
m
eth
o
d
o
lo
g
y
a
d
o
p
ted
f
o
r
o
n
to
lo
g
ical
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
in
MO
OC
s
B
ased
o
n
th
is
m
eth
o
d
o
lo
g
y
,
we
ad
o
p
t
th
r
ee
alg
o
r
ith
m
s
:
th
e
f
ir
s
t
f
o
r
o
n
to
lo
g
ical
m
ap
p
in
g
,
th
e
s
ec
o
n
d
f
o
r
o
n
to
lo
g
ical
lear
n
in
g
,
w
h
ile
th
e
th
ir
d
f
o
r
o
n
to
lo
g
ical
en
r
ich
m
en
t.
T
h
r
o
u
g
h
o
u
t
th
e
s
tag
es
o
f
th
e
r
ea
lizatio
n
o
f
th
e
th
r
ee
s
tated
alg
o
r
ith
m
s
,
we
u
s
e
ar
tific
ial
in
tellig
en
ce
ap
p
r
o
ac
h
es
f
o
r
th
e
e
x
tr
ac
tio
n
/
p
ar
allel
p
r
o
ce
s
s
in
g
o
f
k
n
o
wled
g
e
r
e
ce
iv
ed
f
r
o
m
m
ass
iv
e
d
ata
as a
n
in
p
u
t.
T
h
e
th
r
ee
elem
en
ts
ar
e
in
tr
o
d
u
ce
d
as f
o
llo
w:
−
T
h
e
f
ir
s
t
alg
o
r
ith
m
:
I
n
th
is
alg
o
r
ith
m
,
th
e
s
y
s
tem
r
ec
eiv
es
m
ass
iv
e
d
ata,
wh
ich
ar
e
p
r
e
p
r
o
ce
s
s
ed
b
y
g
en
er
ic
i
n
ter
f
ac
es
a
n
d
ad
ap
te
d
to
th
e
ed
u
ca
tio
n
al
f
ield
,
f
r
o
m
th
e
o
p
er
atio
n
al
m
ass
iv
e
d
ata
lay
er
[
2
]
.
W
o
r
th
n
o
tin
g
is
th
at
th
e
s
y
s
tem
in
v
o
l
v
es
two
ty
p
es
o
f
in
te
r
f
ac
es:
d
atab
ase
in
ter
f
ac
e
a
n
d
t
h
e
o
n
t
o
lo
g
ical
o
n
e.
I
n
th
is
s
tag
e,
o
u
r
al
g
o
r
ith
m
m
ak
es
th
e
m
atch
in
g
b
e
twee
n
d
atab
ase
attr
ib
u
tes
an
d
o
n
to
lo
g
ical
attr
ib
u
tes,
wh
ich
h
av
e
alr
ea
d
y
b
ee
n
p
r
o
p
o
s
ed
in
[
7
]
,
th
at
is
,
th
e
c
o
n
ce
p
t
u
al
f
r
a
m
e
wo
r
k
u
s
ed
f
o
r
k
n
o
wled
g
e
ex
tr
ac
tio
n
f
r
o
m
lear
n
in
g
ac
to
r
s
.
−
T
h
e
s
ec
o
n
d
alg
o
r
ith
m
: I
n
th
is
alg
o
r
ith
m
,
th
e
s
y
s
tem
in
co
r
p
o
r
ates o
n
to
lo
g
ical
lear
n
in
g
ap
p
r
o
ac
h
es d
u
r
in
g
k
n
o
wled
g
e
e
x
tr
ac
tio
n
f
r
o
m
th
e
d
atab
ase
lay
er
in
to
th
e
o
n
to
l
o
g
ical
lay
er
.
Hen
ce
,
t
h
e
s
y
s
tem
s
y
n
ch
r
o
n
izes
th
e
b
ig
d
ata
in
d
u
ce
d
b
y
th
e
o
p
er
atio
n
al
b
ig
d
ata
lay
er
(
SQL
an
d
NOSQL
)
an
d
th
e
o
n
to
lo
g
ical
lay
e
r
wh
ich
is
o
n
th
e
o
th
er
in
ter
f
a
ce
.
I
n
th
is
s
tag
e,
th
e
alg
o
r
ith
m
p
r
o
p
o
s
es
an
ap
p
r
o
ac
h
b
ased
o
n
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
tech
n
iq
u
es
to
b
etter
id
en
tify
n
ew
s
o
u
r
ce
s
o
f
lo
ca
l
o
r
d
is
tan
t
k
n
o
wled
g
e,
o
n
th
e
n
atio
n
al
o
r
in
ter
n
atio
n
al
s
ca
le;
th
en
,
it
f
ee
d
s
th
e
ex
tr
ac
ted
k
n
o
wled
g
e
in
to
o
u
r
r
ep
r
esen
tatio
n
s
y
s
te
m
.
I
n
p
ar
allel,
it
v
er
if
ies
th
e
q
u
ality
o
f
th
e
ac
q
u
ir
ed
k
n
o
wled
g
e
as
well
as
its
im
p
ac
t
o
n
th
e
ac
to
r
s
’
p
r
o
f
iles
in
th
e
ed
u
ca
tio
n
al
f
ield
.
−
T
h
e
th
i
r
d
alg
o
r
ith
m
:
I
n
th
is
alg
o
r
ith
m
,
th
e
s
y
s
tem
m
a
k
es
u
s
e
o
f
s
o
m
e
m
eth
o
d
s
f
o
r
id
en
tify
i
n
g
k
n
o
wled
g
e
in
lo
ca
l
MO
OC
s
/
o
r
o
t
h
er
M
o
r
o
cc
a
n
u
n
iv
er
s
ities
MO
OC
s
.
T
h
en
,
it
ad
a
p
ts
th
em
t
o
o
u
r
o
n
to
lo
g
ical
k
n
o
wled
g
e
r
e
p
r
esen
tatio
n
s
y
s
tem
[
2
]
.
T
h
e
alg
o
r
ith
m
is
b
ased
o
n
W
eb
in
telli
g
en
t
m
eth
o
d
s
co
n
f
ig
u
r
ed
f
o
r
th
e
id
e
n
tific
atio
n
o
f
n
ew
ac
to
r
s
’
k
n
o
wled
g
e
s
o
u
r
ce
s
;
th
en
,
it
ad
ap
ts
th
em
t
o
th
e
g
en
e
r
al
co
n
tex
t o
f
o
u
r
k
n
o
wled
g
e
e
x
tr
ac
tio
n
s
y
s
tem
.
T
h
e
o
b
jectiv
e
o
f
th
e
ab
o
v
em
e
n
tio
n
ed
alg
o
r
ith
m
is
to
cr
ea
te
an
in
tellig
en
t
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
s
y
s
tem
,
wh
ile
in
co
r
p
o
r
atin
g
t
h
e
b
est
m
eth
o
d
s
o
f
m
ass
iv
e
k
n
o
wled
g
e
id
e
n
tific
atio
n
a
n
d
e
x
tr
ac
tio
n
d
e
p
en
d
i
n
g
o
n
th
e
r
esu
lts
in
d
u
ce
d
b
y
th
e
l
ea
r
n
in
g
'
ac
to
r
s
’
in
ter
ac
tio
n
s
in
a
MO
OC
s
y
s
tem
.
4.
M
AS
SI
V
E
DA
T
A
P
RE
P
RO
CE
SS
I
NG
I
n
th
is
s
tag
e,
we
ar
e
p
r
o
p
o
s
ed
a
Ma
p
R
ed
u
ce
m
ac
h
i
n
e
lear
n
in
g
b
ased
o
n
b
i
g
d
ata
p
r
o
d
u
ce
d
b
y
MO
OC
s
[
2
]
to
p
er
f
o
r
m
th
e
p
a
r
allel
p
r
e
-
p
r
o
ce
s
s
in
g
o
f
m
ass
iv
e
d
ata
f
allin
g
with
in
v
ar
i
o
u
s
s
tr
u
ctu
r
es.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
o
f
k
n
o
wled
g
e
s
o
u
r
ce
s
is
ac
h
iev
ed
b
y
v
ir
tu
e
o
f
an
aly
zin
g
th
e
r
esu
lts
in
d
u
ce
d
b
y
th
e
lear
n
i
n
g
ac
to
r
s
’
in
ter
ac
tio
n
s
in
MO
OC
s
.
T
h
is
s
y
s
tem
[
2
]
p
r
o
ce
s
s
es
SQL
an
d
No
SQL
m
ass
iv
e
d
a
ta
b
y
an
alg
o
r
ith
m
b
ased
o
n
th
e
HADO
OP
ec
h
o
s
y
s
tem
ass
o
ciate
d
ap
p
r
o
ac
h
es
.
I
t
o
f
f
er
s
m
ass
iv
e
s
em
i
-
s
tr
u
ctu
r
ed
d
ata
in
XM
L
an
d
R
DF f
o
r
m
at
f
o
r
th
e
o
n
to
lo
g
ica
l k
n
o
wled
g
e
r
ep
r
esen
tatio
n
s
y
s
tem
,
th
e
s
u
b
ject
m
atter
o
f
th
e
p
ap
er
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
Ap
r
il 2
0
2
1
:
1
6
7
5
-
1688
1680
5.
P
RO
P
O
SE
D
M
A
CH
I
N
E
I
n
th
is
d
iag
r
am
,
we
p
r
o
p
o
s
e
a
g
lo
b
al
ar
c
h
itectu
r
e
o
f
o
u
r
o
n
to
lo
g
ical
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
s
y
s
tem
f
o
r
lear
n
in
g
ac
to
r
s
b
as
ed
o
n
b
ig
d
ata
r
esu
ltin
g
f
r
o
m
th
eir
in
ter
ac
tio
n
s
in
o
n
lin
e
lear
n
in
g
.
I
t
s
h
o
u
l
d
b
e
n
o
ted
th
at
o
u
r
s
y
s
tem
is
o
p
e
n
to
all
s
o
r
ts
o
f
k
n
o
wled
g
e
s
o
u
r
ce
s
at
th
e
n
atio
n
al
lev
el;
it
is
en
o
u
g
h
to
lin
k
th
e
s
o
u
r
ce
s
to
th
e
s
y
s
tem
.
Fig
u
r
e
2
p
r
o
p
o
s
es
th
e
elem
en
ts
p
r
er
e
q
u
i
s
ite
to
m
a
k
e
th
e
s
em
an
tic
r
ep
r
esen
tatio
n
o
f
t
h
e
ac
to
r
s
'
k
n
o
wled
g
e.
Fig
u
r
e
2
.
Acto
r
s
’
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
s
y
s
tem
b
ased
o
n
MO
OC
s
5
.
1
.
O
nt
o
lo
g
ica
l
m
a
chine f
o
r
k
no
wledg
e
re
presenta
t
io
n in MOO
C
T
h
is
s
y
s
tem
m
ak
es
th
e
o
n
to
lo
g
ical
r
ep
r
esen
tatio
n
o
f
th
e
b
ig
d
ata
p
r
e
-
p
r
o
ce
s
s
ed
in
[
2
]
.
T
h
e
r
ep
r
esen
tatio
n
b
eg
in
s
with
th
e
o
n
to
lo
g
ical
m
ap
p
i
n
g
alg
o
r
ith
m
(
alg
o
r
ith
m
1)
b
etwe
en
th
e
i
n
p
u
t
Data
Set
an
d
/
o
r
o
n
to
lo
g
ies
k
n
o
wled
g
e
s
o
u
r
ce
s
an
d
th
e
o
u
tp
u
t
o
n
to
lo
g
ies.
T
h
en
,
th
e
o
n
to
lo
g
ical
lear
n
in
g
al
g
o
r
ith
m
(
alg
o
r
ith
m
2
)
f
ee
d
s
k
n
o
wled
g
e
s
o
u
r
ce
s
e
x
tr
ac
ted
f
r
o
m
o
n
lin
e
lear
n
i
n
g
t
h
r
o
u
g
h
in
to
th
e
o
u
tp
u
t o
n
to
lo
g
ies.
T
h
is
p
r
o
ce
s
s
is
r
ea
lized
th
r
o
u
g
h
tr
an
s
f
o
r
m
in
g
m
ass
iv
e
d
ata
in
to
m
ass
iv
e
o
n
to
lo
g
ical
k
n
o
wled
g
e
,
wh
ile
m
ak
in
g
u
s
e
o
f
th
e
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
th
r
o
u
g
h
o
u
t th
e
s
tag
e
s
o
f
o
n
to
lo
g
ical
k
n
o
wled
g
e
co
n
s
tr
u
ctio
n
.
Fin
ally
,
in
an
im
p
o
r
tan
t
later
s
tag
e,
th
e
o
n
to
lo
g
ical
en
r
ich
m
en
t
alg
o
r
ith
m
(
alg
o
r
ith
m
3
)
d
etec
ts
n
ew
k
n
o
wled
g
e
s
o
u
r
ce
s
in
MO
OC
s
.
T
h
is
a
lg
o
r
ith
m
r
ep
r
es
en
ts
o
n
e
s
tag
e
am
o
n
g
o
th
e
r
s
p
r
o
p
o
s
ed
in
o
u
r
Fra
m
ewo
r
k
[
7
]
: I
n
t
h
is
s
tag
e,
we
f
o
cu
s
o
n
s
o
m
e
d
ef
in
itio
n
s
o
f
o
u
r
s
y
s
tem
v
ar
iab
les:
Def
in
itio
n
1
: Fo
r
ea
c
h
g
iv
e
n
o
n
to
lo
g
y
as in
p
u
t o
f
th
e
s
y
s
tem
we
h
av
e:
Oi
n
i
=
{
Oi
n
1
,
Oi
n
2
,
…
.
.
,
Oi
n
n
}
In
tha
t
:
Oi
n
i
=
{
Ci
,
Ri
,
Vi
}
A
n
d
(
Ci
=
{
C1
,
C2
,
…
.
.
,
Cn
}
,
Ri
=
{
R1
,
R2
,
…
.
.
,
Rn
}
,
V
i
=
{
V1
,
V2
,
…
.
.
,
Vn
}
)
in
wi
c
h
Ri
=
{
is
_
pa
r
t
,
pa
r
t
_
of
}
;
Def
in
itio
n
2
:
Fo
r
ea
c
h
g
iv
e
n
o
n
to
lo
g
y
:
DS
in
i
=
{
D
Sin
1
,
DS
in
2
,
…
.
.
,
DS
in
n
}
in
th
at:
DSin
i
=
{
Ai
,
Ti
,
Vi
}
a
n
d
(
Ai
=
{
A1
,
A2
,
…
.
.
,
An
}
,
Ti
=
{
T1
,
T2
,
…
.
.
,
Tn
}
,
Vi
=
{
V1
,
V2
,
…
.
.
,
Vn
}
)
.
Def
in
itio
n
3
:
C
alcu
latio
n
o
f
th
e
s
im
ilar
ity
[
1
]
b
etwe
en
c
o
n
ce
p
ts
Sim
(
C
i,
C
i+1
)
in
th
at:
−
E
x
tr
ac
tio
n
f
u
n
ctio
n
b
ased
wo
r
d
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8
7
0
8
I
n
tellig
en
t m
a
ch
in
e
f
o
r
o
n
to
lo
g
ica
l rep
r
esen
ta
tio
n
o
f
…
(
A
b
d
ella
d
im
Ha
d
io
u
i
)
1681
−
E
x
tr
ac
tio
n
f
u
n
ctio
n
b
ased
co
n
ce
p
ts
(
1
,
2
)
=
2
×
3
1
+
2
+
2
×
3
(
2
)
Su
ch
as:
N
r
ep
r
esen
ts
th
e
lev
e
l
o
f
th
e
n
o
d
e;
wi
r
e
p
r
esen
ts
th
e
en
ter
ed
wo
r
d
s
;
Ci
r
ep
r
esen
ts
th
e
c
o
n
ce
p
t
in
t
h
e
o
n
to
lo
g
ies.
Def
in
itio
n
4
:
Fo
r
ea
c
h
g
iv
e
n
o
n
to
lo
g
y
Oo
uti
=
{
Oi
n
_
pe
r
t
,
Oi
n
_
n
on
pe
r
t
}
in
th
at
:
O
out
_
pe
r
t
=
{
Ci
,
Ri
,
Vi
}
a
n
d
(
Ci
=
{
C1
,
C2
,
…
.
.
,
Cn
}
,
Ri
=
{
R1
,
R2
,
…
.
.
,
Rn
}
,
Vi
=
{
V1
,
V2
,
…
.
.
,
Vn
}
)
a
n
d
O
out
n
o
n
per
t
=
{
Ci
,
Ri
,
Vi
}
a
n
d
(
Ci
=
{
C1
,
C2
,
…
.
.
,
Cn
}
,
Ri
=
{
R1
,
R2
,
…
.
.
,
Rn
}
,
Vi
=
{
V1
,
V2
,
…
.
.
,
Vn
}
)
,
F
or
e
a
c
h
give
n
on
tol
ogy
➔
O
r
e
f
s
uc
h
O
r
e
f
=
O
out
_
pe
r
t
.
Def
in
itio
n
5
:
ar
tific
ial
n
e
u
r
al
n
etwo
r
k
s
ar
e
d
ef
i
n
e
d
b
y
lear
n
in
g
f
u
n
ctio
n
o
n
to
lo
g
y
:
1
()
n
ii
i
f
x
w
x
=
=+
(
3
)
Su
ch
as: wi
an
d
x
i th
e
i
n
p
u
t
o
f
th
e
ANN
m
ac
h
in
e,
β th
e
ac
tiv
atio
n
th
r
esh
o
ld
o
f
n
o
d
e
Def
in
itio
n
6
:
T
h
e
two
m
ath
em
atica
l m
o
d
els f
o
r
ex
t
r
ac
tin
g
th
e
wo
r
d
s
ar
e
C
B
OW
an
d
Sk
ip
-
g
r
am
:
−
C
B
O
W
1
,
0
1
(
)
l
og
(
/
)
n
t
t
j
t
c
j
c
j
f
x
p
w
w
T
+
=
−
=
(
4
)
−
Sk
ip
-
g
r
am
1
,
0
1
(
)
l
og
(
/
)
n
t
j
t
t
c
j
c
j
f
x
p
w
w
T
+
=
−
=
(
5
)
Su
ch
as:
L
et
ar
e
th
e
ce
n
tr
al
tar
g
et
wo
r
d
wt
an
d
th
e
c
o
n
tex
t
w
o
r
d
wj
r
esp
ec
tiv
ely
i
n
d
ex
e
d
to
t
an
d
j
in
th
e
d
ictio
n
ar
y
.
T
h
e
co
n
d
itio
n
al
p
r
o
b
ab
ilit
y
o
f
g
en
e
r
atin
g
t
h
e
wo
r
d
co
n
tex
t
f
o
r
th
e
g
iv
e
n
ce
n
tr
al
tar
g
et
wo
r
d
ca
n
b
e
o
b
tain
ed
b
y
p
e
r
f
o
r
m
in
g
th
e
s
y
s
tem
o
n
th
e
i
n
ter
n
al
p
r
o
d
u
ct
o
f
t
h
e
v
ec
to
r
.
5
.
2
.
T
he
co
ntr
ibu
t
io
n o
f
t
his
m
a
chine
5
.
2
.
1
.
O
n
to
l
o
g
ic
a
l
m
a
p
p
in
g
la
y
e
r
I
n
th
is
s
tag
e,
o
u
r
s
y
s
tem
u
s
es
an
ap
p
r
o
ac
h
wh
ich
is
m
o
r
e
ad
eq
u
ate
f
o
r
m
ak
in
g
co
r
r
esp
o
n
d
e
n
ce
s
b
etwe
en
d
atab
ase
attr
ib
u
tes
(
SQL
AND
N
OSQL
)
an
d
o
n
to
lo
g
ical
attr
ib
u
tes
(
OW
L
,
R
D
F
)
.
Ou
r
in
v
esti
g
atio
n
o
f
th
e
r
elatin
g
liter
atu
r
e
r
ev
ea
ls
th
at
r
esear
ch
er
s
h
av
e
p
r
o
p
o
s
ed
m
an
y
ap
p
r
o
ac
h
es
an
d
m
e
th
o
d
s
d
ea
lin
g
with
m
ass
iv
e
d
ata
in
teg
r
atio
n
[2
9
]
.
I
n
d
ee
d
,
th
e
r
elev
an
ce
o
f
o
u
r
ap
p
r
o
ac
h
is
ap
p
a
r
en
t
at
th
e
le
v
el
o
f
i
n
co
r
p
o
r
atin
g
th
e
ad
d
e
d
v
alu
es
o
f
b
i
g
d
ata
-
b
ased
lin
k
ed
an
d
o
p
en
d
ata
th
r
o
u
g
h
we
b
k
n
o
wled
g
e
in
teg
r
atio
n
.
Hen
ce
,
th
is
alg
o
r
ith
m
o
f
f
e
r
s
g
e
n
er
ic
s
o
lu
t
io
n
s
f
o
r
th
e
m
a
p
p
in
g
b
etwe
en
th
e
ele
m
en
ts
o
f
R
DB
MS
an
d
th
o
s
e
o
f
R
DF
an
d
OW
L
.
T
h
is
lin
k
ag
e
is
i
n
tr
o
d
u
ce
d
b
y
o
u
r
c
o
n
ce
p
t
u
al
m
o
d
el
lin
g
p
r
o
p
o
s
ed
in
o
u
r
o
n
to
lo
g
y
-
b
ased
c
o
n
ce
p
t
u
al
f
r
am
ewo
r
k
[
7
]
,
b
y
s
o
d
o
in
g
,
we
d
eter
m
in
e
d
a
s
tr
u
ctu
r
ed
a
n
d
/
o
r
s
em
i
s
t
r
u
ctu
r
e
d
d
ataset
in
o
n
lin
e
lea
r
n
in
g
s
y
s
tem
s
th
r
o
u
g
h
:
−
DS (
Attr
ib
u
te,
ty
p
e,
v
alu
e)
An
d
OW
L
o
n
to
lo
g
ical
r
ep
r
ese
n
tatio
n
th
r
o
u
g
h
th
e
f
o
llo
win
g
attr
ib
u
tes:
−
ON
(
class
,
R
,
Valu
e)
T
h
e
o
b
jectiv
e
in
t
h
is
s
tag
e
lies
in
th
e
tr
an
s
f
o
r
m
atio
n
o
f
d
ataset
in
to
o
n
t
o
lo
g
y
.
On
li
n
e
lear
n
in
g
s
y
s
tem
s
,
in
th
is
s
tag
e,
p
r
o
d
u
c
e
b
ig
d
ata
i
n
ac
c
o
r
d
a
n
ce
with
s
ev
er
al
s
tr
u
ctu
r
es
th
at
a
r
e
p
r
e
-
p
r
o
ce
s
s
ed
b
y
o
u
r
m
atch
in
g
lear
n
i
n
g
;
th
is
wo
r
k
p
er
f
o
r
m
s
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
o
f
th
e
m
ass
iv
e
d
ata
p
r
o
d
u
ce
d
b
y
ac
to
r
s
[
2
]
.
T
h
is
wo
r
k
tak
es
b
ig
d
ata
f
r
o
m
an
y
s
tr
u
ctu
r
e
as
in
p
u
t;
it
f
o
llo
ws
th
at
it
ap
p
lies
m
an
y
m
eth
o
d
s
to
an
aly
ze
an
d
p
r
e
-
p
r
o
ce
s
s
th
em
.
Ou
r
aim
h
er
e
is
to
m
ak
e
an
au
to
m
atic
m
ap
p
i
n
g
b
etwe
en
d
atab
ase
attr
ib
u
tes
an
d
th
e
o
n
to
lo
g
ical
o
n
es,
r
esp
ec
t
in
g
th
e
s
tan
d
ar
d
s
o
f
o
n
to
lo
g
ical
m
ap
p
in
g
[
1
8
]
.
I
n
a
g
iv
en
s
tag
e,
o
n
t
o
lo
g
ical
m
ap
p
in
g
u
s
es
lin
k
ed
an
d
o
p
en
d
ata
f
o
r
in
co
r
p
o
r
ati
n
g
k
n
o
wled
g
e
f
r
o
m
v
ar
i
o
u
s
s
o
u
r
ce
s
b
ased
o
n
SP
AR
QL
lan
g
u
ag
e
,
wh
ich
is
a
q
u
er
y
la
n
g
u
a
g
e
f
o
r
web
s
em
an
tic
d
ata
ac
ce
s
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
Ap
r
il 2
0
2
1
:
1
6
7
5
-
1688
1682
T
h
e
m
ap
p
in
g
al
g
o
r
ith
m
:
T
h
e
m
ap
p
in
g
f
u
n
ctio
n
s
d
ea
lt
with
in
v
ar
io
u
s
wo
r
k
s
ar
e
o
f
d
if
f
er
en
t
s
o
r
ts
.
Dr
awin
g
o
n
s
u
ch
wo
r
k
s
,
we
d
eter
m
in
e
m
ap
p
i
n
g
f
u
n
ctio
n
s
b
etwe
en
k
n
o
wled
g
e
s
o
u
r
ce
s
(
a
Data
s
et
an
d
/o
r
o
n
to
lo
g
y
in
p
u
t)
an
d
o
n
t
o
lo
g
y
o
u
tp
u
t
in
o
u
r
k
n
o
wled
g
e
ex
t
r
a
ctio
n
s
y
s
tem
[
2
]
.
T
h
e
f
o
llo
win
g
alg
o
r
ith
m
s
h
o
ws,
in
d
etail,
all
th
e
s
tep
s
to
f
o
llo
w:
Alg
o
r
ith
m
Input:
Ω = DS {A, T, V} or O
in
{C
in
, R
in
, V
in
}// Knowledge sources and knowledge destination are not
the same concepts (DataSet or owl to OWL case).
Output:
O
out
{C
out
, R
out
, V
ou
t } // knowledge collections of learning actors according toactor
categories.
Start
IF(DS ≠0) THEN
Ω ← DS
Step 1
://
Source and destination are not the same concepts (the case DataSet to ontology)
,
,
,
l
o
g
(
)
m
a
x
ij
ij
z
z
i
i
f
D
W
fd
=
// Extraction of key concepts wi, j
v
=
1
,
0
1
l
o
g
(
)
T
t
j
t
t
c
j
c
j
p
W
W
T
+
=
−
//matching between source
s attributes (dataset) and
ontologies destination (knowledge)
12
12
12
(
)
(
)
(
,
)
|
(
)
|
|
(
)
|
v
w
v
w
sr
e
l
w
w
v
w
v
w
=
// Calculation of the semantic similarity of knowledge
[relatedness, our ref].
IF(srel = 1) THEN
w1 et w2 are synonymous
ELSE
IF (srel = 0) THEN
w1 and w2 are syn
onymous
ELSE
IF(srel = 0) T
HEN
w1 and w2 are not similar otherwise // we will look for the type of
relationship, we propose an evaluation rule (metonymy, antonym, hyperonym,
hyponym, ....).
SVM on calculating offset
Ri = SVM (wi, wj) // call to our semanti
c relation extraction algor
ithm
O
out
O
out
+ {Wi,Ri,Vi}
END IF
END IF
END IF
ELSE
Ω ← OWL.
Step 2:
//
OWL Alignment of source ontology
and global ontology objects (C,
P, V) the
ontology
O1 (C1, P1, V1) the ontology O2 (C2, P2, V2) the ontology
AL = {en1, e
n2, coresp} en1 an entity of O1, en2 an entity of O2, coresp
correspondence between w1 and en2 //Correspondence between the source
attributes (dataset) and destination (knowledge)
(
1
,
2
)
=
2
×
3
1
+
2
+
2
×
3
// Calculate the similarity between
knowledge
[relatedness,note ref].
FOR each w1 in Entity1 then
Sim_temp = null;
FOR each w2 de Entity2
Sim= {sim (name1, name2), sim (label1, label2), sim (content1, content2)}
IF sim > sim_temp
sim_temp = sim
elemen
t =w2
end if
END
Al
Al+ {w2, elem
ent, sim_temp}
end
O
out
Al
END IF
return O
out
End
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8
7
0
8
I
n
tellig
en
t m
a
ch
in
e
f
o
r
o
n
to
lo
g
ica
l rep
r
esen
ta
tio
n
o
f
…
(
A
b
d
ella
d
im
Ha
d
io
u
i
)
1683
5
.
2
.
2
.
O
n
t
o
l
o
g
ica
l
lea
r
n
i
n
g
la
y
e
r
I
n
th
is
s
tag
e,
o
u
r
m
ac
h
in
e
p
a
r
am
eter
izes
th
e
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
s
y
s
tem
[
7
]
,
wh
ich
is
b
ased
o
n
th
e
r
esu
ltin
g
o
n
to
lo
g
y
o
f
all
k
n
o
wled
g
e
s
o
u
r
ce
s
(
NOSQL
o
r
SQL)
[
2
]
em
an
atin
g
f
r
o
m
th
e
o
p
er
atio
n
al
b
ig
d
ata
lay
er
.
Ou
r
o
b
jectiv
e
h
e
r
e
is
to
p
r
o
p
o
s
e
an
o
p
tim
a
l
m
eth
o
d
f
o
r
au
t
o
m
atic
f
ee
d
in
g
o
f
o
u
r
o
n
to
lo
g
ical
k
n
o
wled
g
e
b
ase
th
r
o
u
g
h
d
ete
ctin
g
th
e
n
ew
k
n
o
wled
g
e
p
r
o
d
u
ce
d
in
o
u
r
b
asic
s
y
s
tem
an
d
b
y
m
ea
s
u
r
in
g
th
e
s
im
ilar
ity
o
f
th
e
r
ec
eiv
e
d
k
n
o
wled
g
e.
T
h
is
o
b
jectiv
e
is
ac
h
iev
ed
r
esti
n
g
o
n
th
e
alr
ea
d
y
co
n
d
u
cted
s
tu
d
ies
on
th
e
b
est
m
eth
o
d
s
o
f
o
n
to
lo
g
ic
al
lear
n
in
g
th
r
o
u
g
h
th
e
ca
lcu
l
atio
n
o
f
th
e
s
im
ilar
ity
o
f
th
e
ac
q
u
ir
ed
k
n
o
wled
g
e.
I
n
o
r
d
er
to
h
a
v
e
a
n
e
n
v
ir
o
n
m
e
n
t
ca
p
a
b
le
o
f
s
y
s
tem
atic
a
n
d
r
ap
id
lear
n
in
g
,
we
h
av
e
m
ad
e
i
n
-
d
ee
p
an
aly
s
is
o
n
th
e
ex
is
tin
g
lear
n
in
g
m
eth
o
d
s
in
th
e
liter
atu
r
e
[3
0
]
.
Am
o
n
g
th
e
m
eth
o
d
s
,
we
h
av
e
id
en
tif
ied
s
u
p
er
v
i
s
ed
an
d
u
n
s
u
p
er
v
is
ed
lear
n
in
g
m
eth
o
d
s
[
3
1
]
.
I
n
th
is
alg
o
r
ith
m
,
th
er
e
is
a
r
an
g
e
o
f
p
r
o
ce
s
s
es
t
o
b
e
a
p
p
lied
o
n
o
u
r
s
y
s
tem
.
Fo
llo
win
g
an
an
aly
s
is
o
f
th
e
wo
r
k
s
p
u
b
lis
h
ed
in
s
cien
tific
jo
u
r
n
als
r
elatin
g
to
o
u
r
r
esear
ch
ar
ea
,
we
o
b
s
er
v
ed
th
at
all
o
f
th
e
ta
k
en
a
p
p
r
o
ac
h
es we
r
e
b
ased
o
n
o
n
e
o
r
all
o
f
t
h
e
f
o
llo
win
g
s
tep
s
:
−
I
d
en
tific
atio
n
o
f
s
tr
u
ctu
r
e
d
d
at
a
r
ec
eiv
ed
f
r
o
m
th
e
o
p
e
r
atio
n
a
l m
ass
iv
e
d
ata
lay
er
.
−
Def
in
itio
n
o
f
t
h
e
tr
an
s
m
is
s
io
n
c
h
an
n
el
b
etwe
en
th
e
m
ass
iv
e
d
ata
an
d
m
ass
iv
e
k
n
o
wled
g
e
i
n
ter
f
ac
es.
−
Def
in
itio
n
o
f
t
h
e
tr
an
s
m
is
s
io
n
m
ea
n
s
f
r
o
m
p
r
e
-
p
r
o
ce
s
s
ed
m
a
s
s
iv
e
d
ata
to
o
n
to
lo
g
ical
lay
er
−
I
m
p
lem
en
tatio
n
o
f
o
n
to
lo
g
ical
lear
n
in
g
alg
o
r
ith
m
.
−
I
n
teg
r
atio
n
o
f
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
-
b
ased
ap
p
r
o
ac
h
es f
o
r
p
ar
allel
p
r
o
ce
s
s
in
g
o
f
d
if
f
er
e
n
t
k
n
o
wled
g
e
s
o
u
r
ce
s
.
L
o
ad
in
g
alg
o
r
ith
m
:
I
n
th
is
alg
o
r
ith
m
,
we
m
o
d
if
y
t
h
e
d
ata
id
en
tifie
d
b
y
o
u
r
k
n
o
wled
g
e
ex
tr
ac
tio
n
s
y
s
tem
.
I
n
th
is
s
tag
e,
th
e
g
o
al
is
to
m
ak
e
o
u
r
lear
n
i
n
g
s
y
s
tem
o
p
tim
al
an
d
f
ast,
an
d
,
th
u
s
,
th
e
m
o
s
t
in
teg
r
ate
d
at
th
e
lev
el
o
f
o
u
r
tar
g
et
k
n
o
w
led
g
e
r
ep
r
esen
tatio
n
s
y
s
tem
.
Hen
ce
,
th
is
alg
o
r
ith
m
is
d
e
f
in
ed
as f
o
llo
ws:
Alg
o
r
ith
m
Input:
Mega_data: the preprocessed
missives data;
Global_Onto: the output ontologies;
C: communicational channel.
Ou
t
pu
t
:
Space of knowledge relevant for learning actors: SPAQL or NSPARCL
Start:
Ad
di
ng
th
e
st
re
am
re
ce
iv
ed
fr
om
Me
ta
_b
ig
da
ta
in
O_
co
ll
ec
ti
on
wh
il
e
re
sp
ec
ti
ng
th
e
structure de
fined at the start(wi , xi )
1
()
n
ii
i
f
x
w
x
=
=
+
// Application of the formula for calculating different
possible cases
IF (f(x) > β ) thenThe activation of neurons if they pass the threshold for the
acquired knowledge.
Y = SVM (act (activities), n
ote, TR (quarter), mm (memory), st (style), kg, peda
(p
edagogies), inter (interpretation), mode_e (mode of education), us_it (IT
usage), inno (Innovation))// we define two classes pert and not pert in such a way
that the actor with the note higher than 10
belongs to the relevant class c
IF(y <1) then
O
out
nonpert= O
out
nonpert+ {Ci, Ri}
ELSE
O
out
pert= O
out
pert+ {Ci, Ri}
END IF
END IF
End
5
.
2
.
3
.
O
nto
lo
g
ica
l e
nrichm
ent
la
y
er
T
h
is
s
tep
is
p
r
o
p
o
s
ed
i
n
o
r
d
er
to
g
iv
e
o
u
r
k
n
o
wled
g
e
r
e
p
r
esen
tatio
n
s
y
s
tem
m
o
r
e
s
ca
lab
ili
ty
in
ca
s
e
o
f
ac
q
u
is
itio
n
o
f
o
th
e
r
k
n
o
w
led
g
e
s
o
u
r
ce
s
(
SQL
an
d
/
o
r
NOSQL
)
an
d
,
th
u
s
,
en
r
ic
h
it
b
y
ea
ch
r
ec
eiv
ed
o
n
to
lo
g
ical
k
n
o
wled
g
e.
T
h
e
s
y
s
tem
in
q
u
esti
o
n
p
r
o
v
id
es
a
r
ich
en
v
ir
o
n
m
e
n
t
f
o
r
e
d
u
ca
tio
n
al
en
titi
es
with
r
eg
ar
d
to
lear
n
in
g
ac
to
r
’
s
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
.
Fo
r
th
e
en
r
ich
m
en
t o
f
s
u
ch
r
ep
r
esen
t
atio
n
,
as
o
u
r
s
tu
d
ies
s
h
o
w,
Mo
r
o
cc
a
n
g
o
v
er
n
m
e
n
t
,
lik
e
o
th
er
g
o
v
e
r
n
m
e
n
ts
,
h
a
s
s
et
th
e
o
b
jectiv
e
o
f
cr
ea
ti
n
g
o
n
li
n
e
lear
n
in
g
s
y
s
tem
s
as
a
r
ef
er
en
ce
(
i.e
.
,
MO
OC
s
)
;
o
u
r
s
y
s
tem
m
ak
es
u
s
e
o
f
ac
to
r
s
'
in
ter
ac
tio
n
s
in
th
ese
s
y
s
tem
s
as
k
n
o
wled
g
e
s
o
u
r
ce
s
.
T
h
e
in
te
g
r
atio
n
o
f
MO
OC
s
y
s
tem
s
i
s
b
ein
g
g
en
er
alize
d
at
th
e
lev
el
o
f
all
Mo
r
o
cc
an
u
n
iv
er
s
ities
[
2
2
,
3
2
]
.
B
y
an
al
y
zin
g
th
ese
s
y
s
tem
s
,
we
f
in
d
th
at
th
ey
y
ield
m
ass
iv
e
k
n
o
wled
g
e
th
at
ca
n
b
e
in
teg
r
ated
in
t
o
o
u
r
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
s
y
s
tem
.
I
t
f
o
llo
ws
th
at
it
is
p
r
er
eq
u
is
ite
t
h
at
we
th
in
k
o
f
th
e
m
ea
n
s
o
f
o
n
to
lo
g
ical
en
r
ich
m
en
t
th
at
m
ak
e
d
is
co
v
er
y
o
f
th
e
b
est
n
ew
k
n
o
wled
g
e
wh
en
co
n
n
ec
ted
with
s
o
m
e
MO
OC
s
in
u
n
iv
er
s
ities
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
Ap
r
il 2
0
2
1
:
1
6
7
5
-
1688
1684
T
h
is
o
b
jectiv
e
is
ac
h
iev
ed
t
h
r
o
u
g
h
th
e
i
n
teg
r
atio
n
o
f
a
r
t
if
icial
in
tellig
en
ce
-
b
ased
ag
e
n
t
s
to
th
e
d
is
co
v
er
y
o
f
k
n
o
wled
g
e
at
th
e
lev
el
o
f
th
e
Mo
r
o
cc
an
MO
OC
s
y
s
tem
.
I
n
th
e
liter
atu
r
e,
we
h
av
e
id
en
tifie
d
n
u
m
er
o
u
s
r
esear
ch
es
wo
r
k
s
th
at
d
ea
l
with
o
n
to
lo
g
ical
en
r
ic
h
m
en
t
p
r
o
jects,
th
e
b
asic
p
r
i
n
ci
p
le
ar
o
u
n
d
wh
ich
r
ev
o
lv
es
th
e
o
n
to
lo
g
ical
r
ep
r
e
s
en
tati
o
n
o
f
ed
u
ca
tio
n
al
r
eso
u
r
ce
s
.
I
n
ad
d
itio
n
to
th
ese
m
eth
o
d
s
,
th
is
alg
o
r
ith
m
aim
s
to
id
en
tify
n
ew
s
o
u
r
ce
s
o
f
k
n
o
wled
g
e,
a
n
d
th
en
a
d
ap
t
s
u
ch
s
o
u
r
ce
s
to
o
u
r
p
r
o
p
o
s
e
d
s
y
s
tem
[
7
]
wh
ich
p
r
o
v
id
es a
f
r
am
ewo
r
k
f
o
r
ex
tr
ac
tin
g
k
n
o
wled
g
e
f
r
o
m
lear
n
in
g
ac
to
r
s
.
E
n
r
ich
m
en
t
Alg
o
r
ith
m
:
On
to
l
o
g
ical
en
r
ich
m
e
n
t:
As
p
r
esen
ted
in
th
e
f
o
r
eg
o
in
g
,
th
is
alg
o
r
ith
m
,
in
p
r
in
cip
le,
p
r
o
p
o
s
es
a
m
eth
o
d
o
f
id
en
tif
y
in
g
d
is
tan
t
k
n
o
wle
d
g
e
s
o
u
r
ce
s
,
b
e
it
o
n
to
lo
g
y
(
Oi)
o
r
m
ass
iv
e
d
ata
(
DSi).
T
h
e
alg
o
r
it
h
m
p
r
o
v
id
es
in
d
etail
th
e
s
tep
s
to
f
o
llo
w
f
o
r
a
b
etter
o
n
to
lo
g
ical
e
n
r
ich
m
e
n
t:
Alg
o
r
ith
m
Input:
Ip, structure, Area, country,
Massive data
D = {di}
An ontology: O = {oi} as input
Output:
Collection of knowledge based on domain ontology.
Start:
A
dding new knowledge to an external knowledge
source location
IF Dsi ≠ 0
Ω = Dsi
•
Call to big data preprocessing approaches;
•
Call to the ontological mapping algorithm;
•
Call to the Step 1 function of the mapping algorithm;
•
Call to the ontological loading algo
rithm.
ELSE
•
Call to the ontological mapping algorithm;
•
Call to the Step 2 function of the mapping algorithm.
END IF
End
6.
E
XP
E
R
I
M
E
N
T
I
n
th
is
ex
p
er
im
e
n
t,
we
em
p
h
asize
th
e
im
p
o
r
ta
n
ce
o
f
th
e
o
n
to
lo
g
ical
m
ap
p
in
g
s
tag
e
in
th
e
ex
p
er
im
en
tal
ev
al
u
atio
n
o
f
th
e
f
u
n
ctio
n
i
n
g
o
f
o
u
r
m
ac
h
i
n
e
.
T
h
e
r
esu
lts
o
f
th
is
ex
p
er
im
e
n
t
g
iv
e
u
s
an
i
d
ea
ab
o
u
t
t
h
e
r
ee
l
ex
p
e
r
ien
ce
o
f
th
is
m
ac
h
in
e.
I
n
th
is
ex
p
er
im
e
n
tal
p
h
ase,
o
u
r
s
y
s
tem
tak
es
a
s
in
p
u
t
m
ass
iv
e
d
ata
o
f
lear
n
in
g
ac
tiv
ity
tr
ac
es
in
XM
L
f
o
r
m
at
(
m
ass
iv
e
d
ata
p
r
e
-
p
r
o
ce
s
s
ed
b
y
o
u
r
lear
n
in
g
m
ac
h
in
e
[
2
]
,
f
o
r
ex
am
p
le
d
ataset
(
2
2
9
0
2
2
r
o
w
)
)
.
Ma
s
s
iv
e
d
ata
tr
ac
es
wer
e
ex
tr
ac
ted
f
r
o
m
th
e
o
n
lin
e
lear
n
i
n
g
s
y
s
tem
o
f
th
e
Mo
h
am
ad
ia
Sch
o
o
l
o
f
E
n
g
in
ee
r
in
g
(
E
MI
)
.
T
o
d
o
th
e
o
n
to
lo
g
ical
m
ap
p
in
g
,
we
will u
s
e
th
e
o
n
t
o
lo
g
ical
r
e
p
r
esen
tatio
n
ed
ito
r
P
r
o
tég
é
,
wh
ich
r
e
p
r
esen
ts
an
o
n
t
o
lo
g
i
ca
l
m
ap
p
i
n
g
t
o
o
l
t
h
at
in
teg
r
a
tes
p
lu
g
-
in
f
o
r
tr
a
n
s
f
o
r
m
i
n
g
k
n
o
wled
g
e
s
o
u
r
ce
s
(
Data
s
et,
XM
L
)
to
o
n
to
lo
g
y
(
OW
L
)
.
T
h
is
to
o
l
p
er
f
o
r
m
s
o
n
to
lo
g
ical
m
ap
p
i
n
g
f
o
r
th
e
s
em
i
s
tr
u
ctu
r
ed
d
ata
(
XM
L
)
.
I
n
th
is
m
ap
p
in
g
s
tag
e,
th
e
Pro
teg
e
o
n
to
lo
g
ical
r
e
p
r
esen
tatio
n
to
o
l
in
teg
r
ates
p
lu
g
-
in
f
o
r
m
ap
p
in
g
,
am
o
n
g
th
ese
to
o
ls
we
h
av
e
i
n
th
e
O
n
to
p
m
ap
p
i
n
g
liter
atu
r
e
wh
ich
r
ep
r
esen
ts
a
n
o
n
to
lo
g
ical
m
ap
p
i
n
g
t
o
o
l.
T
h
e
co
r
r
esp
o
n
d
e
n
ce
is
m
ad
e
eith
er
b
y
co
d
i
n
g
o
r
b
y
g
r
ap
h
ic
ass
is
tan
t.
Fig
u
r
e
3
s
h
o
ws
i
n
d
etail
th
e
co
r
r
esp
o
n
d
en
ce
m
a
d
e
in
o
u
r
c
ase.
I
n
th
is
s
tep
,
we
h
av
e
as
o
u
t
p
u
t
an
o
n
to
lo
g
ical
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
o
f
lear
n
in
g
ac
to
r
s
.
T
h
e
Fig
u
r
e
3
s
h
o
ws
th
e
r
ep
r
esen
tatio
n
class
,
r
esu
ltin
g
f
r
o
m
th
e
ap
p
licatio
n
o
f
th
e
o
n
to
lo
g
ical
m
ap
p
in
g
f
u
n
cti
o
n
p
r
o
v
id
e
d
b
y
th
e
O
n
to
p
p
lu
g
-
i
n
.
Fo
llo
win
g
th
e
an
aly
s
is
o
f
th
e
k
n
o
wled
g
e
p
r
o
d
u
ce
d
b
y
o
u
r
s
y
s
tem
,
we
o
b
s
er
v
e
th
at
th
is
latter
s
o
r
ts
o
u
t
k
n
o
wled
g
e,
wh
ich
is
av
ailab
le
f
o
r
u
s
e
as
p
ar
t
o
f
b
o
t
h
f
o
r
m
al
an
d
in
f
o
r
m
al
o
n
lin
e
lear
n
in
g
s
ess
io
n
s
,
d
e
p
en
d
in
g
o
n
ac
to
r
s
’
p
r
o
f
iles
.
A
cc
o
r
d
in
g
ly
,
it
ca
n
cr
ea
te
an
en
v
ir
o
n
m
en
t
f
o
r
d
ev
elo
p
i
n
g
s
u
ch
p
r
o
f
iles
.
W
e
n
o
ted
th
at
k
n
o
wled
g
e
f
alls
in
to
two
ca
teg
o
r
ies:
a.
R
elev
an
t
k
n
o
wled
g
e,
wh
ich
is
p
ar
t
o
f
th
e
m
ass
iv
e
k
n
o
wled
g
e,
d
ep
en
d
s
o
n
th
e
f
lo
w
o
f
th
e
m
ass
iv
e
d
ata
ex
tr
ac
ted
at
th
e
le
v
el
o
f
th
e
o
p
e
r
atio
n
al
d
ata
lay
er
.
I
n
d
ee
d
,
th
e
ex
tr
ac
ted
d
ata
ar
e
o
f
d
if
f
e
r
en
t
s
o
r
ts
.
W
e
m
ay
r
ef
er
f
o
r
ex
am
p
le
t
o
th
e
f
o
llo
win
g
:
−
Kn
o
wled
g
e
r
elate
d
to
ef
f
ec
ts
:
th
is
ty
p
e
r
e
p
r
esen
ts
th
e
k
n
o
wled
g
e
r
e
f
lectin
g
th
e
e
f
f
ec
ts
o
f
t
h
e
ac
to
r
s
,
s
u
ch
as c
o
p
y
in
g
th
e
f
ile,
c
o
n
s
u
ltin
g
t
h
e
d
o
c
u
m
en
ts
,
an
d
r
ea
d
i
n
g
d
o
c
u
m
en
ts
,
etc.
−
Kn
o
wled
g
e
y
ield
ed
d
u
e
t
o
p
r
o
d
u
ctio
n
s
d
u
r
in
g
a
lear
n
in
g
s
ess
io
n
:
it
is
th
e
r
esu
lt
o
f
ac
t
o
r
s
'
in
ter
ac
tio
n
s
(
an
s
wer
in
g
q
u
esti
o
n
s
,
test
ev
alu
atio
n
s
,
an
d
ex
a
m
s
,
etc.
)
−
Kn
o
wled
g
e
p
r
o
d
u
ce
d
b
y
v
ir
t
u
e
o
f
ac
ce
s
s
to
f
il
e
s
:
it
is
t
h
e
ty
p
e
o
f
k
n
o
wled
g
e
r
elatin
g
to
th
e
s
u
m
m
ar
ies p
r
o
d
u
ce
d
f
r
o
m
t
h
e
f
iles
co
n
s
u
lted
d
u
r
i
n
g
a
lear
n
in
g
s
ess
io
n
etc.
Evaluation Warning : The document was created with Spire.PDF for Python.