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.
15
,
No
.
3
,
J
u
n
e
20
25
,
p
p
.
3107
~
3
1
1
7
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
3
.
pp
3
1
0
7
-
3
1
1
7
3107
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
M
O
ERI
D:
enha
n
cing
o
pen
e
du
ca
ti
o
na
l
r
eso
urce
disc
o
v
er
a
bilit
y
throug
h an
a
rti
fic
ia
l int
ellig
ence
-
po
wered
cha
tbot
rec
o
mm
ender
sy
stem
Sa
nd
o
us
s
i R
im
a
1
,
H
nid
a
M
e
riem
2
,3
,
Da
o
ud
i N
a
j
im
a
2,
1
,
Aj
ho
un
Ra
chida
1
1
N
a
t
i
o
n
a
l
H
i
g
h
e
r
S
c
h
o
o
l
f
o
r
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
S
y
st
e
ms A
n
a
l
y
s
i
s (EN
S
I
A
S
)
,
M
o
h
a
mm
e
d
V
U
n
i
v
e
r
s
i
t
y
i
n
R
a
b
a
t
,
R
a
b
a
t
,
M
o
r
o
c
c
o
2
I
TQ
A
N
Te
a
m,
S
c
h
o
o
l
o
f
I
n
f
o
r
ma
t
i
o
n
S
c
i
e
n
c
e
s (ES
I
)
,
R
a
b
a
t
,
M
o
r
o
c
c
o
3
M
o
h
a
mm
a
d
i
a
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
s (
EM
I
)
,
M
o
h
a
mm
e
d
V
U
n
i
v
e
r
si
t
y
i
n
R
a
b
a
t
,
R
a
b
a
t
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
4
,
2
0
2
4
R
ev
is
ed
J
an
2
4
,
2
0
2
5
Acc
ep
ted
J
an
1
6
,
2
0
2
5
Op
e
n
e
d
u
c
a
ti
o
n
a
l
re
so
u
rc
e
s
(OER)
a
re
v
a
l
u
a
b
le
a
ss
e
ts
i
n
lea
rn
in
g
a
n
d
tea
c
h
in
g
.
T
h
e
y
e
n
s
u
re
c
o
st
-
e
ffe
c
ti
v
e
n
e
ss
a
n
d
c
u
st
o
m
iza
b
il
it
y
,
a
n
d
c
o
n
tri
b
u
te
to
g
lo
b
a
l
c
o
l
lab
o
ra
ti
o
n
in
t
h
e
e
d
u
c
a
ti
o
n
re
a
lm.
He
n
c
e
,
e
d
u
c
a
ti
o
n
sta
k
e
h
o
l
d
e
rs
fa
c
e
a
c
rit
ica
l
c
h
a
ll
e
n
g
e
in
l
o
c
a
ti
n
g
su
it
a
b
le
OERs
th
a
t
m
e
e
t
th
e
ir
n
e
e
d
s
a
n
d
p
e
d
a
g
o
g
ica
l
o
b
j
e
c
ti
v
e
s.
To
c
a
ter
to
th
is
issu
e
,
r
e
se
a
rc
h
e
r
s
p
ro
p
o
se
d
i
v
e
rse
d
ig
it
a
l
so
l
u
ti
o
n
s,
o
n
e
b
e
in
g
re
c
o
m
m
e
n
d
e
r
sy
st
e
m
s
(RS
).
Wh
il
e
a
wid
e
a
rra
y
o
f
th
e
su
g
g
e
ste
d
to
o
ls
fo
c
u
se
d
o
n
lea
rn
e
rs
o
n
l
y
,
th
is
stu
d
y
i
n
tr
o
d
u
c
e
s
M
OERID,
a
n
a
rti
ficia
l
in
telli
g
e
n
c
e
(AI)
-
p
o
w
e
re
d
OER
re
c
o
m
m
e
n
d
e
r
Ch
a
tb
o
t
a
ime
d
a
t
th
e
tea
c
h
in
g
c
o
m
m
u
n
it
y
.
It
a
sp
ires
to
fa
c
il
it
a
te
re
so
u
rc
e
d
isc
o
v
e
ra
b
il
it
y
,
a
ll
o
wi
n
g
in
str
u
c
to
rs
t
o
sa
v
e
ti
m
e
a
n
d
e
n
e
rg
y
to
c
o
n
c
e
n
trate
o
n
o
t
h
e
r
p
e
d
a
g
o
g
ica
l
d
u
t
ies
.
M
OERID en
g
a
g
e
s
n
a
tu
ra
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
(NLP
)
a
n
d
re
c
o
m
m
e
n
d
a
ti
o
n
fil
terin
g
tec
h
n
iq
u
e
s
t
o
lo
c
a
te
a
n
d
d
e
li
v
e
r
re
lev
a
n
t
OE
Rs
to
in
str
u
c
to
rs.
Th
e
st
u
d
y
d
e
sc
rib
e
s
th
e
imp
lem
e
n
tatio
n
o
f
M
OERID,
h
i
g
h
li
g
h
ts
i
ts
e
ffica
c
y
a
n
d
p
ro
v
id
e
s
a
c
ti
o
n
a
b
le
re
c
o
m
m
e
n
d
a
ti
o
n
s f
o
r
fu
tu
re
re
se
a
rc
h
b
y
o
u
tl
i
n
in
g
t
h
e
re
se
a
rc
h
g
a
p
s
.
K
ey
w
o
r
d
s
:
C
h
atb
o
t
Op
en
ed
u
ca
tio
n
al
r
eso
u
r
ce
s
R
ec
o
m
m
en
d
atio
n
s
y
s
tem
R
ec
o
m
m
en
d
er
s
y
s
tem
T
ea
ch
in
g
co
m
m
u
n
ity
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
:
San
d
o
u
s
s
i Ri
m
a
N
atio
n
al
Hig
h
er
Sch
o
o
l f
o
r
C
o
m
p
u
ter
Scien
ce
a
n
d
Sy
s
tem
s
An
aly
s
is
(
E
NSI
AS)
,
Mo
h
am
m
ed
V
Un
iv
er
s
ity
in
R
ab
at
R
ab
at,
Mo
r
o
cc
o
E
m
ail:
s
an
d
o
u
s
s
i.r
im
a@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
C
o
n
f
o
r
m
in
g
to
UNE
SC
O
[
1
]
,
o
p
en
ed
u
ca
tio
n
al
r
eso
u
r
ce
s
(
OE
R
)
in
v
o
lv
es
ed
u
ca
tio
n
al,
in
s
t
r
u
ctio
n
al,
an
d
r
esear
ch
ass
ets
av
ailab
le
in
d
if
f
er
e
n
t
f
o
r
m
ats
an
d
m
ed
iu
m
s
.
T
h
ese
r
eso
u
r
ce
s
b
elo
n
g
to
th
e
p
u
b
lic
d
o
m
ain
,
o
r
ar
e
co
p
y
r
ig
h
ted
b
u
t
ac
ce
s
s
i
b
le
u
n
d
er
an
o
p
en
licen
s
e.
Su
ch
licen
s
es
m
ak
e
th
e
ac
ce
s
s
u
n
ex
clu
s
iv
e,
with
th
e
f
r
ee
d
o
m
to
r
e
u
s
e,
r
ep
u
r
p
o
s
e,
m
o
d
if
y
,
a
n
d
d
is
tr
ib
u
te
th
e
m
ater
ials
.
B
y
p
r
o
v
id
in
g
a
d
iv
er
s
e
r
a
n
g
e
o
f
ed
u
ca
tio
n
al
s
ettin
g
s
an
d
teac
h
in
g
m
eth
o
d
s
,
OE
R
s
p
lay
an
in
h
er
en
t
r
o
le
in
s
u
p
p
o
r
ti
n
g
in
clu
s
iv
ity
an
d
ac
ce
s
s
ib
ilit
y
in
lear
n
in
g
.
I
n
lin
e
with
th
e
g
lo
b
al
g
o
al
o
f
im
p
r
o
v
in
g
ed
u
ca
tio
n
al
r
eso
u
r
ce
s
,
t
h
er
e
is
a
co
n
ce
r
te
d
ef
f
o
r
t
to
d
e
v
elo
p
,
im
p
lem
en
t,
an
d
a
d
ap
t
h
ig
h
-
q
u
ality
O
E
R
.
T
h
is
m
o
v
em
e
n
t
en
c
o
u
r
ag
es
ed
u
ca
to
r
s
t
o
co
llab
o
r
ate
an
d
estab
lis
h
in
ter
n
atio
n
al
s
tan
d
ar
d
s
f
o
r
th
e
q
u
ality
an
d
ac
ce
s
s
ib
ilit
y
o
f
O
E
R
.
T
h
e
f
o
cu
s
o
n
p
r
o
d
u
cin
g
h
ig
h
-
q
u
ality
OE
R
aim
s
to
estab
lis
h
a
wo
r
ld
wid
e
s
tan
d
ar
d
f
o
r
ed
u
ca
tio
n
al
r
eso
u
r
ce
s
in
ad
d
itio
n
to
en
co
u
r
a
g
in
g
c
o
llab
o
r
atio
n
with
in
th
e
teac
h
in
g
co
m
m
u
n
ity
[
2
]
.
Nev
er
th
eless
,
n
av
ig
atin
g
th
r
o
u
g
h
th
e
m
ass
iv
e
v
o
lu
m
e
o
f
OE
R
is
ch
allen
g
in
g
,
an
d
f
i
n
d
in
g
a
n
d
d
is
co
v
er
in
g
r
elev
an
t
o
n
es
is
b
ec
o
m
in
g
co
m
p
licated
f
o
r
th
e
teac
h
in
g
co
m
m
u
n
ity
.
Fo
r
in
s
tan
ce
,
m
a
n
y
in
s
tr
u
cto
r
s
s
p
en
d
a
s
ig
n
if
ican
t
am
o
u
n
t
o
f
tim
e
o
n
lin
e,
b
r
o
w
s
in
g
th
r
o
u
g
h
ed
u
ca
tio
n
al
r
eso
u
r
ce
r
ep
o
s
ito
r
ies
to
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.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
1
0
7
-
3
1
1
7
3108
f
in
d
m
ater
ials
th
at
ca
n
h
elp
t
h
em
co
n
s
tr
u
ct
th
eir
c
o
u
r
s
es.
T
o
th
is
en
d
,
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
(
R
S)
h
av
e
g
r
o
wn
in
p
o
p
u
lar
ity
,
in
t
h
is
f
ield
,
an
d
a
r
e
attem
p
tin
g
t
o
ad
d
r
ess
th
is
is
s
u
e
b
y
p
r
o
v
id
i
n
g
in
s
tr
u
cto
r
s
with
s
u
itab
le
lear
n
in
g
m
ater
ials
m
atch
in
g
th
eir
n
ee
d
s
,
c
o
n
tex
ts
,
a
n
d
p
r
ef
er
en
ce
s
.
R
ec
o
m
m
en
d
e
r
s
y
s
tem
s
s
er
v
e
as
an
ef
f
ec
tiv
e
s
o
lu
tio
n
f
o
r
n
a
v
ig
atin
g
th
e
s
ea
r
ch
f
o
r
lea
r
n
in
g
m
ater
ials
with
in
e
x
ten
s
iv
e
r
ep
o
s
ito
r
ies.
T
h
e
y
s
u
g
g
est
item
s
th
at
m
ig
h
t
in
ter
est
u
s
er
s
b
y
a
n
aly
zin
g
b
o
th
th
eir
ex
p
licit
a
n
d
im
p
licit
p
r
ef
e
r
en
ce
s
an
d
th
o
s
e
o
f
u
s
er
s
with
s
im
ilar
p
r
o
f
iles
,
an
d
th
e
ch
ar
ac
te
r
is
tics
o
f
b
o
th
u
s
er
s
an
d
item
s
[
3
]
.
Ho
wev
er
,
OE
R
r
ec
o
m
m
e
n
d
er
s
in
ten
d
ed
f
o
r
th
e
teac
h
in
g
c
o
m
m
u
n
ity
ar
e
way
less
co
m
m
o
n
th
a
n
OE
R
R
S
s
d
esig
n
ed
f
o
r
th
e
lea
r
n
in
g
c
o
m
m
u
n
ity
[
4
]
,
a
n
d
to
a
d
d
r
ess
th
is
p
r
o
b
lem
s
tatem
en
t,
th
is
s
tu
d
y
p
r
esen
ts
an
d
d
is
cu
s
s
es
an
OE
R
R
Ss
ch
atb
o
t
-
d
r
iv
en
t
h
at
r
ec
o
m
m
e
n
d
s
r
eso
u
r
ce
s
b
ased
o
n
th
e
in
s
tr
u
cto
r
s
’
in
p
u
t.
Fo
llo
win
g
a
c
o
m
p
r
e
h
en
s
iv
e
c
o
m
p
ar
ativ
e
an
aly
s
is
o
f
ex
is
tin
g
tech
n
o
lo
g
ies,
th
e
s
y
s
tem
in
t
eg
r
ates
cu
ttin
g
-
e
d
g
e
R
ec
o
m
m
en
d
atio
n
tec
h
n
iq
u
es
an
d
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
(
NL
P)
a
n
d
d
e
p
lo
y
s
a
s
izab
le
d
ataset
o
f
OE
R
s
f
o
r
ac
cu
r
ate
r
ec
o
m
m
en
d
atio
n
.
T
h
e
r
em
ain
d
er
o
f
th
e
s
tu
d
y
is
o
r
g
an
ized
as
f
o
llo
ws:
t
h
e
s
ec
o
n
d
s
ec
tio
n
p
r
o
v
id
es
a
co
m
p
r
e
h
en
s
iv
e
r
ev
iew
o
f
ex
is
tin
g
liter
atu
r
e,
h
ig
h
lig
h
tin
g
k
ey
ad
v
an
ce
m
e
n
ts
in
th
e
f
ield
o
f
OE
R
an
d
R
S.
Sectio
n
3
o
u
tlin
es
th
e
m
eth
o
d
o
lo
g
y
,
d
esig
n
a
n
d
im
p
lem
en
tatio
n
o
f
th
e
s
y
s
tem
.
R
esu
lts
o
f
th
e
s
y
s
tem
’
s
ev
alu
atio
n
ar
e
d
is
cu
s
s
ed
in
s
ec
tio
n
4
,
an
d
s
ec
tio
n
5
r
ec
ap
itu
lates
th
e
k
ey
f
i
n
d
in
g
s
an
d
o
f
f
er
s
in
s
ig
h
ts
in
th
e
p
r
ac
tical
ap
p
licatio
n
o
f
th
e
s
y
s
tem
in
teac
h
in
g
p
r
ac
tices.
Sectio
n
6
,
p
r
o
v
id
es
th
e
r
es
ea
r
ch
co
n
tr
ib
u
tio
n
s
,
lim
itatio
n
s
,
an
d
f
u
tu
r
e
d
ir
ec
tio
n
s
,
b
r
in
g
in
g
th
e
s
tu
d
y
to
a
cl
o
s
e.
2.
RE
L
AT
E
D
WO
RK
S
R
ec
o
m
m
en
d
er
s
y
s
tem
s
(
R
S)
em
er
g
e
as
v
alu
ab
le
i
n
f
o
r
m
atio
n
f
ilter
in
g
tec
h
n
o
lo
g
y
.
T
h
e
y
p
r
o
v
id
e
tailo
r
ed
s
u
g
g
esti
o
n
s
to
u
s
er
s
.
T
h
ese
s
y
s
tem
s
ar
e
b
ased
o
n
v
ar
io
u
s
ap
p
r
o
ac
h
es,
ea
ch
o
f
f
er
in
g
s
tr
en
g
th
s
in
u
n
co
v
e
r
in
g
item
s
p
er
s
o
n
alize
d
to
th
e
u
s
er
p
r
ef
er
e
n
ce
s
.
I
n
t
h
e
liter
atu
r
e,
m
a
n
y
s
tr
ateg
ies
h
av
e
b
ee
n
p
r
o
p
o
s
e
d
f
o
r
th
e
in
te
g
r
atio
n
o
f
R
S
in
to
ed
u
ca
tio
n
al
f
r
am
ewo
r
k
s
,
em
p
h
asizin
g
th
eir
p
o
ten
tia
l
to
im
p
r
o
v
e
th
e
d
ev
elo
p
m
e
n
t o
f
co
u
r
s
es.
T
h
ese
m
eth
o
d
o
lo
g
ies ca
n
b
e
class
if
ied
in
to
co
n
ten
t
-
b
ased
(
C
B
F),
co
llab
o
r
ativ
e
(
C
F),
an
d
h
y
b
r
i
d
m
o
d
els,
wh
ich
m
er
g
e
elem
e
n
ts
o
f
th
e
f
ir
s
t
two
ap
p
r
o
ac
h
es.
C
o
n
ten
t
-
b
a
s
ed
f
ilter
in
g
(
C
B
F)
s
u
g
g
ests
r
elate
d
item
s
b
ased
o
n
attr
ib
u
tes o
f
p
r
e
v
io
u
s
ly
lik
e
d
item
s
b
y
a
u
s
er
,
wh
ile
C
F
r
e
co
m
m
en
d
s
item
s
b
y
an
aly
zin
g
th
e
p
ast
b
eh
av
i
o
r
o
f
u
s
er
s
with
s
im
ilar
p
r
ef
er
en
ce
s
.
Hy
b
r
id
s
y
s
tem
s
g
en
er
ate
r
ec
o
m
m
en
d
atio
n
s
b
y
in
teg
r
atin
g
b
o
th
C
F a
n
d
C
B
F o
r
m
o
r
e
ap
p
r
o
ac
h
es.
R
ec
en
tly
,
a
r
em
ar
k
ab
le
f
o
cu
s
is
p
aid
o
n
im
p
lem
en
tin
g
lar
g
e
lan
g
u
ag
e
m
o
d
el
(
L
L
M)
a
n
d
m
ac
h
in
e
lear
n
in
g
(
ML
)
ap
p
r
o
ac
h
es
to
im
p
r
o
v
e
th
e
ef
f
icac
y
an
d
in
te
llig
en
ce
o
f
th
ese
s
y
s
tem
s
[
5
]
.
T
ab
le
1
co
m
p
ar
es
(
C
B
F),
(
C
F),
an
d
h
y
b
r
id
r
e
co
m
m
en
d
atio
n
s
y
s
tem
s
b
y
p
r
o
v
id
in
g
an
o
v
er
v
iew
o
f
th
e
ir
ad
v
a
n
tag
es
an
d
lim
itatio
n
s
b
ased
o
n
th
e
[
6
]
an
d
[
7
]
s
tu
d
ies.
C
B
F
r
ec
o
m
m
en
d
s
s
im
ilar
item
s
to
th
o
s
e
p
r
ev
io
u
s
ly
lik
ed
,
h
an
d
lin
g
n
ew
o
n
es,
y
et,
s
tr
u
g
g
lin
g
with
n
ew
u
s
er
s
an
d
e
m
er
g
in
g
item
s
.
C
F
r
ec
o
m
m
e
n
d
s
item
s
b
ased
o
n
s
im
ilar
u
s
er
s
’
p
r
e
f
er
en
ce
s
,
p
r
o
v
id
in
g
ac
cu
r
ate
p
r
ed
ictio
n
s
,
B
u
t,
s
tr
u
g
g
lin
g
with
“
c
o
ld
s
ta
r
t,
”
s
ca
lab
ilit
y
,
an
d
d
ata
s
p
ar
s
ity
.
Fin
ally
,
h
y
b
r
i
d
r
ec
o
m
m
en
d
er
s
co
m
b
in
e
d
iv
er
s
e
m
eth
o
d
s
ad
d
r
ess
in
g
d
if
f
e
r
e
n
t
n
ee
d
s
f
o
r
b
etter
ac
cu
r
ac
y
.
Ho
we
v
er
,
th
is
ty
p
e
o
f
R
S
is
co
m
p
u
tatio
n
ally
ex
p
e
n
s
iv
e
an
d
co
m
p
lex
to
m
an
ag
e
.
R
esear
ch
er
s
o
f
p
a
p
er
[
8
]
f
o
cu
s
o
n
d
e
v
elo
p
in
g
a
C
B
F
r
ec
o
m
m
en
d
er
f
o
r
s
u
g
g
esti
n
g
elec
t
iv
e
co
u
r
s
es
alig
n
ed
with
s
tu
d
en
ts
'
ab
ilit
ies
.
I
t
d
ep
lo
y
s
p
r
e
p
r
o
ce
s
s
ed
wo
r
d
item
s
f
r
o
m
u
s
er
s
'
ac
ad
em
ic
h
is
to
r
y
,
ca
lcu
latin
g
weig
h
ted
co
s
in
e
s
im
ilar
ity
b
etwe
en
elec
tiv
e
co
u
r
s
e
s
y
llab
i
an
d
u
s
er
p
r
o
f
iles
.
T
h
e
s
y
s
tem
is
ev
alu
ated
u
s
in
g
q
u
esti
o
n
n
air
es
an
d
v
alid
atio
n
m
eth
o
d
s
,
with
r
esu
lts
in
d
icatin
g
a
h
ig
h
lev
el
o
f
r
ec
o
m
m
en
d
atio
n
d
iv
er
s
ity
an
d
an
av
er
ag
e
ac
c
u
r
ac
y
.
J
u
lian
ti
et
a
l.
[
9
]
b
u
ilt
a
R
S
to
m
ak
e
th
e
p
r
o
ce
s
s
o
f
n
a
v
ig
atin
g
t
h
e
r
ig
h
t
s
k
ills
f
o
r
a
ca
r
ee
r
in
a
s
p
ec
if
ic
f
ield
o
r
d
o
m
ain
less
co
m
p
le
x
.
T
h
is
s
y
s
tem
m
ak
es
r
ec
o
m
m
en
d
atio
n
s
b
ased
o
n
u
s
er
d
ata
an
d
p
r
e
f
er
en
ce
s
.
I
t
au
t
o
m
ate
s
f
ilter
in
g
,
allo
win
g
u
s
er
s
to
r
ec
eiv
e
an
o
n
lin
e
p
er
s
o
n
alize
d
ex
p
er
ie
n
ce
.
th
is
s
y
s
tem
u
tili
ze
s
C
B
F a
n
d
ML
.
T
h
e
p
o
ten
tial
f
o
r
s
tr
ea
m
lin
in
g
th
e
co
u
r
s
e
p
r
o
d
u
ctio
n
p
r
o
c
ess
m
ad
e
th
e
in
teg
r
atio
n
o
f
R
S
wi
th
in
lear
n
in
g
m
a
n
ag
em
en
t
s
y
s
tem
s
(
L
MS)
a
s
u
b
ject
o
f
in
ter
est
in
th
e
r
ap
i
d
ly
ev
o
l
v
in
g
r
ea
lm
o
f
d
ig
ital
ed
u
ca
tio
n
.
T
h
e
cr
ea
tio
n
o
f
M
o
o
d
leR
ec
[
1
0
]
,
a
p
lu
g
i
n
f
o
r
th
e
L
MS
Mo
o
d
le,
is
a
n
o
tewo
r
th
y
d
e
v
elo
p
m
en
t
in
th
is
f
ield
.
I
t
ass
is
ts
teac
h
er
s
in
th
e
p
r
o
ce
s
s
o
f
co
u
r
s
es’
cr
ea
tio
n
b
y
u
s
in
g
k
ey
wo
r
d
-
b
ased
s
ea
r
ch
es
to
f
in
d
lear
n
in
g
o
b
jects
(
L
Os)
ac
r
o
s
s
r
ep
o
s
ito
r
ies.
T
h
e
ex
p
er
im
en
t
s
h
o
wed
a
6
1
.
4
%
s
ati
s
f
ac
tio
n
r
ate,
with
ch
al
len
g
es
lik
e
th
e
co
ld
s
tar
t
p
r
o
b
lem
a
n
d
lim
ited
s
o
c
ial
f
ea
tu
r
e
u
s
ag
e.
Fu
tu
r
e
s
u
g
g
esti
o
n
s
in
clu
d
e
n
o
n
-
e
x
p
er
im
en
tal
u
s
e,
a
ce
n
tr
a
l
s
er
v
er
s
etu
p
,
an
d
im
p
r
o
v
em
e
n
ts
f
o
r
m
o
r
e
m
ea
n
in
g
f
u
l
q
u
er
ies,
ad
d
r
ess
in
g
L
O
s
p
ec
if
icatio
n
v
ar
iatio
n
s
.
T
h
e
s
tu
d
y
[
1
1
]
p
r
esen
ts
a
C
B
F
m
o
d
el
f
o
r
a
p
er
s
o
n
alize
d
lear
n
i
n
g
R
S.
I
t
ca
lcu
lates
s
im
ilar
ities
b
etwe
en
lear
n
in
g
m
ater
ials
an
d
c
o
u
r
s
e
d
escr
ip
tio
n
s
to
r
ec
o
m
m
e
n
d
lear
n
in
g
co
n
ten
t.
T
h
e
s
y
s
tem
'
s
g
o
al
is
to
m
ee
t
lear
n
in
g
o
b
jectiv
es a
n
d
p
r
ev
en
t
d
r
o
p
o
u
ts
b
y
r
esp
o
n
d
in
g
to
in
d
iv
id
u
al
lear
n
in
g
n
ee
d
s
in
o
n
lin
e
lear
n
i
n
g
en
v
i
r
o
n
m
e
n
ts
.
I
n
r
ec
e
n
t
s
tu
d
ies,
R
S
ar
e
b
ec
o
m
in
g
in
c
r
ea
s
in
g
ly
v
alu
ab
le
i
n
ed
u
ca
tio
n
.
T
h
ey
h
a
v
e
th
e
ab
ilit
y
to
h
elp
in
s
tr
u
cto
r
s
ch
o
o
s
e
r
eso
u
r
ce
s
an
d
ad
j
u
s
t
th
eir
teac
h
i
n
g
p
r
a
ctice
s
.
Dh
ah
r
i
an
d
Kh
r
i
b
i
[
1
2
]
p
o
in
ted
t
o
th
e
s
ig
n
if
ican
ce
o
f
th
ese
s
y
s
tem
s
in
p
r
o
v
i
d
in
g
p
e
r
s
o
n
alize
d
r
ec
o
m
m
en
d
atio
n
s
f
o
r
teac
h
in
g
e
n
h
an
ce
m
e
n
ts
,
o
f
ten
th
r
o
u
g
h
h
y
b
r
id
ap
p
r
o
ac
h
es.
T
h
e
s
y
s
tem
atic
r
ev
iew
an
aly
ze
d
m
an
y
s
cien
tific
p
ap
er
s
an
d
f
o
u
n
d
th
at
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:
2088
-
8
7
0
8
MOER
I
D:
en
h
a
n
cin
g
o
p
en
e
d
u
ca
tio
n
a
l res
o
u
r
ce
d
is
co
ve
r
y
t
h
r
o
u
g
h
a
n
…
(
R
ima
S
a
n
d
o
u
s
s
i
)
3109
ed
u
ca
tio
n
al
p
o
r
tals
an
d
r
e
p
o
s
i
to
r
ies
wer
e
co
m
m
o
n
ly
u
s
ed
e
n
v
ir
o
n
m
en
ts
f
o
r
g
ath
er
in
g
ed
u
ca
tio
n
al
r
eso
u
r
ce
s
an
d
m
a
k
in
g
r
ec
o
m
m
e
n
d
atio
n
s
.
T
h
e
s
tu
d
y
also
p
r
o
p
o
s
ed
a
te
ac
h
er
r
ec
o
m
m
en
d
er
s
y
s
tem
th
at
aim
s
to
p
r
o
v
id
e
teac
h
er
s
with
th
e
m
o
s
t
r
elev
an
t
OE
R
r
etr
iev
ed
f
r
o
m
c
o
llectio
n
s
o
f
r
eso
u
r
ce
s
alig
n
e
d
with
th
e
UNE
SC
O
I
C
T
co
m
p
eten
cy
f
r
am
ewo
r
k
f
o
r
te
ac
h
er
s
(
C
FT)
[
1
3
]
.
T
ab
le
1
.
Ov
e
r
v
iew
o
f
t
h
e
ad
v
a
n
tag
es a
n
d
lim
itatio
n
s
o
f
r
ec
o
m
m
en
d
atio
n
tech
n
iq
u
es
A
p
p
r
o
a
c
h
d
e
f
i
n
i
t
i
o
n
A
d
v
a
n
t
a
g
e
s
Li
mi
t
a
t
i
o
n
s
A
p
p
r
o
a
c
h
d
e
f
i
n
i
t
i
o
n
A
d
v
a
n
t
a
g
e
s
Li
mi
t
a
t
i
o
n
s
A
p
p
r
o
a
c
h
d
e
f
i
n
i
t
i
o
n
A
d
v
a
n
t
a
g
e
s
Li
mi
t
a
t
i
o
n
s
C
B
F
R
EC
O
M
M
EN
D
ER
S
C
B
F
r
e
c
o
mm
e
n
d
e
r
s
u
se
i
t
e
m
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s,
u
s
e
r
p
r
e
f
e
r
e
n
c
e
s,
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
t
o
a
n
a
l
y
z
e
u
ser
b
e
h
a
v
i
o
r
p
a
t
t
e
r
n
s
,
r
e
c
o
m
me
n
d
i
n
g
p
r
o
d
u
c
t
s wi
t
h
si
mi
l
a
r
f
e
a
t
u
r
e
s
t
o
t
h
o
se
p
r
e
v
i
o
u
s
l
y
p
o
s
i
t
i
v
e
l
y
r
e
v
i
e
w
e
d
.
C
B
F
r
e
c
o
mm
e
n
d
a
t
i
o
n
sy
s
t
e
ms
d
e
p
l
o
y
s NLP
t
o
a
n
a
l
y
z
e
t
e
x
t
r
e
v
i
e
w
s,
a
d
d
r
e
ss
i
n
g
i
ss
u
e
s
w
i
t
h
n
e
w
p
r
o
d
u
c
t
s t
h
r
o
u
g
h
a
ss
i
g
n
e
d
k
e
y
w
o
r
d
s.
Th
e
s
e
a
l
g
o
r
i
t
h
ms
e
x
h
i
b
i
t
r
e
si
l
i
e
n
c
e
t
o
t
h
e
c
o
l
d
st
a
r
t
p
r
o
b
l
e
m
b
u
t
man
i
f
e
st
a
b
i
a
s
t
o
w
a
r
d
e
s
t
a
b
l
i
sh
e
d
c
a
t
e
g
o
r
i
e
s,
o
f
t
e
n
o
v
e
r
l
o
o
k
i
n
g
n
e
w
l
y
e
merg
i
n
g
,
p
o
t
e
n
t
i
a
l
l
y
r
e
l
e
v
a
n
t
o
n
e
s
d
u
e
t
o
t
h
e
i
r
r
e
c
e
n
t
i
n
t
r
o
d
u
c
t
i
o
n
.
C
F
R
EC
O
M
M
EN
D
ER
S
C
F
e
n
g
i
n
e
s
u
s
e
M
L
a
l
g
o
r
i
t
h
ms
t
o
a
n
a
l
y
z
e
u
sers’
p
r
e
f
e
r
e
n
c
e
s,
su
g
g
e
st
i
t
e
ms
b
a
s
e
d
o
n
s
i
m
i
l
a
r
t
a
st
e
s,
a
n
d
g
a
t
h
e
r
u
ser
d
a
t
a
t
h
r
o
u
g
h
e
x
p
l
i
c
i
t
o
r
i
mp
l
i
c
i
t
d
a
t
a
c
o
l
l
e
c
t
i
o
n
.
U
se
d
m
a
ssi
v
e
l
y
i
n
E
-
c
o
mm
e
r
c
e
a
n
d
m
o
v
i
e
s
R
e
c
o
mm
e
n
d
a
t
i
o
n
s
Th
e
a
b
i
l
i
t
y
t
o
a
c
c
u
r
a
t
e
l
y
p
r
e
d
i
c
t
u
ser
i
n
t
e
r
e
st
i
n
u
n
f
a
m
i
l
i
a
r
p
r
o
d
u
c
t
s
w
i
t
h
o
u
t
r
e
q
u
i
r
i
n
g
d
e
t
a
i
l
e
d
i
t
e
m
d
e
s
c
r
i
p
t
i
o
n
s
a
n
d
su
b
s
e
q
u
e
n
t
l
y
i
mp
r
o
v
i
n
g
r
e
c
o
m
me
n
d
a
t
i
o
n
a
c
c
u
r
a
c
y
.
C
F
f
a
c
e
s
c
h
a
l
l
e
n
g
e
s
l
i
k
e
c
o
l
d
st
a
r
t
p
r
o
b
l
e
m
,
sc
a
l
a
b
i
l
i
t
y
,
r
i
c
h
-
g
e
t
-
r
i
c
h
e
r
e
f
f
e
c
t
,
d
a
t
a
sp
a
r
si
t
y
,
a
n
d
s
h
i
l
l
i
n
g
a
t
t
a
c
k
s
,
a
f
f
e
c
t
i
n
g
r
e
c
o
m
me
n
d
a
t
i
o
n
a
c
c
u
r
a
c
y
a
n
d
e
n
h
a
n
c
i
n
g
p
o
p
u
l
a
r
i
t
e
ms a
t
t
h
e
e
x
p
e
n
se
o
f
n
e
w
o
n
e
s
.
H
Y
B
R
I
D
R
EC
O
M
M
EN
D
ER
S
A
c
o
m
b
i
n
a
t
i
o
n
o
f
t
h
e
t
w
o
p
r
e
v
i
o
u
s
t
e
c
h
n
i
q
u
e
s
o
r
m
o
r
e
H
y
b
r
i
d
r
e
c
o
mm
e
n
d
a
t
i
o
n
sy
st
e
ms
e
n
h
a
n
c
e
u
ser
e
x
p
e
r
i
e
n
c
e
b
y
merg
i
n
g
v
a
r
i
o
u
s
t
e
c
h
n
i
q
u
e
s,
o
f
f
e
r
i
n
g
t
a
i
l
o
r
e
d
s
u
g
g
e
st
i
o
n
s
a
n
d
b
e
t
t
e
r
h
a
n
d
l
i
n
g
n
e
w
u
sers
o
r
i
t
e
ms w
i
t
h
l
i
mi
t
e
d
d
a
t
a
(
c
o
l
d
st
a
r
t
i
ss
u
e
)
.
T
h
e
y
l
e
v
e
r
a
g
e
t
h
e
st
r
e
n
g
t
h
s
o
f
mu
l
t
i
p
l
e
me
t
h
o
d
s fo
r
mo
r
e
a
c
c
u
r
a
t
e
r
e
c
o
mm
e
n
d
a
t
i
o
n
s.
I
t
c
a
n
b
e
a
d
i
sa
d
v
a
n
t
a
g
e
o
f
h
y
b
r
i
d
s
y
s
t
e
ms
t
o
n
e
e
d
mo
r
e
p
r
o
c
e
ss
i
n
g
p
o
w
e
r
a
n
d
r
e
s
o
u
r
c
e
s
b
y
r
e
q
u
i
r
i
n
g
h
i
g
h
c
o
mp
u
t
a
t
i
o
n
a
l
c
o
m
p
l
e
x
i
t
y
.
A
l
s
o
,
h
a
n
d
l
i
n
g
a
n
e
x
t
e
n
si
v
e
d
a
t
a
b
a
se
o
f
r
a
t
i
n
g
s
f
r
o
m v
a
r
i
o
u
s
s
o
u
r
c
e
s
i
s
p
a
r
t
o
f
man
a
g
i
n
g
a
h
y
b
r
i
d
s
y
s
t
e
m
.
R
esear
ch
er
s
in
p
ap
er
[
1
4
]
p
r
esen
ted
a
q
u
ality
-
d
r
iv
en
,
o
n
to
lo
g
y
-
b
ased
f
r
a
m
ewo
r
k
t
o
p
r
o
v
id
e
ed
u
ca
to
r
s
with
th
e
ac
ce
s
s
to
h
i
g
h
-
q
u
ality
OE
R
s
an
d
ass
is
t
th
em
m
ak
e
m
o
r
e
in
f
o
r
m
ed
d
ec
is
io
n
s
in
ed
u
ca
tio
n
al
co
n
tex
ts
.
Fu
r
th
er
m
o
r
e,
r
esear
ch
[
4
]
d
em
o
n
s
tr
ated
a
g
r
o
win
g
in
ter
est
in
OE
R
r
ec
o
m
m
en
d
er
s
b
y
p
r
o
p
o
s
in
g
a
ch
atb
o
t
-
b
ased
s
y
s
tem
d
esig
n
e
d
f
o
r
th
e
teac
h
in
g
c
o
m
m
u
n
ity
.
Her
r
er
a
-
C
u
b
id
es
et
a
l.
[
1
5
]
h
av
e
ex
am
in
e
d
th
e
in
f
lu
en
ce
o
f
p
ed
a
g
o
g
ical
q
u
ality
s
co
r
es
in
OE
R
r
ec
o
m
m
en
d
er
s
,
p
o
in
tin
g
th
at
th
ese
s
co
r
es
co
u
ld
im
p
r
o
v
e
th
e
s
elec
tio
n
o
f
h
ig
h
-
q
u
ality
r
es
o
u
r
ce
s
with
o
u
t
d
im
in
is
h
in
g
r
elev
an
ce
.
T
h
ese
s
tu
d
ies
jo
i
n
tly
u
n
d
e
r
lin
e
th
e
r
em
ar
k
ab
le
r
o
le
o
f
ad
v
a
n
ce
d
R
S in
en
r
ich
in
g
ed
u
ca
tio
n
al
p
r
ac
tices a
n
d
r
eso
u
r
ce
u
tili
za
tio
n
.
I
n
s
u
m
m
ar
y
,
t
h
e
i
n
t
e
g
r
ati
o
n
o
f
a
d
v
a
n
c
ed
r
e
c
o
m
m
e
n
d
at
io
n
s
y
s
te
m
s
i
n
l
ea
r
n
i
n
g
m
a
n
a
g
em
e
n
t
s
y
s
te
m
s
r
e
p
r
ese
n
ts
a
s
i
g
n
i
f
i
ca
n
t
a
d
v
a
n
ce
m
e
n
t
i
n
o
p
ti
m
i
zi
n
g
d
i
g
it
al
ed
u
c
ati
o
n
.
T
h
ese
s
y
s
te
m
s
u
s
e
d
if
f
er
en
t
m
e
th
o
d
s
,
lik
e
co
n
t
e
n
t
-
b
ase
d
f
i
lte
r
i
n
g
an
d
m
a
ch
in
e
le
ar
n
i
n
g
,
t
o
im
p
r
o
v
e
h
o
w
co
u
r
s
es
a
r
e
c
r
e
ate
d
a
n
d
t
o
g
i
v
e
le
ar
n
er
s
a
m
o
r
e
tai
lo
r
e
d
e
x
p
e
r
i
en
ce
.
H
o
wev
er
,
t
h
e
r
e
is
a
g
a
p
in
lit
er
at
u
r
e
a
b
o
u
t
th
e
c
u
r
r
en
t
tr
e
n
d
s
o
n
O
E
R
r
e
c
o
m
m
e
n
d
e
r
s
in
c
lu
d
i
n
g
l
im
ita
ti
o
n
s
a
n
d
o
p
p
o
r
tu
n
i
ties
i
n
t
ea
c
h
i
n
g
p
r
ac
tic
e
s
.
I
n
th
is
r
e
g
a
r
d
,
th
e
f
o
ll
o
wi
n
g
s
e
cti
o
n
s
r
e
p
o
r
t
t
h
e
im
p
le
m
e
n
t
ati
o
n
o
f
a
n
ed
u
c
at
o
r
-
c
en
te
r
e
d
C
h
a
tb
o
t
-
d
r
iv
e
n
O
E
R
r
ec
o
m
m
e
n
d
e
r
b
ase
d
o
n
C
B
F t
ec
h
n
iq
u
es.
3.
M
E
T
H
O
DO
L
O
G
Y
I
n
th
is
p
ap
er
,
we
in
tr
o
d
u
ce
“
MO
E
R
I
D
”
(
My
Op
en
E
d
u
ca
tio
n
al
R
eso
u
r
ce
f
o
r
I
n
s
tr
u
ctio
n
a
l
Deliv
er
y
-
th
e
ac
r
o
n
y
m
is
d
er
i
v
ed
f
r
o
m
t
h
e
Ar
ab
ic
wo
r
d
“
r
eso
u
r
ce
”
)
,
a
ch
atb
o
t
-
d
r
iv
en
R
S
f
o
r
OE
R
.
Un
lik
e
o
th
er
m
o
d
els
th
at
r
ely
o
n
s
tatic
r
ec
o
m
m
en
d
atio
n
s
,
th
is
s
y
s
tem
d
y
n
a
m
ically
ex
ch
an
g
es
with
ed
u
ca
to
r
s
th
r
o
u
g
h
a
co
n
v
er
s
atio
n
al
in
ter
f
ac
e,
f
o
r
a
b
etter
u
n
d
er
s
tan
d
in
g
o
f
th
eir
p
r
ef
er
e
n
ce
s
lev
er
a
g
in
g
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
(
NL
P)
an
d
m
ac
h
i
n
e
lear
n
in
g
(
ML
)
tech
n
iq
u
es.
I
n
th
is
s
ec
tio
n
we
o
u
tlin
e
th
e
s
y
s
tem
atic
p
r
o
ce
s
s
o
f
MO
E
R
I
D’
s
im
p
lem
en
tatio
n
.
T
h
e
r
esear
ch
o
u
tlin
es
th
e
s
y
s
tem
ar
ch
itectu
r
e
b
y
p
r
esen
tin
g
th
eir
m
ain
co
m
p
o
n
en
ts
: A
u
th
en
ticatio
n
s
y
s
tem
to
s
ec
u
r
es a
cc
es
s
u
s
in
g
u
s
er
cr
ed
en
tials
,
ch
atb
o
t in
ter
f
ac
e
as a
G
UI
-
b
ased
in
ter
ac
tiv
e
s
y
s
tem
b
u
ilt
u
s
in
g
th
e
T
k
in
ter
lib
r
a
r
y
f
o
r
u
s
er
-
f
r
i
en
d
ly
o
p
er
atio
n
a
n
d
th
e
r
ec
o
m
m
en
d
er
e
n
g
in
e
th
at
C
o
m
b
in
es
NL
P
an
d
C
B
F
tech
n
iq
u
es
to
g
en
er
ate
tailo
r
ed
r
e
co
m
m
en
d
atio
n
s
.
T
h
e
r
esear
ch
also
h
ig
h
lig
h
ts
th
e
d
ata
co
llectio
n
p
r
o
ce
s
s
b
y
ev
a
lu
atin
g
m
u
ltip
le
d
atasets
f
o
r
a
co
m
p
ar
ativ
e
an
aly
s
is
to
s
elec
t
a
d
ataset
with
r
ic
h
m
etad
ata
th
at
s
u
p
p
o
r
ts
s
em
an
tic
s
im
ilar
ity
co
m
p
u
tatio
n
s
n
e
ce
s
s
ar
y
f
o
r
C
B
F.
T
h
e
r
esear
ch
also
e
m
p
h
asizes
d
ata
p
r
ep
r
o
ce
s
s
in
g
b
y
u
s
in
g
Me
tad
ata
Stan
d
ar
d
izatio
n
to
f
ill
m
is
s
in
g
v
alu
es,
tex
t
clea
n
in
g
th
r
o
u
g
h
NL
P
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.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
1
0
7
-
3
1
1
7
3110
p
r
ep
r
o
ce
s
s
in
g
(
to
k
e
n
izatio
n
,
lem
m
atiza
tio
n
)
u
s
in
g
`
S
p
aCy
`
to
en
s
u
r
e
d
ata
c
o
n
s
is
ten
cy
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
v
ec
to
r
izatio
n
f
o
r
C
B
F.
T
h
e
r
esear
ch
d
e
p
icts
th
e
r
ec
o
m
m
en
d
atio
n
en
g
i
n
e
alg
o
r
ith
m
s
th
at
ar
e:
W
o
r
d
2
Vec
f
o
r
em
b
ed
d
in
g
tex
tu
al
f
ea
tu
r
es
an
d
co
s
in
e
s
im
ilar
ity
f
o
r
s
im
ilar
ity
s
co
r
in
g
.
Fo
r
th
e
d
esig
n
an
d
im
p
lem
e
n
tatio
n
,
th
e
s
y
s
tem
lev
er
ag
es
in
ten
t
an
d
en
tity
r
e
co
g
n
itio
n
.
I
ts
wo
r
k
f
lo
w
in
clu
d
es
p
ar
s
in
g
u
s
er
in
p
u
t
to
ex
tr
ac
t
k
ey
in
f
o
r
m
atio
n
,
m
atch
in
g
u
s
er
p
r
ef
er
e
n
ce
s
with
OE
R
m
etad
ata
v
ia
th
e
r
e
co
m
m
en
d
atio
n
en
g
in
e
an
d
f
i
n
ally
p
r
esen
tin
g
a
r
an
k
ed
lis
t
o
f
OE
R
lin
k
s
to
th
e
u
s
er
a
n
d
ca
p
tu
r
in
g
f
ee
d
b
a
ck
f
o
r
iter
ativ
e
im
p
r
o
v
em
en
t
s
.
T
o
ev
alu
ate
th
e
s
y
s
tem
’
s
ef
f
icac
y
,
we
g
en
e
r
a
ted
s
y
n
th
etic
u
s
er
p
r
ef
er
e
n
ce
s
to
s
im
u
late
r
ea
l
-
wo
r
ld
i
n
ter
ac
tio
n
s
to
c
o
m
p
u
te
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
s
co
r
e
f
o
r
o
f
f
lin
e
ev
alu
atio
n
.
T
h
u
s
,
to
m
itig
ate
C
o
ld
Star
t
is
s
u
es,
we
d
ep
lo
y
ed
war
m
-
s
tar
t te
ch
n
iq
u
es to
r
ec
o
m
m
en
d
item
s
with
lim
ited
u
s
er
h
is
to
r
y
.
Fig
u
r
e
1
d
ep
icts
th
e
d
etailed
m
eth
o
d
o
lo
g
y
:
Fig
u
r
e
1
.
R
esear
ch
m
eth
o
d
o
l
o
g
y
3
.
1
.
M
O
E
RID
a
rc
hite
ct
ure
MO
E
R
I
D
is
an
ar
tific
ial
in
tel
lig
en
ce
(
AI
)
-
d
r
iv
e
n
c
h
atb
o
t
t
h
at
u
s
es
s
tate
-
of
-
th
e
-
ar
t
r
ec
o
m
m
en
d
atio
n
tech
n
iq
u
es
an
d
NL
P.
Acc
ess
to
th
e
c
h
atb
o
t
is
s
ec
u
r
e
d
th
r
o
u
g
h
an
au
th
e
n
ticatio
n
p
r
o
ce
s
s
,
wh
ich
r
eq
u
ir
es
u
s
er
s
to
au
th
en
ticate
th
e
m
s
elv
es
u
s
in
g
lo
g
in
cr
e
d
en
tials
.
Fo
r
in
s
ta
n
ce
,
Fig
u
r
e
2
p
r
esen
ts
an
u
p
d
a
ted
o
v
er
v
iew
o
f
th
e
s
y
s
tem
ar
ch
itectu
r
e
p
r
ev
io
u
s
ly
elab
o
r
ated
in
[
1
6
]
.
Au
th
o
r
s
in
th
is
p
r
ec
ed
in
g
v
er
s
io
n
r
ely
o
n
th
e
Op
en
AI
API
,
in
s
tead
o
f
an
OE
R
Data
s
et
to
g
et
th
e
r
ec
o
m
m
en
d
e
d
OE
R
UR
L
s
.
I
t
also
u
s
es
a
s
tatic
co
n
v
er
s
atio
n
al
m
o
o
d
th
at
is
b
ased
o
n
a
s
et
o
f
ch
a
n
g
eless
q
u
esti
o
n
s
to
e
x
tr
ac
t
th
e
i
n
te
n
ts
an
d
e
n
titi
es
b
ased
o
n
GPT3
.
San
d
o
u
s
s
i
et
a
l.
[
1
6
]
u
tili
ze
d
GPT3
s
in
ce
its
GPT
alg
o
r
ith
m
s
ar
e
th
e
o
n
ly
co
m
p
atib
le
o
n
es
with
th
e
AP
I
m
eth
o
d
to
ex
tr
ac
t
r
ec
o
m
m
en
d
atio
n
.
MO
E
R
I
D
r
elies
o
n
NL
P
tec
h
n
iq
u
es
an
d
is
an
A
I
b
ased
r
ec
o
m
m
en
d
e
r
th
at
is
d
esig
n
ed
f
o
r
th
e
teac
h
in
g
co
m
m
u
n
ity
.
Un
lik
e
o
th
er
s
y
s
tem
s
th
at
f
o
cu
s
o
n
t
h
e
lear
n
er
s
o
n
ly
an
d
ad
o
p
t
s
tatic
s
ea
r
ch
m
eth
o
d
s
,
th
is
s
y
s
tem
is
co
n
v
er
s
atio
n
al
an
d
d
ep
l
o
y
s
an
OE
R
d
ataset.
a.
User
lo
g
s
to
th
e
s
y
s
tem
u
s
in
g
p
er
s
o
n
al
cr
ed
e
n
tials
.
b.
User
g
ets a
g
r
ee
tin
g
m
ess
ag
e
o
n
ce
lo
g
g
ed
.
c.
User
ty
p
es a
n
d
en
ter
s
a
p
ar
ag
r
ap
h
to
e
x
p
r
ess
th
e
s
p
ec
if
icities
o
f
th
e
n
ee
d
ed
OE
R
s
.
d.
Sy
s
tem
u
s
es NL
P to
ass
im
ilat
e
th
e
s
em
an
tic
m
ea
n
in
g
o
f
t
h
e
u
s
er
’
s
q
u
er
y
.
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:
2088
-
8
7
0
8
MOER
I
D:
en
h
a
n
cin
g
o
p
en
e
d
u
ca
tio
n
a
l res
o
u
r
ce
d
is
co
ve
r
y
t
h
r
o
u
g
h
a
n
…
(
R
ima
S
a
n
d
o
u
s
s
i
)
3111
e.
Sy
s
tem
d
ep
lo
y
s
s
p
ec
if
ically
t
h
e
NL
U
to
e
x
tr
ac
t
I
n
ten
ts
an
d
E
n
titi
es
to
u
n
d
er
s
tan
d
t
h
e
s
em
an
tic
m
ea
n
in
g
o
f
th
e
u
s
er
’
s
p
ar
ag
r
a
p
h
.
f.
Sy
s
tem
s
en
d
s
a
li
s
t
o
f
OE
R
s
li
n
k
s
f
r
o
m
th
e
av
ailab
le
OE
R
in
th
e
d
ataset,
b
y
u
tili
zin
g
C
B
F
f
ilter
in
g
b
ased
o
n
th
e
I
n
ten
ts
an
d
E
n
titi
es
p
r
ev
io
u
s
ly
ex
tr
ac
te
d
,
th
is
p
r
o
ce
s
s
is
en
s
u
r
ed
in
th
e
C
o
r
e
r
ec
o
m
m
en
d
er
e
n
g
in
e
o
f
th
e
ch
at
b
o
t
.
g.
Sy
s
tem
p
r
esen
ts
th
e
l
is
t
o
f
li
n
k
s
to
th
e
ch
atb
o
t
in
ter
f
ac
e
f
o
r
th
e
u
s
er
s
v
ia
NL
P
an
d
ask
s
f
o
r
th
e
u
s
er
’
s
f
ee
d
b
ac
k
a
b
o
u
t t
h
e
r
ec
o
m
m
en
d
ed
lis
t o
f
OE
R
s
lin
k
s
.
h.
User
g
iv
es its
f
ee
d
b
ac
k
b
y
r
ati
n
g
th
e
r
ec
o
m
m
en
d
atio
n
.
Fig
u
r
e
2
.
MO
E
R
I
D
ar
ch
itectu
r
e
3
.
2
.
Da
t
a
c
o
llect
io
n
Ob
tain
in
g
f
r
ee
d
atasets
f
r
o
m
OE
R
r
ep
o
s
ito
r
ies
lik
e
Me
r
lo
t a
n
d
C
o
m
m
o
n
OE
R
to
test
ed
u
ca
tio
n
al
R
S
is
n
o
t
a
co
m
m
o
n
ly
u
s
ed
p
r
ac
t
ice.
Du
e
to
leg
al
an
d
eth
ical
co
n
ce
r
n
s
,
we
o
p
te
d
f
o
r
r
ea
l
-
w
o
r
ld
d
atasets
f
r
ee
ly
av
ailab
le
o
n
o
n
lin
e
co
m
m
u
n
it
y
p
latf
o
r
m
s
s
u
ch
as
R
esear
ch
Gate
,
Kag
g
le,
an
d
GitHu
b
.
A
f
ir
s
t
ex
am
p
le
is
th
e
“
T
r
av
el
well
d
ataset
”
[
1
7
]
,
s
o
u
r
ce
d
f
r
o
m
th
e
lear
n
i
n
g
r
eso
u
r
ce
ex
ch
an
g
e
p
o
r
tal,
co
m
p
r
is
in
g
d
ata
f
r
o
m
t
h
e
E
C
-
f
u
n
d
e
d
ME
L
T
p
r
o
ject'
s
p
ilo
t
p
h
ase
(
Au
g
u
s
t
2
0
0
8
t
o
Feb
r
u
a
r
y
2
0
0
9
)
in
v
o
lv
in
g
9
8
u
s
er
s
.
T
h
e
d
ataset
co
n
tain
s
ex
p
licit
in
ter
est
in
d
icato
r
s
,
al
lo
win
g
in
f
er
e
n
ce
o
f
r
eso
u
r
c
e
r
elev
an
ce
b
ased
o
n
u
s
er
r
ati
n
g
s
an
d
ta
g
s
.
T
h
e
s
ec
o
n
d
f
in
d
in
g
s
ar
e
th
e
C
iteUlik
e
-
a
[
1
8
]
an
d
C
iteUlik
e
-
t
[
1
9
]
d
atasets
,
co
n
tain
in
g
ar
ticle
s
in
f
o
r
m
atio
n
f
r
o
m
C
iteUL
ik
e
an
d
Go
o
g
le
Sch
o
lar
.
T
h
o
u
g
h
,
th
ese
two
d
atasets
ar
e
n
o
t
lab
eled
as
OE
R
.
T
h
e
t
h
ir
d
ex
am
p
le
is
th
e
ITM
-
R
ec
d
ataset,
g
ath
er
ed
f
r
o
m
s
tu
d
en
t
q
u
esti
o
n
n
air
es
at
th
e
I
T
M
d
ep
ar
tm
en
t,
I
llin
o
is
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
,
USA,
o
f
f
er
s
p
r
e
f
er
en
ce
s
o
n
f
i
n
al
p
r
o
ject
to
p
ics in
d
atab
ase
an
d
d
ata
s
cien
ce
cl
ass
es
[
2
0
]
.
T
o
s
elec
t
th
e
m
o
s
t
s
u
itab
le
d
ataset
an
d
m
ak
e
an
in
f
o
r
m
e
d
d
e
cisi
o
n
ab
o
u
t
wh
ich
o
n
e
alig
n
s
b
est
wit
h
o
u
r
o
b
jectiv
es,
we
h
av
e
estab
l
is
h
ed
th
ese
cr
iter
ia:
a.
Ov
er
v
iew
an
d
User
E
n
g
ag
e
m
en
t
:
T
h
is
cr
iter
io
n
p
r
esen
ts
th
e
d
ataset
'
s
ch
ar
ac
ter
is
tics
,
s
tr
u
ctu
r
e,
an
d
co
n
ten
t.
T
h
e
g
o
al
is
to
g
ain
in
s
ig
h
ts
in
to
v
ar
io
u
s
asp
ec
t
s
o
f
th
e
d
ataset,
co
n
s
id
er
in
g
th
e
in
ter
ac
tio
n
,
in
ter
est,
an
d
in
v
o
lv
em
en
t t
h
at
u
s
er
s
ex
h
ib
it with
th
e
d
ata.
b.
Per
s
o
n
aliza
tio
n
:
T
h
is
cr
iter
io
n
f
o
cu
s
es
o
n
u
n
d
er
s
tan
d
in
g
h
o
w
ea
ch
OE
R
d
ataset
s
u
p
p
o
r
ts
a
p
er
s
o
n
alize
d
lear
n
in
g
en
v
ir
o
n
m
en
t.
W
e
lo
o
k
f
o
r
in
f
o
r
m
atio
n
th
at
r
ef
le
cts
h
o
w
th
e
d
ataset
ca
ter
s
to
in
d
iv
id
u
alize
d
ed
u
ca
tio
n
al
ex
p
er
ien
ce
s
.
c.
Me
tad
ata
an
d
co
n
te
x
t
:
Her
e,
we
ex
am
in
e
in
f
o
r
m
atio
n
r
elate
d
to
m
etad
ata
an
d
c
o
n
tex
tu
al
d
etails
ass
o
ciate
d
with
a
s
et
o
f
f
ea
tu
r
es
in
th
e
d
ataset.
I
t
h
el
p
s
u
s
u
n
d
er
s
tan
d
th
e
ad
d
itio
n
al
in
f
o
r
m
atio
n
p
r
o
v
id
e
d
alo
n
g
s
id
e
th
e
co
r
e
d
ata
elem
e
n
ts
.
d.
Data
q
u
ality
:
T
h
is
cr
iter
io
n
ass
ess
e
s
th
e
q
u
ality
an
d
s
u
itab
ilit
y
o
f
th
e
t
h
r
ee
d
atasets
an
d
h
o
w
ea
ch
d
ataset
alig
n
s
with
th
e
n
ee
d
s
o
f
a
d
if
f
er
en
t ty
p
e
o
f
r
ec
o
m
m
en
d
er
s
.
T
ab
le
2
ev
al
u
ates
th
e
d
atasets
(
T
E
L
,
C
iteUL
ik
e
-
a,
an
d
I
T
M)
b
ased
o
n
th
eir
ch
a
r
ac
ter
i
s
tics
.
T
E
L
R
ec
o
r
d
u
s
er
ac
tiv
ities
f
o
r
E
u
r
o
p
ea
n
c
o
u
r
s
es
with
r
ich
m
eta
d
ata
(
1
9
f
ea
tu
r
es)
an
d
h
ig
h
d
ata
q
u
ality
,
s
u
itab
le
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.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
1
0
7
-
3
1
1
7
3112
f
o
r
C
B
F
an
d
C
F
r
ec
o
m
m
en
d
er
s
.
C
iteUL
ik
e
-
a
em
p
h
asizes
Go
o
g
le
Sch
o
lar
a
r
ticles
with
m
in
im
al
t
o
p
o
o
r
m
etad
ata.
Valid
f
o
r
C
F
r
ec
o
m
m
en
d
er
s
b
u
t
u
n
s
u
itab
le
f
o
r
C
B
F
tes
tin
g
.
I
T
M
f
o
c
u
s
es
o
n
s
tu
d
en
ts
’
p
r
e
f
er
en
ce
s
f
o
r
p
r
o
ject
to
p
ics with
lim
ited
m
etad
ata.
I
t f
its
co
n
tex
t
-
awa
r
e
an
d
C
F r
ec
o
m
m
e
n
d
er
s
b
u
t
n
o
t CB
F.
T
ab
le
2
.
Data
co
m
p
ar
is
o
n
D
a
t
a
s
e
t
/
c
h
a
r
a
c
t
e
r
i
st
i
c
O
v
e
r
v
i
e
w
a
n
d
u
s
e
r
e
n
g
a
g
e
m
e
n
t
P
e
r
so
n
a
l
i
z
a
t
i
o
n
M
e
t
a
d
a
t
a
a
n
d
c
o
n
t
e
x
t
D
a
t
a
q
u
a
l
i
t
y
TEL
9
8
u
s
e
r
s
1
3
.
9
2
2
u
ser
a
c
t
i
v
i
t
i
e
s
w
e
r
e
r
e
c
o
r
d
e
d
o
n
1
.
9
2
3
r
e
so
u
r
c
e
s
-
x
l
s
f
o
r
mat
D
i
v
e
r
s
e
p
r
i
mar
y
a
n
d
s
e
c
o
n
d
a
r
y
c
o
u
r
ses
f
r
o
m
a
l
l
o
v
e
r
E
u
r
o
p
e
i
n
d
i
v
e
r
se
s
u
b
j
e
c
t
s
A
r
a
n
g
e
o
f
1
9
f
e
a
t
u
r
e
o
f
met
a
d
a
t
a
V
a
l
i
d
a
n
d
a
c
c
u
r
a
t
e
w
i
t
h
l
i
t
t
l
e
t
o
n
o
m
i
ssi
n
g
d
a
t
a
-
f
i
t
s
C
B
F
a
n
d
C
F
r
e
c
o
m
me
n
d
e
r
s
C
i
t
e
U
l
i
k
e
-
a
5
5
5
1
u
sers
a
n
d
1
6
9
8
0
i
t
e
ms w
i
t
h
2
0
4
9
8
7
u
ser
-
i
t
e
ms
p
a
i
r
s
-
.
d
a
t
f
o
r
m
a
t
R
e
s
o
u
r
c
e
s
a
r
t
i
c
l
e
s fr
o
m
g
o
o
g
l
e
sch
o
l
a
r
N
o
t
o
l
o
w
met
a
d
a
t
a
A
c
c
u
r
a
t
e
f
o
r
s
o
c
i
a
l
a
n
d
C
F
r
e
c
o
mm
e
n
d
e
r
s
w
i
t
h
r
e
g
r
e
ss
i
o
n
p
r
o
b
l
e
ms
I
n
v
a
l
i
d
f
o
r
C
B
F
r
e
c
o
m
me
n
d
e
r
s t
e
st
i
n
g
I
TM
4
7
6
u
sers
a
n
d
7
0
i
t
e
ms
w
i
t
h
5
2
3
0
r
a
t
i
n
g
-
c
s
v
f
o
r
mat
st
u
d
e
n
t
a
n
d
g
r
o
u
p
p
r
e
f
e
r
e
n
c
e
s
o
n
t
h
e
t
o
p
i
c
s
o
f
f
i
n
a
l
p
r
o
j
e
c
t
s
i
n
d
a
t
a
b
a
se
a
n
d
d
a
t
a
s
c
i
e
n
c
e
c
l
a
ss
e
s,
c
o
l
l
e
c
t
e
d
f
r
o
m s
t
u
d
e
n
t
q
u
e
st
i
o
n
n
a
i
r
e
s
a
t
t
h
e
I
TM
d
e
p
a
r
t
me
n
t
,
I
l
l
i
n
o
i
s I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
U
S
A
N
o
t
o
l
o
w
met
a
d
a
t
a
V
a
l
i
d
f
o
r
C
o
n
t
e
x
t
-
a
w
a
r
e
,
g
r
o
u
p
a
n
d
C
F
r
e
c
o
m
me
n
d
e
r
s
i
n
a
c
c
u
r
a
t
e
f
o
r
C
B
F
r
e
c
o
m
me
n
d
e
r
s t
e
st
i
n
g
3
.
3
.
Da
t
a
prepro
ce
s
s
ing
:
Selectin
g
a
s
u
itab
le
d
ataset
is
a
cr
u
cial
p
h
ase
f
o
r
im
p
lem
en
t
in
g
a
R
S.
T
h
e
d
ataset
f
o
r
th
e
p
u
r
p
o
s
e
o
f
th
is
r
esear
ch
o
u
g
h
t
to
co
n
tain
a
wid
e
r
an
g
e
o
f
r
eso
u
r
ce
s
,
co
v
er
in
g
d
iv
er
s
e
s
u
b
jects
an
d
le
v
els
o
f
co
m
p
lex
ity
,
to
en
s
u
r
e
th
at
th
e
s
y
s
tem
ca
n
ca
ter
to
a
b
r
o
ad
ex
p
a
n
s
e
o
f
u
s
er
p
r
ef
er
en
ce
s
.
T
o
ef
f
icien
tly
co
m
p
u
te
s
im
ilar
ity
b
etwe
en
r
eso
u
r
ce
s
an
d
g
e
n
er
at
e
r
elev
an
t
r
ec
o
m
m
en
d
atio
n
s
,
t
h
e
d
ataset
s
h
o
u
ld
in
cl
u
d
e
m
eticu
lo
u
s
an
d
d
i
v
er
s
e
m
etad
ata
f
o
r
ea
ch
r
eso
u
r
ce
an
d
s
h
o
u
ld
b
e
s
u
f
f
icien
t
in
s
ize
to
allo
w
th
e
lear
n
in
g
o
f
s
ig
n
if
ican
t
p
atter
n
s
.
T
h
e
m
o
s
t
ac
cu
r
ate
d
ataset
f
o
r
a
C
B
F
task
th
at
r
elies
o
n
d
i
f
f
er
e
n
t
tex
tu
al
f
ea
tu
r
es
an
d
m
etad
ata
f
r
o
m
T
a
b
le
1
is
T
E
L
.
I
t
in
clu
d
es
a
wid
e
r
an
g
e
o
f
m
etad
ata,
wh
ich
allo
w
u
s
er
s
to
o
b
tain
o
p
tim
al
r
esp
o
n
s
es
to
th
eir
q
u
er
ies.
Fig
u
r
e
3
illu
s
tr
ates
an
o
v
er
v
iew
o
f
T
E
L
m
etad
ata.
T
h
is
d
a
taset
co
n
tain
in
g
2
2
co
lu
m
n
s
an
d
1
2
,
0
4
1
en
tr
ies,
with
m
o
s
t c
o
lu
m
n
s
ar
e
f
u
lly
p
o
p
u
lated
.
I
ts
k
ey
f
ea
tu
r
es a
r
e
p
r
esen
ted
as f
o
llo
ws:
a.
Gen
er
al
co
lu
m
n
s
:
I
n
clu
d
es
USER_
I
D,
AC
T
I
ON,
C
ONT
E
X
T
,
an
d
I
NSERTI
ON_
T
I
ME
STAM
P
to
tr
ac
k
u
s
er
in
ter
ac
tio
n
s
.
b.
User
attr
ib
u
tes
:
C
o
lu
m
n
s
lik
e
SP
OKE
N_
L
ANGU
AGE
S,
MO
T
HE
R
_
T
ONGU
E
,
SUB
J
E
C
T
S_
O
F_
I
NT
E
R
E
ST,
an
d
C
OUNT
R
Y
p
r
o
v
id
e
u
s
er
-
s
p
ec
if
ic
d
etails.
c.
C
o
n
ten
t
m
etad
ata
:
I
n
clu
d
es
T
AG,
T
I
T
L
E
,
SUB
J
E
C
T
,
C
L
ASSIF_
KE
Y
W
OR
DS,
R
E
S
O
UR
C
E
_
T
YPE,
an
d
ME
T
ADAT
A_
PR
OVI
DE
R
f
o
r
d
escr
ib
in
g
an
d
ca
te
g
o
r
iz
in
g
r
eso
u
r
ce
s
.
Fig
u
r
e
3
.
Data
s
et
o
v
er
v
iew
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:
2088
-
8
7
0
8
MOER
I
D:
en
h
a
n
cin
g
o
p
en
e
d
u
ca
tio
n
a
l res
o
u
r
ce
d
is
co
ve
r
y
t
h
r
o
u
g
h
a
n
…
(
R
ima
S
a
n
d
o
u
s
s
i
)
3113
3
.
4
.
Rec
o
mm
enda
t
io
n a
lg
o
ri
t
hm
T
o
o
p
tim
ize
th
e
ch
o
ice
o
f
th
e
C
B
F
alg
o
r
ith
m
,
a
co
m
p
r
e
h
en
s
iv
e
co
m
p
ar
is
o
n
o
f
t
h
e
C
B
F
alg
o
r
ith
m
s
an
d
tech
n
iq
u
es,
m
en
tio
n
e
d
in
th
e
tech
n
ical
f
r
am
ewo
r
k
p
ar
a
g
r
ap
h
is
co
n
d
u
cted
.
Me
asu
r
in
g
th
e
u
tili
ty
o
f
C
B
F
is
co
m
m
o
n
ly
ca
lcu
lated
b
y
u
s
in
g
h
e
u
r
is
tic
f
u
n
ctio
n
s
,
an
d
o
n
e
o
f
t
h
e
m
o
s
t
u
s
ed
is
th
e
c
o
s
in
e
s
im
ilar
ity
m
etr
ic
[
2
1
]
.
Hen
ce
,
t
h
e
m
eth
o
d
d
e
p
lo
y
s
a
s
co
r
e
s
im
ilar
ity
co
m
p
ar
is
o
n
.
Fo
r
th
is
p
u
r
p
o
s
e,
g
r
o
u
n
d
tr
u
th
an
d
co
n
ca
ten
ate
tex
t
co
lu
m
n
s
f
o
r
a
co
s
in
e
co
m
p
ar
is
o
n
a
n
aly
s
is
ar
e
estab
lis
h
ed
.
Me
an
co
s
in
e
s
im
ilar
ities
f
o
r
th
e
p
r
ev
io
u
s
ly
cited
tech
n
i
q
u
es,
n
am
ely
T
F
-
I
DF,
N
-
g
r
am
,
W
o
r
d
2
Vec
,
L
SA,
L
DA,
Fas
tTe
x
t,
Glo
Ve,
an
d
B
E
R
T
ar
e
im
p
lem
en
ted
an
d
co
m
p
u
ted
.
E
ac
h
o
f
th
e
tech
n
iq
u
es
u
s
ed
in
th
e
s
cr
ip
t,
g
en
er
ates
n
u
m
er
ical
v
ec
to
r
s
th
at
p
r
esen
t d
o
c
u
m
en
ts
.
I
n
o
th
er
wo
r
d
s
,
th
e
co
m
p
a
r
is
o
n
u
s
es
m
ath
em
atica
l
ap
p
r
o
a
ch
es
to
esti
m
ate
th
e
s
im
i
lar
it
y
b
etwe
en
item
s
.
s
tar
tin
g
b
y
co
n
v
er
tin
g
tex
tu
al
d
ata
to
n
u
m
e
r
ical
m
o
d
e
ls
.
E
ac
h
d
o
cu
m
en
t d
is
r
ep
r
esen
ted
as a
v
ec
to
r
in
wh
ich
ev
er
y
co
m
p
o
n
e
n
t
r
e
p
r
esen
ts
th
e
T
F
-
I
DF
s
co
r
e
o
f
a
ter
m
in
th
e
d
o
cu
m
e
n
t.
T
h
e
co
s
in
e
s
im
ilar
ity
b
etwe
en
d
o
c
u
m
en
t d
i a
n
d
d
o
c
u
m
en
t
is
r
ep
r
esen
ted
as f
o
llo
ws:
_
(
,
)
=
∥
∥
×
∥
∥
⋅
As
d
ep
icted
in
Fig
u
r
e
4
,
wo
r
d
2
Vec
r
ev
ea
ls
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
in
ter
m
s
o
f
m
ea
n
co
s
in
e
s
im
ilar
ity
.
T
h
is
f
in
d
in
g
em
p
h
asizes
th
e
ef
f
ec
tiv
en
ess
o
f
W
o
r
d
2
Vec
em
b
ed
d
in
g
s
in
g
r
asp
i
n
g
n
u
an
c
ed
s
em
an
tic
r
elatio
n
s
h
ip
s
with
in
th
e
tex
t
c
o
r
p
u
s
.
T
h
e
o
b
s
er
v
ed
d
is
tin
ctio
n
o
f
W
o
r
d
2
Vec
s
u
g
g
ests
its
p
o
ten
tial
as
a
r
o
b
u
s
t
an
d
r
eliab
le
ch
o
ice
f
o
r
th
e
tas
k
o
f
th
e
s
tu
d
y
.
Fig
u
r
e
4
.
A
lg
o
r
ith
m
s
co
m
p
ar
i
s
o
n
3
.
5
.
Sy
s
t
e
m
im
plem
ent
a
t
io
n
MO
E
R
I
D
is
b
u
ilt as f
o
llo
ws:
a.
User
au
th
en
ticatio
n
:
T
o
s
ec
u
r
e
ac
ce
s
s
to
th
e
s
y
s
tem
an
d
to
ass
u
r
e
a
p
er
s
o
n
alize
d
u
s
er
-
b
a
s
ed
ex
p
er
ie
n
ce
,
MO
E
R
I
D
is
en
d
o
wed
with
an
au
th
en
ticatio
n
s
y
s
tem
r
e
q
u
ir
in
g
id
e
n
tific
atio
n
cr
ed
e
n
tials
.
I
t
is
also
a
s
ec
u
r
ity
p
r
o
to
c
o
l r
eg
u
latin
g
ac
ce
s
s
to
th
e
MO
E
R
I
D
'
s
in
ter
f
ac
e.
b.
E
n
tity
ex
tr
ac
tio
n
u
s
in
g
`
S
p
a
C
y
`
:
T
o
ca
teg
o
r
ize
th
e
I
n
ten
t
s
an
d
E
n
titi
es
with
in
u
s
er
s
'
i
n
p
u
t,
we
u
tili
ze
n
atu
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
(
NL
P),
d
ep
lo
y
in
g
th
e
Sp
aCy
lib
r
ar
y
.
I
t
en
s
u
r
es
th
e
ch
at
b
o
t'
s
s
em
an
ti
c
co
m
p
r
eh
e
n
s
io
n
b
y
co
m
p
r
eh
e
n
d
in
g
an
d
id
en
tif
y
in
g
e
n
titi
es.
c.
L
an
g
u
ag
e
d
etec
to
r
a
n
d
h
an
d
l
er
:
A
p
ar
t
o
f
th
e
NL
P
th
at
h
a
n
d
les
d
if
f
er
e
n
t
lan
g
u
a
g
es
s
in
ce
th
e
OE
R
s
ar
e
o
r
ig
in
ally
co
m
in
g
f
r
o
m
d
if
f
er
e
n
t E
u
r
o
p
ea
n
c
o
u
n
tr
ies ad
o
p
tin
g
d
if
f
er
e
n
t la
n
g
u
ag
es.
d.
C
o
n
ten
t
-
b
ased
f
ilter
in
g
(
C
B
F
)
r
ec
o
m
m
e
n
d
atio
n
u
s
in
g
`
W
o
r
d
2
Vec
`
:
T
o
tailo
r
OE
R
r
e
co
m
m
en
d
atio
n
s
b
ased
o
n
s
em
an
tic
co
n
ten
t
s
i
m
ilar
ity
.
T
h
e
R
S
d
ep
lo
y
s
th
e
W
o
r
d
2
Vec
m
o
d
el
f
r
o
m
th
e
G
en
s
im
lib
r
ar
y
.
I
t
cr
ea
tes
v
ec
to
r
r
ep
r
esen
tatio
n
s
f
o
r
u
s
er
q
u
er
ies
an
d
r
eso
u
r
ce
tex
ts
.
T
h
e
co
s
in
e
s
im
ilar
ity
m
etr
ic
is
ca
lcu
lated
th
en
to
q
u
an
tif
y
th
e
p
ar
ity
b
etwe
en
p
r
ef
er
e
n
ce
s
a
n
d
r
ec
o
m
m
en
d
atio
n
s
.
T
h
e
r
ea
s
o
n
to
p
air
C
B
F
alg
o
r
ith
m
s
an
d
c
o
s
in
e
s
im
ilar
ity
is
th
at
th
is
ap
p
r
o
ac
h
h
as
d
em
o
n
s
tr
ated
p
r
o
m
is
in
g
r
esu
lts
in
m
ax
im
izin
g
r
ec
o
m
m
en
d
atio
n
ac
c
u
r
ac
y
in
s
ev
er
al
ca
s
es,
s
u
ch
as in
[
2
2
]
.
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.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
1
0
7
-
3
1
1
7
3114
e.
User
f
ee
d
b
ac
k
m
ec
h
an
is
m
:
T
o
en
ab
le
u
s
er
in
p
u
t
f
o
r
c
o
n
tin
u
o
u
s
p
r
o
g
r
ess
an
d
im
p
r
o
v
e
m
e
n
t,
we
o
p
t
f
o
r
a
s
y
s
tem
atic
u
s
er
f
ee
d
b
ac
k
p
r
o
ce
s
s
.
T
h
is
m
ec
h
an
is
m
i
s
b
as
ed
o
n
p
r
o
m
p
tin
g
th
e
u
s
er
f
o
r
in
p
u
t
th
at
is
co
llected
an
d
s
to
r
e
d
as r
atin
g
.
T
h
e
s
y
s
tem
o
p
ted
f
o
r
a
m
o
d
u
lar
d
esig
n
b
ased
o
n
s
ev
er
al
class
es.
I
t
is
an
ar
ch
itectu
r
al
ap
p
r
o
ac
h
to
en
h
an
ce
t
h
e
co
d
e
o
r
g
an
izatio
n
,
co
m
p
r
eh
e
n
s
io
n
,
a
n
d
m
ain
t
ain
ab
ilit
y
.
T
h
is
m
o
d
u
lar
asp
ec
t
is
r
esp
ec
tiv
ely
r
esp
o
n
s
ib
le
f
o
r
th
e
p
r
ev
i
o
u
s
a
ctio
n
s
:
au
th
en
ticatio
n
class
,
in
p
u
t
p
r
o
ce
s
s
in
g
class
,
r
ec
o
m
m
en
d
atio
n
g
en
er
atio
n
class
,
u
s
er
f
ee
d
b
ac
k
class
an
d
m
ain
ch
atb
o
t
cla
ss.
T
o
en
s
u
r
e
u
s
er
in
ter
ac
tio
n
,
th
e
c
h
atb
o
t
d
ep
lo
y
s
a
g
r
a
p
h
ical
u
s
er
in
ter
f
ac
e
(
GUI
)
b
ased
o
n
th
e
T
k
in
ter
lib
r
a
r
y
[
2
3
]
.
Fig
u
r
e
5
s
h
o
wca
s
es
MO
E
R
I
D’
s
g
r
ap
h
ical
u
s
er
in
te
r
f
ac
e
(
G
UI
)
.
T
h
e
lo
g
in
s
cr
ee
n
d
em
o
n
s
tr
ates
th
at
u
s
er
s
m
u
s
t
en
ter
th
eir
u
s
er
n
am
e
an
d
p
ass
wo
r
d
to
ac
ce
s
s
th
e
ch
atb
o
t.
T
h
e
ch
at
I
n
te
r
f
ac
e
p
r
o
v
es
th
at
u
s
er
s
ca
n
in
ter
ac
t w
ith
MO
E
R
I
D
b
y
en
ter
in
g
tex
t q
u
er
ies o
r
p
ar
a
g
r
ap
h
s
in
th
e
in
p
u
t f
ield
.
I
t a
ls
o
f
ea
tu
r
es o
p
tio
n
s
to
r
ate
r
ec
o
m
m
en
d
atio
n
s
an
d
s
u
b
m
it
in
p
u
ts
f
o
r
f
u
r
th
e
r
ass
is
tan
ce
.
Fig
u
r
e
5
.
MO
E
R
I
D’
s
in
ter
f
ac
e
3
.
5
.
Sy
nthet
ic
da
t
a
ev
a
lua
t
io
n
T
h
e
u
s
ef
u
ln
ess
o
f
s
y
n
th
etic
d
ata
ex
ten
d
s
f
r
o
m
th
e
ef
f
icien
c
y
o
f
s
y
n
th
etic
r
ev
iews
in
ev
alu
atin
g
R
S
[
2
4
]
to
ex
am
in
in
g
s
y
n
th
etic
d
atasets
f
o
r
c
o
n
v
e
r
s
atio
n
al
R
S
[
2
5
]
.
T
h
e
g
en
er
atio
n
o
f
t
h
is
ty
p
e
o
f
d
ata,
is
d
ef
in
ed
as
th
e
ap
p
r
o
ac
h
to
cr
ea
te
d
ata
with
s
tatis
tically
eq
u
iv
alen
t
p
r
o
p
er
ties
to
r
ea
l
-
wo
r
ld
d
ata.
T
h
ese
tech
n
iq
u
es
d
ee
m
c
o
n
s
id
er
ab
l
y
ef
f
icien
t
in
ev
al
u
atin
g
an
d
te
s
tin
g
s
ev
er
al
s
y
s
tem
s
[
2
6
]
,
[
2
7
]
.
I
n
s
p
ir
e
d
b
y
th
e
r
esear
ch
[
2
8
]
,
s
y
n
th
etic
lo
g
ic
is
u
s
ed
to
g
en
er
ate
s
im
u
lated
u
s
er
p
r
ef
e
r
en
ce
s
co
m
b
i
n
in
g
UR
L
s
an
d
in
ter
est
s
co
r
es.
C
alcu
latin
g
p
r
ec
is
io
n
,
r
ec
all
an
d
F1
s
co
r
e
as
th
ey
ar
e
th
e
m
o
s
t
u
s
ed
ev
alu
atio
n
m
etr
ics
[
2
9
]
.
T
ec
h
n
ically
,
t
h
e
u
s
ed
m
eth
o
d
u
tili
ze
s
s
y
n
th
etic
u
s
er
p
r
ef
er
en
ce
s
s
to
r
ed
in
th
e
s
y
n
th
et
ic_
u
s
er
_
p
r
e
f
er
en
ce
s
d
ictio
n
ar
y
to
s
im
u
late
u
s
er
in
t
er
est
in
a
s
et
o
f
UR
L
s
.
Fig
u
r
e
6
d
e
p
icts
th
e
p
e
r
f
o
r
m
an
ce
m
et
r
ics
o
f
t
h
e
s
y
s
tem
.
Pre
cisi
o
n
is
d
ef
in
ed
b
y
th
e
ac
cu
r
ac
y
o
f
p
o
s
itiv
e
p
r
ed
ictio
n
s
,
an
d
r
e
p
o
r
te
d
at
0
.
9
3
.
R
ec
all,
r
ep
r
esen
ted
b
y
th
e
s
y
s
tem
'
s
r
elev
an
ce
to
ca
p
tu
r
e
p
er
tin
en
t item
s
an
d
o
b
s
er
v
ed
a
t 0
.
8
0
.
An
d
t
h
e
F1
s
co
r
e
is
in
ter
p
r
eted
as a
b
allast
o
f
p
r
ec
is
io
n
an
d
r
ec
all
ca
p
tu
r
i
n
g
th
e
o
v
e
r
all
p
er
f
o
r
m
an
ce
o
f
th
e
s
y
s
tem
an
d
is
r
ep
o
r
ted
as
0
.
8
6
.
T
h
ese
v
alu
es
s
u
g
g
est an
ac
cu
r
ate
a
n
d
r
eliab
l
e
m
o
d
el
with
b
ala
n
ce
d
p
r
ec
is
io
n
an
d
r
ec
all.
Fig
u
r
e
6
.
E
v
alu
atio
n
m
etr
ics
4.
DIS
CU
SS
I
O
N
T
h
e
MO
E
R
I
D
ch
atb
o
t
is
d
ee
m
ed
to
b
e
ef
f
icien
t
as
d
em
o
n
s
tr
ated
b
y
th
e
ev
al
u
atio
n
m
etr
ics.
T
h
e
f
ea
tu
r
es
u
s
ed
f
o
r
th
is
m
o
d
el
ar
e
‘
SUB
J
E
C
T
'
,
'T
I
T
L
E
'
,
'
T
A
G
'
,
'SU
B
J
E
C
T
S_
OF_
I
NT
E
R
E
ST
'
,
'
S
POKE
N_
L
ANGU
AGE
S
'
,
a
n
d
'
MO
T
HE
R
_
T
ONGU
E
’
,
as
th
ey
ar
e
th
e
m
o
s
t
r
elev
an
t
m
e
tad
ata.
MO
E
R
I
D
is
u
s
er
-
f
r
ien
d
l
y
an
d
s
im
p
le
to
m
an
ip
u
late.
T
h
e
o
b
tain
ed
v
alu
e
s
in
d
icate
th
at
th
e
r
ec
o
m
m
en
d
atio
n
s
ar
e
r
elev
an
t
an
d
ac
cu
r
ate.
W
e
ap
p
lied
a
war
m
s
tar
t
m
eth
o
d
in
s
p
ir
ed
b
y
San
d
o
u
s
s
i
et
a
l.
[
1
6
]
,
to
m
i
tig
ate
th
e
co
ld
s
tar
t
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:
2088
-
8
7
0
8
MOER
I
D:
en
h
a
n
cin
g
o
p
en
e
d
u
ca
tio
n
a
l res
o
u
r
ce
d
is
co
ve
r
y
t
h
r
o
u
g
h
a
n
…
(
R
ima
S
a
n
d
o
u
s
s
i
)
3115
p
r
o
b
lem
,
th
e
C
B
F
m
o
d
el
aim
s
to
r
ec
o
m
m
en
d
item
s
s
im
ilar
to
th
o
s
e
p
r
ev
io
u
s
ly
u
p
lo
a
d
ed
b
y
th
e
u
s
er
to
th
e
d
ataset,
en
s
u
r
in
g
r
elev
a
n
ce
ev
en
with
lim
ited
u
s
er
h
is
to
r
y
[
3
0
]
.
T
h
e
s
y
s
tem
ad
d
r
e
s
s
es
l
iter
atu
r
e
g
ap
s
h
ig
h
lig
h
ted
in
[
4
]
.
I
t
im
p
lem
en
ts
th
e
en
v
is
io
n
ed
ar
ch
itectu
r
e
in
[
1
6
]
.
T
o
m
ak
e
m
o
d
if
ica
tio
n
an
d
u
p
g
r
ad
i
n
g
u
n
p
r
o
b
lem
atic,
th
e
s
y
s
tem
is
m
o
d
u
lab
le
th
r
o
u
g
h
a
class
-
b
ased
s
tr
u
ctu
r
e,
en
d
o
wed
with
a
ch
atb
o
t
to
s
u
p
p
o
r
t
an
in
ter
ac
tiv
e
a
n
d
e
n
g
ag
in
g
u
s
er
ex
p
er
ien
ce
,
m
o
tiv
atin
g
ed
u
ca
to
r
s
to
u
tili
ze
th
e
s
y
s
tem
f
o
r
th
eir
i
n
s
tr
u
ctio
n
al
n
ee
d
s
.
Desp
ite
its
p
r
o
m
is
in
g
p
er
f
o
r
m
an
ce
,
MO
E
R
I
D
r
eq
u
ir
e
s
f
u
r
th
er
v
alid
atio
n
u
n
d
er
r
ea
l
-
wo
r
ld
co
n
d
itio
n
s
.
Fo
r
m
o
r
e
ef
f
icien
t
test
in
g
,
we
ex
p
ec
t
to
ex
p
e
r
im
en
t
with
a
r
ea
l
-
wo
r
ld
r
e
v
iew
ev
alu
atio
n
to
b
etter
u
n
d
er
s
tan
d
t
h
e
s
y
s
tem
’
s
p
r
ac
tical
im
p
licatio
n
s
.
W
e
also
a
im
to
ad
d
a
d
o
wn
lo
a
d
in
g
f
e
atu
r
e
to
em
p
o
wer
ed
u
ca
to
r
s
to
c
o
n
tr
ib
u
te
n
ew
O
E
R
,
en
r
ich
in
g
th
e
d
ataset
an
d
ex
p
an
d
i
n
g
th
e
d
iv
er
s
ity
o
f
r
ec
o
m
m
en
d
atio
n
s
.
Fu
tu
r
e
wo
r
k
will
f
o
cu
s
o
n
in
teg
r
atin
g
C
F
as
a
v
alu
ab
le
tech
n
iq
u
e
to
f
in
e
-
tu
n
e
an
d
en
h
an
c
e
r
ec
o
m
m
en
d
atio
n
s
b
y
in
co
r
p
o
r
atin
g
u
s
er
-
item
in
ter
ac
tio
n
s
an
d
g
r
o
u
p
p
r
ef
er
en
ce
s
.
B
y
a
d
d
in
g
C
F,
a
wid
ely
u
s
ed
r
ec
o
m
m
en
d
atio
n
tech
n
iq
u
e,
we
aim
to
im
p
r
o
v
e
th
e
s
y
s
tem
’
s
ac
cu
r
ac
y
an
d
tr
an
s
itio
n
it
in
to
a
h
y
b
r
id
r
ec
o
m
m
en
d
er
.
A
d
d
itio
n
ally
,
as
a
f
u
tu
r
e
task
,
we
p
lan
to
o
p
tim
ize
MO
E
R
I
D’
s
r
esp
o
n
s
e
tim
e
f
o
r
b
etter
p
er
f
o
r
m
an
ce
.
5.
CO
NCLU
SI
O
N
T
h
e
r
ec
o
m
m
e
n
d
atio
n
s
y
s
tem
h
as r
ev
o
lu
tio
n
ize
d
ed
u
ca
tio
n
al
p
r
ac
tices.
Ho
wev
er
,
m
o
s
t o
f
th
e
cu
r
r
en
t
OE
R
R
Ss
h
av
e
f
o
c
u
s
ed
o
n
d
ev
elo
p
in
g
lear
n
e
r
-
ce
n
ter
e
d
OE
R
r
ec
o
m
m
en
d
er
s
b
u
t
h
av
e
n
o
t
y
et
f
o
cu
s
ed
m
u
ch
o
n
in
s
tr
u
ct
o
r
s
-
ce
n
ter
ed
OE
R
r
ec
o
m
m
en
d
e
r
s
.
I
n
th
is
p
ap
er
,
we
b
u
ilt
a
r
ec
o
m
m
en
d
a
tio
n
s
y
s
tem
f
o
r
t
h
e
teac
h
in
g
co
m
m
u
n
ity
b
y
co
m
b
in
in
g
C
B
F
an
d
NL
P
tech
n
iq
u
es
to
en
d
o
w
it
with
a
ch
at
b
o
t.
First,
we
u
s
ed
co
s
in
e
s
im
ilar
ity
to
id
en
tify
th
e
b
est
alg
o
r
ith
m
th
at
s
u
it
es
o
u
r
ca
s
e.
Nex
t,
we
s
elec
ted
wo
r
d
2
v
ec
as
a
r
ec
o
m
m
en
d
atio
n
alg
o
r
ith
m
an
d
we
ad
d
e
d
an
NL
P
co
m
p
o
n
e
n
t
to
b
u
ild
o
u
r
c
h
atb
o
t.
T
h
e
u
s
ed
d
ata
ar
e
f
r
o
m
a
r
ea
l
-
life
d
ataset
f
o
r
ac
c
u
r
ate
r
esu
lts
an
d
o
p
tim
al
r
ec
o
m
m
en
d
atio
n
s
.
W
e
also
d
ep
lo
y
ed
s
y
n
th
etic
d
ata
to
ev
alu
ate
th
e
s
y
s
tem
an
d
we
o
b
tain
ed
o
u
ts
tan
d
in
g
r
esu
lts
.
Ho
wev
er
,
we
s
till
en
co
u
n
ter
lim
itatio
n
s
,
s
u
ch
as th
e
o
p
tim
izatio
n
o
f
d
ata
p
r
o
ce
s
s
in
g
s
p
ee
d
d
u
e
to
th
e
m
ac
h
in
e
r
eso
u
r
ce
lim
its
an
d
th
e
v
o
lu
m
e
o
f
th
e
d
ataset.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
San
d
o
u
s
s
i Ri
m
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Hn
id
a
Me
r
iem
✓
✓
✓
✓
✓
✓
✓
✓
Dao
u
d
i
Najim
a
✓
✓
✓
✓
✓
✓
✓
Ajh
o
u
n
R
ac
h
id
a
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
au
th
o
r
s
co
n
f
ir
m
th
at
th
e
d
ata
s
u
p
p
o
r
tin
g
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
ailab
le
with
in
th
e
ar
ticle
an
d
r
ef
e
r
en
ce
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.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
1
0
7
-
3
1
1
7
3116
RE
F
E
R
E
NC
E
S
[
1
]
O
p
e
n
e
d
u
c
a
t
i
o
n
a
l
res
o
u
r
c
e
s
.
G
E
M
R
e
p
o
r
t
U
N
ES
C
O
,
2
0
2
3
.
d
o
i
:
1
0
.
5
4
6
7
6
/
l
b
i
v
3
3
3
7
.
[
2
]
“
R
e
c
o
mm
e
n
d
a
t
i
o
n
o
n
o
p
e
n
e
d
u
c
a
t
i
o
n
a
l
r
e
so
u
r
c
e
s
(
O
E
R
)
-
Le
g
a
l
a
f
f
a
i
r
s
,
”
U
n
d
e
rg
r
o
u
n
d
Pi
p
e
l
i
n
e
C
o
rr
o
s
i
o
n
:
D
e
t
e
c
t
i
o
n
,
An
a
l
y
s
i
s
a
n
d
Pre
v
e
n
t
i
o
n
.
h
t
t
p
s
:
/
/
w
w
w
.
u
n
e
sc
o
.
o
r
g
/
e
n
/
l
e
g
a
l
-
a
f
f
a
i
r
s
/
r
e
c
o
mm
e
n
d
a
t
i
o
n
-
o
p
e
n
-
e
d
u
c
a
t
i
o
n
a
l
-
r
e
s
o
u
r
c
e
s
-
o
e
r
(
a
c
c
e
sse
d
N
o
v
.
1
5
,
2
0
2
4
)
.
[
3
]
X
.
N
.
La
m,
T.
V
u
,
T.
D
.
Le
,
a
n
d
A
.
D
.
D
u
o
n
g
,
“
A
d
d
r
e
ss
i
n
g
c
o
l
d
-
st
a
r
t
p
r
o
b
l
e
m
i
n
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
st
e
ms,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
U
b
i
q
u
i
t
o
u
s
I
n
f
o
rm
a
t
i
o
n
M
a
n
a
g
e
m
e
n
t
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
,
I
C
U
I
MC
-
2
0
0
8
,
J
a
n
.
2
0
0
8
,
p
p
.
2
0
8
–
2
1
1
.
d
o
i
:
1
0
.
1
1
4
5
/
1
3
5
2
7
9
3
.
1
3
5
2
8
3
7
.
[
4
]
S
.
R
i
ma
,
H
.
M
e
r
i
e
m
,
D
.
N
a
j
i
ma,
a
n
d
A
.
R
a
c
h
i
d
a
,
“
S
y
st
e
ma
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
o
n
o
p
e
n
e
d
u
c
a
t
i
o
n
a
l
r
e
so
u
r
c
e
s
r
e
c
o
mm
e
n
d
e
r
sy
st
e
ms,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
t
e
ra
c
t
i
v
e
M
o
b
i
l
e
T
e
c
h
n
o
l
o
g
i
e
s
,
v
o
l
.
1
6
,
n
o
.
1
8
,
p
p
.
4
4
–
7
7
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
3
9
9
1
/
i
j
i
m
.
v
1
6
i
1
8
.
3
2
1
9
7
.
[
5
]
E.
Ç
a
n
o
a
n
d
M
.
M
o
r
i
si
o
,
“
H
y
b
r
i
d
r
e
c
o
mm
e
n
d
e
r
s
y
st
e
ms:
A
s
y
st
e
ma
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
I
n
t
e
l
l
i
g
e
n
t
D
a
t
a
A
n
a
l
y
s
i
s
,
v
o
l
.
2
1
,
n
o
.
6
,
p
p
.
1
4
8
7
–
1
5
2
4
,
N
o
v
.
2
0
1
7
,
d
o
i
:
1
0
.
3
2
3
3
/
I
D
A
-
1
6
3
2
0
9
.
[
6
]
M
.
T.
S
h
a
r
a
d
P
h
a
l
l
e
a
n
d
P
.
S
.
B
h
u
s
h
a
n
,
“
C
o
n
t
e
n
t
-
b
a
s
e
d
f
i
l
t
e
r
i
n
g
a
n
d
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
:
A
c
o
mp
a
r
a
t
i
v
e
st
u
d
y
,
”
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
Z
o
o
l
o
g
y
,
p
p
.
9
6
–
1
0
0
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
5
3
5
5
5
/
j
a
z
.
v
4
5
i
s4
.
4
1
5
8
.
[
7
]
S
.
S
.
L
a
k
sh
m
i
a
n
d
T
.
A
.
L
a
k
s
h
mi
,
‘
R
e
c
o
mm
e
n
d
a
t
i
o
n
S
y
st
e
ms:I
ssu
e
s
a
n
d
c
h
a
l
l
e
n
g
e
s.’
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
i
j
c
s
i
t
.
c
o
m/
d
o
c
s/
V
o
l
u
m
e
%2
0
5
/
v
o
l
5
i
ss
u
e
0
4
/
i
j
c
s
i
t
2
0
1
4
0
5
0
4
2
0
7
.
p
d
f
[
8
]
Y
.
A
d
i
l
a
k
sa
a
n
d
A
.
M
u
s
d
h
o
l
i
f
a
h
,
“
R
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
st
e
m fo
r
e
l
e
c
t
i
v
e
c
o
u
r
ses
u
si
n
g
c
o
n
t
e
n
t
-
b
a
s
e
d
f
i
l
t
e
r
i
n
g
a
n
d
w
e
i
g
h
t
e
d
c
o
si
n
e
si
mi
l
a
r
i
t
y
,
”
i
n
2
0
2
1
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
S
e
m
i
n
a
r
o
n
R
e
se
a
rc
h
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s,
I
S
RI
T
I
2
0
2
1
,
D
e
c
.
2
0
2
1
,
p
p
.
5
1
–
5
5
.
d
o
i
:
1
0
.
1
1
0
9
/
I
S
R
I
T
I
5
4
0
4
3
.
2
0
2
1
.
9
7
0
2
7
8
8
.
[
9
]
M
.
R
.
Ju
l
i
a
n
t
i
,
Y
.
H
e
r
y
a
d
i
,
B
.
Y
u
l
i
a
n
t
o
,
a
n
d
W
.
B
u
d
i
h
a
r
t
o
,
“
R
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
st
e
m
mo
d
e
l
f
o
r
p
e
r
so
n
a
l
i
z
e
d
l
e
a
r
n
i
n
g
i
n
h
i
g
h
e
r
e
d
u
c
a
t
i
o
n
u
s
i
n
g
c
o
n
t
e
n
t
-
b
a
se
d
f
i
l
t
e
r
i
n
g
me
t
h
o
d
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
2
0
2
2
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
Ma
n
a
g
e
m
e
n
t
a
n
d
T
e
c
h
n
o
l
o
g
y
,
I
C
I
MTec
h
2
0
2
2
,
A
u
g
.
2
0
2
2
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
M
Te
c
h
5
5
9
5
7
.
2
0
2
2
.
9
9
1
5
1
0
9
.
[
1
0
]
C
.
D
e
M
e
d
i
o
,
C
.
L
i
m
o
n
g
e
l
l
i
,
F
.
S
c
i
a
r
r
o
n
e
,
a
n
d
M
.
Te
m
p
e
r
i
n
i
,
“
M
o
o
d
l
e
R
E
C
:
A
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
st
e
m f
o
r
c
r
e
a
t
i
n
g
c
o
u
r
s
e
s
u
si
n
g
t
h
e
m
o
o
d
l
e
e
-
l
e
a
r
n
i
n
g
p
l
a
t
f
o
r
m,
”
C
o
m
p
u
t
e
rs
i
n
H
u
m
a
n
B
e
h
a
v
i
o
r
,
v
o
l
.
1
0
4
,
p
.
1
0
6
1
6
8
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
h
b
.
2
0
1
9
.
1
0
6
1
6
8
.
[
1
1
]
S
.
R
.
G
o
u
d
a
r
a
n
d
G
.
S
h
i
d
a
g
a
n
t
i
,
“
M
u
l
t
i
-
p
a
r
a
me
t
e
r
b
a
se
d
e
d
u
c
a
t
i
o
n
a
l
r
e
c
o
m
men
d
a
t
i
o
n
s
y
st
e
m
f
o
r
o
n
l
i
n
e
c
o
u
r
ses:
A
c
o
n
t
e
n
t
-
b
a
se
d
f
i
l
t
e
r
i
n
g
a
p
p
r
o
a
c
h
,
”
i
n
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
N
e
t
w
o
rk,
Mu
l
t
i
m
e
d
i
a
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
N
MIT
C
O
N
2
0
2
3
,
S
e
p
.
2
0
2
3
,
p
p
.
1
–
7
.
d
o
i
:
1
0
.
1
1
0
9
/
N
M
I
TC
O
N
5
8
1
9
6
.
2
0
2
3
.
1
0
2
7
6
1
5
3
.
[
1
2
]
M
.
D
h
a
h
r
i
a
n
d
M
.
K
.
K
h
r
i
b
i
,
“
A
r
e
v
i
e
w
o
f
e
d
u
c
a
t
i
o
n
a
l
r
e
c
o
mm
e
n
d
e
r
s
y
s
t
e
ms
f
o
r
t
e
a
c
h
e
r
s,
”
1
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
g
n
i
t
i
o
n
a
n
d
E
x
p
l
o
r
a
t
o
r
y
L
e
a
r
n
i
n
g
i
n
D
i
g
i
t
a
l
Ag
e
,
C
ELD
A
2
0
2
1
,
p
p
.
1
3
1
–
1
3
8
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
6
5
/
c
e
l
d
a
2
0
2
1
_
2
0
2
1
0
8
l
0
1
6
.
[
1
3
]
M
.
B
e
l
l
a
l
,
A
.
M
e
j
r
i
,
a
n
d
L
.
C
h
e
n
i
t
i
-
B
e
l
c
a
d
h
i
,
“
To
w
a
r
d
s
a
q
u
a
l
i
t
y
-
d
r
i
v
e
n
a
n
d
o
n
t
o
l
o
g
y
-
b
a
s
e
d
r
e
c
o
mm
e
n
d
e
r
f
r
a
mew
o
r
k
f
o
r
o
p
e
n
e
d
u
c
a
t
i
o
n
a
l
r
e
s
o
u
r
c
e
s
,
”
i
n
1
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
N
n
o
v
a
t
i
o
n
s
i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
sT
e
m
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
I
N
I
S
T
A
2
0
2
3
-
Pro
c
e
e
d
i
n
g
s
,
S
e
p
.
2
0
2
3
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
N
I
S
TA
5
9
0
6
5
.
2
0
2
3
.
1
0
3
1
0
5
2
1
.
[
1
4
]
A
.
G
o
r
d
i
l
l
o
,
D
.
Ló
p
e
z
-
F
e
r
n
á
n
d
e
z
,
a
n
d
K
.
V
e
r
b
e
r
t
,
“
Ex
a
mi
n
i
n
g
t
h
e
u
sef
u
l
n
e
ss
o
f
q
u
a
l
i
t
y
sc
o
r
e
s
f
o
r
g
e
n
e
r
a
t
i
n
g
l
e
a
r
n
i
n
g
o
b
j
e
c
t
r
e
c
o
m
me
n
d
a
t
i
o
n
s
i
n
r
e
p
o
si
t
o
r
i
e
s
o
f
o
p
e
n
e
d
u
c
a
t
i
o
n
a
l
r
e
so
u
r
c
e
s,”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
0
,
n
o
.
1
3
,
p
.
4
6
3
8
,
J
u
l
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
0
1
3
4
6
3
8
.
[
1
5
]
J.
F
.
H
e
r
r
e
r
a
-
C
u
b
i
d
e
s,
P
.
A
.
G
a
o
n
a
-
G
a
r
c
í
a
,
C
.
E
.
M
o
n
t
e
n
e
g
r
o
-
M
a
r
í
n
,
a
n
d
S
.
S
á
n
c
h
e
z
-
A
l
o
n
so
,
“
I
mp
r
o
v
i
n
g
O
ER
d
e
scri
p
t
i
o
n
s
t
o
e
n
h
a
n
c
e
t
h
e
i
r
a
v
a
i
l
a
b
i
l
i
t
y
,
r
e
u
s
e
,
a
n
d
e
n
r
i
c
h
me
n
t
,
”
Ed
u
c
a
t
i
o
n
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s
,
v
o
l
.
2
7
,
n
o
.
2
,
p
p
.
1
8
1
1
–
1
8
3
9
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
6
3
9
-
0
2
1
-
1
0
6
4
1
-
w.
[
1
6
]
R
.
S
a
n
d
o
u
ss
i
,
M
.
H
n
i
d
a
,
N
.
D
a
o
u
d
i
,
a
n
d
R
.
A
j
h
o
u
n
,
“
M
O
ER
I
D
:
D
e
s
i
g
n
a
n
d
i
mp
l
e
m
e
n
t
a
t
i
o
n
o
f
a
G
P
T
-
3
-
b
a
se
d
g
e
n
e
r
a
t
i
v
e
c
h
a
t
b
o
t
f
o
r
p
e
r
so
n
a
l
i
z
e
d
o
p
e
n
e
d
u
c
a
t
i
o
n
a
l
r
e
so
u
r
c
e
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
i
n
t
e
a
c
h
i
n
g
,
”
i
n
D
i
g
i
t
a
l
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
S
p
r
i
n
g
e
r
N
a
t
u
r
e
S
w
i
t
z
e
r
l
a
n
d
,
2
0
2
4
,
p
p
.
6
4
–
7
3
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
031
-
6
8
6
5
3
-
5
_
7
.
[
1
7
]
“
R
.
V
u
o
r
i
k
a
r
i
,
‘
Tr
a
v
e
l
w
e
l
l
d
a
t
a
se
t
,
’
N
o
v
.
2
0
1
7
.
d
o
i
:
1
0
.
1
3
1
4
0
/
R
G
.
2
.
2
.
2
7
7
4
2
.
7
4
5
6
2
”
.
[
1
8
]
C
.
W
a
n
g
a
n
d
D
.
M
.
B
l
e
i
,
“
C
o
l
l
a
b
o
r
a
t
i
v
e
t
o
p
i
c
m
o
d
e
l
i
n
g
f
o
r
r
e
c
o
mm
e
n
d
i
n
g
sc
i
e
n
t
i
f
i
c
a
r
t
i
c
l
e
s,”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
AC
M
S
I
G
K
D
D
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
K
n
o
w
l
e
d
g
e
D
i
sc
o
v
e
r
y
a
n
d
D
a
t
a
Mi
n
i
n
g
,
A
u
g
.
2
0
1
1
,
p
p
.
4
4
8
–
4
5
6
.
d
o
i
:
1
0
.
1
1
4
5
/
2
0
2
0
4
0
8
.
2
0
2
0
4
8
0
.
[
1
9
]
H
.
W
a
n
g
,
B
.
C
h
e
n
,
a
n
d
W
.
J
.
L
i
,
“
C
o
l
l
a
b
o
r
a
t
i
v
e
t
o
p
i
c
r
e
g
r
e
s
si
o
n
w
i
t
h
s
o
c
i
a
l
r
e
g
u
l
a
r
i
z
a
t
i
o
n
f
o
r
t
a
g
r
e
c
o
mm
e
n
d
a
t
i
o
n
,
”
i
n
I
J
C
AI
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
r
e
n
c
e
o
n
A
rt
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
2
0
1
3
,
p
p
.
2
7
1
9
–
2
7
2
5
.
[
2
0
]
Y
.
Zh
e
n
g
,
“
I
TM
-
R
e
c
:
A
n
o
p
e
n
d
a
t
a
s
e
t
f
o
r
e
d
u
c
a
t
i
o
n
a
l
r
e
c
o
mm
e
n
d
e
r
sy
s
t
e
ms,”
a
rX
i
v
:
2
3
0
3
.
1
0
2
3
0
,
2
0
2
3.
[
2
1
]
Z.
F
a
y
y
a
z
,
M
.
E
b
r
a
h
i
m
i
a
n
,
D
.
N
a
w
a
r
a
,
A
.
I
b
r
a
h
i
m,
a
n
d
R
.
K
a
s
h
e
f
,
“
R
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
st
e
ms:
A
l
g
o
r
i
t
h
ms,
c
h
a
l
l
e
n
g
e
s,
m
e
t
r
i
c
s,
a
n
d
b
u
s
i
n
e
ss
o
p
p
o
r
t
u
n
i
t
i
e
s,”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
0
,
n
o
.
2
1
,
p
p
.
1
–
2
0
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
0
2
1
7
7
4
8
.
[
2
2
]
V
.
T
h
a
d
a
a
n
d
V
.
J
a
g
l
a
n
,
“
C
o
m
p
a
r
i
so
n
o
f
Ja
c
c
a
r
d
,
D
i
c
e
,
C
o
si
n
e
S
i
m
i
l
a
r
i
t
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
n
o
v
a
t
i
o
n
s
i
n
E
n
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(
I
J
I
ET)
,
v
o
l
.
2
,
n
o
.
4
,
2
0
1
3
.
[
2
3
]
A
.
D
.
M
o
o
r
e
,
P
y
t
h
o
n
G
U
I
Pro
g
r
a
m
m
i
n
g
w
i
t
h
T
k
i
n
t
e
r:
D
e
si
g
n
a
n
d
b
u
i
l
d
f
u
n
c
t
i
o
n
a
l
a
n
d
u
s
e
r
-
f
ri
e
n
d
l
y
G
U
I
a
p
p
l
i
c
a
t
i
o
n
s
.
2
0
2
1
.
[
2
4
]
M
.
F
.
A
b
d
u
r
r
a
f
i
a
n
d
D
.
H
.
U
.
N
i
n
g
si
h
,
“
C
o
n
t
e
n
t
-
b
a
s
e
d
f
i
l
t
e
r
i
n
g
u
s
i
n
g
c
o
si
n
e
si
m
i
l
a
r
i
t
y
a
l
g
o
r
i
t
h
m
f
o
r
a
l
t
e
r
n
a
t
i
v
e
sel
e
c
t
i
o
n
o
n
t
r
a
i
n
i
n
g
p
r
o
g
r
a
ms,
”
J
o
u
r
n
a
l
o
f
S
o
f
t
C
o
m
p
u
t
i
n
g
Ex
p
l
o
r
a
t
i
o
n
,
v
o
l
.
4
,
n
o
.
4
,
p
p
.
2
0
4
–
2
1
2
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
5
2
4
6
5
/
j
o
sce
x
.
v
4
i
4
.
2
3
2
.
[
2
5
]
S
.
O
u
y
a
n
g
,
A
.
La
w
l
o
r
,
F
.
C
o
s
t
a
,
a
n
d
P
.
D
o
l
o
g
,
“
I
mp
r
o
v
i
n
g
e
x
p
l
a
i
n
a
b
l
e
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
w
i
t
h
s
y
n
t
h
e
t
i
c
r
e
v
i
e
w
s,
”
a
rXi
v
:
1
8
0
7
.
0
6
9
7
8
,
2
0
1
8
.
[
2
6
]
H
.
La
r
a
a
n
d
M
.
Ti
w
a
r
i
,
“
E
v
a
l
u
a
t
i
o
n
o
f
s
y
n
t
h
e
t
i
c
d
a
t
a
se
t
s
f
o
r
c
o
n
v
e
r
sat
i
o
n
a
l
r
e
c
o
mm
e
n
d
e
r
s
y
s
t
e
ms
,
”
a
rX
i
v
:
2
2
1
2
.
0
8
1
6
7
,
D
e
c
.
2
0
2
2
.
[
2
7
]
M
.
D
.
E
k
st
r
a
n
d
,
A
.
C
h
a
n
e
y
,
P
.
C
a
s
t
e
l
l
s,
R
.
B
u
r
k
e
,
D
.
R
o
h
d
e
,
a
n
d
M
.
S
l
o
k
o
m,
“
S
i
m
u
R
e
c
:
W
o
r
k
s
h
o
p
o
n
s
y
n
t
h
e
t
i
c
d
a
t
a
a
n
d
si
mu
l
a
t
i
o
n
me
t
h
o
d
s
f
o
r
r
e
c
o
mm
e
n
d
e
r
sy
s
t
e
ms
r
e
se
a
r
c
h
,
”
i
n
R
e
c
S
y
s
2
0
2
1
-
1
5
t
h
A
C
M
C
o
n
f
e
r
e
n
c
e
o
n
Re
c
o
m
m
e
n
d
e
r
S
y
st
e
m
s
,
S
e
p
.
2
0
2
1
,
p
p
.
8
0
3
–
8
0
5
.
d
o
i
:
1
0
.
1
1
4
5
/
3
4
6
0
2
3
1
.
3
4
7
0
9
3
8
.
[
2
8
]
F
.
K
.
D
a
n
k
a
r
a
n
d
M
.
I
b
r
a
h
i
m,
“
F
a
k
e
i
t
t
i
l
l
y
o
u
ma
k
e
i
t
:
G
u
i
d
e
l
i
n
e
s
f
o
r
e
f
f
e
c
t
i
v
e
s
y
n
t
h
e
t
i
c
d
a
t
a
g
e
n
e
r
a
t
i
o
n
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
1
,
n
o
.
5
,
p
p
.
1
–
1
8
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
1
0
5
2
1
5
8
.
[
2
9
]
E.
S
t
a
v
i
n
o
v
a
,
A
.
G
r
i
g
o
r
i
e
v
s
k
i
y
,
A
.
V
o
l
o
d
k
e
v
i
c
h
,
P
.
C
h
u
n
a
e
v
,
K
.
B
o
c
h
e
n
i
n
a
,
a
n
d
D
.
B
u
g
a
y
c
h
e
n
k
o
,
“
S
y
n
t
h
e
t
i
c
d
a
t
a
-
b
a
s
e
d
si
mu
l
a
t
o
r
s
f
o
r
r
e
c
o
mm
e
n
d
e
r
s
y
st
e
ms:
A
su
r
v
e
y
,
”
a
rX
i
v
:
2
2
0
6
.
1
1
3
3
8
v
1
,
J
u
n
.
2
0
2
2
.
[
3
0
]
I
.
B
a
r
j
a
s
t
e
h
,
R
.
F
o
r
sa
t
i
,
D
.
R
o
s
s,
A
.
H
.
Esf
a
h
a
n
i
a
n
,
a
n
d
H
.
R
a
d
h
a
,
“
C
o
l
d
-
st
a
r
t
r
e
c
o
mm
e
n
d
a
t
i
o
n
w
i
t
h
p
r
o
v
a
b
l
e
g
u
a
r
a
n
t
e
e
s
:
A
d
e
c
o
u
p
l
e
d
a
p
p
r
o
a
c
h
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
K
n
o
w
l
e
d
g
e
a
n
d
D
a
t
a
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
8
,
n
o
.
6
,
p
p
.
1
4
6
2
–
1
4
7
4
,
Ju
n
.
2
0
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
T
K
D
E.
2
0
1
6
.
2
5
2
2
4
2
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.