I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
2
,
A
p
r
il 2
0
2
6
,
p
p
.
1
8
6
3
~
1
8
7
5
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
2
.
p
p
1
8
6
3
-
1
8
7
5
1863
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Resea
rch t
hemes
a
nd t
rends
in
the
field
o
f
blockcha
i
n
eng
ineering
:
a
topic mo
delling
ana
ly
sis
Dina
ra
Z
ha
is
a
no
v
a
1,
2
,
M
a
din
a
M
a
ns
uro
v
a
1
1
D
e
p
a
r
t
me
n
t
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
B
i
g
D
a
t
a
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
ma
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
A
l
-
F
a
r
a
b
i
K
a
z
a
k
h
N
a
t
i
o
n
a
l
U
n
i
v
e
r
si
t
y
,
A
l
mat
y
,
K
a
z
a
k
h
s
t
a
n
2
K
i
n
g
’
s
C
o
l
l
e
g
e
o
f
L
o
n
d
o
n
,
K
i
n
g
’
s
-
B
o
l
a
sh
a
q
B
e
sp
o
k
e
P
r
o
g
r
a
mm
e
,
L
o
n
d
o
n
,
U
n
i
t
e
d
K
i
n
g
d
o
m
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
2
8
,
2
0
2
5
R
ev
is
ed
J
an
1
8
,
2
0
2
6
Acc
ep
ted
Feb
6
,
2
0
2
6
Th
is
stu
d
y
e
m
p
lo
y
e
d
t
o
p
ic
m
o
d
e
li
n
g
t
o
id
e
n
ti
fy
k
e
y
re
se
a
rc
h
th
e
m
e
s
in
b
lo
c
k
c
h
a
in
e
n
g
in
e
e
rin
g
a
n
d
e
x
a
m
in
e
d
h
o
w
t
h
e
se
th
e
m
e
s
h
a
v
e
e
v
o
lv
e
d
o
v
e
r
ti
m
e
.
Th
e
d
a
tas
e
t
o
f
c
o
ll
e
c
ted
a
b
s
trac
ts f
ro
m
3
,
6
6
5
re
lev
a
n
t
p
a
p
e
rs
o
f
Web
o
f
S
c
ien
c
e
(W
o
S
)
c
o
re
c
o
ll
e
c
ti
o
n
fo
r
th
e
p
e
rio
d
fro
m
2
0
1
9
to
2
0
2
4
wa
s
a
n
a
ly
z
e
d
with
late
n
t
Diric
h
let
a
ll
o
c
a
ti
o
n
(LDA)
a
p
p
ro
a
c
h
.
Ba
se
d
o
n
t
h
e
re
su
lt
s
o
f
th
e
to
p
ic
d
e
v
e
lo
p
m
e
n
t
tre
n
d
s
a
n
a
ly
sis,
th
e
t
o
p
ics
c
o
ll
e
c
ti
v
e
ly
h
ig
h
li
g
h
t
th
e
e
v
o
l
v
in
g
lan
d
sc
a
p
e
o
f
tec
h
n
o
l
o
g
ies
su
c
h
a
s
b
lo
c
k
c
h
a
in
,
sm
a
rt
c
o
n
tra
c
ts,
t
h
e
i
n
tern
e
t
o
f
t
h
in
g
s
(I
o
T),
a
n
d
e
d
g
e
c
o
m
p
u
ti
n
g
,
f
o
c
u
si
n
g
o
n
t
h
e
ir
in
teg
ra
ti
o
n
a
n
d
imp
a
c
t
a
c
ro
ss
se
c
to
rs
li
k
e
fi
n
a
n
c
e
,
h
e
a
lt
h
c
a
re
,
su
p
p
l
y
c
h
a
in
m
a
n
a
g
e
m
e
n
t,
a
n
d
e
n
e
rg
y
sy
s
tem
s.
It
o
ffe
rs
v
a
lu
a
b
le
in
si
g
h
ts
a
n
d
imp
li
c
a
ti
o
n
s
fo
r
re
se
a
rc
h
re
late
d
to
b
l
o
c
k
c
h
a
in
e
n
g
in
e
e
ri
n
g
.
Late
n
t
se
m
a
n
ti
c
in
d
e
x
in
g
(L
S
I)
p
ro
v
id
e
d
f
u
rt
h
e
r
u
n
d
e
rsta
n
d
i
n
g
b
y
h
i
g
h
l
ig
h
ti
n
g
stro
n
g
c
o
n
n
e
c
ti
o
n
s
b
e
twe
e
n
sp
e
c
ifi
c
to
p
ics
,
su
c
h
a
s
e
n
e
rg
y
trad
in
g
,
su
p
p
ly
c
h
a
i
n
s,
a
n
d
m
e
d
ica
l
a
p
p
li
c
a
ti
o
n
s.
A
c
o
m
p
a
riso
n
o
f
LDA
a
n
d
LS
I
t
o
p
i
c
s
re
v
e
a
led
o
v
e
rla
p
p
in
g
t
h
e
m
e
s,
wh
ich
su
p
p
o
rts
t
h
e
re
li
a
b
il
it
y
o
f
t
h
e
t
o
p
i
c
stru
c
tu
re
id
e
n
ti
fie
d
b
y
LDA.
K
ey
w
o
r
d
s
:
B
lo
ck
ch
ain
d
ev
elo
p
m
en
t
B
lo
ck
ch
ain
en
g
in
ee
r
in
g
L
aten
t D
ir
ich
let
allo
ca
tio
n
Natu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
T
o
p
ic
m
o
d
elin
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
:
Din
ar
a
Z
h
aisan
o
v
a
Dep
ar
tm
en
t o
f
Ar
tific
ial
I
n
tellig
en
ce
an
d
B
ig
Data
,
Facu
lty
o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
Al
-
Far
ab
i K
az
ak
h
Natio
n
al
U
n
iv
er
s
ity
7
1
Al
-
Far
ab
i a
v
e
.
,
B
o
s
tan
d
y
k
Dis
tr
ict,
Alm
aty
-
0
5
0
0
4
0
,
Kaz
ak
h
s
tan
E
m
ail: z
h
aisan
o
v
a1
5
@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
B
lo
ck
ch
ain
tech
n
o
lo
g
y
h
as
em
er
g
ed
as
a
r
ev
o
lu
tio
n
a
r
y
f
o
r
ce
ac
r
o
s
s
v
ar
io
u
s
in
d
u
s
tr
ie
s
,
o
f
f
er
in
g
d
ec
en
tr
alize
d
,
s
ec
u
r
e,
a
n
d
t
r
an
s
p
ar
en
t
s
o
lu
tio
n
s
f
o
r
co
m
p
le
x
p
r
o
b
lem
s
.
Ac
r
o
s
s
m
u
ltip
le
in
d
u
s
tr
ies,
b
lo
ck
ch
ain
s
u
p
p
o
r
ts
p
ee
r
-
to
-
p
ee
r
ex
ch
a
n
g
e
o
f
d
ig
ital
ass
ets
—
s
u
ch
as
cu
r
r
en
cies,
s
ec
u
r
ities
,
v
o
tes,
s
h
ar
es,
an
d
co
m
m
o
d
ities
—
en
ab
les
tr
an
s
p
ar
en
t
tr
ac
k
in
g
o
f
d
ata
r
elate
d
to
f
in
an
cial
ass
ets
an
d
p
h
y
s
ical
g
o
o
d
s
,
an
d
au
to
m
ates
th
e
ex
ec
u
tio
n
an
d
a
d
m
in
is
tr
atio
n
o
f
v
a
r
io
u
s
ty
p
es o
f
co
n
tr
ac
ts
,
in
clu
d
i
n
g
in
s
u
r
an
ce
ag
r
ee
m
e
n
ts
an
d
p
r
o
g
r
a
m
m
ab
le
p
a
y
m
en
t
s
y
s
tem
s
[
1
]
−
[
4
]
.
As
th
e
f
ield
o
f
b
l
o
ck
ch
ain
e
n
g
in
ee
r
in
g
co
n
tin
u
es
to
ev
o
lv
e
r
ap
id
ly
,
it
h
as
b
ec
o
m
e
i
n
cr
ea
s
in
g
ly
i
m
p
o
r
tan
t
to
u
n
d
er
s
tan
d
th
e
u
n
d
er
ly
i
n
g
tr
en
d
s
an
d
laten
t
to
p
ics
d
r
iv
in
g
its
d
ev
elo
p
m
e
n
t.
I
d
en
tify
i
n
g
th
ese
tr
en
d
s
n
o
t
o
n
ly
h
elp
s
in
tr
ac
k
in
g
t
h
e
p
r
o
g
r
ess
io
n
o
f
th
e
tec
h
n
o
lo
g
y
b
u
t
also
in
an
ticip
atin
g
f
u
tu
r
e
d
ir
ec
tio
n
s
an
d
ch
allen
g
es in
th
e
d
o
m
ain
.
L
aten
t
Dir
ich
let
allo
ca
tio
n
(
L
DA)
to
p
ic
m
o
d
ellin
g
h
as
d
e
m
o
n
s
tr
ated
its
ef
f
ec
tiv
en
ess
a
s
a
to
o
l
f
o
r
u
n
co
v
e
r
in
g
h
id
d
en
s
tr
u
ctu
r
es
with
in
lar
g
e
tex
t
c
o
r
p
o
r
a.
T
o
p
ic
m
o
d
ellin
g
[
5
]
is
a
m
eth
o
d
u
s
ed
in
tex
t
class
if
icatio
n
to
id
en
tify
th
e
u
n
d
er
ly
i
n
g
to
p
ics
with
in
a
te
x
t
co
r
p
u
s
,
with
L
DA
b
ei
n
g
th
e
m
o
s
t
wid
el
y
u
s
ed
tech
n
iq
u
e.
R
ec
en
t
s
tu
d
ies
h
av
e
d
em
o
n
s
tr
ated
th
e
v
er
s
atility
o
f
L
DA
i
n
d
i
v
er
s
e
f
ield
s
,
in
clu
d
in
g
a
g
r
icu
ltu
r
e
an
d
f
o
o
d
in
d
u
s
tr
y
[
6
]
,
p
ed
ag
o
g
y
an
d
k
n
o
wled
g
e
[
7
]
,
tr
a
n
s
p
o
r
tatio
n
[
8
]
,
an
d
AI
ap
p
licatio
n
[
9
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
8
6
3
-
1
8
7
5
1864
I
n
th
e
c
o
n
tex
t
o
f
b
lo
ck
c
h
ain
en
g
in
ee
r
i
n
g
,
w
h
er
e
th
e
v
o
l
u
m
e
o
f
ac
ad
em
ic
p
u
b
licatio
n
s
,
tech
n
ical
r
ep
o
r
ts
,
a
n
d
i
n
d
u
s
tr
y
wh
ite
p
a
p
er
s
is
r
ap
id
l
y
ex
p
an
d
i
n
g
,
L
D
A
o
f
f
er
s
a
m
eth
o
d
o
l
o
g
ically
s
o
u
n
d
ap
p
r
o
ac
h
to
d
is
till
in
g
co
m
p
lex
in
f
o
r
m
atio
n
in
to
co
h
e
r
en
t
to
p
ics.
T
h
is
i
s
p
ar
ticu
lar
ly
r
elev
an
t
as
th
e
f
ield
o
f
b
lo
c
k
ch
ain
ev
o
lv
es
r
a
p
id
ly
,
r
eq
u
ir
in
g
s
y
s
tem
atic
m
eth
o
d
s
t
o
tr
ac
k
its
m
u
ltifa
ce
ted
d
e
v
elo
p
m
e
n
t.
R
e
ce
n
t
ap
p
licatio
n
s
o
f
L
DA
in
tech
n
o
lo
g
y
d
o
m
ai
n
s
h
av
e
s
h
o
wn
its
p
o
ten
tial
f
o
r
i
d
en
tify
in
g
t
r
en
d
s
an
d
k
n
o
wle
d
g
e
g
ap
s
,
m
a
k
in
g
it
an
id
ea
l
to
o
l
f
o
r
an
aly
zi
n
g
b
l
o
ck
ch
ain
liter
atu
r
e
[
1
0
]
,
[
1
1
]
.
I
n
th
is
way
,
Sh
ar
m
a
et
a
l
.
[
1
2
]
id
en
tifie
d
c
u
r
r
e
n
t
tr
en
d
s
in
b
lo
ck
ch
ain
tech
n
o
lo
g
y
to
g
u
id
e
f
u
tu
r
e
r
esear
ch
b
y
co
llectin
g
d
ata
f
r
o
m
I
E
E
E
,
S
p
r
in
g
er
,
AC
M,
an
d
o
th
er
d
ig
ital
d
ata
b
ases
,
ap
p
ly
i
n
g
L
DA
f
o
r
to
p
ic
m
o
d
elin
g
,
a
n
d
an
aly
zi
n
g
th
e
m
o
d
el
’
s
o
u
t
co
m
es
th
r
o
u
g
h
k
ey
ter
m
s
an
d
d
o
cu
m
en
ts
ass
o
ci
ated
with
ea
c
h
t
o
p
ic.
L
ee
et
a
l.
[
1
3
]
a
n
aly
ze
d
s
ch
o
lar
ly
p
u
b
licatio
n
s
o
n
b
lo
ck
ch
ain
to
f
o
r
ec
ast
em
er
g
in
g
in
d
u
s
tr
ies
with
a
h
ig
h
p
o
ten
tial
f
o
r
b
lo
ck
ch
ai
n
ad
o
p
tio
n
.
T
h
eir
s
tu
d
y
em
p
lo
y
ed
L
DA
an
d
d
y
n
am
i
c
to
p
ic
m
o
d
elin
g
to
p
r
o
ce
s
s
lar
g
e
-
s
ca
le
tex
tu
al
d
ata,
ef
f
ec
tiv
ely
r
ed
u
ci
n
g
d
im
en
s
io
n
ality
an
d
ex
tr
ac
tin
g
in
s
ig
h
ts
f
r
o
m
th
e
u
n
d
e
r
ly
in
g
k
n
o
wled
g
e
s
tr
u
ctu
r
e
o
f
th
e
liter
atu
r
e.
T
h
is
p
ap
er
aim
s
to
ap
p
ly
L
DA
to
p
ic
m
o
d
ellin
g
to
a
co
m
p
r
e
h
en
s
iv
e
d
ataset
o
f
b
lo
ck
ch
ain
en
g
in
ee
r
in
g
liter
atu
r
e
to
id
en
ti
f
y
an
d
an
al
y
ze
th
e
laten
t
to
p
ic
s
an
d
em
er
g
in
g
tr
e
n
d
s
with
in
th
e
f
ield
.
B
y
d
o
in
g
s
o
,
th
e
s
ea
r
ch
was
m
ad
e
f
o
r
c
o
n
tr
ib
u
tio
n
to
a
d
ee
p
e
r
c
o
m
p
r
eh
en
s
io
n
o
f
th
e
p
r
esen
t
c
o
n
d
it
io
n
a
n
d
p
r
o
s
p
ec
tiv
e
d
ev
elo
p
m
e
n
t
o
f
b
lo
ck
ch
ain
en
g
in
ee
r
in
g
,
p
r
o
v
i
d
in
g
a
v
alu
a
b
le
r
eso
u
r
ce
f
o
r
b
o
th
r
esear
ch
er
s
an
d
p
r
ac
titi
o
n
er
s
.
Su
ch
in
s
ig
h
ts
ar
e
cr
u
cial
n
o
t o
n
ly
f
o
r
ad
v
a
n
cin
g
ac
a
d
em
ic
r
e
s
ea
r
ch
b
u
t a
ls
o
f
o
r
g
u
i
d
in
g
in
d
u
s
tr
y
in
n
o
v
atio
n
in
b
lo
ck
ch
ain
tech
n
o
l
o
g
ies.
B
u
ild
in
g
u
p
o
n
p
ast
r
esear
c
h
,
th
is
s
tu
d
y
ex
a
m
in
es
a
to
t
al
o
f
3
,
6
6
5
p
u
b
licatio
n
s
p
e
r
tain
in
g
to
b
lo
ck
ch
ain
e
n
g
in
ee
r
i
n
g
f
r
o
m
th
e
p
er
io
d
o
f
2
0
1
9
to
2
0
2
3
,
as
in
d
ex
ed
in
th
e
W
eb
o
f
Scien
ce
(
W
o
S
)
.
B
y
em
p
lo
y
in
g
a
c
o
m
b
in
atio
n
o
f
to
p
ic
m
o
d
ellin
g
tech
n
iq
u
es
a
n
d
to
p
ic
ev
o
l
u
tio
n
a
n
aly
s
is
,
th
e
ab
s
tr
ac
t
tex
ts
o
f
th
ese
p
ap
er
s
a
r
e
an
al
y
ze
d
t
o
i
d
en
tify
t
h
e
k
e
y
r
esear
ch
to
p
ics
an
d
tr
ac
e
t
h
e
d
e
v
elo
p
m
e
n
tal
t
r
en
d
s
in
b
lo
c
k
ch
ain
r
esear
ch
f
r
o
m
a
g
lo
b
al
p
er
s
p
ec
tiv
e.
T
h
e
s
tu
d
y
is
g
u
id
ed
b
y
t
wo
co
r
e
r
esear
c
h
q
u
esti
o
n
s
:
Q1
:
wh
ich
to
p
ics r
ep
r
esen
t th
e
m
o
s
t sig
n
if
ican
t f
o
c
u
s
o
f
cu
r
r
en
t r
esear
ch
?
Q2
:
wh
at
em
er
g
in
g
tr
en
d
s
ar
e
p
r
o
jecte
d
to
s
h
a
p
e
th
e
f
u
tu
r
e
d
ev
elo
p
m
en
t
o
f
th
ese
to
p
ics?
T
o
ad
d
r
ess
th
e
af
o
r
em
en
tio
n
e
d
r
esear
ch
q
u
esti
o
n
s
,
th
e
a
b
s
tr
ac
ts
o
f
3
,
6
6
5
d
o
c
u
m
en
ts
wer
e
an
aly
ze
d
u
s
in
g
ter
m
f
r
eq
u
en
cy
–
in
v
er
s
e
d
o
cu
m
e
n
t
f
r
e
q
u
en
c
y
(
TF
-
I
DF
)
–
b
ased
id
e
n
tific
atio
n
o
f
k
e
y
wo
r
d
s
to
c
o
n
s
tr
u
ct
a
co
llectio
n
o
f
e
x
tr
ac
ted
k
ey
wo
r
d
s
.
T
o
p
ic
e
v
o
lu
tio
n
was
ass
e
s
s
ed
u
s
in
g
th
e
b
ib
lio
m
etr
ic
p
ac
k
ag
e
in
R
,
wh
ile
L
DA
to
p
ic
m
o
d
ellin
g
was
e
m
p
lo
y
ed
to
id
e
n
tify
n
in
e
d
is
tin
ct
to
p
ics
with
in
th
e
co
r
p
u
s
.
T
h
e
p
r
o
p
e
r
ties
an
d
ad
v
an
ce
m
e
n
t
tr
ajec
to
r
ies
o
f
ea
ch
id
e
n
tifie
d
t
o
p
ic
was
s
u
b
s
eq
u
en
tly
ex
am
in
e
d
.
W
h
ile
s
ev
er
al
p
r
io
r
s
tu
d
ies
[
1
0
]
,
[
12
]
,
[
1
3
]
h
a
v
e
a
p
p
lied
L
DA
to
p
ic
m
o
d
ellin
g
t
o
r
elate
d
d
o
m
ai
n
s
,
th
is
s
tu
d
y
is
am
o
n
g
th
e
f
ir
s
t
to
ex
ten
s
iv
ely
ap
p
ly
L
DA
to
b
l
o
ck
ch
ain
en
g
i
n
ee
r
in
g
r
esear
ch
.
No
tab
ly
,
k
ey
p
ar
am
eter
s
,
in
c
lu
d
in
g
th
e
n
u
m
b
e
r
o
f
to
p
ics,
wer
e
d
eter
m
in
ed
b
y
m
ea
n
s
o
f
tr
ain
in
g
m
ac
h
in
e
lear
n
in
g
m
o
d
els
u
s
in
g
p
er
p
lex
ity
an
d
co
h
er
e
n
ce
m
etr
ics
to
o
p
tim
ize
th
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
.
T
h
e
an
aly
s
is
en
co
m
p
ass
ed
3
,
6
6
5
d
o
c
u
m
e
n
ts
f
r
o
m
th
e
W
o
S,
co
v
er
in
g
th
e
p
er
io
d
f
r
o
m
2
0
1
9
to
2
0
2
3
.
B
y
lev
er
ag
in
g
a
lar
g
e
-
s
ca
le
tex
tu
al
d
ataset,
t
h
is
s
tu
d
y
ex
tr
ac
ted
r
esear
ch
to
p
ics
an
d
d
ev
elo
p
m
en
tal
tr
en
d
s
in
b
lo
ck
ch
ai
n
en
g
in
ee
r
in
g
,
th
er
eb
y
o
f
f
er
i
n
g
b
o
th
th
e
o
r
etica
l
in
s
ig
h
ts
an
d
m
eth
o
d
o
lo
g
ical
f
r
am
ewo
r
k
s
f
o
r
f
u
tu
r
e
r
esear
ch
i
n
th
e
d
o
m
ain
.
B
lo
ck
ch
ain
en
g
in
ee
r
in
g
is
a
m
u
ltid
is
cip
lin
ar
y
f
ield
th
at
c
o
m
b
in
es
p
r
i
n
cip
les
f
r
o
m
co
m
p
u
ter
s
cien
ce
,
cr
y
p
to
g
r
ap
h
y
,
d
is
tr
ib
u
ted
s
y
s
t
em
s
,
an
d
ec
o
n
o
m
ics
to
d
ev
elo
p
d
ec
e
n
tr
alize
d
s
y
s
tem
s
th
at
e
n
s
u
r
e
d
ata
in
teg
r
ity
,
s
ec
u
r
ity
,
an
d
tr
an
s
p
ar
e
n
cy
.
Sin
ce
th
e
i
n
ce
p
tio
n
o
f
b
lo
c
k
ch
ai
n
tech
n
o
lo
g
y
with
B
itco
in
in
2
0
0
8
[
1
4
]
,
t
h
e
f
ield
h
as
s
ee
n
r
ap
i
d
ex
p
an
s
io
n
in
to
v
ar
io
u
s
s
ec
to
r
s
co
v
e
r
in
g
f
in
a
n
ce
,
s
u
p
p
ly
c
h
ain
m
a
n
ag
em
e
n
t,
h
ea
lth
ca
r
e
,
an
d
o
th
er
a
p
p
licatio
n
ar
ea
s
.
T
o
p
ic
m
o
d
ellin
g
,
p
ar
ticu
lar
ly
L
DA,
h
as
g
ai
n
ed
p
r
o
m
i
n
en
ce
as
an
ef
f
ec
tiv
e
m
eth
o
d
f
o
r
tex
t
m
in
in
g
a
n
d
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
(
NL
P
)
task
s
.
L
DA
h
as
b
ee
n
co
m
m
o
n
ly
em
p
lo
y
ed
u
s
ed
in
v
ar
io
u
s
d
o
m
ain
s
to
u
n
co
v
er
h
id
d
en
to
p
ics
with
in
lar
g
e
tex
t
c
o
r
p
o
r
a
,
f
ac
ilit
atin
g
th
e
u
n
d
er
s
tan
d
in
g
o
f
t
h
em
atic
s
tr
u
ctu
r
es
an
d
tr
en
d
s
o
v
er
tim
e
[
1
5
]
,
[
1
6
]
.
I
n
ac
ad
em
ic
r
ese
ar
ch
,
L
DA
h
as
b
ee
n
ap
p
lied
t
o
an
al
y
ze
to
p
ics
in
f
ield
s
as d
iv
er
s
e
as b
len
d
ed
lear
n
in
g
[
1
7
]
,
m
i
n
in
g
an
al
y
s
is
o
f
ed
u
ca
tio
n
al
s
cien
tific
r
esear
c
h
p
r
o
jects [
1
8
]
,
an
d
s
y
s
tem
atic
tech
n
o
lo
g
y
an
al
y
s
is
an
d
r
o
a
d
m
ap
f
o
r
m
u
latio
n
with
in
t
h
e
b
lo
ck
ch
ai
n
d
o
m
ain
[
1
9
]
.
T
h
ese
ap
p
licatio
n
s
d
em
o
n
s
tr
ate
th
e
b
r
o
ad
ap
p
licab
ilit
y
o
f
L
DA
in
h
an
d
lin
g
la
r
g
e
d
atasets
an
d
its
u
tili
ty
in
r
ev
ea
lin
g
in
s
ig
h
ts
th
at
ar
e
n
o
t im
m
e
d
iately
ap
p
ar
e
n
t.
Z
im
m
er
m
an
n
et
a
l.
[
2
0
]
ad
d
r
e
s
s
ed
ex
is
tin
g
s
h
o
r
tco
m
in
g
s
b
y
p
r
o
p
o
s
in
g
n
ew
ap
p
r
o
ac
h
es th
at
en
h
an
ce
to
p
ic
co
h
er
en
ce
with
o
u
t
i
n
cr
e
asin
g
co
m
p
u
tatio
n
al
c
o
m
p
lex
i
ty
an
d
p
r
o
v
id
e
an
o
b
jectiv
e
m
eth
o
d
f
o
r
s
elec
tin
g
th
e
o
p
tim
al
n
u
m
b
er
o
f
to
p
ics
in
a
te
x
t
co
r
p
u
s
.
T
h
eir
ap
p
r
o
ac
h
in
clu
d
es
t
h
e
d
e
v
elo
p
m
e
n
t
o
f
a
m
o
r
e
r
ef
i
n
ed
s
to
p
wo
r
d
lis
t,
a
n
ew
d
im
en
s
io
n
ality
-
r
ed
u
ctio
n
h
e
u
r
is
tic
th
at
ass
es
s
es
wo
r
d
im
p
o
r
tan
ce
,
an
d
an
eig
en
v
alu
e
tech
n
iq
u
e
f
o
r
to
p
ic
d
eter
m
in
atio
n
.
T
h
ese
m
eth
o
d
s
ar
e
in
teg
r
ated
in
to
th
e
Z
im
m
ap
p
r
o
ac
h
,
wh
ic
h
d
em
o
n
s
tr
ates su
p
er
io
r
p
er
f
o
r
m
an
ce
to
L
DA
b
y
co
r
r
ec
tly
id
en
tify
in
g
th
e
n
u
m
b
er
o
f
to
p
ics in
7
o
u
t o
f
9
s
u
b
s
ets
o
f
th
e
20
-
n
ewsg
r
o
u
p
d
ataset,
co
m
p
ar
ed
t
o
L
DA
’
s
ac
cu
r
ac
y
in
n
o
n
e
o
f
th
e
s
u
b
s
ets.
L
u
o
e
t
a
l.
[
2
1
]
p
r
esen
ted
th
e
in
n
o
v
ativ
e
g
r
ap
h
co
n
tr
a
s
tiv
e
n
eu
r
al
to
p
ic
m
o
d
el
(
GC
T
M)
,
wh
ich
u
tili
ze
s
a
g
r
a
p
h
-
b
ased
s
am
p
lin
g
tech
n
iq
u
e
th
at
lev
er
a
g
es
d
etailed
co
r
r
elatio
n
s
an
d
ir
r
ele
v
an
cies
b
etwe
en
d
o
cu
m
en
ts
an
d
wo
r
d
s
.
T
h
e
m
o
d
el
co
n
ce
p
tu
alize
s
an
in
p
u
t
d
o
c
u
m
en
t
as
a
b
i
p
ar
tite
g
r
a
p
h
lin
k
in
g
d
o
cu
m
en
ts
an
d
wo
r
d
s
,
co
n
s
tr
u
ctin
g
n
etwo
r
k
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
R
esea
r
ch
th
eme
s
a
n
d
tr
en
d
s
in
th
e
field
o
f b
lo
ck
c
h
a
in
e
n
g
in
e
erin
g
:
a
to
p
ic
…
(
Din
a
r
a
Zh
a
is
a
n
o
va
)
1865
lin
k
in
g
b
o
t
h
p
o
s
itiv
ely
an
d
n
eg
ativ
ely
co
-
o
cc
u
r
r
in
g
wo
r
d
s
to
ca
p
tu
r
e
s
o
p
h
is
ticated
s
em
an
tic
ass
o
ciatio
n
s
b
etwe
en
ter
m
s
.
Ozk
a
r
a
et
a
l
.
[
2
2
]
s
o
u
g
h
t
t
o
d
e
m
o
n
s
tr
ate
th
e
ef
f
ec
tiv
en
ess
o
f
NL
P
a
n
d
to
p
ic
m
o
d
elin
g
ap
p
r
o
ac
h
es
f
o
r
o
r
g
an
izin
g
a
n
d
in
ter
p
r
etin
g
la
r
g
e
-
s
ca
le
s
ch
o
lar
ly
liter
atu
r
e
in
s
tr
o
k
e
r
ese
ar
ch
.
T
h
eir
f
i
n
d
in
g
s
s
h
o
w
th
at
th
ese
m
eth
o
d
s
ca
n
s
tr
ea
m
lin
e
liter
atu
r
e
r
ev
iews,
u
n
co
v
e
r
h
id
d
e
n
th
em
atic
s
tr
u
ctu
r
es,
an
d
m
o
n
ito
r
em
er
g
in
g
r
esear
ch
d
ir
ec
tio
n
s
,
h
ig
h
lig
h
tin
g
th
e
p
r
o
m
i
n
e
n
ce
o
f
a
n
im
al
m
o
d
els,
th
e
g
r
o
win
g
f
o
cu
s
o
n
r
eh
ab
ilit
atio
n
s
tu
d
ies,
an
d
th
e
cr
u
cial
r
o
le
o
f
r
ep
er
f
u
s
io
n
th
er
ap
y
.
Ak
ar
an
d
Yö
r
ü
k
[
2
3
]
u
s
ed
th
e
L
DA
alg
o
r
ith
m
,
a
to
p
ic
-
m
o
d
elin
g
m
eth
o
d
with
in
th
e
f
ield
o
f
tex
t m
in
in
g
,
t
o
elu
cid
ate
t
h
e
p
r
in
ci
p
al
r
esear
ch
th
em
es
ass
o
ciate
d
with
p
s
y
ch
o
lo
g
ical
co
n
tr
ac
t
b
r
ea
ch
es
a
n
d
v
io
latio
n
s
,
em
p
h
asizin
g
th
e
s
h
if
ts
in
f
o
cu
s
o
v
er
tim
e
an
d
p
ar
ticu
lar
ly
d
u
r
in
g
t
h
e
C
OVI
D
-
1
9
p
a
n
d
em
ic.
Alk
am
li
an
d
Alab
d
u
ljab
b
ar
[
2
4
]
a
d
o
p
ted
a
d
ata
-
d
r
iv
e
n
m
eth
o
d
o
l
o
g
y
th
at
co
m
b
in
ed
T
witter
d
ata
an
aly
s
is
w
ith
a
u
s
er
s
u
r
v
ey
to
in
v
esti
g
ate
p
r
iv
ac
y
is
s
u
es
a
s
s
o
ciate
d
with
C
h
atGPT
,
a
wid
ely
u
s
ed
g
en
er
ativ
e
AI
m
o
d
el.
B
y
a
p
p
l
y
in
g
L
DA
to
p
ic
m
o
d
elin
g
an
d
d
ata
class
if
icatio
n
tech
n
iq
u
es,
th
e
s
tu
d
y
id
en
tifi
ed
m
ajo
r
p
r
iv
ac
y
-
r
elate
d
co
n
ce
r
n
s
,
co
n
tr
ib
u
tin
g
to
a
d
ee
p
er
u
n
d
e
r
s
tan
d
in
g
o
f
u
s
er
p
er
ce
p
tio
n
s
an
d
p
r
o
v
id
i
n
g
in
s
ig
h
ts
to
s
u
p
p
o
r
t
p
o
licy
f
o
r
m
u
latio
n
a
n
d
g
u
id
e
f
u
t
u
r
e
r
es
ea
r
ch
o
n
p
r
iv
ac
y
in
g
en
er
ativ
e
AI
.
Saq
ib
et
a
l
.
[
2
5
]
an
al
y
ze
d
L
DA
an
d
n
o
n
n
eg
ativ
e
m
atr
i
x
f
ac
to
r
izatio
n
(
NM
F)
u
s
in
g
laten
t
s
em
an
tic
in
d
ex
in
g
(
L
SI)
to
e
v
alu
ate
th
e
ir
ef
f
ec
tiv
en
ess
in
o
p
in
i
o
n
a
n
d
tex
t
m
i
n
in
g
,
co
n
cl
u
d
in
g
th
at
wh
ile
b
o
t
h
m
o
d
els
p
er
f
o
r
m
well
in
to
p
ic
d
etec
tio
n
,
NM
F
d
em
o
n
s
tr
ates
a
s
lig
h
t
ad
v
an
ta
g
e
o
v
er
L
DA.
Ho
r
as
an
[
2
6
]
p
r
o
p
o
s
ed
a
h
y
b
r
id
m
o
d
el
f
o
r
co
llab
o
r
ativ
e
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
(
C
R
S)
b
ased
o
n
L
SI,
d
em
o
n
s
tr
atin
g
th
at
L
SI
-
b
ased
u
s
er
,
item
,
an
d
h
y
b
r
id
m
o
d
els
o
u
tp
er
f
o
r
m
tr
ad
itio
n
al
Pear
s
o
n
co
r
r
elatio
n
co
e
f
f
icien
t
(
PC
C
)
m
o
d
els
in
p
r
ed
ictio
n
ac
c
u
r
ac
y
wh
ile
ac
h
iev
in
g
lo
wer
co
m
p
u
tatio
n
al
co
m
p
lex
ity
th
r
o
u
g
h
d
im
e
n
s
io
n
ality
r
ed
u
ctio
n
,
with
th
e
h
y
b
r
id
m
o
d
el
y
ield
in
g
th
e
m
o
s
t
p
r
ec
is
e
r
ec
o
m
m
en
d
atio
n
s
.
R
o
y
et
a
l.
[
2
7
]
in
v
esti
g
ate
d
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
f
o
r
u
n
c
o
v
er
in
g
s
o
c
ial
an
d
b
e
h
av
io
r
al
d
eter
m
in
a
n
t
s
o
f
h
ea
lth
(
SB
DH)
f
r
o
m
u
n
s
tr
u
ctu
r
ed
elec
tr
o
n
ic
h
ea
lth
r
ec
o
r
d
(
E
HR
)
n
o
tes,
d
em
o
n
s
tr
atin
g
th
at
L
SI
,
ap
p
lie
d
to
2
,
0
8
3
,
1
8
0
clin
ical
n
o
tes
f
r
o
m
t
h
e
m
ed
ical
in
f
o
r
m
atio
n
m
ar
t
f
o
r
in
ten
s
iv
e
ca
r
e
I
I
I
(
MI
MI
C
-
III
)
d
ataset,
p
er
f
o
r
m
ed
co
m
p
ar
a
b
ly
to
GPT
-
3
.
5
an
d
GPT
-
4
wh
ile
o
f
f
e
r
in
g
ad
v
a
n
tag
es
s
u
c
h
as
r
o
b
u
s
tn
ess
,
d
ete
r
m
in
is
m
,
an
d
s
ca
lab
ilit
y
with
o
u
t
d
o
cu
m
en
t
-
s
ize
lim
itatio
n
s
o
r
co
s
t c
o
n
s
tr
ain
ts
,
m
ak
i
n
g
it
well
-
s
u
ited
f
o
r
r
ea
l
-
wo
r
ld
h
ea
l
th
ca
r
e
ap
p
licatio
n
s
.
Desp
ite
th
e
g
r
o
win
g
in
ter
est
in
b
lo
ck
c
h
ain
tech
n
o
lo
g
y
,
t
h
e
ap
p
licatio
n
o
f
L
DA
to
p
ic
m
o
d
elin
g
with
in
th
is
d
o
m
ain
r
em
ain
s
r
e
lativ
ely
u
n
d
e
r
ex
p
lo
r
ed
.
A
f
ew
s
tu
d
ies
h
av
e
b
eg
u
n
to
e
m
p
lo
y
L
DA
to
a
n
aly
ze
b
lo
ck
ch
ain
-
r
elate
d
co
n
te
n
t,
s
u
ch
as
r
esear
ch
p
ap
er
s
,
p
aten
ts
,
an
d
s
o
cial
m
ed
ia
d
is
cu
s
s
i
o
n
s
,
to
id
en
tify
k
e
y
tr
en
d
s
an
d
em
er
g
in
g
ar
ea
s
o
f
in
ter
est
[
2
8
]
,
[
2
9
]
.
T
h
ese
s
tu
d
ies
h
av
e
co
n
tr
ib
u
te
d
in
itial
k
n
o
wled
g
e
r
e
g
ar
d
i
n
g
th
e
th
em
atic
p
r
o
g
r
ess
io
n
o
f
b
lo
ck
ch
ain
r
esear
ch
,
y
et
th
ey
also
h
ig
h
lig
h
t
th
e
n
ee
d
f
o
r
m
o
r
e
co
m
p
r
e
h
en
s
iv
e
an
aly
s
es th
at
co
n
s
id
er
a
wid
er
r
an
g
e
o
f
s
o
u
r
ce
s
an
d
a
m
o
r
e
e
x
ten
s
iv
e
tem
p
o
r
al
s
co
p
e.
W
h
ile
ex
is
tin
g
r
esear
ch
h
as
l
aid
th
e
g
r
o
u
n
d
wo
r
k
f
o
r
u
n
d
e
r
s
tan
d
in
g
t
h
e
th
em
atic
d
ev
el
o
p
m
en
t
o
f
b
lo
ck
ch
ain
e
n
g
in
ee
r
i
n
g
,
s
ev
er
al
g
ap
s
r
em
ain
.
First,
co
m
p
r
e
h
en
s
iv
e
s
tu
d
ies
ar
e
cu
r
r
en
tly
lack
in
g
th
at
ap
p
ly
L
DA
to
a
b
r
o
a
d
d
ataset
o
f
b
lo
ck
ch
ain
e
n
g
in
ee
r
i
n
g
liter
atu
r
e,
in
clu
d
in
g
b
o
t
h
ac
ad
em
ic
a
n
d
in
d
u
s
tr
y
s
o
u
r
ce
s
.
Seco
n
d
,
p
r
e
v
io
u
s
s
tu
d
ies
h
av
e
o
f
ten
f
o
cu
s
ed
o
n
s
p
ec
if
ic
asp
ec
ts
o
f
b
lo
ck
ch
ain
,
s
u
ch
as
s
ec
u
r
ity
o
r
s
ca
lab
ilit
y
,
with
o
u
t
p
r
o
v
id
in
g
a
h
o
lis
tic
v
iew
o
f
th
e
f
ield
’
s
ev
o
lu
tio
n
.
L
astl
y
,
th
er
e
is
a
n
ee
d
f
o
r
an
a
ly
s
es
th
at
ca
n
tr
ac
k
th
e
tem
p
o
r
al
d
y
n
am
ics
o
f
to
p
ics
with
in
b
lo
ck
ch
ai
n
en
g
in
ee
r
in
g
,
h
elp
in
g
to
id
e
n
tify
n
o
t
o
n
ly
c
u
r
r
en
t
tr
en
d
s
b
u
t
also
p
o
ten
tial
f
u
tu
r
e
d
ir
e
ctio
n
s
.
T
h
is
p
ap
e
r
aim
s
to
ad
d
r
ess
th
e
g
ap
s
i
d
en
tifie
d
b
y
ap
p
ly
in
g
L
DA
to
a
co
m
p
r
eh
e
n
s
iv
e
d
ataset
o
f
b
lo
ck
ch
ain
en
g
in
ee
r
in
g
liter
atu
r
e,
p
r
o
v
id
in
g
a
m
o
r
e
d
etailed
an
d
d
y
n
am
ic
u
n
d
er
s
tan
d
i
n
g
o
f
th
e
laten
t to
p
ics an
d
tr
en
d
s
s
h
ap
in
g
th
e
f
iel
d
.
2.
M
E
T
H
O
D
T
h
is
r
esear
ch
p
er
f
o
r
m
ed
a
q
u
an
titativ
e
ex
am
in
atio
n
o
f
a
lar
g
e
b
o
d
y
o
f
b
lo
c
k
ch
ain
e
n
g
in
ee
r
in
g
p
u
b
licatio
n
s
,
f
o
cu
s
in
g
o
n
a
b
s
tr
ac
t
-
lev
el
co
n
te
n
t
an
al
y
s
is
.
Fig
u
r
e
1
p
r
esen
ts
th
e
w
o
r
k
f
lo
w
f
o
r
d
ataset
co
llectio
n
an
d
an
aly
tical
p
r
o
c
ed
u
r
es.
T
h
e
m
eth
o
d
o
lo
g
y
was
s
tr
u
ctu
r
ed
in
to
th
r
ee
m
ain
s
ta
g
es:
d
ata
co
llectio
n
an
d
p
r
e
p
r
o
ce
s
s
in
g
,
to
p
ic
ex
tr
a
ctio
n
u
s
in
g
L
DA,
an
d
v
alid
ati
o
n
o
f
th
e
r
esu
ltin
g
t
o
p
ic
s
tr
u
ct
u
r
e.
Fig
u
r
e
1
.
T
h
e
f
lo
wch
a
r
t d
ep
ict
in
g
th
e
m
eth
o
d
o
l
o
g
y
f
o
r
d
ataset
ac
q
u
is
itio
n
an
d
a
n
aly
s
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
8
6
3
-
1
8
7
5
1866
2
.
1
.
Da
t
a
c
o
llect
io
n a
nd
prepa
ra
t
io
n
I
n
th
is
s
tu
d
y
,
th
e
wid
ely
r
ec
o
g
n
ized
liter
atu
r
e
d
atab
ase
W
o
S,
wh
ich
p
r
o
v
id
es
ac
ce
s
s
to
jo
u
r
n
als
in
d
ex
ed
in
th
e
s
o
cial
s
cien
ce
s
citatio
n
in
d
e
x
(
SS
C
I
)
an
d
th
e
s
cien
ce
citatio
n
in
d
e
x
(
SC
I
)
,
was
c
h
o
s
en
as
a
co
m
p
r
eh
e
n
s
iv
e
d
ata
b
ase
th
at
o
f
f
er
s
h
ig
h
-
q
u
ality
d
ata
f
o
r
c
o
n
d
u
ctin
g
r
esear
ch
ev
alu
atio
n
s
[
3
0
]
−
[
3
2
]
.
E
n
s
u
r
in
g
h
ig
h
-
q
u
ality
liter
atu
r
e
co
n
ten
t
was
v
ital
to
ac
h
iev
in
g
r
eli
ab
le
r
esear
ch
r
esu
lts
.
T
h
e
d
a
ta
was
q
u
er
ied
o
n
J
u
ly
3
1
,
2
0
2
4
,
to
in
clu
d
e
all
p
u
b
licatio
n
s
in
th
e
W
o
S d
atab
a
s
e
till
2
0
2
3
.
T
h
e
d
escr
ip
tiv
e
a
n
aly
s
is
r
ev
ea
led
k
ey
in
f
o
r
m
atio
n
,
in
clu
d
in
g
a
to
tal
o
f
1
0
,
0
7
9
a
u
th
o
r
s
an
d
an
av
er
ag
e
p
u
b
licatio
n
a
g
e
o
f
3
.
9
2
y
ea
r
s
.
E
ac
h
p
ap
e
r
r
ec
eiv
ed
a
m
ea
n
o
f
1
9
.
2
5
citatio
n
s
,
with
an
a
v
er
ag
e
o
f
3
.
2
9
citatio
n
s
p
er
d
o
c
u
m
en
t p
er
y
e
ar
.
Ad
d
itio
n
ally
,
th
e
p
er
ce
n
tag
e
o
f
in
ter
n
atio
n
al
co
-
au
th
o
r
s
h
ip
s
was 3
3
.
6
2
%.
T
h
e
liter
atu
r
e
s
ea
r
ch
was
lim
ited
to
d
o
c
u
m
en
ts
ca
teg
o
r
ized
as
“a
r
ticle”
with
in
th
e
W
o
S.
T
h
e
s
ea
r
ch
s
tr
ateg
y
was
d
ev
elo
p
ed
b
ased
o
n
an
u
n
d
e
r
s
tan
d
in
g
o
f
b
lo
c
k
ch
ain
d
e
v
elo
p
m
e
n
t
an
d
o
n
s
e
ar
ch
ter
m
s
a
d
o
p
te
d
f
r
o
m
Z
h
aisan
o
v
a
an
d
Ma
n
s
u
r
o
v
a
[
3
3
]
.
Sp
ec
if
ically
,
th
e
ad
v
an
ce
d
s
ea
r
ch
f
u
n
ctio
n
o
f
th
e
W
o
S
d
atab
ase
wa
s
u
s
ed
to
ap
p
ly
th
e
cr
iter
ia:
“T
o
p
ic=
(
‘
B
lo
ck
ch
ain
d
ev
elo
p
m
en
t’
)
OR
T
o
p
ic=
(
‘
B
lo
ck
ch
ain
en
g
in
ee
r
in
g
’
)
”.
Her
e,
to
p
ic
s
ea
r
ch
es
en
c
o
m
p
ass
ed
titl
es,
ab
s
tr
ac
ts
,
an
d
au
th
o
r
k
ey
wo
r
d
s
r
elev
an
t
to
b
lo
c
k
ch
ain
e
n
g
in
ee
r
i
n
g
r
esear
ch
p
u
b
lis
h
ed
b
etwe
en
2
0
1
9
a
n
d
2
0
2
3
.
All
p
u
b
licatio
n
s
d
ee
m
ed
r
elev
an
t
to
a
d
d
r
ess
in
g
th
e
r
esear
ch
q
u
esti
o
n
s
wer
e
co
llected
.
Fo
llo
win
g
th
e
e
x
clu
s
io
n
o
f
n
o
n
-
E
n
g
lis
h
p
u
b
licatio
n
s
,
an
i
n
itial
s
et
o
f
3
,
6
6
5
a
r
ticles
was
o
b
tain
ed
.
Fo
r
ea
ch
ar
ticle
,
b
ib
lio
g
r
a
p
h
ic
in
f
o
r
m
atio
n
s
u
ch
as
th
e
titl
e,
ab
s
tr
ac
t,
y
ea
r
o
f
p
u
b
licatio
n
,
an
d
jo
u
r
n
al
n
am
e
was
ex
tr
ac
ted
.
T
h
e
in
clu
s
io
n
c
r
iter
ia
co
m
p
r
i
s
ed
p
ee
r
-
r
e
v
iewe
d
jo
u
r
n
al
ar
t
icles
p
u
b
lis
h
ed
in
E
n
g
lis
h
b
etwe
en
2
0
1
9
a
n
d
2
0
2
3
,
with
a
f
o
cu
s
o
n
b
l
o
ck
c
h
ain
d
e
v
elo
p
m
e
n
t,
b
lo
ck
ch
ai
n
en
g
i
n
ee
r
in
g
,
an
d
r
elate
d
ap
p
licatio
n
s
.
T
h
e
e
x
cl
u
s
io
n
cr
iter
ia
in
v
o
l
v
ed
o
m
itti
n
g
n
o
n
-
E
n
g
lis
h
p
u
b
licatio
n
s
,
d
o
cu
m
en
t
ty
p
es
o
th
er
th
an
jo
u
r
n
al
ar
ticles
(
in
clu
d
in
g
co
n
f
e
r
en
ce
p
ap
er
s
,
r
e
v
iews,
an
d
b
o
o
k
c
h
ap
ter
s
)
,
as
well
as
s
tu
d
ies
n
o
t
d
ir
ec
tl
y
r
elate
d
to
b
lo
c
k
ch
ain
e
n
g
in
ee
r
in
g
.
As
illu
s
tr
ated
in
Fig
u
r
e
2
,
th
e
n
u
m
b
er
o
f
d
o
wn
lo
a
d
s
f
o
r
r
ele
v
an
t
liter
atu
r
e
s
h
o
wed
a
g
en
er
al
u
p
war
d
tr
en
d
.
Fig
u
r
e
2
s
h
o
ws
th
at
r
esear
ch
r
elate
d
to
b
lo
ck
ch
ai
n
d
e
v
elo
p
m
en
t
ex
p
an
d
e
d
r
ap
id
ly
f
r
o
m
2
3
4
ar
ticles
to
1
,
0
2
3
u
n
til
2
0
2
2
,
r
ea
ch
in
g
a
p
ea
k
at
2
0
2
3
with
1
,
0
5
2
ar
ticle
s
.
T
h
is
s
tu
d
y
c
o
n
d
u
cted
t
o
p
ic
m
o
d
el
m
i
n
in
g
u
s
in
g
ab
s
tr
ac
t
tex
ts
as
th
e
r
esear
ch
f
o
cu
s
.
C
u
r
r
e
n
t
r
esear
ch
e
m
p
lo
y
s
L
DA
to
id
en
tif
y
co
n
ce
p
tu
al
tr
en
d
s
an
d
em
er
g
in
g
t
h
em
es
in
b
lo
ck
c
h
ai
n
en
g
in
ee
r
i
n
g
,
as
illu
s
tr
ated
in
Fig
u
r
e
3
.
B
y
a
p
p
ly
in
g
th
e
L
DA
tech
n
iq
u
e
to
a
d
ataset
co
m
p
r
is
in
g
3
,
6
6
5
ar
tic
les,
th
e
r
esear
ch
aim
s
to
ex
tr
a
ct
p
r
ev
ailin
g
tr
en
d
s
a
n
d
p
atter
n
s
with
in
th
e
f
ield
o
f
b
lo
c
k
ch
ain
e
n
g
in
ee
r
i
n
g
.
Fig
u
r
e
2
.
An
n
u
al
s
cien
tific
p
r
o
d
u
ctio
n
p
er
y
ea
r
(
2
0
1
9
–
2
0
2
3
)
I
t
was
r
ev
ea
led
th
e
m
ain
s
tep
s
o
f
L
DA
m
o
d
el
ac
co
r
d
i
n
g
to
th
e
Fig
u
r
e
3
.
Prio
r
to
th
is
,
d
ata
p
r
ep
r
o
ce
s
s
in
g
was
r
eq
u
ir
e
d
.
P
r
ep
r
o
ce
s
s
in
g
in
cl
u
d
ed
r
em
o
v
i
n
g
m
is
s
in
g
v
al
u
es,
to
k
e
n
izin
g
th
e
tex
t
in
to
wo
r
d
s
,
co
n
v
er
tin
g
to
lo
wer
ca
s
e,
r
em
o
v
in
g
n
o
n
-
al
p
h
ab
etic
c
h
ar
ac
ter
s
an
d
s
to
p
wo
r
d
s
.
C
r
ea
tin
g
a
p
r
o
ce
s
s
ed
v
er
s
io
n
o
f
th
e
tex
t
d
ata
e
n
ab
lin
g
d
iv
e
r
s
e
NL
P
ap
p
licatio
n
s
,
in
clu
d
in
g
to
p
ic
m
o
d
elin
g
,
s
en
tim
en
t
an
aly
s
is
,
an
d
tex
t
class
if
icatio
n
.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
in
clu
d
ed
th
e
f
o
llo
win
g
:
i)
Han
d
lin
g
m
is
s
in
g
v
alu
es: in
iti
ally
,
all
r
ec
o
r
d
s
with
m
is
s
in
g
ab
s
tr
ac
t te
x
ts
wer
e
r
em
o
v
ed
to
m
ain
tain
d
ata
in
teg
r
ity
.
T
h
is
r
esu
lted
in
an
i
n
itial selectio
n
co
r
p
u
s
o
f
X
ar
t
icles.
ii)
T
o
k
en
izatio
n
:
th
e
tex
t
d
ata
was
to
k
en
ized
in
to
in
d
iv
i
d
u
a
l
wo
r
d
s
u
s
in
g
t
h
e
n
atu
r
al
la
n
g
u
ag
e
to
o
l
k
it
(
NL
T
K)
,
en
ab
lin
g
f
u
r
th
er
lin
g
u
is
tic
p
r
o
ce
s
s
in
g
.
iii)
C
ase
n
o
r
m
aliza
tio
n
:
all
tex
t
was
co
n
v
er
ted
to
lo
wer
ca
s
e
t
o
en
s
u
r
e
u
n
if
o
r
m
ity
a
n
d
av
o
i
d
d
u
p
licatio
n
o
f
ter
m
s
d
u
e
to
ca
s
e
d
if
f
er
en
ce
s
.
iv
)
R
em
o
v
al
o
f
n
o
n
-
alp
h
ab
etic
ch
ar
ac
ter
s
:
p
u
n
ctu
atio
n
m
a
r
k
s
,
n
u
m
er
als
an
d
s
p
ec
ial
s
y
m
b
o
ls
wer
e
elim
in
ated
,
r
etain
in
g
o
n
ly
alp
h
ab
etic
wo
r
d
s
r
elev
an
t
f
o
r
a
n
al
y
s
is
.
234
472
727
1023
1052
0
2
0
0
4
0
0
6
0
0
8
0
0
1
0
0
0
1
2
0
0
2
0
1
9
2
0
2
0
2
0
2
1
2
0
2
2
2
0
2
3
N
u
mb
e
r
o
f
a
r
t
i
c
l
e
s
Y
e
a
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
R
esea
r
ch
th
eme
s
a
n
d
tr
en
d
s
in
th
e
field
o
f b
lo
ck
c
h
a
in
e
n
g
in
e
erin
g
:
a
to
p
ic
…
(
Din
a
r
a
Zh
a
is
a
n
o
va
)
1867
v)
Sto
p
wo
r
d
p
r
o
ce
s
s
in
g
:
co
m
m
o
n
E
n
g
lis
h
wo
r
d
s
ex
clu
d
ed
f
r
o
m
an
aly
s
is
(
e.
g
.
,
“th
e,
”
“is,”
“a
n
d
”)
wer
e
elim
in
ated
u
s
in
g
NL
T
K’
s
p
r
e
d
ef
in
ed
s
to
p
wo
r
d
lis
t to
en
h
an
ce
th
e
f
o
cu
s
o
n
m
ea
n
in
g
f
u
l te
r
m
s
.
Fo
llo
win
g
p
r
ep
r
o
ce
s
s
in
g
,
a
r
ef
in
ed
co
r
p
u
s
was
cr
ea
ted
,
c
o
n
s
is
tin
g
o
f
Y
ar
ticles
af
ter
f
i
lter
in
g
an
d
tex
t
clea
n
in
g
.
T
h
is
co
r
p
u
s
was
th
en
tr
a
n
s
f
o
r
m
e
d
in
t
o
a
s
tr
u
ctu
r
ed
f
o
r
m
at
s
u
itab
le
f
o
r
to
p
ic
m
o
d
elin
g
.
A
d
ictio
n
ar
y
was
co
n
s
tr
u
cte
d
u
s
in
g
th
e
p
r
o
ce
s
s
ed
to
k
e
n
s
,
m
ap
p
in
g
u
n
iq
u
e
wo
r
d
s
to
th
eir
r
esp
ec
tiv
e
n
u
m
er
ical
I
Ds.
Fin
ally
,
a
b
ag
-
of
-
wo
r
d
s
r
ep
r
esen
tatio
n
was
g
en
er
ated
f
o
r
ea
ch
d
o
c
u
m
en
t,
f
o
r
m
i
n
g
t
h
e
f
i
n
al
co
r
p
u
s
f
o
r
an
aly
s
is
.
T
h
e
L
DA
m
o
d
el
in
th
e
p
r
o
v
id
ed
c
o
d
e
u
s
es
s
ev
er
al
h
y
p
er
p
ar
a
m
e
ter
s
:
co
r
p
u
s
,
wh
ich
r
ep
r
esen
ts
th
e
d
ataset
in
a
b
ag
-
of
-
wo
r
d
s
f
o
r
m
at;
id
2
wo
r
d
a
m
ap
p
in
g
o
f
wo
r
d
s
to
u
n
iq
u
e
id
en
tifie
r
s
;
n
u
m
_
to
p
ics,
s
ettin
g
th
e
n
u
m
b
er
o
f
to
p
ics
to
ex
tr
ac
t;
r
an
d
o
m
_
s
tate,
en
s
u
r
in
g
r
e
p
r
o
d
u
ci
b
ilit
y
;
alp
h
a,
s
et
to
‘
au
to
’
,
allo
win
g
t
h
e
m
o
d
el
to
d
y
n
am
ically
ad
j
u
s
t th
e
d
o
cu
m
en
t
-
to
p
ic
d
is
tr
ib
u
tio
n
; a
n
d
p
er
_
wo
r
d
_
t
o
p
ics,
s
et
to
t
r
u
e,
wh
ich
e
n
ab
les th
e
ass
ig
n
m
en
t o
f
to
p
ic
d
is
tr
ib
u
tio
n
s
to
in
d
iv
id
u
al
w
o
r
d
s
.
Fig
u
r
e
3
.
L
DA
m
o
d
el
2
.
2
.
T
o
pic mo
delin
g
L
DA
is
a
p
r
o
b
a
b
ilis
tic
ap
p
r
o
ac
h
f
o
r
id
en
tif
y
in
g
laten
t
t
o
p
ics
with
in
a
s
et
o
f
d
o
cu
m
en
ts
.
As
a
g
en
er
ativ
e
m
o
d
el,
it
ass
u
m
es
th
at
ea
ch
d
o
c
u
m
en
t
ar
is
es
f
r
o
m
a
co
m
b
in
atio
n
o
f
to
p
ics,
with
ea
ch
to
p
i
c
r
ep
r
esen
ted
as a
p
r
o
b
a
b
ilit
y
d
i
s
tr
ib
u
tio
n
o
v
e
r
wo
r
d
s
.
−
L
et
b
e
th
e
n
u
m
b
er
o
f
to
p
ics.
−
is
th
e
to
p
ic
d
is
tr
ib
u
tio
n
f
o
r
d
o
cu
m
en
t
,
wh
ich
f
o
llo
ws a
Dir
ich
let
d
is
tr
ib
u
tio
n
:
∼
Dir
ich
let(
)
,
wh
er
e
is
th
e
h
y
p
er
p
ar
am
eter
c
o
n
tr
o
llin
g
th
e
d
is
tr
ib
u
tio
n
o
v
er
to
p
ics.
−
is
th
e
wo
r
d
d
is
tr
ib
u
tio
n
f
o
r
to
p
ic
,
wh
ich
also
f
o
llo
ws a
Dir
ich
let
d
is
tr
ib
u
tio
n
:
∼
Dir
ich
let(
)
,
wh
er
e
is
th
e
h
y
p
er
p
ar
am
eter
c
o
n
tr
o
llin
g
th
e
d
is
tr
ib
u
tio
n
o
v
er
wo
r
d
s
f
o
r
e
ac
h
to
p
ic.
−
Do
cu
m
en
t
g
e
n
er
atio
n
p
r
o
ce
s
s
: f
o
r
ea
c
h
wo
r
d
in
d
o
c
u
m
en
t
d
is
tr
ib
u
tio
n
:
C
h
o
o
s
e
a
to
p
ic
∼
Mu
ltin
o
m
i
al(
)
C
h
o
o
s
e
a
wo
r
d
f
r
o
m
(
∣
,
)
L
DA
m
o
d
el
f
itti
n
g
,
o
b
jectiv
e
f
u
n
ctio
n
:
th
e
g
o
al
is
to
m
ax
im
ize
th
e
lik
elih
o
o
d
o
f
th
e
d
at
a
g
iv
en
th
e
p
ar
am
eter
s
an
d
as in
(
1
)
.
=
(
∣
,
)
=
∏
∏
∑
=
1
=
1
=
1
(
|
−
,
)
(
|
)
(
1
)
Var
iatio
n
al
B
ay
es
o
r
Gib
b
s
s
am
p
lin
g
is
u
s
ed
to
esti
m
ate
a
n
d
f
o
r
o
p
tim
izatio
n
.
Me
tr
ics
co
m
m
o
n
ly
u
s
ed
in
to
p
ic
m
o
d
elin
g
in
clu
d
e
p
er
p
le
x
ity
an
d
co
h
er
e
n
ce
.
Per
p
lex
it
y
ass
es
s
es
h
o
w
we
ll
th
e
m
o
d
el
ass
ig
n
s
wo
r
d
s
to
s
p
ec
if
ic
to
p
ics
b
y
ev
alu
atin
g
t
h
e
m
o
d
el
’
s
lik
elih
o
o
d
v
alu
e
.
C
o
h
er
en
ce
s
co
r
e
in
d
icate
s
h
o
w
clo
s
ely
th
e
wo
r
d
s
in
a
to
p
ic
ar
e
r
elate
d
in
m
ea
n
in
g
.
T
h
e
c
o
h
er
e
n
ce
s
co
r
e
(
)
f
o
r
t
o
p
ic
is
co
m
p
u
ted
u
s
in
g
th
e
p
air
wis
e
co
-
o
cc
u
r
r
en
ce
o
f
th
e
t
o
p
wo
r
d
s
in
th
e
to
p
ic
as in
(
2
)
.
(
)
=
∑
∑
(
,
)
+
1
(
)
−
1
=
1
=
2
(
2
)
W
h
er
e
,
(
,
)
d
en
o
tes
th
e
n
u
m
b
e
r
o
f
d
o
cu
m
en
ts
in
wh
ich
b
o
th
t
er
m
s
an
d
ap
p
ea
r
,
an
d
(
ₗ
)
r
ef
er
s
to
th
e
co
u
n
t o
f
d
o
cu
m
e
n
ts
th
at
in
clu
d
e
th
e
ter
m
.
L
SI
i
s
an
o
th
er
to
p
ic
m
o
d
elin
g
ap
p
r
o
ac
h
th
at
ap
p
lies
s
in
g
u
lar
v
alu
e
d
ec
o
m
p
o
s
itio
n
(
SVD)
to
ac
h
iev
e
d
im
e
n
s
io
n
al
ity
r
ed
u
ctio
n
o
f
t
h
e
ter
m
–
d
o
cu
m
en
t m
atr
ix
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
8
6
3
-
1
8
7
5
1868
T
er
m
–
d
o
cu
m
en
t
m
atr
ix
:
a
m
atr
ix
is
co
n
s
tr
u
cte
d
s
u
ch
t
h
at
ea
ch
elem
en
t
co
r
r
esp
o
n
d
s
to
th
e
weig
h
t
(
f
o
r
e
x
am
p
le,
a
T
F
–
I
DF
v
alu
e)
o
f
ter
m
in
d
o
c
u
m
en
t
.
SVD:
th
e
m
atr
ix
is
f
ac
to
r
ized
in
to
th
r
ee
co
m
p
o
n
en
t m
atr
ices
as in
(
3
)
.
=
∑
(
3
)
W
h
er
e
is
ter
m
-
to
p
ic
m
atr
ix
,
Ʃ
is
a
d
iag
o
n
al
m
atr
ix
c
o
n
tain
in
g
s
in
g
u
lar
v
alu
es,
is
d
o
cu
m
en
t
-
to
p
ic
m
atr
i
x
.
2
.
3
.
T
o
pic
re
presenta
t
io
n
wit
h L
SI
T
h
e
r
o
ws
o
f
co
r
r
esp
o
n
d
to
th
e
“
to
p
ic
”
v
ec
to
r
s
,
an
d
th
e
co
lu
m
n
s
o
f
co
r
r
esp
o
n
d
to
th
e
r
ep
r
esen
tatio
n
o
f
d
o
cu
m
en
ts
in
th
e
r
ed
u
ce
d
-
d
im
e
n
s
io
n
al
s
p
ac
e.
R
etain
th
e
t
o
p
s
in
g
u
lar
v
alu
es
t
o
ap
p
r
o
x
im
ate
with
lo
wer
-
r
an
k
m
atr
ices,
ef
f
ec
tiv
ely
r
ed
u
ci
n
g
th
e
n
o
is
e
a
n
d
f
o
cu
s
in
g
o
n
t
h
e
m
o
s
t
s
ig
n
if
ica
n
t
“
to
p
ics
”
.
Hea
tm
ap
o
f
d
o
cu
m
en
t
s
im
ilar
ities
was
cr
ea
ted
b
y
co
m
p
u
tatio
n
th
e
co
s
in
e
s
im
ilar
ity
m
atr
ix
S
b
etwe
en
d
o
c
u
m
en
ts
as in
(
4
)
.
=
∗
|
|
|
|
|
|
|
|
(
4
)
T
h
e
s
tu
d
y
ap
p
lied
th
e
L
DA
m
o
d
el
m
o
d
u
le
f
r
o
m
th
e
well
-
estab
lis
h
ed
Gen
s
im
Py
th
o
n
lib
r
a
r
y
to
p
er
f
o
r
m
to
p
ic
m
o
d
elin
g
a
n
d
u
s
ed
a
co
h
e
r
en
c
e
m
etr
ic
to
id
en
tif
y
th
e
o
p
tim
a
l n
u
m
b
er
o
f
t
o
p
ics.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
em
atic
ev
o
lu
tio
n
p
lo
t
s
h
o
w
n
in
Fig
u
r
e
4
h
as
b
ee
n
g
en
er
a
ted
u
s
in
g
b
ib
lio
m
etr
ic
,
an
R
-
b
ased
to
o
l.
T
h
is
v
is
u
aliza
tio
n
is
b
ased
o
n
th
e
“
ab
s
tr
ac
t
”
f
ield
an
d
u
s
es
N
-
g
r
am
s
with
“
tr
ig
r
a
m
s
”
to
id
en
tify
k
e
y
r
esear
ch
th
em
es.
T
h
e
v
is
u
aliza
tio
n
,
d
i
s
p
lay
ed
as
a
San
k
ey
d
iag
r
a
m
,
illu
s
tr
ates
th
e
ev
o
lu
tio
n
o
f
b
lo
ck
ch
ain
-
r
elate
d
r
esear
ch
th
em
es
f
r
o
m
2
0
1
9
to
2
0
2
4
.
C
o
lo
r
e
d
b
l
o
ck
s
r
e
p
r
esen
t
d
o
m
i
n
an
t
to
p
ics
in
ea
ch
p
er
io
d
,
wh
ile
co
n
n
ec
tin
g
f
lo
ws s
h
o
w
th
eir
c
o
n
tin
u
ity
,
tr
a
n
s
f
o
r
m
atio
n
,
o
r
d
ec
lin
e
o
v
er
tim
e.
Fig
u
r
e
4
.
T
h
em
atic
ev
o
l
u
tio
n
o
f
b
lo
c
k
ch
ain
e
n
g
in
ee
r
i
n
g
ar
e
a
I
n
2
0
1
9
,
r
esear
ch
f
o
c
u
s
ed
o
n
f
o
u
n
d
atio
n
al
th
em
es
s
u
ch
as
i
n
itial
co
in
o
f
f
e
r
in
g
s
(
I
C
Os),
d
is
tr
ib
u
ted
led
g
er
tec
h
n
o
lo
g
y
,
AI
,
s
m
ar
t
co
n
tr
ac
ts
,
b
u
s
in
ess
p
r
o
ce
s
s
m
an
ag
em
en
t,
an
d
s
u
p
p
ly
ch
a
in
ap
p
licatio
n
s
.
B
y
2
0
2
0
,
th
e
s
co
p
e
e
x
p
an
d
ed
to
ap
p
lied
d
o
m
ain
s
in
cl
u
d
in
g
E
HR
s
,
r
en
ewa
b
le
en
er
g
y
,
d
ata
s
ec
u
r
ity
,
an
d
m
o
b
ile
ed
g
e
co
m
p
u
tin
g
,
r
e
f
lectin
g
in
c
r
ea
s
ed
r
ea
l
-
wo
r
ld
ad
o
p
tio
n
o
f
b
lo
ck
ch
ain
.
I
n
2
0
2
1
,
m
o
r
e
ad
v
an
ce
d
ap
p
licatio
n
s
em
er
g
ed
,
in
cl
u
d
in
g
b
lo
ck
ch
ai
n
in
f
in
an
ce
,
f
i
n
e
-
g
r
ai
n
ed
ac
c
ess
co
n
tr
o
l,
s
elf
-
s
o
v
er
eig
n
id
e
n
tity
,
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
,
an
d
tr
u
s
t
in
d
is
tr
ib
u
ted
s
y
s
tem
s
.
T
h
e
2
0
2
2
p
er
io
d
m
ar
k
ed
a
s
tr
o
n
g
er
em
p
h
asis
o
n
s
m
ar
t
co
n
tr
ac
ts
,
in
d
u
s
tr
ial
ad
o
p
tio
n
,
s
u
p
p
ly
ch
ain
r
esil
ien
ce
,
an
d
s
u
s
tain
ab
ili
ty
.
I
n
2
0
2
3
-
2
0
2
4
,
b
l
o
ck
ch
ain
r
esear
ch
r
ea
ch
ed
a
m
atu
r
e
s
tag
e,
h
ig
h
lig
h
tin
g
r
esil
ien
cy
-
by
-
d
esig
n
,
b
lo
c
k
ch
ain
-
AI
in
teg
r
atio
n
,
th
r
ea
t
in
tellig
en
ce
,
co
n
tr
ac
t
v
u
ln
er
ab
ilit
y
d
etec
tio
n
,
e
d
g
e
c
o
m
p
u
tin
g
,
an
d
en
v
ir
o
n
m
e
n
tal
im
p
ac
t a
s
s
ess
m
en
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
R
esea
r
ch
th
eme
s
a
n
d
tr
en
d
s
in
th
e
field
o
f b
lo
ck
c
h
a
in
e
n
g
in
e
erin
g
:
a
to
p
ic
…
(
Din
a
r
a
Zh
a
is
a
n
o
va
)
1869
T
h
is
Fig
u
r
e
4
ef
f
ec
tiv
ely
illu
s
t
r
ated
th
e
d
y
n
am
ic
ev
o
l
u
tio
n
o
f
b
lo
ck
ch
ain
-
r
elate
d
r
esear
ch
t
o
p
ics o
v
er
tim
e.
T
h
e
tr
an
s
itio
n
f
r
o
m
b
asi
c
co
n
ce
p
ts
to
m
o
r
e
co
m
p
le
x
a
n
d
in
ter
d
is
cip
lin
ar
y
ap
p
licatio
n
s
h
ig
h
lig
h
ted
t
h
e
in
cr
ea
s
in
g
m
atu
r
ity
o
f
b
lo
c
k
c
h
ain
tech
n
o
l
o
g
y
a
n
d
its
in
teg
r
atio
n
with
v
ar
io
u
s
in
d
u
s
tr
ies.
T
h
e
co
n
tin
u
o
u
s
f
lo
w
o
f
to
p
ics
ac
r
o
s
s
d
if
f
er
en
t
y
ea
r
s
in
d
icate
s
s
u
s
tain
ed
in
ter
est
a
n
d
o
n
g
o
in
g
ad
v
a
n
ce
m
en
ts
,
wi
th
em
er
g
i
n
g
tr
en
d
s
s
u
g
g
esti
n
g
a
f
u
t
u
r
e
f
o
cu
s
o
n
s
ec
u
r
ity
,
AI
in
te
g
r
atio
n
,
a
n
d
s
u
s
tain
ab
le
b
lo
ck
ch
ain
s
o
l
u
tio
n
s
.
3
.
1
.
Det
er
m
ina
t
io
n o
f
o
ptima
l pa
ra
m
et
er
s
L
DA
is
a
h
ig
h
ly
r
e
g
ar
d
e
d
to
p
ic
m
o
d
elin
g
m
eth
o
d
k
n
o
wn
f
o
r
it
i
s
em
p
ir
ical
p
e
r
f
o
r
m
an
ce
[
3
0
]
.
T
h
is
u
n
s
u
p
er
v
is
ed
m
eth
o
d
r
eq
u
ir
es
p
r
ed
ef
in
ed
p
a
r
am
eter
s
—
s
u
ch
as
n
u
m
b
er
o
f
to
p
ics
(
K
)
,
to
p
ic
d
is
tr
ib
u
tio
n
p
r
io
r
(
α
)
,
an
d
to
p
ic
–
wo
r
d
d
is
tr
ib
u
t
io
n
p
r
io
r
(
η
)
—
wh
ich
p
lay
a
cr
u
cial
r
o
le
in
d
eter
m
in
in
g
to
p
ic
q
u
ality
.
T
o
p
ic
m
o
d
el
p
er
f
o
r
m
an
ce
is
co
m
m
o
n
ly
e
v
alu
ated
b
y
em
p
l
o
y
in
g
m
ea
s
u
r
es
lik
e
p
er
p
le
x
ity
a
n
d
co
h
er
en
ce
,
with
co
h
er
en
ce
em
p
h
asizin
g
in
ter
p
r
etab
ilit
y
.
Giv
en
th
e
im
p
o
r
ta
n
ce
o
f
in
ter
p
r
etab
ilit
y
f
o
r
m
ea
n
in
g
f
u
l
an
aly
s
is
an
d
p
r
ac
tical
u
s
e,
co
h
er
en
ce
was
ch
o
s
en
as
th
e
p
r
im
ar
y
e
v
alu
atio
n
cr
iter
io
n
.
T
h
e
p
r
i
o
r
s
α
an
d
η
wer
e
s
et
au
to
m
atica
lly
,
an
d
th
e
o
p
tim
a
l
n
u
m
b
e
r
o
f
to
p
ics
was
d
eter
m
in
ed
b
ased
o
n
c
o
h
er
e
n
ce
m
etr
ics.
As
s
h
o
wn
in
Fig
u
r
e
5
,
th
e
m
o
d
el
ac
h
iev
ed
i
ts
h
ig
h
est co
h
er
en
ce
v
alu
e
(
0
.
4
1
)
wh
e
n
K
was set to
n
in
e
to
p
ics.
Fig
u
r
e
5
.
T
o
p
ics n
u
m
b
er
a
n
d
c
o
h
er
en
ce
On
ce
th
e
m
o
d
el
was
estab
lis
h
ed
,
th
e
to
p
ics
wer
e
n
am
ed
m
an
u
ally
b
ased
o
n
th
e
r
esu
lts
,
wh
ich
s
ig
n
if
ican
tly
en
h
a
n
ce
d
th
e
in
t
er
p
r
etab
ilit
y
o
f
th
e
f
in
d
i
n
g
s
.
T
r
ad
itio
n
ally
,
n
am
in
g
is
p
r
im
ar
ily
g
u
i
d
ed
b
y
th
e
to
p
ic
-
wo
r
d
p
r
o
b
ab
ilit
y
(
∣
)
,
with
k
ey
wo
r
d
s
ex
h
ib
itin
g
h
i
g
h
(
∣
)
v
alu
es
ch
o
s
en
f
o
r
t
o
p
ic
n
am
in
g
.
T
h
e
co
r
r
elatio
n
f
o
r
m
u
la
u
s
ed
in
th
i
s
p
r
o
ce
s
s
in
v
o
lv
es
a
p
ar
am
ete
r
,
wh
ich
s
p
ec
if
ies
t
h
e
weig
h
t
o
f
a
to
p
ic
wo
r
d
b
ased
o
n
its
s
ig
n
if
ican
ce
with
in
to
p
ic
t
.
Af
ter
ad
ju
s
tin
g
,
t
h
e
an
aly
s
is
r
ev
ea
led
th
at
s
ettin
g
=0
.
6
p
r
o
v
id
ed
th
e
m
o
s
t
r
elev
an
t
an
d
p
r
o
m
in
en
t
ter
m
s
ac
r
o
s
s
to
p
ics.
An
o
v
er
v
iew
o
f
th
e
to
p
ics
id
en
tifie
d
u
s
in
g
L
SI
f
o
r
th
e
2019
-
2
0
2
4
d
ataset
is
p
r
o
v
id
ed
in
T
ab
le
1
,
s
h
o
win
g
t
h
e
f
in
al
t
o
p
ics d
eter
m
in
ed
th
r
o
u
g
h
t
h
is
p
r
o
ce
s
s
.
L
SI
id
en
tifie
d
n
in
e
d
is
tin
ct
to
p
ics
in
th
e
d
ataset,
ea
ch
r
ep
r
esen
ted
b
y
a
s
et
o
f
te
r
m
s
an
d
a
p
r
o
p
o
r
tio
n
al
s
h
ar
e
o
f
th
e
co
r
p
u
s
,
r
ef
lectin
g
its
p
r
ev
ale
n
ce
ac
r
o
s
s
th
e
an
aly
ze
d
d
o
cu
m
e
n
ts
.
−
T
o
p
ic
1
f
o
cu
s
es
o
n
th
e
i
n
ter
n
et
o
f
t
h
in
g
s
(
I
o
T
)
,
p
ar
ticu
lar
ly
s
ec
u
r
ity
an
d
s
m
ar
t
d
e
v
ices,
h
ig
h
lig
h
tin
g
b
lo
ck
ch
ain
as
a
s
o
l
u
tio
n
f
o
r
e
n
h
an
cin
g
d
ata
p
r
iv
ac
y
,
d
ev
ice
au
th
en
ticatio
n
,
an
d
p
r
o
tectio
n
ag
ain
s
t
cy
b
er
th
r
ea
ts
.
T
h
is
in
teg
r
atio
n
is
es
p
ec
ially
r
elev
an
t
f
o
r
s
m
ar
t
h
o
m
es,
in
d
u
s
tr
ial
au
to
m
atio
n
,
an
d
h
ea
lth
ca
r
e
ap
p
licatio
n
s
.
−
T
o
p
ic
2
ce
n
ter
s
o
n
b
l
o
ck
ch
ain
tech
n
o
l
o
g
y
an
d
its
r
o
le
in
in
f
o
r
m
atio
n
m
an
a
g
em
en
t
s
y
s
tem
s
.
I
t
em
p
h
asizes
b
lo
ck
ch
ain
’
s
d
ec
en
tr
alize
d
ar
ch
itectu
r
e
f
o
r
s
ec
u
r
in
g
d
ig
ital
tr
an
s
ac
tio
n
s
,
i
m
p
r
o
v
i
n
g
d
ata
h
an
d
lin
g
,
an
d
en
h
an
cin
g
tr
an
s
p
ar
en
cy
an
d
tr
u
s
t
ac
r
o
s
s
s
ec
to
r
s
s
u
ch
as
f
in
an
ce
,
s
u
p
p
ly
ch
ain
m
an
ag
em
en
t,
an
d
g
o
v
e
r
n
an
ce
.
−
T
o
p
ic
3
ad
d
r
ess
es
s
u
p
p
ly
ch
ai
n
m
an
a
g
em
en
t
a
n
d
tr
a
ce
ab
ilit
y
,
esp
ec
ially
in
th
e
f
o
o
d
s
ec
to
r
.
B
lo
ck
ch
ain
im
p
r
o
v
es
tr
a
n
s
p
ar
en
cy
,
p
r
o
d
u
ct
au
th
en
ticatio
n
,
an
d
r
eg
u
lato
r
y
c
o
m
p
lian
ce
b
y
e
n
ab
lin
g
i
m
m
u
tab
le
an
d
r
ea
l
-
tim
e
tr
ac
k
in
g
ac
r
o
s
s
p
r
o
d
u
ctio
n
an
d
d
is
tr
ib
u
tio
n
p
r
o
ce
s
s
es.
−
T
o
p
ic
4
h
ig
h
lig
h
ts
d
ata
s
ec
u
r
ity
an
d
p
r
i
v
ac
y
,
f
o
cu
s
in
g
o
n
b
lo
c
k
ch
ain
-
b
ased
s
ch
em
es
f
o
r
p
r
o
tectin
g
s
en
s
itiv
e
in
f
o
r
m
atio
n
.
T
h
ese
s
o
lu
tio
n
s
en
h
an
ce
s
y
s
tem
r
esil
ien
ce
an
d
in
teg
r
ity
in
d
o
m
ain
s
s
u
ch
a
s
f
in
an
ce
,
h
ea
lth
c
ar
e,
an
d
clo
u
d
s
to
r
ag
e
b
y
elim
in
atin
g
ce
n
tr
ali
ze
d
p
o
in
ts
o
f
f
ailu
r
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
8
6
3
-
1
8
7
5
1870
−
T
o
p
ic
5
ex
am
i
n
es
b
lo
c
k
ch
ai
n
ap
p
licatio
n
s
in
e
n
er
g
y
m
ar
k
ets,
p
ar
ticu
lar
l
y
p
ee
r
-
to
-
p
ee
r
elec
tr
icity
tr
ad
in
g
an
d
s
m
ar
t
g
r
id
m
an
a
g
em
en
t.
B
lo
ck
ch
ain
s
u
p
p
o
r
ts
ef
f
icien
t,
tr
an
s
p
ar
en
t
e
n
er
g
y
tr
an
s
ac
tio
n
s
an
d
f
ac
ilit
ates th
e
in
teg
r
atio
n
o
f
d
i
s
tr
ib
u
ted
r
en
ewa
b
le
e
n
er
g
y
r
es
o
u
r
ce
s
.
−
T
o
p
ic
6
ex
p
lo
r
es
th
e
b
r
o
ad
er
r
esear
ch
lan
d
s
ca
p
e
o
f
b
l
o
ck
ch
ain
,
in
cl
u
d
in
g
c
h
allen
g
es
r
elate
d
to
s
ca
lab
ilit
y
,
in
ter
o
p
er
ab
ilit
y
,
a
n
d
g
o
v
e
r
n
an
ce
.
Ad
v
an
ce
s
in
co
n
s
en
s
u
s
m
ec
h
an
is
m
s
an
d
cr
y
p
to
g
r
ap
h
ic
tech
n
iq
u
es a
r
e
d
r
iv
in
g
b
lo
ck
c
h
ain
ad
o
p
tio
n
a
n
d
d
i
g
ital tr
an
s
f
o
r
m
atio
n
ac
r
o
s
s
in
d
u
s
tr
ies.
−
T
o
p
ic
7
d
is
cu
s
s
es
b
lo
ck
ch
ain
-
b
ased
s
y
s
tem
an
d
s
o
f
twar
e
d
esig
n
,
em
p
h
asizin
g
ar
ch
itectu
r
al
co
n
s
id
er
atio
n
s
f
o
r
d
ec
en
tr
aliz
ed
ap
p
licatio
n
s
.
Su
ch
s
y
s
tem
s
en
ab
le
s
ec
u
r
e,
s
ca
lab
le,
an
d
au
to
n
o
m
o
u
s
d
ig
ital ser
v
ices in
ar
ea
s
in
clu
d
in
g
f
in
an
ce
,
e
-
g
o
v
er
n
an
ce
,
a
n
d
clo
u
d
co
m
p
u
tin
g
.
−
T
o
p
ic
8
f
o
c
u
s
es
o
n
h
ea
lth
ca
r
e,
em
p
h
asizin
g
b
lo
c
k
ch
ain
’
s
r
o
le
in
s
ec
u
r
in
g
m
ed
ical
d
a
ta,
im
p
r
o
v
in
g
in
ter
o
p
er
a
b
ilit
y
,
an
d
en
s
u
r
in
g
th
e
in
teg
r
ity
o
f
p
atien
t
r
ec
o
r
d
s
.
T
h
ese
ap
p
licatio
n
s
ar
e
c
r
itical
f
o
r
E
HR
s
,
clin
ical
tr
ials
,
an
d
p
h
ar
m
ac
eu
t
ical
s
u
p
p
ly
ch
ain
s
.
−
T
o
p
ic
9
ad
d
r
ess
es
s
m
ar
t
co
n
tr
ac
ts
an
d
b
lo
ck
ch
ai
n
-
b
ase
d
f
in
an
cial
tec
h
n
o
l
o
g
ies.
Sm
ar
t
co
n
tr
ac
ts
au
to
m
ate
an
d
s
ec
u
r
e
f
in
a
n
ci
al
tr
an
s
ac
tio
n
s
,
s
u
p
p
o
r
ti
n
g
d
ec
en
tr
alize
d
f
in
an
ce
(
DeFi)
p
latf
o
r
m
s
an
d
im
p
r
o
v
in
g
ef
f
icien
c
y
in
b
an
k
i
n
g
,
in
s
u
r
a
n
ce
,
an
d
in
v
estme
n
t
s
er
v
ices.
T
ab
le
2
p
r
esen
ts
t
h
e
r
esu
lts
o
b
tain
ed
f
r
o
m
th
e
L
DA
m
o
d
el,
in
clu
d
in
g
t
h
e
r
e
p
r
esen
tativ
e
t
er
m
s
an
d
th
eir
p
r
o
p
o
r
tio
n
s
with
in
th
e
c
o
r
p
u
s
.
T
h
e
id
en
tifie
d
to
p
ics
co
v
er
a
b
r
o
ad
r
an
g
e
o
f
th
em
es,
s
u
ch
as
I
o
T
s
ec
u
r
ity
,
b
lo
ck
ch
ain
a
p
p
licatio
n
s
in
h
ea
lth
ca
r
e,
s
m
ar
t
co
n
tr
ac
ts
,
an
d
e
n
er
g
y
s
y
s
tem
s
.
T
h
ese
th
em
es r
ef
lect
th
e
d
iv
er
s
ity
o
f
r
esear
ch
d
ir
ec
tio
n
s
ca
p
tu
r
e
d
b
y
th
e
m
o
d
el.
−
T
o
p
ic
1
f
o
cu
s
es
o
n
ac
ad
em
ic
r
esear
ch
in
AI
an
d
k
n
o
wled
g
e
m
an
ag
e
m
en
t,
em
p
h
asizin
g
r
esear
c
h
m
eth
o
d
o
l
o
g
ies,
ap
p
licatio
n
s
,
an
d
f
u
tu
r
e
tr
en
d
s
.
T
h
ese
s
tu
d
ies
co
n
tr
ib
u
te
to
i
n
tellig
en
t
s
y
s
tem
s
th
at
s
u
p
p
o
r
t
au
to
m
atio
n
,
d
ata
-
d
r
iv
en
d
ec
is
io
n
-
m
ak
i
n
g
,
an
d
in
n
o
v
atio
n
ac
r
o
s
s
d
o
m
ain
s
s
u
ch
a
s
h
ea
lth
ca
r
e,
f
in
an
ce
,
an
d
ed
u
ca
tio
n
.
−
T
o
p
ic
2
a
d
d
r
ess
es
d
ig
ital
tr
a
n
s
f
o
r
m
atio
n
in
in
d
u
s
tr
ies,
p
ar
ticu
lar
ly
in
s
u
p
p
l
y
ch
ain
m
an
ag
em
en
t.
T
h
e
to
p
ic
h
ig
h
lig
h
ts
h
o
w
em
er
g
in
g
tech
n
o
lo
g
ies
en
h
an
ce
e
f
f
ici
en
cy
,
tr
an
s
p
a
r
en
cy
,
an
d
a
d
ap
t
ab
ilit
y
th
r
o
u
g
h
au
to
m
atio
n
,
r
ea
l
-
tim
e
d
ata
ac
c
ess
,
an
d
im
p
r
o
v
ed
co
o
r
d
in
atio
n
am
o
n
g
s
tak
eh
o
ld
e
r
s
.
−
T
o
p
ic
3
r
elate
s
to
d
ig
ital
h
ea
lt
h
ca
r
e
p
latf
o
r
m
s
,
in
clu
d
in
g
p
atien
t
d
ata
m
an
a
g
em
en
t
an
d
b
l
o
ck
ch
ain
-
b
ased
s
o
lu
tio
n
s
.
T
h
ese
tech
n
o
lo
g
ies
en
h
an
ce
d
ata
s
ec
u
r
ity
,
in
ter
o
p
er
ab
ilit
y
,
an
d
s
er
v
ice
ef
f
icien
c
y
,
s
u
p
p
o
r
tin
g
telem
ed
icin
e,
r
ea
l
-
tim
e
m
o
n
it
o
r
in
g
,
a
n
d
s
ec
u
r
e
in
f
o
r
m
atio
n
s
h
ar
in
g
.
−
T
o
p
ic
4
ex
am
in
es
I
o
T
tec
h
n
o
lo
g
ies
with
a
p
r
io
r
itizatio
n
o
f
d
ata
s
ec
u
r
ity
an
d
p
r
i
v
ac
y
,
an
d
s
ec
u
r
e
co
m
m
u
n
icatio
n
.
I
t
h
ig
h
lig
h
ts
m
ec
h
an
is
m
s
f
o
r
p
r
o
tectin
g
I
o
T
s
y
s
tem
s
f
r
o
m
cy
b
er
th
r
ea
ts
,
wh
ich
ar
e
cr
itical
f
o
r
ap
p
licatio
n
s
in
s
m
ar
t c
ities
,
in
d
u
s
tr
ial
au
to
m
atio
n
,
an
d
h
ea
lth
ca
r
e.
−
T
o
p
ic
5
ce
n
ter
s
o
n
s
m
ar
t
co
n
t
r
ac
ts
,
b
lo
ck
ch
ain
,
an
d
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
T
h
e
in
teg
r
atio
n
o
f
th
ese
tech
n
o
lo
g
ies
en
a
b
les
au
to
m
at
ed
tr
an
s
ac
tio
n
s
,
f
r
au
d
d
etec
ti
o
n
,
an
d
in
tellig
en
t
d
ec
is
io
n
-
m
ak
in
g
ac
r
o
s
s
d
ec
en
tr
alize
d
n
etwo
r
k
s
.
−
T
o
p
ic
6
f
o
cu
s
es
o
n
in
f
o
r
m
ati
o
n
m
an
ag
em
e
n
t
an
d
d
ata
s
h
ar
in
g
in
s
u
p
p
ly
ch
ain
s
.
Secu
r
e
ac
ce
s
s
co
n
tr
o
l
an
d
ef
f
icien
t
in
f
o
r
m
atio
n
ex
ch
an
g
e
en
h
a
n
ce
tr
an
s
p
ar
e
n
cy
,
co
o
r
d
in
atio
n
,
an
d
o
p
er
atio
n
al
r
eliab
ilit
y
am
o
n
g
s
u
p
p
ly
c
h
ain
p
a
r
ticip
an
ts
.
−
T
o
p
ic
7
h
i
g
h
lig
h
ts
s
ec
u
r
ity
an
d
p
r
i
v
ac
y
is
s
u
es
in
I
o
T
a
n
d
h
ea
lth
ca
r
e
en
v
ir
o
n
m
en
ts
,
em
p
h
asizin
g
p
r
o
tectiv
e
m
ea
s
u
r
es
f
o
r
cl
o
u
d
-
b
ased
d
ata
p
r
o
ce
s
s
in
g
a
n
d
s
t
o
r
ag
e
to
en
s
u
r
e
r
eg
u
lato
r
y
c
o
m
p
lian
ce
an
d
tr
u
s
t in
d
ig
ital ser
v
ices.
−
T
o
p
ic
8
ad
d
r
ess
es
b
lo
ck
ch
ain
n
etwo
r
k
s
ec
u
r
ity
an
d
co
n
s
en
s
u
s
m
ec
h
an
is
m
s
.
I
t
ex
am
in
es
alg
o
r
ith
m
s
th
at
en
s
u
r
e
tr
an
s
ac
tio
n
v
alid
ity
,
s
y
s
tem
in
teg
r
ity
,
an
d
r
esis
tan
ce
to
attac
k
s
in
d
ec
en
tr
alize
d
ap
p
l
icatio
n
s
.
−
T
o
p
ic
9
f
o
c
u
s
es
o
n
e
n
er
g
y
m
ar
k
ets
an
d
s
m
ar
t
g
r
id
s
,
em
p
h
asizin
g
d
ec
e
n
tr
alize
d
e
n
er
g
y
tr
ad
in
g
u
s
in
g
b
lo
ck
ch
ain
tech
n
o
lo
g
y
an
d
ef
f
icien
t
r
eso
u
r
ce
m
an
a
g
em
en
t.
T
h
ese
tech
n
o
lo
g
ies
s
u
p
p
o
r
t
s
u
s
tain
ab
le,
r
esil
ien
t,
an
d
d
ec
en
tr
alize
d
en
er
g
y
in
f
r
astru
ctu
r
es.
As
ca
n
b
e
s
ee
n
f
r
o
m
T
ab
les
1
an
d
2
,
it
was
d
ef
in
ed
p
r
e
d
o
m
in
an
t
r
esear
c
h
to
p
ics
in
th
e
f
ield
o
f
b
lo
ck
ch
ain
e
n
g
in
ee
r
in
g
ac
c
o
r
d
in
g
to
r
esear
c
h
q
u
esti
o
n
1
.
T
h
e
h
ea
tm
ap
as
s
h
o
wn
i
n
Fig
u
r
e
6
v
is
u
alize
s
th
e
d
if
f
er
en
ce
s
b
etwe
en
to
p
ics
in
a
to
p
ic
m
o
d
elin
g
an
aly
s
is
,
s
p
ec
if
ically
u
s
in
g
th
e
J
ac
ca
r
d
d
is
tan
ce
as
t
h
e
m
ea
s
u
r
e
o
f
d
if
f
er
e
n
ce
.
Her
e’
s
a
d
etailed
d
escr
ip
tio
n
o
f
wh
at
th
e
p
lo
t r
ep
r
esen
ts
.
T
h
e
x
-
an
d
y
-
ax
e
s
r
ep
r
es
en
t
n
in
e
to
p
i
c
s
(
0
–
8
)
id
en
tif
ied
b
y
th
e
m
o
d
e
l,
wh
il
e
th
e
c
o
lo
r
s
ca
l
e
r
an
g
e
s
f
r
o
m
0
to
1
,
in
d
ic
at
i
n
g
J
a
cc
a
r
d
d
i
s
tan
c
e
b
e
tw
ee
n
to
p
i
c
p
ai
r
s
.
Da
r
k
b
lu
e
v
al
u
es
r
ep
r
e
s
en
t
lo
w
d
i
s
ta
n
ce
an
d
h
ig
h
s
im
i
la
r
i
ty
,
wh
er
ea
s
d
ar
k
r
ed
v
a
lu
e
s
in
d
ica
te
h
ig
h
d
i
s
tan
ce
an
d
m
i
n
im
a
l
o
v
er
l
ap
.
T
h
e
r
ed
d
iag
o
n
al
r
ef
le
ct
s
s
elf
-
co
m
p
ar
i
s
o
n
s
o
f
t
o
p
i
cs
,
wh
i
ch
is
e
x
p
ec
ted
,
wh
il
e
o
f
f
-
d
i
ag
o
n
a
l
c
el
ls
s
h
o
w
p
a
ir
w
i
s
e
to
p
i
c
s
i
m
i
lar
i
tie
s
.
L
ig
h
ter
b
lu
e
ce
lls
s
u
g
g
est
m
o
d
er
ate
o
v
er
lap
b
etwe
en
to
p
i
cs,
in
d
icatin
g
r
elate
d
th
e
m
es
o
r
s
h
ar
ed
v
o
ca
b
u
lar
y
,
wh
er
ea
s
d
ar
k
e
r
b
lu
e
ce
lls
r
ef
lect
s
tr
o
n
g
er
s
im
ilar
ity
.
Fo
r
in
s
tan
ce
,
to
p
ics
0
an
d
2
s
h
o
w
m
o
d
er
ate
o
v
er
lap
,
wh
ile
to
p
ics
s
u
ch
as
4
an
d
6
ap
p
ea
r
m
o
r
e
d
is
tin
ct,
r
ef
lectin
g
u
n
iq
u
e
th
em
atic
c
o
n
ten
t.
Ov
er
all,
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
R
esea
r
ch
th
eme
s
a
n
d
tr
en
d
s
in
th
e
field
o
f b
lo
ck
c
h
a
in
e
n
g
in
e
erin
g
:
a
to
p
ic
…
(
Din
a
r
a
Zh
a
is
a
n
o
va
)
1871
v
is
u
aliza
tio
n
d
em
o
n
s
tr
ates
th
at
th
e
to
p
ic
m
o
d
el
e
f
f
ec
tiv
el
y
d
if
f
er
en
tiates
b
etwe
en
th
e
m
es
wh
ile
r
ev
ea
lin
g
ar
ea
s
o
f
th
em
atic
o
v
er
lap
.
Ad
d
itio
n
al
in
s
ig
h
ts
f
r
o
m
L
SI
h
ig
h
lig
h
t
s
tr
o
n
g
ass
o
ciatio
n
s
am
o
n
g
to
p
ics
r
elate
d
to
en
e
r
g
y
tr
ad
in
g
,
s
u
p
p
ly
ch
ain
s
,
an
d
h
ea
lth
ca
r
e
.
T
h
e
co
n
s
is
ten
cy
b
etwe
en
L
DA
an
d
L
SI
r
esu
lts
r
ein
f
o
r
ce
s
t
h
e
r
o
b
u
s
tn
ess
o
f
th
e
id
en
tifie
d
to
p
ic
s
tr
u
ctu
r
e
.
T
o
p
ic
r
elatio
n
s
h
ip
s
wer
e
v
is
u
alize
d
u
s
in
g
p
y
L
DAv
is
,
with
Fig
u
r
e
7
s
u
m
m
ar
izin
g
th
e
in
ter
to
p
ic
s
im
ilar
ities
.
T
ab
le
1
.
B
lo
ck
ch
ai
n
en
g
i
n
ee
r
i
n
g
to
p
ics (
2
0
1
9
-
2
0
2
4
)
f
o
r
L
SI
No
To
p
i
c
n
a
me
(
p
r
o
p
o
r
t
i
o
n
i
n
t
h
e
w
h
o
l
e
c
o
r
p
u
s)
R
e
p
r
e
se
n
t
a
t
i
v
e
t
e
r
ms
1
I
o
T
a
n
d
s
e
c
u
r
i
t
y
(
1
5
%)
“
i
o
t
”
(
0
.
0
2
2
)
,
“
sec
u
r
i
t
y
”
(
0
.
0
1
7
)
,
“
sma
r
t
”
(
0
.
0
1
4
)
,
“
b
l
o
c
k
c
h
a
i
n
”
(
0
.
0
1
1
)
,
“
n
e
t
w
o
r
k
”
(
0
.
0
1
1
)
,
“
l
e
a
r
n
i
n
g
”
(
0
.
0
1
0
)
,
“
d
e
v
i
c
e
s
”
(
0
.
0
0
9
)
,
“
i
n
t
e
r
n
e
t
”
(
0
.
0
0
8
)
,
“
d
a
t
a
”
(
0
.
0
0
8
)
,
“
p
r
o
p
o
se
d
”
(
0
.
0
0
7
)
2
B
l
o
c
k
c
h
a
i
n
t
e
c
h
n
o
l
o
g
y
a
n
d
s
y
st
e
ms
(
1
8
%)
“
b
l
o
c
k
c
h
a
i
n
”
(
0
.
0
2
6
)
,
“
t
e
c
h
n
o
l
o
g
y
”
(
0
.
0
2
3
)
,
“
d
e
v
e
l
o
p
m
e
n
t
”
(
0
.
0
1
8
)
,
“
mo
d
e
l
”
(
0
.
0
1
2
)
,
“
i
n
f
o
r
ma
t
i
o
n
”
(
0
.
0
1
2
)
,
“
ma
n
a
g
e
m
e
n
t
”
(
0
.
0
1
1
)
,
“
sy
s
t
e
m
”
(
0
.
0
1
1
)
,
“
b
a
se
d
”
(
0
.
0
1
0
)
,
“
d
a
t
a
”
(
0
.
0
1
0
)
,
“
p
a
p
e
r
”
(
0
.
0
0
9
)
3
B
l
o
c
k
c
h
a
i
n
i
n
s
u
p
p
l
y
c
h
a
i
n
ma
n
a
g
e
m
e
n
t
(
1
2
%)
“
su
p
p
l
y
”
(
0
.
0
4
2
)
,
“
c
h
a
i
n
”
(
0
.
0
4
1
)
,
“
b
l
o
c
k
c
h
a
i
n
”
(
0
.
0
1
8
)
,
“
t
e
c
h
n
o
l
o
g
y
”
(
0
.
0
1
2
)
,
“
f
o
o
d
”
(
0
.
0
1
2
)
,
“
m
o
d
e
l
”
(
0
.
0
0
9
)
,
“
p
r
o
d
u
c
t
”
(
0
.
0
0
8
)
,
“
c
h
a
i
n
s
”
(
0
.
0
0
8
)
,
“
st
u
d
y
”
(
0
.
0
0
7
)
,
“
t
r
a
c
e
a
b
i
l
i
t
y
”
(
0
.
0
0
7
)
4
B
l
o
c
k
c
h
a
i
n
se
c
u
r
i
t
y
s
y
st
e
ms
(
1
4
%)
“
d
a
t
a
”
(
0
.
0
3
2
)
,
“
b
l
o
c
k
c
h
a
i
n
”
(
0
.
0
2
0
)
,
“
se
c
u
r
i
t
y
”
(
0
.
0
1
3
)
,
“
sy
s
t
e
m
”
(
0
.
0
1
2
)
,
“
p
r
o
p
o
se
d
”
(
0
.
0
1
0
)
,
“
sc
h
e
m
e
”
(
0
.
0
0
8
)
,
“
d
e
v
e
l
o
p
me
n
t
”
(
0
.
0
0
8
)
,
“
p
r
i
v
a
c
y
”
(
0
.
0
0
7
)
,
“
b
a
se
d
”
(
0
.
0
0
7
)
,
“
t
e
c
h
n
o
l
o
g
y
”
(
0
.
0
0
7
)
5
B
l
o
c
k
c
h
a
i
n
i
n
e
n
e
r
g
y
t
r
a
d
i
n
g
(
9
,
0
%)
“
e
n
e
r
g
y
”
(
0
.
0
5
6
)
,
“
p
o
w
e
r
”
(
0
.
0
1
7
)
,
“
t
r
a
d
i
n
g
”
(
0
.
0
1
5
)
,
“
b
l
o
c
k
c
h
a
i
n
”
(
0
.
0
1
1
)
,
“
m
a
r
k
e
t
”
(
0
.
0
1
0
)
,
“
e
l
e
c
t
r
i
c
i
t
y
”
(
0
.
0
0
9
)
,
“
g
r
i
d
”
(
0
.
0
0
8
)
,
“
d
e
v
e
l
o
p
m
e
n
t
”
(
0
.
0
0
8
)
,
“
s
y
s
t
e
m
”
(
0
.
0
0
8
)
,
“
sm
a
r
t
”
(
0
.
0
0
7
)
6
B
l
o
c
k
c
h
a
i
n
r
e
se
a
r
c
h
a
n
d
t
e
c
h
n
o
l
o
g
i
c
a
l
a
d
v
a
n
c
e
me
n
t
s
(
1
1
%)
“
b
l
o
c
k
c
h
a
i
n
”
(
0
.
0
2
1
)
,
“
r
e
s
e
a
r
c
h
”
(
0
.
0
1
7
)
,
“
t
e
c
h
n
o
l
o
g
y
”
(
0
.
0
1
3
)
,
“
t
e
c
h
n
o
l
o
g
i
e
s
”
(
0
.
0
1
2
)
,
“
st
u
d
y
”
(
0
.
0
1
1
)
,
“
d
i
g
i
t
a
l
”
(
0
.
0
1
1
)
,
“
d
e
v
e
l
o
p
m
e
n
t
”
(
0
.
0
1
0
)
,
“
i
n
d
u
st
r
y
”
(
0
.
0
0
7
)
,
“
p
a
p
e
r
”
(
0
.
0
0
6
)
,
“
c
h
a
l
l
e
n
g
e
s
”
(
0
.
0
0
6
)
7
B
l
o
c
k
c
h
a
i
n
so
f
t
w
a
r
e
a
n
d
sy
s
t
e
m
d
e
si
g
n
(
1
0
%)
“
b
l
o
c
k
c
h
a
i
n
”
(
0
.
0
1
6
)
,
“
d
a
t
a
”
(
0
.
0
1
4
)
,
“
s
y
st
e
m
”
(
0
.
0
1
0
)
,
“
s
o
f
t
w
a
r
e
”
(
0
.
0
0
8
)
,
“
d
e
s
i
g
n
”
(
0
.
0
0
7
)
,
“
i
n
f
o
r
mat
i
o
n
”
(
0
.
0
0
7
)
,
“
u
se
”
(
0
.
0
0
6
)
,
“
d
i
g
i
t
a
l
”
(
0
.
0
0
6
)
,
“
t
e
c
h
n
o
l
o
g
y
”
(
0
.
0
0
6
)
,
“
d
e
c
e
n
t
r
a
l
i
z
e
d
”
(
0
.
0
0
6
)
8
B
l
o
c
k
c
h
a
i
n
i
n
h
e
a
l
t
h
c
a
r
e
(
1
3
%)
“
d
a
t
a
”
(
0
.
0
2
9
)
,
“
me
d
i
c
a
l
”
(
0
.
0
2
3
)
,
“
h
e
a
l
t
h
”
(
0
.
0
2
1
)
,
“
h
e
a
l
t
h
c
a
r
e
”
(
0
.
0
2
0
)
,
“
s
y
st
e
m
”
(
0
.
0
1
3
)
,
“
b
l
o
c
k
c
h
a
i
n
”
(
0
.
0
1
2
)
,
“
i
n
f
o
r
m
a
t
i
o
n
”
(
0
.
0
0
9
)
,
“
t
e
c
h
n
o
l
o
g
y
”
(
0
.
0
0
8
)
,
“
p
a
t
i
e
n
t
”
(
0
.
0
0
7
)
,
“
p
a
t
i
e
n
t
s
”
(
0
.
0
0
7
)
9
S
mart
c
o
n
t
r
a
c
t
s
a
n
d
b
l
o
c
k
c
h
a
i
n
i
n
f
i
n
a
n
c
i
a
l
a
p
p
l
i
c
a
t
i
o
n
s
(
1
2
%)
“
smar
t
”
(
0
.
0
2
0
)
,
“
b
l
o
c
k
c
h
a
i
n
”
(
0
.
0
1
6
)
,
“
c
o
n
t
r
a
c
t
s
”
(
0
.
0
1
5
)
,
“
f
i
n
a
n
c
i
a
l
”
(
0
.
0
1
1
)
,
“
d
e
v
e
l
o
p
me
n
t
”
(
0
.
0
1
1
)
,
“
c
o
n
t
r
a
c
t
”
(
0
.
0
1
0
)
,
“
d
i
g
i
t
a
l
”
(
0
.
0
0
8
)
,
“
t
e
c
h
n
o
l
o
g
y
”
(
0
.
0
0
8
)
,
“
t
r
a
n
sa
c
t
i
o
n
s
”
(
0
.
0
0
6
)
,
“
c
r
y
p
t
o
c
u
r
r
e
n
c
y
”
(
0
.
0
0
5
)
T
ab
le
2
.
B
lo
ck
ch
ai
n
en
g
i
n
ee
r
i
n
g
to
p
ics (
2
0
1
9
-
2
0
2
4
)
f
o
r
L
DA
No
To
p
i
c
n
a
me
(
p
r
o
p
o
r
t
i
o
n
i
n
t
h
e
w
h
o
l
e
c
o
r
p
u
s)
R
e
p
r
e
se
n
t
a
t
i
v
e
t
e
r
ms
1
G
e
n
e
r
a
l
r
e
s
e
a
r
c
h
i
n
AI
a
n
d
k
n
o
w
l
e
d
g
e
man
a
g
e
me
n
t
(
1
0
.
5
%)
“
r
e
sea
r
c
h
”
(
0
.
0
2
5
)
,
“
p
a
p
e
r
”
(
0
.
0
1
0
)
,
“
a
n
a
l
y
s
i
s
”
(
0
.
0
0
9
)
,
“
f
i
e
l
d
”
(
0
.
0
0
8
)
,
“
a
p
p
l
i
c
a
t
i
o
n
”
(
0
.
0
0
8
)
,
“
st
u
d
y
”
(
0
.
0
0
8
)
,
“
i
n
t
e
l
l
i
g
e
n
c
e
”
(
0
.
0
0
7
)
,
“
k
n
o
w
l
e
d
g
e
”
(
0
.
0
0
7
)
,
“
ai
”
(
0
.
0
0
7
)
,
“
f
u
t
u
r
e
”
(
0
.
0
0
6
)
2
D
i
g
i
t
a
l
t
r
a
n
sf
o
r
m
a
t
i
o
n
a
n
d
s
u
p
p
l
y
c
h
a
i
n
man
a
g
e
me
n
t
(
9
.
0
%)
“
st
u
d
y
”
(
0
.
0
1
3
)
,
“
d
i
g
i
t
a
l
”
(
0
.
0
1
0
)
,
“
r
e
sea
r
c
h
”
(
0
.
0
0
9
)
,
“
i
n
d
u
st
r
y
”
(
0
.
0
0
8
)
,
“
c
h
a
i
n
”
(
/
)
,
“
s
u
p
p
l
y
”
(
0
.
0
0
7
)
,
“
p
a
p
e
r
”
(
0
.
0
0
6
)
,
“
b
u
si
n
e
ss
”
(
0
.
0
0
6
)
,
“
n
e
w
”
(
0
.
0
0
5
)
,
“
ma
n
a
g
e
m
e
n
t
”
(
0
.
0
0
5
)
3
D
i
g
i
t
a
l
h
e
a
l
t
h
p
l
a
t
f
o
r
ms
a
n
d
b
l
o
c
k
c
h
a
i
n
i
n
h
e
a
l
t
h
c
a
r
e
(
8
.
0
%)
“
h
e
a
l
t
h
”
(
0
.
0
1
8
)
,
“
p
l
a
t
f
o
r
m
”
(
0
.
0
1
2
)
,
“
me
d
i
c
a
l
”
(
0
.
0
1
2
)
,
“
p
a
t
i
e
n
t
”
(
0
.
0
0
9
)
,
“
r
e
c
o
r
d
”
(
0
.
0
0
8
)
,
“
s
h
a
r
i
n
g
”
(
0
.
0
0
6
)
,
“
b
i
t
c
o
i
n
”
(
0
.
0
0
6
)
,
“
c
a
r
e
”
(
0
.
0
0
6
)
,
“
se
c
u
r
i
t
y
”
(
0
.
0
0
6
)
,
“
n
f
t
”
(
0
.
0
0
6
)
4
I
o
T
sec
u
r
i
t
y
,
p
r
i
v
a
c
y
,
a
n
d
c
o
mm
u
n
i
c
a
t
i
o
n
p
r
o
t
o
c
o
l
s
(
1
1
.
0
%)
“
sc
h
e
me
”
(
0
.
0
2
0
)
,
“
s
t
o
r
a
g
e
”
(
0
.
0
1
1
)
,
“
v
e
h
i
c
l
e
”
(
0
.
0
1
0
)
,
“
s
e
c
u
r
i
t
y
”
(
0
.
0
0
9
)
,
“
p
r
o
p
o
se
d
”
(
0
.
0
0
8
)
,
“
i
n
t
e
r
n
e
t
”
(
0
.
0
0
8
)
,
“
n
o
d
e
”
(
0
.
0
0
7
)
,
“
i
o
t
”
(
0
.
0
0
7
)
,
“
c
o
mm
u
n
i
c
a
t
i
o
n
”
(
0
.
0
0
7
)
,
“
p
r
i
v
a
c
y
”
(
0
.
0
0
7
)
5
S
mart
c
o
n
t
r
a
c
t
s
,
b
l
o
c
k
c
h
a
i
n
t
e
c
h
n
o
l
o
g
y
,
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
(
1
2
.
5
%)
“
c
o
n
t
r
a
c
t
”
(
0
.
0
3
2
)
,
“
smar
t
”
(
0
.
0
3
0
)
,
“
mo
d
e
l
”
(
0
.
0
1
7
)
,
“
me
t
h
o
d
”
(
0
.
0
1
0
)
,
“
p
r
o
p
o
se
d
”
(
0
.
0
0
8
)
,
“
d
e
t
e
c
t
i
o
n
”
(
0
.
0
0
8
)
,
“
n
e
t
w
o
r
k
”
(
0
.
0
0
7
)
,
“
l
e
a
r
n
i
n
g
”
(
0
.
0
0
7
)
,
“
r
e
s
u
l
t
”
(
0
.
0
0
6
)
,
“
c
o
d
e
”
(
0
.
0
0
6
)
6
I
n
f
o
r
mat
i
o
n
m
a
n
a
g
e
m
e
n
t
a
n
d
u
ser
a
c
c
e
ss
i
n
su
p
p
l
y
c
h
a
i
n
s
(
7
.
5
%)
“
c
h
a
i
n
”
(
0
.
0
1
5
)
,
“
i
n
f
o
r
ma
t
i
o
n
”
(
0
.
0
1
3
)
,
“
m
a
n
a
g
e
me
n
t
”
(
0
.
0
1
1
)
,
“
s
u
p
p
l
y
”
(
0
.
0
1
0
)
,
“
u
ser
”
(
0
.
0
1
0
)
,
“
m
o
d
e
l
”
(
0
.
0
1
0
)
,
“
sh
a
r
i
n
g
”
(
0
.
0
0
9
)
,
“
p
r
o
b
l
e
m
”
(
0
.
0
0
9
)
,
“
me
c
h
a
n
i
sm
”
(
0
.
0
0
8
)
,
“
a
c
c
e
s
s
”
(
0
.
0
0
8
)
7
P
r
i
v
a
c
y
a
n
d
se
c
u
r
i
t
y
i
n
I
o
T
a
n
d
C
l
o
u
d
serv
i
c
e
s
(
9
.
5
%)
“
sec
u
r
i
t
y
”
(
0
.
0
2
2
)
,
“
i
o
t
”
(
0
.
0
2
0
)
,
“
p
r
i
v
a
c
y
”
(
0
.
0
1
4
)
,
“
d
e
v
i
c
e
”
(
0
.
0
1
0
)
,
“
h
e
a
l
t
h
c
a
r
e
”
(
0
.
0
0
9
)
,
“
p
r
o
p
o
se
d
”
(
0
.
0
0
9
)
,
“
i
n
t
e
r
n
e
t
”
(
0
.
0
0
9
)
,
“
c
l
o
u
d
”
(
0
.
0
0
8
)
,
“
ser
v
i
c
e
”
(
0
.
0
0
7
)
,
“
t
h
i
n
g
”
(
0
.
0
0
7
)
8
N
e
t
w
o
r
k
s
e
c
u
r
i
t
y
a
n
d
c
o
n
se
n
s
u
s
a
l
g
o
r
i
t
h
ms
i
n
b
l
o
c
k
c
h
a
i
n
(
1
0
.
0
%)
“
n
e
t
w
o
r
k
”
(
0
.
0
2
4
)
,
“
sec
u
r
i
t
y
”
(
0
.
0
1
8
)
,
“
c
o
n
s
e
n
su
s
”
(
0
.
0
1
1
)
,
“
a
p
p
l
i
c
a
t
i
o
n
”
(
0
.
0
1
1
)
,
“
smar
t
”
(
0
.
0
0
9
)
,
“
a
l
g
o
r
i
t
h
m
”
(
0
.
0
0
8
)
,
“
c
o
mm
u
n
i
c
a
t
i
o
n
”
(
0
.
0
0
7
)
,
“
p
r
o
p
o
se
d
”
(
0
.
0
0
7
)
,
“
t
r
a
n
sa
c
t
i
o
n
”
(
0
.
0
0
7
)
,
“
m
e
c
h
a
n
i
s
m
”
(
0
.
0
0
7
)
9
En
e
r
g
y
t
r
a
d
i
n
g
,
s
mart
g
r
i
d
s,
a
n
d
r
e
so
u
r
c
e
man
a
g
e
me
n
t
(
1
2
.
0
%)
“
e
n
e
r
g
y
”
(
0
.
0
3
9
)
,
“
p
o
w
e
r
”
(
0
.
0
1
2
)
,
“
t
r
a
d
i
n
g
”
(
0
.
0
1
2
)
,
“
sm
a
r
t
”
(
0
.
0
1
1
)
,
“
t
r
a
n
sa
c
t
i
o
n
”
(
0
.
0
1
0
)
,
“
mo
d
e
l
”
(
0
.
0
0
9
)
,
“
mar
k
e
t
”
(
0
.
0
0
8
)
,
“
p
r
o
p
o
se
d
”
(
0
.
0
0
8
)
,
“
g
r
i
d
”
(
0
.
0
0
7
)
,
“
r
e
s
o
u
r
c
e
”
(
0
.
0
0
7
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
8
6
3
-
1
8
7
5
1872
Fig
u
r
e
6
.
Hea
tm
ap
o
f
d
o
cu
m
e
n
t similar
ities
Fig
u
r
e
7
.
Vis
u
aliza
tio
n
o
f
to
p
i
cs
Fig
u
r
e
7
illu
s
tr
ates
th
e
o
u
tco
m
es
o
f
th
e
L
DA
-
b
ased
to
p
ic
m
o
d
elin
g
th
r
o
u
g
h
an
in
te
r
to
p
ic
d
is
tan
ce
m
ap
al
o
n
g
s
id
e
a
T
o
p
-
30
m
o
s
t
s
alien
t
ter
m
s
v
is
u
aliza
tio
n
,
p
r
o
v
id
in
g
an
o
v
er
v
iew
o
f
t
h
e
c
o
r
p
u
s
’
s
u
n
d
er
ly
in
g
th
em
atic
s
tr
u
ctu
r
e.
Dis
p
lay
ed
in
th
e
lef
t p
an
el
is
t
h
e
in
ter
t
o
p
ic
d
is
tan
ce
m
a
p
p
r
o
d
u
ce
d
u
s
in
g
m
u
ltid
im
e
n
s
io
n
al
s
ca
lin
g
(
MD
S),
in
w
h
ich
ea
c
h
cir
cle
co
r
r
esp
o
n
d
s
to
a
to
p
ic,
a
n
d
th
e
cir
cle
s
ize
r
ef
lects
its
r
e
lativ
e
p
r
o
m
i
n
en
ce
with
in
th
e
d
ataset.
Sp
atial
p
r
o
x
im
ity
r
ef
lects
s
em
an
tic
s
im
i
l
ar
ity
b
etwe
en
to
p
ics,
wh
ile
th
e
PC
1
an
d
P
C
2
ax
es
ca
p
tu
r
e
th
e
m
ain
v
ar
ian
ce
in
to
p
ic
–
wo
r
d
d
is
tr
ib
u
ti
o
n
s
.
A
m
ar
g
in
al
to
p
ic
d
is
tr
ib
u
tio
n
in
s
et
s
u
m
m
ar
izes
th
e
o
v
er
all
co
n
t
r
ib
u
tio
n
o
f
ea
c
h
to
p
ic
to
th
e
co
r
p
u
s
.
T
h
e
r
ig
h
t
p
a
n
el
illu
s
tr
ates
th
e
3
0
m
o
s
t
im
p
o
r
tan
t
ter
m
s
,
with
b
lu
e
b
ar
s
in
d
icatin
g
o
v
er
all
ter
m
f
r
eq
u
e
n
cy
a
n
d
r
ed
o
v
e
r
lay
s
s
h
o
win
g
to
p
ic
-
s
p
ec
if
ic
r
ele
v
an
c
e.
Fre
q
u
e
n
tly
o
cc
u
r
r
i
n
g
te
r
m
s
s
u
ch
as
b
lo
c
k
ch
ain
,
co
n
tr
ac
t,
s
m
ar
t,
s
ec
u
r
ity
,
co
n
s
en
s
u
s
,
an
d
p
r
iv
ac
y
i
n
d
icate
s
tr
o
n
g
r
ep
r
esen
tatio
n
o
f
b
lo
ck
c
h
ain
,
cy
b
er
s
ec
u
r
ity
,
Evaluation Warning : The document was created with Spire.PDF for Python.