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.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
,
p
p
.
373
~
382
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
1
6
i
1
.
pp
3
7
3
-
3
8
2
373
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Applica
tion o
f
de
ep learning
and
ma
chine learning
techniqu
es
for the
det
ection
o
f
mis
lea
ding
hea
lth
repo
r
ts
Ra
v
ind
ra
B
a
bu
J
a
la
da
nk
i
1
,
G
a
ra
pa
t
i Sa
t
y
a
na
ra
y
a
na
M
urt
hy
2
,
Venu G
o
pa
l G
a
dd
a
m
3
,
Chip
pa
da
Na
g
a
m
a
ni
4
,
J
a
njh
y
a
m
Ven
k
a
t
a
Na
g
a
Ra
m
esh
5
,
Ra
m
esh
E
luri
6
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
P
r
a
s
a
d
V
.
P
o
t
l
u
r
i
S
i
d
d
h
a
r
t
h
a
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
V
i
j
a
y
a
w
a
d
a
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
A
d
i
t
y
a
U
n
i
v
e
r
si
t
y
,
A
n
d
h
r
a
P
r
a
d
e
s
h
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
(
A
I
a
n
d
M
L)
,
B
V
R
a
j
u
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
H
y
d
e
r
a
b
a
d
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
K
o
n
e
r
u
L
a
k
sh
m
a
i
a
h
E
d
u
c
a
t
i
o
n
F
o
u
n
d
a
t
i
o
n
,
A
n
d
h
r
a
P
r
a
d
e
s
h
,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
G
r
a
p
h
i
c
Er
a
H
i
l
l
U
n
i
v
e
r
si
t
y
,
G
r
a
p
h
i
c
Er
a
D
e
e
me
d
t
o
b
e
U
n
i
v
e
r
si
t
y
,
D
e
h
r
a
d
u
n
,
I
n
d
i
a
6
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
R
.
V
.
R
& J
.
C
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
A
n
d
h
r
a
P
r
a
d
e
s
h
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l 1
9
,
2
0
2
4
R
ev
is
ed
J
u
n
1
9
,
2
0
2
5
Acc
ep
ted
No
v
2
3
,
2
0
2
5
In
t
h
e
c
u
rre
n
t
e
ra
o
f
v
a
st
i
n
fo
rm
a
ti
o
n
a
v
a
i
lab
il
it
y
,
th
e
d
isse
m
in
a
ti
o
n
o
f
m
islea
d
in
g
h
e
a
lt
h
i
n
fo
rm
a
ti
o
n
p
o
se
s
a
c
o
n
sid
e
ra
b
le
o
b
sta
c
le,
jeo
p
a
rd
izi
n
g
p
u
b
li
c
h
e
a
lt
h
a
n
d
o
v
e
ra
ll
we
ll
-
b
e
in
g
.
T
o
tac
k
le
th
is
c
h
a
ll
e
n
g
e
,
e
x
p
e
rts
h
a
v
e
u
ti
li
z
e
d
a
rti
ficia
l
in
telli
g
e
n
c
e
m
e
th
o
d
s,
e
sp
e
c
ially
m
a
c
h
i
n
e
lea
rn
in
g
(M
L)
a
n
d
d
e
e
p
lea
rn
i
n
g
(DL),
to
c
re
a
te
a
u
to
m
a
ted
sy
ste
m
s
t
h
a
t
c
a
n
id
e
n
t
ify
m
islea
d
in
g
h
e
a
lt
h
-
re
late
d
i
n
fo
rm
a
ti
o
n
.
T
h
is
stu
d
y
th
o
ro
u
g
h
l
y
in
v
e
stig
a
tes
M
L
a
n
d
DL
tec
h
n
iq
u
e
s
fo
r
d
e
te
c
ti
n
g
fra
u
d
u
le
n
t
h
e
a
lt
h
n
e
ws
.
Th
e
a
n
a
ly
sis
d
e
lv
e
s
in
t
o
d
isti
n
c
t
m
e
th
o
d
o
lo
g
ies
,
e
x
p
l
o
ri
n
g
t
h
e
ir
u
n
i
q
u
e
a
p
p
r
o
a
c
h
e
s,
m
e
tri
c
s,
a
n
d
c
h
a
ll
e
n
g
e
s.
Th
is
st
u
d
y
e
x
p
l
o
re
s
v
a
rio
u
s
tec
h
n
iq
u
e
s
u
ti
li
z
e
d
in
fe
a
tu
re
e
n
g
i
n
e
e
rin
g
,
m
o
d
e
l
a
rc
h
i
tec
tu
re
,
a
n
d
e
v
a
l
u
a
ti
o
n
m
e
tri
c
s
with
in
t
h
e
re
a
lms
o
f
m
a
c
h
in
e
lea
rn
in
g
a
n
d
d
e
e
p
lea
rn
in
g
m
e
th
o
d
o
l
o
g
ies
.
Ad
d
it
io
n
a
ll
y
,
we
a
n
a
ly
z
e
th
e
c
o
n
se
q
u
e
n
c
e
s
o
f
o
u
r
re
su
lt
s
o
n
e
n
h
a
n
c
i
n
g
th
e
e
ffica
c
y
o
f
sy
ste
m
s
d
e
sig
n
e
d
to
d
e
tec
t
c
o
u
n
terfe
it
h
e
a
lt
h
n
e
ws
a
n
d
p
r
o
p
o
s
e
p
o
ss
ib
le
a
v
e
n
u
e
s fo
r
f
u
t
u
re
in
v
e
stig
a
ti
o
n
i
n
th
is v
it
a
l
a
re
a
.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
Dee
p
lear
n
in
g
Fak
e
h
ea
lth
n
ews
Hea
lth
ca
r
e
Ma
ch
in
e
lear
n
in
g
R
ea
d
ab
ilit
y
f
ea
tu
r
es
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
av
in
d
r
a
B
ab
u
J
alad
an
k
i
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
i
n
g
,
Pra
s
ad
V.
Po
tlu
r
i Sid
d
h
ar
th
a
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
Vijay
awa
d
a,
I
n
d
ia
E
m
ail:
jr
b
0
0
0
9
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
to
d
a
y
'
s
d
ig
ital
lan
d
s
ca
p
e,
wh
er
e
in
f
o
r
m
atio
n
is
r
ea
d
ily
ac
ce
s
s
ib
le
an
d
d
is
s
em
in
ated
at
r
em
ar
k
ab
le
s
p
ee
d
s
,
th
e
r
is
e
o
f
m
is
in
f
o
r
m
atio
n
,
p
ar
ticu
lar
ly
in
h
ea
lt
h
-
r
elate
d
m
atter
s
,
h
as
em
er
g
ed
as
a
cr
itical
an
d
ch
allen
g
in
g
is
s
u
e.
I
n
ac
cu
r
ate
h
ea
lth
in
f
o
r
m
atio
n
en
co
m
p
ass
es
a
w
id
e
s
p
ec
tr
u
m
o
f
m
is
in
f
o
r
m
atio
n
,
r
an
g
in
g
f
r
o
m
e
x
ag
g
e
r
ated
claim
s
a
b
o
u
t
th
e
ef
f
icac
y
o
f
s
p
ec
if
ic
t
r
ea
tm
en
ts
to
co
m
p
letely
f
alse
d
at
a
r
elate
d
to
d
is
ea
s
es
an
d
p
u
b
lic
h
ea
lth
m
ea
s
u
r
es.
T
h
e
co
n
s
u
m
p
tio
n
o
f
d
is
in
f
o
r
m
a
tio
n
ca
n
lead
to
s
ig
n
if
ican
t
co
n
s
eq
u
en
ce
s
,
s
u
ch
as
m
ak
in
g
er
r
o
n
eo
u
s
h
ea
lth
ch
o
i
ce
s
,
en
d
o
r
s
in
g
h
az
ar
d
o
u
s
p
r
ac
tices,
an
d
er
o
d
in
g
co
n
f
id
en
c
e
in
cr
ed
ib
le
s
o
u
r
ce
s
[
1
]
.
T
h
e
r
is
e
o
f
s
o
cial
m
ed
ia
p
latf
o
r
m
s
,
o
n
lin
e
f
o
r
u
m
s
,
an
d
in
s
tan
t
m
ess
ag
in
g
ap
p
licatio
n
s
h
as
en
ab
led
th
e
s
wif
t
s
p
r
ea
d
o
f
m
is
lead
in
g
h
e
alth
in
f
o
r
m
atio
n
,
f
r
e
q
u
en
tly
o
u
tp
ac
in
g
th
e
ca
p
ac
ity
o
f
f
ac
t
-
ch
ec
k
er
s
an
d
h
ea
lth
au
th
o
r
ities
to
co
u
n
ter
f
alse
claim
s
.
T
h
e
co
r
o
n
av
ir
u
s
d
is
ea
s
e
(
C
OVI
D
-
19
)
p
an
d
em
ic
h
a
s
ex
ac
er
b
ated
th
e
s
itu
atio
n
b
y
f
ac
ilit
atin
g
th
e
s
wif
t
d
is
s
em
in
atio
n
o
f
m
is
in
f
o
r
m
atio
n
r
eg
ar
d
i
n
g
t
h
e
v
i
r
u
s
,
v
ac
cin
es,
an
d
p
u
b
lic
h
ea
lth
m
ea
s
u
r
es
ac
r
o
s
s
d
ig
ital
p
latf
o
r
m
s
.
T
h
is
h
as
led
to
ta
n
g
ib
le
c
o
n
s
eq
u
en
ce
s
,
s
u
ch
as
h
esit
an
cy
t
o
war
d
s
v
ac
cin
es
an
d
n
o
n
-
ad
h
er
en
ce
t
o
p
r
ev
e
n
tiv
e
s
tr
ateg
ies
[
2
]
,
[
3
]
.
I
n
r
esp
o
n
s
e
to
th
e
g
r
o
win
g
is
s
u
e
o
f
m
is
lead
in
g
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.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
3
7
3
-
382
374
h
ea
lth
in
f
o
r
m
atio
n
,
s
ch
o
lar
s
an
d
en
g
in
ee
r
s
h
av
e
b
ee
n
in
v
esti
g
atin
g
in
n
o
v
ativ
e
a
p
p
r
o
ac
h
es
th
at
lev
er
ag
e
ar
tific
ial
in
tellig
en
ce
(
AI
)
tec
h
n
iq
u
es.
Ma
ch
i
n
e
lear
n
i
n
g
(
M
L
)
an
d
d
ee
p
lear
n
in
g
(
DL
)
a
r
e
p
o
wer
f
u
l
to
o
ls
f
o
r
th
e
au
to
m
atic
d
etec
tio
n
o
f
f
r
a
u
d
u
len
t
h
ea
lth
-
r
elate
d
i
n
f
o
r
m
a
tio
n
.
Ma
ch
in
e
lea
r
n
in
g
alg
o
r
it
h
m
s
,
en
co
m
p
ass
in
g
tr
ad
itio
n
al
class
if
ier
s
an
d
en
s
em
b
le
m
eth
o
d
s
,
h
a
v
e
b
ee
n
em
p
lo
y
e
d
to
an
al
y
ze
th
e
t
ex
tu
al,
v
is
u
al,
an
d
co
n
tex
tu
al
f
ea
t
u
r
es
o
f
h
ea
lth
n
ews
ar
ticles
an
d
s
o
cial
m
ed
ia
co
n
ten
t.
At
th
e
s
am
e
ti
m
e,
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
,
k
n
o
wn
f
o
r
th
eir
ca
p
ac
ity
to
c
o
m
p
r
e
h
en
d
co
m
p
lex
p
atter
n
s
f
r
o
m
lar
g
e
d
at
asets
,
h
av
e
s
h
o
wn
p
r
o
m
is
e
in
id
e
n
tify
in
g
n
u
a
n
ce
d
s
ig
n
s
o
f
f
ak
e
n
ews
[
4
]
.
T
h
is
s
tu
d
y
aim
s
to
p
r
o
v
i
d
e
a
co
m
p
r
eh
en
s
iv
e
a
n
aly
s
is
o
f
th
e
tech
n
iq
u
es
in
ML
an
d
DL
th
at
ar
e
em
p
l
o
y
ed
f
o
r
t
h
e
d
etec
tio
n
o
f
f
ak
e
h
ea
lth
n
ews.
T
h
e
f
o
c
u
s
is
o
n
co
n
d
u
ctin
g
a
co
m
p
ar
ativ
e
an
a
ly
s
is
o
f
v
a
r
io
u
s
m
eth
o
d
o
lo
g
ie
s
,
p
er
f
o
r
m
an
ce
in
d
icato
r
s
,
a
n
d
ch
allen
g
es
r
elate
d
to
th
is
task
.
B
y
s
y
n
th
esizin
g
a
n
d
ex
am
i
n
in
g
c
u
r
r
e
n
t
r
esear
ch
,
we
s
ee
k
to
p
r
o
v
i
d
e
a
m
ea
n
in
g
f
u
l
co
n
tr
ib
u
tio
n
to
th
e
ad
v
an
ce
m
e
n
t
o
f
ar
tific
ial
in
tellig
en
ce
-
d
r
iv
e
n
s
o
lu
tio
n
s
th
at
co
u
ld
ef
f
ec
tiv
ely
ad
d
r
ess
m
is
in
f
o
r
m
atio
n
in
th
e
h
ea
lth
s
ec
to
r
[
5
]
.
T
h
is
co
m
p
ar
is
o
n
s
tu
d
y
aim
s
to
an
aly
ze
an
d
co
m
p
r
eh
en
d
th
e
b
en
e
f
its
an
d
d
r
awb
ac
k
s
o
f
ML
an
d
DL
tech
n
iq
u
es.
T
h
r
o
u
g
h
th
is
ap
p
r
o
ac
h
,
we
aim
to
ac
q
u
ir
e
s
ig
n
if
ican
t
in
s
ig
h
ts
th
at
ca
n
en
h
an
ce
th
e
p
r
ec
is
io
n
an
d
d
ep
e
n
d
ab
ilit
y
o
f
s
y
s
tem
s
d
esig
n
ed
to
d
etec
t f
al
s
e
h
ea
lth
n
ews.
I
n
th
e
f
o
llo
win
g
s
ec
tio
n
s
,
we
will
r
ev
iew
th
e
liter
atu
r
e
o
n
i
d
en
tify
in
g
f
ak
e
h
ea
lth
in
f
o
r
m
atio
n
.
T
h
is
will
in
clu
d
e
an
ex
a
m
in
atio
n
o
f
m
ac
h
in
e
lear
n
i
n
g
a
n
d
d
e
ep
lear
n
in
g
alg
o
r
ith
m
s
,
tr
ain
in
g
an
d
ev
alu
atio
n
d
atasets
,
f
ea
tu
r
e
g
en
e
r
atio
n
s
tr
ateg
ies,
an
d
m
o
d
el
p
er
f
o
r
m
an
ce
in
d
icato
r
s
.
W
e
will
also
ex
am
in
e
th
e
d
if
f
icu
lties
o
f
id
e
n
tify
in
g
b
o
g
u
s
h
ea
lth
in
f
o
r
m
atio
n
an
d
s
u
g
g
est
way
s
to
im
p
r
o
v
e
AI
-
d
r
iv
en
s
o
lu
tio
n
s
to
co
m
b
at
h
ea
lth
m
is
in
f
o
r
m
atio
n
[
6
]
.
C
o
m
p
u
ter
s
cien
tis
ts
,
in
f
o
r
m
atio
n
s
cien
tis
ts
,
an
d
p
u
b
lic
h
ea
lth
ex
p
er
ts
ar
e
in
ter
ested
in
id
en
tify
in
g
f
ak
e
h
ea
lth
n
ews.
T
h
is
s
ec
tio
n
s
u
m
m
ar
izes
ML
an
d
DL
s
tu
d
ies
o
n
f
alse
h
ea
lth
n
ews
d
etec
tio
n
.
Key
ap
p
r
o
ac
h
es,
d
atasets
,
f
ea
tu
r
e
en
g
in
ee
r
in
g
m
eth
o
d
s
,
an
d
ev
al
u
atio
n
m
e
asu
r
es
f
r
o
m
ea
r
lier
wo
r
k
s
ar
e
h
ig
h
lig
h
te
d
[
7
]
.
Sev
er
al
r
esear
ch
h
as u
s
ed
ty
p
ical
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
to
d
etec
t f
ak
e
h
ea
lth
n
ews.
Z
ih
an
et
a
l.
u
s
ed
lan
g
u
ag
e
f
ea
t
u
r
es
an
d
u
s
er
f
ac
to
r
s
to
ca
teg
o
r
ize
h
ea
lth
-
r
elate
d
twee
ts
as
r
ea
l
o
r
d
ec
ep
tiv
e
u
s
in
g
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
.
T
h
eir
ef
f
o
r
ts
id
en
tifie
d
d
ec
ep
tiv
e
s
m
o
k
in
g
ce
s
s
atio
n
twee
ts
with
p
o
ten
tial
r
esu
lts
[
8
]
.
C
asti
llo
et
a
l.
d
etec
ted
h
ea
lth
f
o
r
u
m
m
is
in
f
o
r
m
atio
n
u
s
in
g
n
ai
v
e
B
ay
es
clas
s
if
ier
s
.
T
ex
tu
al
attr
ib
u
tes
an
d
u
s
er
in
ter
ac
tio
n
p
atter
n
s
wer
e
u
s
ed
[
9
]
.
Alo
n
g
with
th
e
ab
o
v
e
m
e
th
o
d
s
,
f
alse
h
ea
lth
n
ews
d
etec
tio
n
h
as
u
s
ed
r
an
d
o
m
f
o
r
ests
an
d
g
r
a
d
ien
t
b
o
o
s
tin
g
.
Olu
s
o
la
et
a
l.
u
s
ed
a
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
to
ev
alu
ate
C
OVI
D
-
19
r
elate
d
n
ews
s
to
r
ies
as
tr
u
s
two
r
th
y
o
r
u
n
tr
u
s
two
r
th
y
b
ased
o
n
lan
g
u
ag
e
an
d
s
o
u
r
ce
r
eliab
ilit
y
.
E
n
s
em
b
le
lear
n
in
g
alg
o
r
ith
m
s
wer
e
ac
cu
r
ate
in
id
en
tify
in
g
d
u
b
io
u
s
n
ews
s
o
u
r
ce
s
,
r
ed
u
cin
g
d
is
in
f
o
r
m
atio
n
d
u
r
in
g
p
u
b
lic
h
ea
lth
cr
is
es
[
1
0
]
.
Dee
p
lear
n
in
g
alg
o
r
ith
m
s
ca
n
f
in
d
co
m
p
lex
p
atter
n
s
in
r
aw
d
ata,
wh
ich
m
ig
h
t
r
e
v
ea
l
f
ak
e
h
ea
lth
n
ews.
T
ex
t
ca
teg
o
r
izat
io
n
,
in
clu
d
in
g
f
ak
e
n
ews
d
etec
tio
n
,
is
a
co
m
m
o
n
u
s
e
o
f
c
o
n
v
o
lu
tio
n
al
n
e
u
r
al
n
etwo
r
k
s
(
C
NNs
)
.
W
an
g
et
a
l.
u
s
ed
a
C
NN
to
id
en
tify
h
ea
lth
-
r
elate
d
twee
ts
as
tr
u
s
two
r
th
y
o
r
u
n
tr
u
s
two
r
th
y
.
T
h
eir
r
esu
lts
s
h
o
wed
th
at
t
h
eir
s
tr
ateg
y
o
u
tp
er
f
o
r
m
e
d
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
[
1
1
]
.
R
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
s
(
R
NNs)
,
in
clu
d
in
g
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
an
d
g
ate
d
r
ec
u
r
r
en
t
u
n
it
(
GR
U)
,
h
av
e
b
ee
n
u
s
ed
t
o
p
r
ed
ict
s
eq
u
e
n
ce
s
an
d
d
etec
t
f
alse
h
ea
lth
n
ews.
C
h
en
et
a
l.
u
s
ed
tex
tu
al
an
d
co
n
tex
tu
al
d
ata
to
ca
teg
o
r
ize
h
ea
lth
ar
ticles
as
tr
u
s
t
wo
r
th
y
o
r
u
n
tr
u
s
two
r
th
y
u
s
in
g
an
L
S
T
M
-
b
ased
m
o
d
el.
T
h
eir
m
eth
o
d
id
e
n
tifie
d
c
o
u
n
t
er
f
eit
h
ea
lth
n
ews
s
to
r
ies
b
etter
th
an
m
ac
h
in
e
lear
n
in
g
m
et
h
o
d
s
,
s
h
o
win
g
th
at
d
ee
p
lear
n
i
n
g
ca
n
r
ec
o
g
n
ize
t
em
p
o
r
al
lin
k
ag
es
an
d
co
m
p
le
x
lin
g
u
is
tic
clu
es.
Mu
lti
-
d
atas
et
m
o
d
els
h
av
e
b
ee
n
tr
ain
ed
an
d
ev
alu
ate
d
to
i
d
en
t
if
y
b
o
g
u
s
h
ea
lth
n
ews.
T
h
e
d
atasets
in
clu
d
e
p
u
b
licly
a
v
ailab
le
co
llectio
n
s
lik
e
Hea
lth
Misin
f
o
an
d
p
r
o
p
r
ietar
y
d
atasets
b
ased
o
n
o
n
lin
e
f
o
r
u
m
an
d
s
o
cial
m
ed
ia
d
ata.
M
o
d
els
th
at
r
ec
o
g
n
ize
b
o
g
u
s
h
ea
lth
n
ews
ar
e
ev
alu
a
ted
u
s
in
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
I
n
th
ese
jo
b
s
,
elim
in
atin
g
f
alse
p
o
s
itiv
es
an
d
n
eg
ativ
es
m
u
s
t
b
e
b
alan
ce
d
[
1
2
]
.
I
d
en
tif
y
in
g
f
r
au
d
u
len
t
h
ea
lth
in
f
o
r
m
atio
n
h
as
im
p
r
o
v
ed
,
b
u
t
m
a
n
y
o
b
s
tacle
s
r
em
ain
.
T
h
e
g
r
o
wth
o
f
d
is
in
f
o
r
m
atio
n
ac
r
o
s
s
v
ar
io
u
s
p
latf
o
r
m
s
,
m
al
icio
u
s
ac
to
r
s
'
ev
er
-
ch
an
g
in
g
m
eth
o
d
s
,
an
d
th
e
la
ck
o
f
lab
eled
d
ata
f
o
r
ex
ac
t
d
etec
tio
n
m
o
d
els
ar
e
m
ajo
r
h
u
r
d
les
in
th
is
s
ec
to
r
.
Sch
o
lar
s
,
p
r
o
f
ess
io
n
als,
an
d
d
ec
is
io
n
-
m
ak
er
s
f
r
o
m
d
if
f
er
en
t
f
ield
s
m
u
s
t
c
o
llab
o
r
ate
to
s
o
l
v
e
th
ese
p
r
o
b
lem
s
.
Ad
d
itio
n
ally
,
b
r
ea
k
t
h
r
o
u
g
h
AI
-
p
o
wer
e
d
s
o
lu
tio
n
s
th
at
ca
n
ad
ap
t
to
ch
an
g
in
g
in
f
o
r
m
atio
n
en
v
ir
o
n
m
e
n
ts
an
d
s
to
p
th
e
s
p
r
ea
d
o
f
in
co
r
r
e
ct
h
ea
lth
in
f
o
r
m
atio
n
ar
e
n
ee
d
ed
.
T
h
e
f
o
llo
win
g
s
ec
tio
n
s
will
c
o
m
p
ar
e
ML
an
d
D
L
m
eth
o
d
s
f
o
r
d
etec
tin
g
b
o
g
u
s
h
ea
lth
n
ews
[
1
3
]
,
[
1
4
]
.
T
h
eir
s
tr
en
g
th
s
,
s
h
o
r
tco
m
in
g
s
,
an
d
p
er
f
o
r
m
a
n
ce
m
ea
s
u
r
es
will
b
e
an
aly
ze
d
u
s
i
n
g
s
tan
d
ar
d
d
atasets
.
W
e
will
also
ex
am
in
e
h
o
w
o
u
r
f
in
d
in
g
s
m
ay
af
f
ec
t
f
u
tu
r
e
h
ea
lth
s
ec
to
r
m
is
in
f
o
r
m
ati
o
n
s
tu
d
ies an
d
ap
p
licatio
n
s
.
2.
M
E
T
H
O
D
I
d
en
tify
in
g
f
alse
h
ea
lth
n
ews
ca
n
b
e
ac
h
iev
ed
th
r
o
u
g
h
m
ac
h
in
e
lear
n
in
g
b
y
em
p
lo
y
i
n
g
a
r
an
g
e
o
f
alg
o
r
ith
m
s
an
d
f
ea
t
u
r
e
en
g
i
n
e
er
in
g
m
eth
o
d
s
.
T
h
is
d
is
cu
s
s
io
n
f
o
cu
s
es
o
n
v
ar
i
o
u
s
p
er
f
o
r
m
a
n
ce
m
etr
ics,
f
ea
tu
r
e
en
g
in
ee
r
in
g
s
tr
ateg
ies,
an
d
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
ai
m
ed
at
id
en
tify
in
g
f
r
au
d
u
len
t
h
ea
lth
n
ews
ar
ticle
s
[
1
5
]
.
On
e
m
eth
o
d
to
d
etec
t
m
is
lead
in
g
h
ea
lth
in
f
o
r
m
ati
o
n
in
v
o
lv
es
th
e
ap
p
licatio
n
o
f
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
es,
n
aiv
e
b
ay
es,
d
ec
is
i
o
n
tr
ee
s
,
o
r
r
an
d
o
m
f
o
r
ests
.
Giv
en
its
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
in
h
ig
h
-
d
im
en
s
io
n
al
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
A
p
p
lica
tio
n
o
f d
ee
p
lea
r
n
in
g
a
n
d
ma
c
h
in
e
lea
r
n
in
g
tech
n
iq
u
es fo
r
…
(
R
a
vin
d
r
a
B
a
b
u
Ja
l
a
d
a
n
ki
)
375
f
ea
tu
r
e
s
p
ac
es,
SVM
h
as
b
ee
n
u
tili
ze
d
t
o
class
if
y
h
ea
lth
-
r
ela
ted
tex
t
b
y
tak
in
g
in
to
ac
co
u
n
t
lex
ical,
s
y
n
tactic,
an
d
s
em
an
tic
f
ac
to
r
s
.
Naiv
e
B
ay
es
clas
s
if
ier
s
d
em
o
n
s
tr
ate
an
im
p
r
ess
iv
e
ca
p
ab
ilit
y
to
d
if
f
er
en
tiate
b
etwe
en
au
th
en
tic
an
d
f
r
au
d
u
len
t
h
ea
l
th
r
ec
o
r
d
s
,
ev
e
n
with
m
in
im
al
tr
ain
in
g
d
ata,
h
ig
h
lig
h
tin
g
th
eir
ef
f
ec
tiv
en
ess
d
esp
ite
an
ap
p
ea
r
an
ce
o
f
s
im
p
licity
[
1
6
]
.
Dec
is
io
n
tr
ee
s
an
d
r
an
d
o
m
f
o
r
ests
ex
ce
l
at
m
an
ag
in
g
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
an
d
f
ea
t
u
r
e
in
t
er
ac
tio
n
s
,
en
ab
lin
g
th
em
t
o
id
en
tify
n
u
an
ce
d
s
ig
n
s
o
f
m
is
lead
in
g
h
ea
lth
in
f
o
r
m
atio
n
.
E
n
s
em
b
le
m
eth
o
d
s
lik
e
r
an
d
o
m
f
o
r
ests
im
p
r
o
v
e
g
e
n
er
aliza
tio
n
an
d
r
e
d
u
ce
o
v
er
f
itti
n
g
b
y
co
m
b
in
in
g
th
e
p
r
ed
ictio
n
s
o
f
m
u
ltip
le
b
ase
lear
n
er
s
[
1
7
]
.
Featu
r
e
en
g
in
ee
r
in
g
tr
a
n
s
f
o
r
m
s
r
aw
tex
t
in
to
s
ig
n
if
ican
t
r
ep
r
esen
tatio
n
s
f
o
r
class
if
icatio
n
,
h
elp
in
g
m
ac
h
in
e
lear
n
in
g
id
e
n
tify
b
o
g
u
s
h
ea
lth
n
ews.
T
er
m
f
r
eq
u
e
n
cy
-
in
v
er
s
e
d
o
cu
m
e
n
t
f
r
eq
u
en
c
y
(
TF
-
I
DF
)
weig
h
ts
,
wo
r
d
em
b
ed
d
in
g
s
,
b
ag
-
of
-
wo
r
d
s
r
ep
r
esen
tatio
n
s
,
an
d
s
y
n
tactic
o
r
s
em
an
tic
lin
g
u
is
tic
an
aly
s
is
f
ea
tu
r
es
a
r
e
u
s
ed
[
1
8
]
.
B
ag
-
of
-
wo
r
d
s
a
p
p
r
o
ac
h
es
ig
n
o
r
e
tex
t
s
tr
u
ctu
r
e
an
d
o
r
d
er
wh
en
esti
m
atin
g
wo
r
d
f
r
eq
u
e
n
cy
.
T
F
-
I
DF
weig
h
tin
g
h
ig
h
lig
h
ts
v
al
u
ab
le
tr
aits
wh
ile
d
o
wn
p
lay
in
g
co
m
m
o
n
p
h
r
as
es
b
y
b
o
o
s
tin
g
d
is
cr
im
in
ativ
e
ter
m
s
th
r
o
u
g
h
o
u
t
d
o
cu
m
en
ts
.
W
o
r
d
2
Vec
an
d
Glo
Ve
u
s
e
co
n
tin
u
o
u
s
v
ec
to
r
s
p
ac
e
to
d
en
s
ely
r
ep
r
esen
t
w
o
r
d
s
,
ca
p
tu
r
in
g
c
o
n
tex
tu
al
n
u
an
ce
s
an
d
s
em
an
tic
co
m
m
o
n
alities
[
1
9
]
.
Ma
ch
in
e
lear
n
in
g
alg
o
r
ith
m
s
lev
er
a
g
e
u
s
er
en
g
ag
e
m
en
t
in
d
icato
r
s
lik
e
lik
es,
s
h
ar
es,
an
d
co
m
m
en
ts
,
p
u
b
licatio
n
tim
elin
ess
,
an
d
s
o
u
r
ce
cr
e
d
ib
ilit
y
to
d
etec
t
f
ak
e
h
ea
lth
n
ew
s
.
T
h
ese
m
etad
ata
ch
ar
ac
ter
is
tics
im
p
r
o
v
e
class
if
icatio
n
m
o
d
el
d
is
cr
im
in
atio
n
u
s
in
g
co
n
tex
tu
al
in
f
o
r
m
atio
n
[
2
0
]
.
Ma
ch
in
e
lear
n
in
g
s
y
s
tem
s
th
at
r
ec
o
g
n
ize
b
o
g
u
s
h
ea
lth
n
ews
ar
e
ev
alu
ated
u
s
in
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
T
h
e
r
a
tio
o
f
co
r
r
ec
tly
ca
teg
o
r
ized
o
cc
u
r
r
e
n
ce
s
d
eter
m
in
es
m
o
d
el
ac
cu
r
ac
y
[
2
1
]
.
Pre
cisi
o
n
m
ea
s
u
r
es
th
e
p
er
ce
n
tag
e
o
f
r
ea
l
p
o
s
itiv
es
to
to
tal
p
o
s
itiv
es,
wh
ile
r
ec
all
m
ea
s
u
r
es
m
o
d
el
ac
cu
r
ac
y
.
I
n
im
b
alan
ce
d
class
d
is
tr
ib
u
tio
n
s
,
th
e
F1
-
s
co
r
e
—
th
e
h
ar
m
o
n
i
c
m
ea
n
o
f
r
ec
all
an
d
p
r
ec
is
io
n
—
im
p
r
o
v
es m
o
d
el
p
er
f
o
r
m
an
ce
[
2
2
]
.
A
r
ea
u
n
d
e
r
th
e
r
ec
eiv
er
o
p
er
atin
g
ch
ar
ac
ter
is
tic
cu
r
v
e
(
AUC
-
R
OC
)
an
d
a
r
ea
u
n
d
er
th
e
p
r
ec
is
io
n
-
r
ec
all
cu
r
v
e
(
AUC
-
PR
)
ar
e
u
s
ed
to
ev
alu
ate
m
ac
h
in
e
lear
n
in
g
m
o
d
els'
d
is
cr
im
in
ativ
e
ca
p
ab
ilit
y
an
d
r
o
b
u
s
tn
ess
at
d
if
f
er
en
t
class
if
icatio
n
th
r
esh
o
ld
s
[
2
3
]
.
Ma
ch
in
e
lear
n
in
g
ev
alu
ates
h
ea
lth
n
ews
s
to
r
ies
u
s
in
g
alg
o
r
ith
m
s
,
f
ea
tu
r
e
e
n
g
in
ee
r
i
n
g
,
an
d
p
er
f
o
r
m
an
ce
in
d
icato
r
s
.
T
h
ese
alg
o
r
ith
m
s
ar
e
ef
f
e
ctiv
e,
b
u
t
th
ey
m
ay
s
tr
u
g
g
le
to
r
ec
o
g
n
ize
m
in
o
r
l
an
g
u
ag
e
v
ar
iatio
n
s
an
d
ad
a
p
t
to
ev
il
p
eo
p
le'
s
d
ec
ep
tio
n
.
T
h
e
p
r
o
s
an
d
co
n
s
o
f
u
s
in
g
m
ac
h
i
n
e
lear
n
in
g
an
d
d
ee
p
lear
n
in
g
to
id
en
tif
y
f
a
k
e
h
ea
lth
n
ews
will
b
e
e
x
am
in
ed
[
2
4
]
.
Dee
p
lear
n
in
g
s
y
s
tem
s
ca
n
au
to
m
atica
lly
u
n
d
er
s
tan
d
co
m
p
le
x
p
atter
n
s
in
s
eq
u
en
tial,
v
is
u
al,
an
d
tex
tu
al
d
ata,
id
en
tify
in
g
b
o
g
u
s
h
ea
lth
n
ews.
T
ec
h
n
i
q
u
es,
m
o
d
el
d
esig
n
s
,
an
d
p
e
r
f
o
r
m
an
ce
m
ea
s
u
r
es
f
o
r
r
ec
o
g
n
izin
g
f
ak
e
h
ea
lth
in
f
o
r
m
atio
n
ar
e
c
o
v
er
e
d
h
e
r
e
.
Ad
v
an
ce
d
tech
n
i
q
u
es
u
s
e
s
eq
u
en
tial
o
r
tex
tu
al
n
eu
r
al
n
etwo
r
k
d
esig
n
s
to
r
ec
o
g
n
ize
d
ec
ep
tiv
e
h
ea
lth
i
n
f
o
r
m
atio
n
.
T
e
x
t
ca
teg
o
r
izatio
n
o
f
ten
u
s
es
C
NNs.
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
b
u
ild
h
ier
ar
c
h
ical
tex
t
r
ep
r
e
s
en
tatio
n
s
u
s
in
g
co
n
v
o
l
u
tio
n
al
an
d
p
o
o
lin
g
lay
er
s
.
C
NN
-
b
ased
m
o
d
els
ca
n
ca
p
tu
r
e
l
o
ca
l
an
d
g
lo
b
al
tex
t
t
r
en
d
s
u
s
in
g
wo
r
d
e
m
b
ed
d
in
g
s
as
d
en
s
e
v
ec
to
r
s
[
2
5
]
.
Fig
u
r
e
1
s
h
o
ws
h
o
w
d
ee
p
lear
n
in
g
a
n
d
m
ac
h
in
e
lear
n
in
g
ar
e
u
s
ed
to
c
r
ea
te
m
o
d
els
u
s
in
g
m
ater
ial
an
d
r
ec
o
m
m
en
d
ed
attr
ib
u
tes.
Fals
e
n
ews
m
o
d
els
ar
e
p
r
o
d
u
ce
d
o
n
ly
f
r
o
m
co
n
ten
t,
wh
ile
f
e
atu
r
e
-
b
ased
m
o
d
els
ar
e
b
u
ilt
u
s
in
g
co
n
ten
t
a
n
d
r
ea
d
ab
ilit
y
f
ea
tu
r
es.
W
e
co
m
p
ar
e
th
eir
p
er
f
o
r
m
a
n
ce
.
L
STM
an
d
GR
U
ex
ce
l
at
s
eq
u
en
tial
d
ata
m
o
d
elin
g
a
n
d
lo
n
g
-
r
an
g
e
r
elatio
n
s
h
ip
s
.
T
r
ad
itio
n
al
R
NN
s
s
tr
u
g
g
le
with
v
an
is
h
in
g
g
r
a
d
i
en
ts
,
wh
er
ea
s
L
STM
an
d
GR
U
v
ar
iatio
n
s
p
r
eser
v
e
te
x
t
s
e
q
u
en
ce
co
n
tex
t
an
d
tem
p
o
r
al
d
y
n
am
ics
[
2
6
]
.
T
h
e
co
n
tex
t
an
d
wo
r
d
o
r
d
e
r
o
f
o
n
lin
e
d
is
cu
s
s
io
n
s
,
n
ews
s
to
r
ies,
an
d
s
o
cial
m
ed
ia
u
p
d
ates
g
r
ea
tly
af
f
ec
t
b
eliev
a
b
ilit
y
.
T
h
ese
m
o
d
els
h
el
p
ev
alu
ate
s
u
ch
co
n
ten
t.
T
r
a
n
s
f
o
r
m
e
r
-
b
ased
m
o
d
els
lik
e
b
id
ir
ec
tio
n
al
en
c
o
d
er
r
ep
r
esen
tatio
n
s
f
r
o
m
tr
an
s
f
o
r
m
er
s
(
B
E
R
T
)
an
d
its
v
ar
ian
ts
h
av
e
id
e
n
tifie
d
f
ak
e
h
ea
lth
n
ews.
B
E
R
T
m
o
d
els
u
s
e
s
elf
-
atten
tio
n
p
r
o
ce
s
s
es
to
g
at
h
er
b
id
ir
ec
tio
n
al
co
n
tex
tu
al
in
f
o
r
m
atio
n
f
r
o
m
in
p
u
t
s
eq
u
en
ce
s
to
u
n
d
er
s
tan
d
c
o
m
p
licated
tex
tu
al
r
ep
r
esen
tat
io
n
s
with
o
u
t
s
eq
u
en
tial
p
r
o
c
ess
in
g
.
Pre
-
tr
ain
ed
B
E
R
T
em
b
ed
d
in
g
s
f
in
e
-
tu
n
ed
u
s
in
g
d
o
m
ain
-
s
p
ec
if
ic
d
ataset
s
p
er
f
o
r
m
well
at
id
en
tify
in
g
b
o
g
u
s
h
ea
lth
n
ews.
Dee
p
lear
n
in
g
alg
o
r
ith
m
s
em
p
h
asize
lin
g
u
is
tic
n
u
a
n
ce
s
,
c
o
n
tex
tu
al
s
ig
n
als,
a
n
d
s
em
an
t
ic
lin
k
s
to
id
e
n
tify
d
ec
ep
tiv
e
h
ea
lth
n
ews.
W
o
r
d
2
Vec
,
Glo
Ve,
an
d
Fas
tTe
x
t
ca
p
tu
r
e
co
n
tex
tu
al
n
u
an
ce
s
a
n
d
s
em
an
tic
s
im
ilar
ities
b
y
r
ep
r
esen
tin
g
wo
r
d
s
as
d
en
s
e
v
ec
to
r
s
u
s
in
g
co
n
tin
u
o
u
s
v
ec
to
r
s
p
ac
es.
Dy
n
am
ic
r
ele
v
an
ce
f
o
cu
s
in
g
u
s
es
wo
r
d
em
b
ed
d
in
g
s
an
d
atten
tio
n
m
ec
h
a
n
is
m
s
to
r
ed
u
ce
ir
r
elev
an
t
d
ata
an
d
em
p
h
a
s
ize
r
elev
an
t
in
p
u
t
s
eq
u
en
ce
s
in
d
ee
p
lear
n
in
g
m
o
d
els.
Giv
in
g
in
f
o
r
m
ativ
e
wo
r
d
s
an
d
p
h
r
ases
m
o
r
e
weig
h
t
h
elp
s
th
e
co
m
p
u
ter
d
is
ce
r
n
f
ac
tu
al
f
r
o
m
f
alse
co
n
ten
t.
Dee
p
lear
n
in
g
m
o
d
els
th
at
r
ec
o
g
n
ize
b
o
g
u
s
h
ea
lth
n
ews
ar
e
ass
es
s
ed
u
s
in
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e.
AUC
-
R
OC
an
d
AUC
-
PR
ar
e
ad
d
itio
n
al
m
ea
s
u
r
es
f
o
r
ass
ess
in
g
d
ee
p
lear
n
in
g
m
o
d
els'
d
is
cr
i
m
in
ativ
e
p
o
wer
an
d
r
o
b
u
s
tn
ess
ac
r
o
s
s
clas
s
if
icatio
n
cr
it
er
ia.
Dee
p
lear
n
in
g
m
o
d
els
ar
e
tr
ain
ed
o
n
lar
g
e
l
ab
eled
d
atasets
an
d
ev
alu
ated
o
n
d
is
tin
ct
test
s
et
s
to
en
s
u
r
e
g
en
er
aliza
tio
n
.
B
y
d
iv
id
in
g
d
ata
i
n
to
s
m
aller
s
et
s
,
cr
o
s
s
-
v
alid
atio
n
ca
n
c
h
ec
k
m
o
d
el
s
tab
ilit
y
an
d
v
ar
iab
ili
ty
.
DL
-
b
ased
f
alse
h
ea
lth
n
ews
d
etec
tio
n
s
y
s
tem
s
ca
n
b
e
ass
ess
ed
q
u
alitativ
ely
f
o
r
e
r
r
o
r
an
aly
s
is
an
d
m
o
d
el
i
n
ter
p
r
etab
ilit
y
[
2
7
]
.
Dee
p
lear
n
in
g
u
s
es
tr
an
s
f
o
r
m
er
s
,
R
NNs,
an
d
C
NNs
to
d
etec
t
h
ea
lth
n
ews
m
is
in
f
o
r
m
atio
n
in
tex
t
u
al
o
r
s
eq
u
en
tial
d
ata.
T
h
ese
m
o
d
els
g
en
er
ate
co
m
p
lex
r
e
p
r
esen
tatio
n
s
o
f
in
co
m
i
n
g
in
f
o
r
m
atio
n
v
ia
ass
im
ilatio
n
o
f
s
em
an
tic
lin
k
s
an
d
c
o
n
tex
tu
al
cu
es
o
f
d
is
h
o
n
esty
.
T
r
a
d
itio
n
a
l
m
etr
ics
an
d
q
u
alitativ
e
ass
es
s
m
en
ts
ar
e
u
s
ed
to
ev
alu
ate
d
ee
p
lear
n
in
g
m
o
d
els
.
Fo
llo
win
g
s
ec
tio
n
s
will
ex
am
in
e
th
e
p
r
o
s
an
d
co
n
s
o
f
u
s
in
g
d
ee
p
lear
n
in
g
an
d
m
ac
h
in
e
lear
n
in
g
to
d
etec
t f
ak
e
h
ea
lth
n
ews.
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.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
3
7
3
-
382
376
Fig
u
r
e
1
.
Me
th
o
d
o
lo
g
y
p
r
o
p
o
s
ed
2
.
1
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
A
co
m
p
ar
is
o
n
o
f
m
ac
h
i
n
e
lea
r
n
in
g
a
n
d
d
ee
p
lear
n
in
g
m
eth
o
d
s
f
o
r
id
e
n
tify
in
g
f
alse
h
ea
lt
h
n
ews
is
p
r
esen
ted
,
in
cl
u
d
in
g
an
an
aly
s
is
o
f
th
eir
p
er
f
o
r
m
a
n
ce
m
ea
s
u
r
es
an
d
ass
o
ciate
d
c
h
allen
g
es.
An
an
al
y
s
is
o
f
th
e
ad
v
an
tag
es
an
d
lim
itatio
n
s
o
f
b
o
th
tech
n
iq
u
es
is
co
n
d
u
cted
to
ass
ess
th
eir
ef
f
ec
tiv
en
ess
i
n
m
itig
atin
g
h
ea
lth
m
is
in
f
o
r
m
atio
n
.
I
n
m
ac
h
i
n
e
lear
n
in
g
tec
h
n
iq
u
es,
h
an
d
cr
af
ted
ch
ar
ac
ter
is
tics
an
d
class
ical
alg
o
r
ith
m
s
a
r
e
em
p
lo
y
ed
to
class
if
y
h
ea
lth
co
n
ten
t
as
eith
er
au
th
en
tic
o
r
f
alse.
T
h
ese
m
eth
o
d
s
r
eq
u
ir
e
s
ig
n
if
ican
t
f
ea
tu
r
e
en
g
in
ee
r
in
g
an
d
d
o
m
ain
k
n
o
wled
g
e
to
d
er
iv
e
v
alu
a
b
le
f
e
atu
r
es
f
r
o
m
u
n
p
r
o
ce
s
s
ed
tex
t
u
al
d
ata.
Ma
ch
in
e
lear
n
in
g
m
o
d
els
h
av
e
th
e
p
o
t
en
tial
to
r
iv
al
well
-
co
n
s
tr
u
cte
d
f
ea
tu
r
es
an
d
en
s
em
b
le
m
eth
o
d
s
;
h
o
we
v
er
,
th
ey
o
f
ten
f
ac
e
c
h
allen
g
es
in
i
d
en
ti
f
y
in
g
in
t
r
icate
p
atter
n
s
an
d
ad
v
an
ce
d
lin
g
u
is
tic
cu
es
ass
o
ciate
d
with
m
is
lead
in
g
h
ea
lth
n
ews
[
2
8
]
.
R
ath
er
t
h
an
r
ely
in
g
o
n
f
ea
tu
r
e
en
g
in
e
er
in
g
,
d
ee
p
lear
n
in
g
tech
n
iq
u
es
em
p
lo
y
n
e
u
r
al
n
etwo
r
k
ar
c
h
itectu
r
es
to
a
u
to
n
o
m
o
u
s
ly
lear
n
r
e
p
r
esen
tatio
n
s
o
f
in
p
u
t
d
ata.
Dee
p
lear
n
in
g
m
o
d
els,
p
ar
ticu
lar
ly
th
o
s
e
b
ased
o
n
tr
an
s
f
o
r
m
er
ar
ch
itectu
r
es
s
u
ch
as
B
E
R
T
,
ar
e
ca
p
ab
le
o
f
ca
p
tu
r
in
g
in
tr
icate
s
em
an
tic
co
n
n
ec
tio
n
s
an
d
c
o
n
tex
tu
al
d
etails
f
r
o
m
tex
tu
al
d
ata,
th
er
eb
y
en
h
a
n
cin
g
th
e
d
etec
tio
n
o
f
f
alse
h
ea
lth
n
ews.
Dee
p
lear
n
in
g
m
o
d
els
o
f
ten
r
eq
u
ir
e
ex
te
n
s
iv
e
lab
eled
d
atasets
an
d
s
ig
n
if
ican
t
co
m
p
u
tatio
n
al
p
o
wer
f
o
r
tr
ain
in
g
,
w
h
ich
ca
n
lim
it
th
eir
u
s
e
in
en
v
ir
o
n
m
e
n
ts
with
lim
ited
r
eso
u
r
ce
s
.
Me
tr
ics
s
u
ch
as
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e
ar
e
em
p
l
o
y
ed
to
ass
ess
m
ac
h
in
e
lear
n
in
g
an
d
d
ee
p
lear
n
in
g
m
o
d
els
in
th
e
co
n
tex
t
o
f
i
d
en
tify
in
g
f
ak
e
h
ea
lth
n
ews.
W
ith
ca
r
e
f
u
lly
c
r
af
ted
f
ea
tu
r
es
an
d
f
i
n
ely
tu
n
e
d
h
y
p
er
p
a
r
am
eter
s
,
m
ac
h
in
e
lear
n
in
g
m
o
d
els
ca
n
p
er
f
o
r
m
c
o
m
p
etitiv
ely
o
n
b
e
n
ch
m
ar
k
d
atasets
.
T
h
er
e
is
a
p
o
s
s
ib
ilit
y
th
at
th
ey
will n
o
t b
e
ab
le
to
g
en
er
alize
t
o
n
ew
in
f
o
r
m
atio
n
o
r
ad
ju
s
t to
th
e
d
ec
ep
tiv
e
s
tr
ateg
ies em
p
lo
y
ed
b
y
ad
v
e
r
s
ar
ial
en
titi
es.
Dee
p
lear
n
in
g
m
o
d
e
ls
h
av
e
th
e
ca
p
a
b
ilit
y
to
id
e
n
tify
in
tr
icate
p
atter
n
s
with
in
u
n
p
r
o
ce
s
s
ed
d
ata,
s
u
r
p
ass
in
g
tr
ad
itio
n
al
m
ac
h
i
n
e
lear
n
in
g
ap
p
r
o
ac
h
es
in
t
h
e
d
etec
tio
n
o
f
f
alse
h
ea
lth
n
ews.
T
r
an
s
f
o
r
m
e
r
ar
ch
itectu
r
es lev
er
ag
e
p
r
e
-
tr
ai
n
ed
em
b
ed
d
in
g
s
an
d
s
elf
-
atten
tio
n
m
ec
h
an
is
m
s
to
id
en
tify
s
u
b
tle
lin
g
u
is
tic
cu
es
ass
o
ciate
d
with
f
r
au
d
u
len
t
o
r
d
ec
ep
tiv
e
co
n
te
n
t,
d
em
o
n
s
tr
atin
g
s
tr
o
n
g
p
er
f
o
r
m
an
ce
o
n
b
e
n
ch
m
ar
k
d
atasets
.
Dee
p
lear
n
in
g
m
o
d
els
ca
n
e
x
h
ib
it
o
v
e
r
f
itti
n
g
ten
d
en
cies,
p
ar
ticu
lar
ly
w
h
en
tr
ain
e
d
o
n
lim
ited
d
atasets
,
n
ec
ess
itatin
g
f
in
e
-
tu
n
in
g
with
d
o
m
ain
-
s
p
ec
if
ic
d
ata
to
ac
h
ie
v
e
o
p
tim
al
p
er
f
o
r
m
a
n
ce
.
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
A
p
p
lica
tio
n
o
f d
ee
p
lea
r
n
in
g
a
n
d
ma
c
h
in
e
lea
r
n
in
g
tech
n
iq
u
es fo
r
…
(
R
a
vin
d
r
a
B
a
b
u
Ja
l
a
d
a
n
ki
)
377
3.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
T
h
e
ac
ce
s
s
ib
ilit
y
o
f
GPUs
f
o
r
in
ten
s
iv
e
co
m
p
u
tatio
n
s
en
a
b
les
co
n
d
itio
n
-
b
ased
m
ai
n
ten
an
ce
(
C
B
M)
an
d
f
ailu
r
e
-
b
ased
m
ai
n
ten
an
c
e
(
FB
M)
to
im
p
lem
en
t
m
ac
h
in
e
lear
n
in
g
an
d
d
ee
p
lear
n
in
g
tech
n
iq
u
es
with
i
n
th
e
Go
o
g
le
C
o
lab
f
r
am
ewo
r
k
.
T
h
e
co
d
e
was
d
e
v
elo
p
e
d
u
s
in
g
s
ev
er
al
Py
th
o
n
p
ac
k
ag
es,
i
n
clu
d
in
g
Ma
tp
lo
tlib
,
Scik
it
-
lear
n
,
Nu
m
Py
,
p
an
d
as,
an
d
Ker
as.
T
h
e
d
ee
p
lear
n
in
g
m
o
d
els
em
p
lo
y
ed
a
1
0
0
-
d
im
en
s
io
n
al
Glo
Ve
wo
r
d
em
b
ed
d
i
n
g
.
A
s
eq
u
e
n
tial
m
o
d
el
f
ea
tu
r
i
n
g
m
u
ltip
le
lay
er
s
o
f
n
eu
r
o
n
s
,
a
v
ailab
le
in
K
er
as,
was
u
tili
ze
d
to
b
u
ild
th
e
m
o
d
els
th
at
d
ep
e
n
d
o
n
d
ee
p
lear
n
i
n
g
.
T
o
e
v
alu
ate
th
e
p
r
ec
is
io
n
o
f
f
alse
n
ews
c
lass
if
icatio
n
,
C
B
M
em
p
lo
y
ed
f
iv
e
m
ac
h
i
n
e
lear
n
in
g
alg
o
r
ith
m
s
:
d
ec
is
io
n
tr
ee
,
r
an
d
o
m
f
o
r
est,
s
u
p
p
o
r
t
v
e
cto
r
m
ac
h
in
e
,
A
d
aBo
o
s
t
-
d
ec
is
io
n
tr
ee
,
an
d
Ad
aBo
o
s
t
-
r
an
d
o
m
f
o
r
est
.
T
h
e
r
esu
lts
ar
e
illu
s
tr
ated
in
Fig
u
r
e
2
.
W
e
co
n
d
u
cted
a
n
an
aly
s
is
o
f
th
e
p
er
f
o
r
m
an
ce
s
o
f
f
iv
e
m
ac
h
in
e
lear
n
in
g
alg
o
r
it
h
m
s
u
s
in
g
FB
M.
Fig
u
r
e
3
p
r
esen
ts
th
e
r
esu
lts
,
in
co
r
p
o
r
atin
g
th
e
r
ea
d
ab
ilit
y
f
ea
tu
r
es
in
c
o
n
ju
n
ctio
n
with
th
e
co
n
ten
t.
T
h
e
p
e
r
f
o
r
m
an
ce
s
o
f
C
NN
-
L
STM
an
d
C
NN
-
B
iL
STM
wer
e
an
aly
ze
d
f
o
r
b
o
th
th
e
C
B
M
an
d
th
e
p
r
o
p
o
s
ed
FB
M.
T
h
e
m
ater
ials
a
r
e
an
aly
ze
d
t
h
r
o
u
g
h
a
s
o
p
h
is
ticated
m
eth
o
d
o
lo
g
y
f
o
r
th
e
FB
M,
u
tili
zin
g
s
t
ate
-
of
-
th
e
-
a
r
t
tech
n
iq
u
es
in
c
lu
d
in
g
th
e
Glo
Ve
e
m
b
ed
d
in
g
ap
p
r
o
ac
h
,
SMOG
s
co
r
e,
an
d
T
T
R
.
T
h
ese
tech
n
iq
u
es
ar
e
u
tili
ze
d
to
p
r
o
d
u
c
e
ex
ac
t
an
d
r
eliab
le
in
p
u
t
v
ec
to
r
s
.
Fig
u
r
es
4
an
d
5
illu
s
tr
ate
a
c
o
m
p
ar
ativ
e
an
al
y
s
is
o
f
th
e
p
er
f
o
r
m
a
n
ce
b
etwe
en
C
NN
-
L
STM
an
d
C
NN
-
B
iL
STM
f
o
r
b
o
th
C
B
M
an
d
FB
M.
T
h
e
f
ig
u
r
es a
r
e
o
r
g
an
ized
ac
co
r
d
in
g
to
th
eir
p
e
r
f
o
r
m
an
ce
m
etr
ics.
Fig
u
r
e
2
.
An
ev
alu
atio
n
o
f
t
h
e
ef
f
icac
y
o
f
co
n
v
en
tio
n
al
m
ac
h
in
e
lear
n
in
g
m
o
d
els in
co
m
p
ar
is
o
n
to
co
n
ten
t
-
b
ased
m
o
d
els
Fig
u
r
e
3
.
A
c
o
m
p
ar
is
o
n
o
f
h
o
w
well
tr
ad
itio
n
al
m
ac
h
in
e
lea
r
n
in
g
m
o
d
els wo
r
k
in
th
e
a
r
ea
o
f
f
ea
tu
r
e
-
b
ased
lear
n
in
g
T
h
e
F1
-
s
co
r
e
s
er
v
es
as
an
im
p
o
r
tan
t
m
etr
ic
f
o
r
ass
ess
in
g
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el,
as
it
tak
es
in
to
ac
co
u
n
t
b
o
t
h
Pre
cisi
o
n
a
n
d
R
ec
all.
T
h
e
m
o
d
el'
s
ca
p
ab
ilit
y
to
p
r
ed
ict
a
n
d
id
e
n
tify
g
en
u
in
e
in
s
tan
ce
s
is
cr
u
cial
f
o
r
r
ec
o
g
n
izin
g
f
alse n
ews.
T
h
e
to
p
-
p
er
f
o
r
m
in
g
m
o
d
el
in
ea
ch
ca
teg
o
r
y
was
id
e
n
tif
ied
ac
co
r
d
in
g
to
its
F1
-
s
co
r
e.
Fig
u
r
e
6
p
r
esen
ts
th
e
to
p
m
o
d
el
in
ea
ch
ca
teg
o
r
y
,
ac
co
m
p
an
ied
b
y
its
p
e
r
f
o
r
m
an
ce
m
etr
ics.
T
h
e
ex
p
er
im
en
ts
in
d
icate
th
at
f
ea
tu
r
e
-
b
ased
m
o
d
els
d
em
o
n
s
tr
ate
s
u
p
er
io
r
p
e
r
f
o
r
m
an
ce
co
m
p
ar
ed
to
tr
ad
itio
n
al
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.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
3
7
3
-
382
378
m
o
d
els.
T
h
e
f
i
n
d
in
g
s
in
d
icate
th
at
Ad
aBo
o
s
t
-
R
F
s
tan
d
s
o
u
t
as
th
e
lead
in
g
p
er
f
o
r
m
er
am
o
n
g
th
e
c
o
n
ten
t
an
d
f
ea
tu
r
e
b
ased
m
o
d
els
.
Up
o
n
ex
am
in
atio
n
o
f
b
o
th
g
r
o
u
p
s
,
i
t
is
clea
r
th
at
Ad
aBo
o
s
t
-
R
F
attain
ed
th
e
h
ig
h
est
F1
-
s
co
r
e.
I
n
th
e
co
m
p
ar
is
o
n
b
etwe
en
Ad
aBo
o
s
t
-
R
F
an
d
f
ea
tu
r
e
b
as
ed
Ad
aBo
o
s
t
-
R
F,
it
is
n
o
tab
le
th
at
th
e
f
o
r
m
er
r
ea
ch
es
an
F1
-
s
co
r
e
o
f
9
8
.
5
%
in
C
B
M,
wh
er
ea
s
th
e
latter
s
u
r
p
ass
es
th
is
with
a
s
c
o
r
e
o
f
9
8
.
9
%.
T
h
e
Ad
aBo
o
s
t
-
r
an
d
o
m
f
o
r
est
m
o
d
el,
well
-
r
esp
ec
ted
in
its
d
o
m
ain
,
is
af
f
iliated
with
th
e
FB
M
g
r
o
u
p
an
d
is
f
r
eq
u
e
n
tly
em
p
lo
y
ed
f
o
r
th
e
class
if
icatio
n
o
f
f
alse n
ews.
Fig
u
r
e
4
.
T
h
e
p
r
o
p
o
s
ed
d
ee
p
l
ea
r
n
in
g
m
o
d
els'
p
er
f
o
r
m
a
n
ce
i
s
co
m
p
ar
ed
u
n
d
e
r
th
e
co
n
ten
t
-
b
ased
ca
teg
o
r
y
Fig
u
r
e
5
.
Featu
r
e
-
b
ased
p
e
r
f
o
r
m
an
ce
co
m
p
ar
is
o
n
o
f
s
u
g
g
est
ed
d
ee
p
lear
n
in
g
m
o
d
els
Fig
u
r
e
6
.
T
h
e
to
p
m
o
d
els in
ea
ch
ca
teg
o
r
y
ar
e
c
o
m
p
ar
e
d
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
A
p
p
lica
tio
n
o
f d
ee
p
lea
r
n
in
g
a
n
d
ma
c
h
in
e
lea
r
n
in
g
tech
n
iq
u
es fo
r
…
(
R
a
vin
d
r
a
B
a
b
u
Ja
l
a
d
a
n
ki
)
379
4.
CO
NCLU
SI
O
N
T
h
e
s
p
r
e
ad
o
f
in
ac
cu
r
at
e
h
ea
lth
in
f
o
r
m
a
tio
n
o
cc
u
r
s
s
wif
t
l
y
o
n
s
o
ci
al
m
ed
i
a
an
d
o
n
l
in
e
p
la
tf
o
r
m
s
,
p
r
e
s
en
tin
g
a
s
ig
n
if
ic
an
t
r
is
k
to
p
u
b
l
ic
h
e
al
th
.
E
x
p
e
r
t
s
h
a
v
e
u
ti
li
ze
d
m
ac
h
in
e
l
ea
r
n
in
g
an
d
d
e
ep
le
ar
n
i
n
g
tech
n
iq
u
e
s
to
cr
e
at
e
au
to
m
ated
s
y
s
te
m
s
ca
p
ab
l
e
o
f
i
d
en
t
if
y
in
g
an
d
ad
d
r
es
s
in
g
m
i
s
l
ea
d
in
g
h
e
al
th
in
f
o
r
m
at
io
n
.
T
h
i
s
in
v
es
t
ig
a
t
io
n
ex
am
in
e
s
th
e
ap
p
r
o
ac
h
es
,
o
b
s
t
ac
le
s
,
an
d
p
r
o
s
p
ec
t
iv
e
co
n
c
ep
t
s
f
o
r
id
en
tif
y
in
g
f
r
au
d
u
len
t
h
ea
lth
in
f
o
r
m
at
io
n
.
I
n
r
e
s
o
u
r
ce
-
co
n
s
t
r
a
in
ed
en
v
i
r
o
n
m
en
t
s
,
it
i
s
p
o
s
s
i
b
l
e
to
ac
h
iev
e
in
t
er
p
r
e
ta
b
l
e
m
ac
h
in
e
le
ar
n
in
g
s
o
lu
tio
n
s
b
y
em
p
l
o
y
in
g
tr
a
d
it
io
n
a
l
m
e
th
o
d
o
l
o
g
i
es
an
d
h
an
d
cr
af
t
ed
f
ea
tu
r
e
s
.
T
h
e
s
e
m
eth
o
d
s
m
ig
h
t
f
a
ce
ch
al
le
n
g
e
s
in
id
en
t
if
y
i
n
g
co
m
p
lex
p
at
te
r
n
s
an
d
n
u
an
ce
d
lin
g
u
i
s
t
ic
s
ig
n
a
l
s
as
s
o
ci
at
ed
wi
th
d
ec
ep
t
iv
e
h
e
al
th
n
ew
s
.
No
n
eth
el
e
s
s
,
ad
v
an
ce
d
m
e
th
o
d
o
lo
g
ie
s
li
k
e
co
n
v
o
lu
t
io
n
al
n
eu
r
al
n
et
wo
r
k
s
,
r
ec
u
r
r
en
t
n
eu
r
al
n
e
two
r
k
s
,
an
d
tr
an
s
f
o
r
m
er
-
b
a
s
e
d
m
o
d
el
s
d
em
o
n
s
tr
a
te
e
x
ce
p
t
io
n
a
l
ca
p
ab
il
ity
in
u
n
co
v
er
in
g
s
u
b
t
le
s
em
a
n
t
ic
r
e
la
tio
n
s
h
ip
s
an
d
co
n
t
ex
t
u
al
d
e
t
ai
ls
f
r
o
m
r
aw
t
ex
tu
al
d
a
ta.
D
e
ep
lear
n
in
g
m
o
d
el
s
d
em
o
n
s
t
r
at
e
co
n
s
id
er
ab
l
e
ef
f
ec
t
iv
e
n
e
s
s
;
h
o
wev
er
,
t
h
e
ir
ap
p
li
ca
tio
n
i
s
o
f
t
en
l
im
i
te
d
b
y
t
h
e
r
eq
u
ir
em
en
t
f
o
r
lar
g
e
lab
el
ed
d
at
a
s
e
t
s
an
d
s
u
b
s
tan
ti
al
co
m
p
u
t
at
io
n
a
l
r
e
s
o
u
r
ce
s
d
u
r
in
g
th
e
tr
a
in
in
g
p
r
o
ce
s
s
.
R
ec
o
g
n
i
zin
g
m
i
s
l
ea
d
in
g
h
e
al
th
in
f
o
r
m
a
t
i
o
n
m
o
v
in
g
f
o
r
wa
r
d
n
ec
e
s
s
it
at
es
co
o
p
er
at
io
n
a
m
o
n
g
v
ar
io
u
s
f
ie
ld
s
,
th
e
ap
p
l
ic
at
io
n
o
f
cu
t
tin
g
-
ed
g
e
r
e
s
e
ar
ch
t
ec
h
n
iq
u
es
,
an
d
th
e
e
s
t
ab
l
is
h
m
en
t
o
f
s
tr
in
g
en
t
a
s
s
es
s
m
en
t
f
r
am
e
wo
r
k
s
.
Fu
t
u
r
e
s
tu
d
i
e
s
s
h
o
u
ld
co
n
ce
n
t
r
at
e
o
n
c
r
ea
t
in
g
m
o
d
el
s
th
a
t
wi
th
s
t
an
d
ad
v
er
s
a
r
i
al
at
ta
ck
s
,
wi
th
th
e
ab
i
l
ity
to
id
en
tif
y
an
d
co
u
n
ter
ac
t
th
e
s
e
t
h
r
ea
ts
.
Fu
r
th
e
r
m
o
r
e,
i
t
i
s
es
s
e
n
ti
al
to
in
v
e
s
tig
at
e
th
e
ap
p
l
ica
tio
n
o
f
m
u
lt
im
o
d
al
co
n
t
en
t
an
a
ly
s
i
s
f
o
r
a
s
s
e
s
s
in
g
v
ar
io
u
s
f
o
r
m
s
o
f
in
f
o
r
m
at
i
o
n
.
Ad
d
it
io
n
a
l
ly
,
it
i
s
e
s
s
en
t
ia
l
to
im
p
r
o
v
e
t
h
e
cla
r
i
ty
an
d
u
n
d
er
s
tan
d
in
g
o
f
d
ete
ct
io
n
m
o
d
e
ls
.
T
h
e
co
m
p
i
la
tio
n
o
f
co
m
p
r
eh
en
s
iv
e
co
ll
ec
t
io
n
s
o
f
c
at
eg
o
r
iz
ed
d
ata
s
et
s
f
r
o
m
v
ar
io
u
s
f
ab
r
ic
at
ed
h
ea
lth
n
ew
s
s
o
u
r
c
e
s
w
il
l
f
ac
i
l
it
ate
th
e
a
d
v
an
ce
m
en
t
o
f
s
c
al
ab
l
e,
ef
f
ic
ien
t,
an
d
r
e
al
-
t
im
e
d
e
tec
t
io
n
a
lg
o
r
i
t
h
m
s
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
wo
u
ld
lik
e
to
ex
p
r
ess
th
eir
s
in
ce
r
e
g
r
atitu
d
e
to
t
h
eir
r
esp
ec
tiv
e
in
s
titu
tio
n
s
f
o
r
p
r
o
v
id
in
g
th
e
n
ec
ess
ar
y
r
esear
ch
f
ac
ilit
ies,
ac
ad
em
ic
s
u
p
p
o
r
t,
a
n
d
a
c
o
n
d
u
ci
v
e
en
v
ir
o
n
m
en
t
f
o
r
c
o
m
p
letin
g
th
is
s
tu
d
y
.
T
h
e
en
co
u
r
ag
em
en
t
a
n
d
in
f
r
a
s
tr
u
ctu
r
e
o
f
f
er
e
d
b
y
th
eir
d
ep
ar
tm
en
ts
an
d
r
esear
ch
ce
n
ter
s
g
r
ea
tly
co
n
tr
ib
u
ted
to
th
e
s
u
cc
ess
f
u
l e
x
ec
u
tio
n
o
f
th
e
wo
r
k
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
d
id
n
o
t
r
ec
eiv
e
an
y
s
p
ec
if
ic
g
r
an
t
f
r
o
m
f
u
n
d
i
n
g
ag
en
cies
in
th
e
p
u
b
lic,
co
m
m
er
cial,
o
r
not
-
f
o
r
-
p
r
o
f
it
s
ec
to
r
s
.
T
h
e
a
u
th
o
r
s
co
n
d
u
cted
th
is
wo
r
k
with
th
e
s
u
p
p
o
r
t
o
f
th
eir
r
esp
ec
tiv
e
in
s
titu
tio
n
s
,
wh
ich
p
r
o
v
id
e
d
th
e
n
ec
ess
ar
y
f
ac
ilit
ies an
d
ac
ad
em
ic
en
v
ir
o
n
m
en
t
f
o
r
ca
r
r
y
in
g
o
u
t th
e
s
tu
d
y
.
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
R
av
in
d
r
a
B
ab
u
J
alad
an
k
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Gar
ap
ati
Saty
an
ar
ay
an
a
Mu
r
th
y
✓
✓
✓
✓
✓
✓
✓
Ven
u
Go
p
al
Gad
d
am
✓
✓
✓
✓
✓
✓
✓
✓
C
h
ip
p
ad
a
Nag
am
an
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
J
an
jh
y
am
Ven
k
ata
Nag
a
R
am
esh
✓
✓
✓
✓
✓
✓
✓
R
am
esh
E
lu
r
i
✓
✓
✓
✓
✓
✓
✓
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
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.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
3
7
3
-
382
380
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
th
ey
h
av
e
n
o
k
n
o
wn
f
in
a
n
cial
o
r
p
er
s
o
n
al
co
n
f
licts
o
f
in
te
r
est
th
at
co
u
ld
h
av
e
in
f
lu
en
ce
d
th
e
w
o
r
k
r
ep
o
r
ted
in
th
is
p
ap
e
r
.
All
a
u
th
o
r
s
co
n
f
ir
m
th
at
th
e
r
e
ar
e
n
o
c
o
m
p
etin
g
in
ter
ests
r
elate
d
to
th
e
r
esear
c
h
,
au
th
o
r
s
h
ip
,
o
r
p
u
b
licatio
n
o
f
th
is
s
tu
d
y
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
is
s
tu
d
y
d
o
es
n
o
t
in
v
o
lv
e
h
u
m
an
p
ar
ticip
a
n
ts
,
an
im
al
s
,
o
r
s
en
s
itiv
e
p
er
s
o
n
al
d
ata
r
eq
u
ir
in
g
in
s
titu
tio
n
al
eth
ical
clea
r
an
ce
.
All
d
atasets
u
s
ed
in
th
is
r
esear
ch
ar
e
p
u
b
licly
a
v
ailab
le
o
r
a
n
o
n
y
m
ize
d
p
r
io
r
to
u
s
e.
T
h
er
ef
o
r
e,
f
o
r
m
al
eth
ical
ap
p
r
o
v
al
was n
o
t r
eq
u
ir
ed
f
o
r
th
e
co
n
d
u
ct
o
f
t
h
is
s
tu
d
y
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
atasets
u
s
ed
an
d
a
n
aly
z
ed
in
th
is
s
tu
d
y
a
r
e
p
u
b
licly
av
ailab
le
an
d
ca
n
b
e
ac
ce
s
s
ed
f
r
o
m
th
e
r
esp
ec
tiv
e
o
n
lin
e
r
ep
o
s
ito
r
ies
cited
with
in
th
e
p
ap
er
.
An
y
a
d
d
itio
n
al
d
ata
g
e
n
er
ated
d
u
r
in
g
th
e
r
esear
ch
ar
e
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
H
.
L
u
o
,
M
.
C
a
i
,
a
n
d
Y
.
C
u
i
,
“
S
p
r
e
a
d
o
f
mi
s
i
n
f
o
r
mat
i
o
n
i
n
so
c
i
a
l
n
e
t
w
o
r
k
s:
A
n
a
l
y
si
s
b
a
se
d
o
n
W
e
i
b
o
t
w
e
e
t
s,”
S
e
c
u
ri
t
y
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
N
e
t
w
o
rk
s
,
v
o
l
.
2
0
2
1
,
p
p
.
1
–
2
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
7
9
9
9
7
6
0
.
[
2
]
M
.
S
a
y
e
e
d
,
“
C
O
V
I
D
-
19
-
r
e
l
a
t
e
d
s
o
c
i
a
l
me
d
i
a
f
a
k
e
n
e
w
s
i
n
I
n
d
i
a
,
”
J
o
u
rn
a
l
i
sm
a
n
d
Me
d
i
a
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
1
0
0
–
1
1
4
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
j
o
u
r
n
a
l
me
d
i
a
2
0
1
0
0
0
7
.
[
3
]
M
.
I
t
t
e
f
a
q
,
“
‘
I
t
f
r
u
st
r
a
t
e
s
me
b
e
y
o
n
d
w
o
r
d
s
t
h
a
t
I
c
a
n
’
t
f
i
x
t
h
a
t
’
:
H
e
a
l
t
h
m
i
si
n
f
o
r
ma
t
i
o
n
c
o
r
r
e
c
t
i
o
n
o
n
F
a
c
e
b
o
o
k
d
u
r
i
n
g
C
O
V
I
D
-
1
9
,
”
H
e
a
l
t
h
C
o
m
m
u
n
i
c
a
t
i
o
n
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
0
/
1
0
4
1
0
2
3
6
.
2
0
2
3
.
2
2
8
2
2
7
9
.
[
4
]
P
.
A
k
h
t
a
r
,
A
.
M
.
G
h
o
u
r
i
,
H
.
U
.
R
.
K
h
a
n
,
a
n
d
O
t
h
e
r
s,
“
D
e
t
e
c
t
i
n
g
f
a
k
e
n
e
w
s
a
n
d
d
i
s
i
n
f
o
r
ma
t
i
o
n
u
s
i
n
g
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
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
o
a
v
o
i
d
su
p
p
l
y
c
h
a
i
n
d
i
sr
u
p
t
i
o
n
s,
”
A
n
n
a
l
s
o
f
O
p
e
r
a
t
i
o
n
s
Re
s
e
a
r
c
h
,
v
o
l
.
3
2
7
,
p
p
.
6
3
3
–
6
5
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
7
9
-
0
2
2
-
0
5
0
1
5
-
5.
[
5
]
E.
A
.
A
l
i
k
h
a
s
h
a
s
h
n
e
h
,
K
.
M
.
O
.
N
a
h
a
r
,
M
.
A
b
u
a
l
-
R
u
b
,
a
n
d
H
.
M
.
A
l
k
h
a
l
d
y
,
“
A
r
o
b
u
st
m
e
t
h
o
d
f
o
r
d
e
t
e
c
t
i
n
g
f
a
k
e
n
e
w
s
u
s
i
n
g
b
o
t
h
mac
h
i
n
e
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s,”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
EEC
S
)
,
v
o
l
.
3
6
,
n
o
.
3
,
p
p
.
1
8
1
6
–
1
8
2
6
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
6
.
i
3
.
p
p
1
8
1
6
-
1
8
2
6
.
[
6
]
H
.
N
a
j
a
d
a
t
,
M
.
T
a
w
a
l
b
e
h
,
a
n
d
R
.
A
w
a
w
d
e
h
,
“
F
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
f
o
r
A
r
a
b
i
c
h
e
a
d
l
i
n
e
s
-
a
r
t
i
c
l
e
s
n
e
w
s
d
a
t
a
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
(
I
J
EC
E
)
,
v
o
l
.
1
2
,
n
o
.
4
,
p
p
.
3
9
5
1
–
3
9
5
9
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
2
i
4
.
p
p
3
9
5
1
-
3
9
5
9
.
[
7
]
M
.
F
.
M
r
i
d
h
a
,
A
.
J
.
K
e
y
a
,
M
.
A
.
H
a
mi
d
,
M
.
M
.
M
o
n
o
w
a
r
,
a
n
d
M
.
S
.
R
a
h
man
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
n
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
5
6
1
5
1
–
1
5
6
1
7
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
2
9
3
2
9
.
[
8
]
Z.
Zi
h
a
n
,
L.
X
i
a
o
sh
e
n
g
,
W
.
L
i
j
u
n
,
a
n
d
H
.
G
u
a
n
g
q
i
u
,
“
P
r
e
d
i
c
t
i
o
n
o
f
b
l
a
st
-
i
n
d
u
c
e
d
g
r
o
u
n
d
v
i
b
r
a
t
i
o
n
u
s
i
n
g
e
i
g
h
t
n
e
w
i
n
t
e
l
l
i
g
e
n
t
mo
d
e
l
s
,
”
I
AEN
G
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
5
1
,
n
o
.
6
,
p
p
.
6
4
2
–
6
4
9
,
2
0
2
4
.
[
9
]
G
.
C
a
st
i
l
l
o
,
“
Te
r
r
i
t
o
r
y
a
s
a
s
o
c
i
o
p
o
l
i
t
i
c
a
l
a
p
p
r
o
p
r
i
a
t
i
o
n
o
f
s
p
a
c
e
.
B
e
t
w
e
e
n
d
e
t
e
r
r
i
t
o
r
i
a
l
i
z
a
t
i
o
n
a
n
d
m
u
l
t
i
t
e
r
r
i
t
o
r
i
a
l
i
t
y
(
i
n
S
p
a
n
i
s
h
)
,
”
I
n
v
e
s
t
i
g
a
c
i
o
n
e
s
G
e
o
g
r
á
f
i
c
a
s
,
n
o
.
1
0
3
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
1
4
3
5
0
/
r
i
g
.
6
0
1
2
7
.
[
1
0
]
O
.
O
l
u
s
o
l
a
,
R
.
D
a
maš
e
v
i
č
i
u
s
,
R
.
M
a
s
k
e
l
i
ū
n
a
s,
a
n
d
S
.
M
i
sr
a
,
“
A
n
e
n
s
e
m
b
l
e
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
C
O
V
I
D
-
1
9
d
e
t
e
c
t
i
o
n
f
r
o
m
b
l
o
o
d
t
e
st
sam
p
l
e
s,
”
S
e
n
so
rs
,
v
o
l
.
2
2
,
n
o
.
6
,
p
.
2
2
2
4
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
2
0
6
2
2
2
4
.
[
1
1
]
Y
.
W
a
n
g
,
M
.
M
c
K
e
e
,
A
.
To
r
b
i
c
a
,
a
n
d
D
.
S
t
u
c
k
l
e
r
,
“
S
y
s
t
e
m
a
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
o
n
t
h
e
s
p
r
e
a
d
o
f
h
e
a
l
t
h
-
r
e
l
a
t
e
d
mi
si
n
f
o
r
m
a
t
i
o
n
o
n
so
c
i
a
l
me
d
i
a
,
”
S
o
c
i
a
l
S
c
i
e
n
c
e
& M
e
d
i
c
i
n
e
,
v
o
l
.
2
4
0
,
p
.
1
1
2
5
5
2
,
N
o
v
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
o
c
s
c
i
m
e
d
.
2
0
1
9
.
1
1
2
5
5
2
.
[
1
2
]
S
.
C
h
e
n
,
L.
X
i
a
o
,
a
n
d
J
.
M
a
o
,
“
P
e
r
su
a
si
o
n
st
r
a
t
e
g
i
e
s
o
f
m
i
si
n
f
o
r
m
a
t
i
o
n
-
c
o
n
t
a
i
n
i
n
g
p
o
s
t
s
i
n
t
h
e
s
o
c
i
a
l
me
d
i
a
,
”
I
n
f
o
rm
a
t
i
o
n
Pro
c
e
ssi
n
g
&
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
5
8
,
n
o
.
5
,
p
.
1
0
2
6
6
5
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
p
m.
2
0
2
1
.
1
0
2
6
6
5
.
[
1
3
]
E.
A
ï
me
u
r
,
S
.
A
mr
i
,
a
n
d
G
.
B
r
a
ssar
d
,
“
F
a
k
e
n
e
w
s
,
d
i
s
i
n
f
o
r
ma
t
i
o
n
a
n
d
mi
s
i
n
f
o
r
mat
i
o
n
i
n
s
o
c
i
a
l
m
e
d
i
a
:
A
r
e
v
i
e
w
,
”
S
o
c
i
a
l
N
e
t
w
o
rk
An
a
l
y
si
s
a
n
d
M
i
n
i
n
g
,
v
o
l
.
1
3
,
n
o
.
3
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
3
2
7
8
-
0
2
3
-
0
1
0
2
8
-
5.
[
1
4
]
J.
A
l
g
h
a
m
d
i
,
S
.
L
u
o
,
a
n
d
Y
.
L
i
n
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
su
r
v
e
y
o
n
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
f
a
k
e
n
e
w
s d
e
t
e
c
t
i
o
n
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
p
p
.
1
–
5
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
0
4
2
-
0
2
3
-
1
7
4
7
0
-
8.
[
1
5
]
L.
H
u
,
S
.
W
e
i
,
Z.
Z
h
a
o
,
a
n
d
B
.
W
u
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
:
A
c
o
mp
r
e
h
e
n
s
i
v
e
s
u
r
v
e
y
,
”
AI
O
p
e
n
,
v
o
l
.
3
,
p
p
.
1
3
3
–
1
5
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
i
o
p
e
n
.
2
0
2
2
.
0
9
.
0
0
1
.
[
1
6
]
I
.
H
.
S
a
r
k
e
r
,
A
.
S
.
K
a
y
e
s,
a
n
d
P
.
W
a
t
t
e
r
s,
“
Ef
f
e
c
t
i
v
e
n
e
ss
a
n
a
l
y
si
s
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
c
a
t
i
o
n
mo
d
e
l
s
f
o
r
p
r
e
d
i
c
t
i
n
g
p
e
r
s
o
n
a
l
i
z
e
d
c
o
n
t
e
x
t
-
a
w
a
r
e
smar
t
p
h
o
n
e
u
sa
g
e
,
”
J
o
u
r
n
a
l
o
f
B
i
g
D
a
t
a
,
v
o
l
.
6
,
n
o
.
1
,
p
p
.
1
–
2
8
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
0
5
3
7
-
019
-
0
2
1
9
-
y.
[
1
7
]
S
.
H
e
g
e
l
i
c
h
,
“
D
e
c
i
s
i
o
n
t
r
e
e
s
a
n
d
r
a
n
d
o
m
f
o
r
e
st
s:
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
t
o
c
l
a
ssi
f
y
r
a
r
e
e
v
e
n
t
s,”
E
u
ro
p
e
a
n
Po
l
i
c
y
A
n
a
l
y
s
i
s
,
v
o
l
.
2
,
n
o
.
1
,
2
0
1
6
,
d
o
i
:
1
0
.
1
8
2
7
8
/
e
p
a
.
2
.
1
.
7
.
[
1
8
]
F
.
A
l
a
r
f
a
j
a
n
d
J.
K
h
a
n
,
“
D
e
e
p
d
i
v
e
i
n
t
o
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
:
F
e
a
t
u
r
e
-
c
e
n
t
r
i
c
c
l
a
ss
i
f
i
c
a
t
i
o
n
w
i
t
h
e
n
s
e
m
b
l
e
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
met
h
o
d
s,
”
A
l
g
o
r
i
t
h
m
s
,
v
o
l
.
1
6
,
n
o
.
1
1
,
p
.
5
0
7
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
1
6
1
1
0
5
0
7
.
[
1
9
]
Y
.
Li
a
n
d
T.
Y
a
n
g
,
“
W
o
r
d
e
m
b
e
d
d
i
n
g
f
o
r
u
n
d
e
r
st
a
n
d
i
n
g
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
:
A
su
r
v
e
y
,
”
i
n
D
e
e
p
L
e
a
r
n
i
n
g
i
n
I
n
t
e
rn
e
t
o
f
T
h
i
n
g
s
,
S
p
r
i
n
g
e
r
,
2
0
1
8
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
5
3
8
1
7
-
4
_
4
.
[
2
0
]
M
.
A
.
A
l
o
n
s
o
,
D
.
V
i
l
a
r
e
s,
C
.
G
ó
m
e
z
-
R
o
d
r
í
g
u
e
z
,
a
n
d
J.
V
i
l
a
r
e
s,
“
S
e
n
t
i
men
t
a
n
a
l
y
si
s
f
o
r
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
,
”
El
e
c
t
ro
n
i
c
s
,
v
o
l
.
1
0
,
n
o
.
1
1
,
p
.
1
3
4
8
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
0
1
1
1
3
4
8
.
[
2
1
]
A
.
N
.
R
a
mk
i
ss
o
o
n
a
n
d
W
.
G
o
o
d
r
i
d
g
e
,
“
E
n
h
a
n
c
i
n
g
t
h
e
p
r
e
d
i
c
t
i
v
e
p
e
r
f
o
r
man
c
e
o
f
c
r
e
d
i
b
i
l
i
t
y
-
b
a
se
d
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
u
si
n
g
e
n
s
e
mb
l
e
l
e
a
r
n
i
n
g
,
”
R
e
v
i
e
w
o
f
S
o
c
i
o
n
e
t
w
o
r
k
S
t
r
a
t
e
g
i
e
s
,
v
o
l
.
1
6
,
p
p
.
2
5
9
–
2
8
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
6
2
6
-
0
2
2
-
0
0
1
2
7
-
7.
[
2
2
]
P
.
Th
ö
l
k
e
a
n
d
O
t
h
e
r
s,
“
C
l
a
ss i
mb
a
l
a
n
c
e
sh
o
u
l
d
n
o
t
t
h
r
o
w
y
o
u
o
f
f
b
a
l
a
n
c
e
:
C
h
o
o
si
n
g
t
h
e
r
i
g
h
t
c
l
a
ss
i
f
i
e
r
s
a
n
d
p
e
r
f
o
r
man
c
e
m
e
t
r
i
c
s
f
o
r
b
r
a
i
n
d
e
c
o
d
i
n
g
w
i
t
h
i
m
b
a
l
a
n
c
e
d
d
a
t
a
,
”
N
e
u
r
o
I
m
a
g
e
,
v
o
l
.
2
7
7
,
p
.
1
2
0
2
5
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
r
o
i
ma
g
e
.
2
0
2
3
.
1
2
0
2
5
3
.
[
2
3
]
K
.
B
o
y
d
,
V
.
C
o
st
a
,
J
.
D
a
v
i
s,
a
n
d
C
.
P
a
g
e
,
“
U
n
a
c
h
i
e
v
a
b
l
e
r
e
g
i
o
n
i
n
p
r
e
c
i
si
o
n
-
r
e
c
a
l
l
sp
a
c
e
a
n
d
i
t
s
e
f
f
e
c
t
o
n
e
m
p
i
r
i
c
a
l
e
v
a
l
u
a
t
i
o
n
,
”
2
0
1
2
.
d
o
i
:
1
0
.
5
5
5
5
/
3
0
4
2
5
7
3
.
3
0
4
2
6
2
2
.
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
A
p
p
lica
tio
n
o
f d
ee
p
lea
r
n
in
g
a
n
d
ma
c
h
in
e
lea
r
n
in
g
tech
n
iq
u
es fo
r
…
(
R
a
vin
d
r
a
B
a
b
u
Ja
l
a
d
a
n
ki
)
381
[
2
4
]
A
.
G
o
t
m
a
r
e
,
G
.
Th
i
t
e
,
a
n
d
L.
B
e
w
o
o
r
,
“
A
m
u
l
t
i
m
o
d
a
l
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
g
e
n
e
r
a
t
e
n
e
w
s
a
r
t
i
c
l
e
s
f
r
o
m
g
e
o
-
t
a
g
g
e
d
i
ma
g
e
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
(
I
J
EC
E)
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
3
4
3
4
–
3
4
4
2
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
3
.
p
p
3
4
3
4
-
3
4
4
2
.
[
2
5
]
M
.
R
.
I
sl
a
m,
S
.
L
i
u
,
X
.
W
a
n
g
,
a
n
d
O
t
h
e
r
s,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
m
i
si
n
f
o
r
m
a
t
i
o
n
d
e
t
e
c
t
i
o
n
o
n
o
n
l
i
n
e
s
o
c
i
a
l
n
e
t
w
o
r
k
s:
a
su
r
v
e
y
a
n
d
n
e
w
p
e
r
s
p
e
c
t
i
v
e
s,”
S
o
c
i
a
l
N
e
t
w
o
r
k
A
n
a
l
y
si
s
a
n
d
M
i
n
i
n
g
,
v
o
l
.
1
0
,
n
o
.
8
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
2
7
8
-
020
-
0
0
6
9
6
-
x.
[
2
6
]
H
.
S
a
k
,
A
.
S
e
n
i
o
r
,
a
n
d
F
.
B
e
a
u
f
a
y
s,
“
L
o
n
g
sh
o
r
t
-
t
e
r
m
mem
o
r
y
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
a
r
c
h
i
t
e
c
t
u
r
e
s
f
o
r
l
a
r
g
e
sca
l
e
a
c
o
u
st
i
c
mo
d
e
l
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
An
n
u
a
l
C
o
n
f
e
re
n
c
e
o
f
t
h
e
I
n
t
e
r
n
a
t
i
o
n
a
l
S
p
e
e
c
h
C
o
m
m
u
n
i
c
a
t
i
o
n
Ass
o
c
i
a
t
i
o
n
(
I
N
T
ERS
PEE
C
H
)
,
2
0
1
4
,
p
p
.
3
3
8
–
3
4
2
.
d
o
i
:
1
0
.
2
1
4
3
7
/
I
n
t
e
r
sp
e
e
c
h
.
2
0
1
4
-
8
0
.
[
2
7
]
S
.
F
.
A
h
m
e
d
,
M
.
S
.
B
.
A
l
a
m
,
M
.
H
a
ssan
,
a
n
d
O
t
h
e
r
s,
“
D
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
l
i
n
g
t
e
c
h
n
i
q
u
e
s:
c
u
r
r
e
n
t
p
r
o
g
r
e
ss,
a
p
p
l
i
c
a
t
i
o
n
s,
a
d
v
a
n
t
a
g
e
s,
a
n
d
c
h
a
l
l
e
n
g
e
s
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
5
6
,
p
p
.
1
3
5
2
1
–
1
3
6
1
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
4
6
2
-
0
2
3
-
1
0
4
6
6
-
8.
[
2
8
]
R
.
A
r
c
h
a
n
a
a
n
d
P
.
S
.
E.
J
e
e
v
a
r
a
j
,
“
D
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
f
o
r
d
i
g
i
t
a
l
i
m
a
g
e
p
r
o
c
e
ssi
n
g
:
a
r
e
v
i
e
w
,
”
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
5
7
,
n
o
.
1
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
6
2
-
0
2
3
-
1
0
6
3
1
-
z.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ra
v
in
d
r
a
Ba
b
u
J
a
la
d
a
n
k
i
re
c
e
iv
e
d
th
e
B.
Tec
h
.
d
e
g
re
e
i
n
e
lec
tro
n
ics
a
n
d
c
o
m
m
u
n
ica
ti
o
n
e
n
g
in
e
e
ri
n
g
fro
m
Ve
lag
a
p
u
d
i
Ra
m
a
k
rish
n
a
S
id
d
h
a
rth
a
En
g
i
n
e
e
rin
g
Co
ll
e
g
e
,
Vijay
a
wa
d
a
,
In
d
ia,
in
2
0
0
0
a
n
d
th
e
M
.
Tec
h
.
a
n
d
P
h
.
D.
d
e
g
re
e
s
in
e
lec
tro
n
ics
a
n
d
c
o
m
m
u
n
ica
ti
o
n
e
n
g
in
e
e
ri
n
g
wit
h
wire
les
s
c
o
m
m
u
n
ica
ti
o
n
s
sp
e
c
ializa
ti
o
n
fr
o
m
Ja
wa
h
a
rlal
Ne
h
ru
Tec
h
n
o
l
o
g
ica
l
U
n
iv
e
rsit
y
Hy
d
e
ra
b
a
d
,
In
d
ia
i
n
2
0
0
4
a
n
d
2
0
2
1
,
re
sp
e
c
ti
v
e
ly
.
Cu
rre
n
tl
y
,
h
e
is
a
n
a
ss
o
c
iativ
e
p
ro
fe
ss
o
r
a
t
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
C
o
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
,
P
.
V.P
S
id
d
h
a
rth
a
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Vijay
a
wa
d
a
,
In
d
ia.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
wire
les
s
c
o
m
m
u
n
ica
ti
o
n
s,
si
g
n
a
l
p
ro
c
e
ss
in
g
,
b
i
o
m
e
d
ica
l
e
n
g
in
e
e
rin
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
jr
b
0
0
0
9
@g
m
a
il
.
c
o
m
.
G
a
r
a
p
a
ti
S
a
ty
a
n
a
r
a
y
a
n
a
Mu
r
t
h
y
is
wo
r
k
i
n
g
a
s
a
p
ro
fe
ss
o
r
o
f
CS
E
in
Ad
it
y
a
Un
iv
e
rsity
,
S
u
ra
m
p
a
lem
.
He
c
o
m
p
lete
d
h
is
P
h
.
D
.
(C
S
E)
i
n
Ra
y
a
la
se
e
m
a
Un
iv
e
rsity
,
Ku
r
n
o
o
l
,
In
d
ia.
He
h
a
s
2
8
+
Ye
a
rs
o
f
tea
c
h
in
g
E
x
p
e
rien
c
e
a
n
d
1
0
+
y
e
a
rs
o
f
r
e
se
a
rc
h
e
x
p
e
rien
c
e
.
He
p
u
b
li
sh
e
d
v
a
rio
u
s
re
se
a
rc
h
a
rti
c
les
in
re
p
u
ted
i
n
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s
.
He
h
a
s
se
v
e
ra
l
p
a
ten
ts
a
n
d
b
o
o
k
c
h
a
p
ters
a
lso
.
He
is
re
v
iew
e
r
fo
r
v
a
ri
o
u
s S
c
o
p
u
s
in
d
e
x
e
d
j
o
u
r
n
a
ls
a
n
d
e
d
it
o
rial
b
o
a
rd
m
e
m
b
e
r
li
k
e
Re
se
a
rc
h
In
d
ia
G
ro
u
p
o
f
Jo
u
rn
a
ls.
He
a
c
ted
a
s
a
n
a
d
v
iso
r
f
o
r
se
v
e
ra
l
in
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s.
He
is
a
m
e
m
b
e
r
fo
r
v
a
rio
u
s
p
r
o
fe
ss
io
n
a
l
b
o
d
ies
li
k
e
IEE
E,
CS
I,
IAENG
a
n
d
CS
TA
.
He
is
t
h
e
BOS
m
e
m
b
e
r
f
o
r
se
v
e
ra
l
p
r
o
fe
ss
io
n
a
l
c
o
ll
e
g
e
s.
His
re
se
a
rc
h
wo
rk
f
o
c
u
se
s
o
n
d
a
ta
m
in
i
n
g
,
i
m
a
g
e
p
ro
c
e
ss
in
g
a
n
d
c
y
b
e
r
se
c
u
rit
y
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
u
rth
y
g
sn
m
@y
a
h
o
o
.
c
o
m
.
Ve
n
u
G
o
p
a
l
G
a
d
d
a
m
wo
rk
in
g
a
s
a
ss
o
c
iate
p
ro
fe
ss
o
r
i
n
C
S
E
(AI
a
n
d
M
L)
d
e
p
a
rtme
n
t
a
t
B
V
Ra
j
u
In
st
it
u
t
e
o
f
Tec
h
n
o
l
o
g
y
,
Na
rsa
p
u
r,
Hy
d
e
ra
b
a
d
.
He
ha
s
1
8
y
e
a
rs
o
f
tea
c
h
in
g
a
n
d
re
se
a
rc
h
e
x
p
e
rien
c
e
.
He
re
c
e
iv
e
d
m
y
d
o
c
t
o
ra
l
d
e
g
re
e
fro
m
Ac
h
a
ry
a
Na
g
a
rju
n
a
Un
iv
e
rsity
(
S
tate
Un
iv
e
rsit
y
)
in
t
h
e
y
e
a
r
2
0
2
2
.
I
p
u
b
li
s
h
e
d
6
S
c
o
p
u
s,
7
c
o
n
fe
re
n
c
e
p
a
p
e
rs an
d
3
b
o
o
k
c
h
a
p
ters
.
8
S
CI
p
a
p
e
rs
a
n
d
3
m
o
re
b
o
o
k
c
h
a
p
ters
a
re
c
o
m
m
u
n
ica
ted
.
His
re
se
a
rc
h
a
re
a
s
in
c
lu
d
e
m
a
c
h
in
e
lea
rn
in
g
,
i
n
ter
n
e
t
o
f
th
i
n
g
s
,
d
a
ta
m
in
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
e
n
u
g
o
p
a
l.
g
@
b
v
ri
t.
a
c
.
in
.
Chi
p
p
a
d
a
Na
g
a
m
a
n
i
re
c
e
iv
e
d
P
h
.
D.
fr
o
m
Ac
h
a
r
y
a
Na
g
a
rju
n
a
Un
i
v
e
rsity
,
An
d
h
ra
P
ra
d
e
sh
in
2
0
2
1
a
n
d
o
b
t
a
in
e
d
h
e
r
M
.
Tec
h
.
i
n
c
o
m
p
u
ter
s
c
ien
c
e
a
n
d
e
n
g
in
e
e
ri
n
g
fro
m
Ac
h
a
ry
a
Na
g
a
rju
n
a
Un
i
v
e
rsity
in
t
h
e
y
e
a
r
2
0
1
0
.
He
r
a
re
a
s
o
f
in
tere
st
in
c
l
u
d
e
m
a
c
h
i
n
e
lea
rn
in
g
,
a
rti
ficia
l
in
telli
g
e
n
c
e
a
n
d
n
e
two
r
k
se
c
u
rit
y
.
S
h
e
p
u
b
li
sh
e
d
v
a
rio
u
s
p
a
p
e
rs
i
n
jo
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
Cu
rre
n
tl
y
s
h
e
is
wo
rk
i
n
g
a
s
a
n
a
ss
o
c
iate
p
r
o
fe
ss
o
r
in
t
h
e
D
e
p
a
rtme
n
t
o
f
CS
E
a
t
KLEF
,
KL
U
n
iv
e
rsit
y
,
G
u
n
t
u
r,
In
d
ia.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t:
d
r
n
a
g
a
m
a
n
ics
e
@g
m
a
il
.
c
o
m
.
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.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
3
7
3
-
382
382
J
a
n
j
h
y
a
m
Ve
n
k
a
t
a
N
a
g
a
Ra
m
e
sh
Ad
j
u
n
c
t
P
ro
fe
ss
o
r
wo
r
k
in
g
in
t
h
e
D
e
p
a
rtme
n
t
o
f
CS
E
,
G
ra
p
h
ic
Era
Hill
U
n
iv
e
rsity
a
n
d
G
ra
p
h
ic
E
ra
De
e
m
e
d
t
o
Be
U
n
iv
e
rsit
y
,
De
h
ra
d
u
n
,
Uttara
k
h
a
n
d
I
n
d
ia.
He
h
a
s
2
0
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
tea
c
h
i
n
g
f
o
r
UG
a
n
d
P
G
e
n
g
in
e
e
rin
g
stu
d
e
n
ts.
He
h
a
s
p
u
b
li
sh
e
d
m
o
re
th
a
n
9
5
Art
icle
s
in
IEE
E/
S
CI/S
c
o
p
u
s/W
o
S
Jo
u
rn
a
ls,
c
o
n
fe
re
n
c
e
s
a
n
d
a
lso
r
e
v
iew
e
r
in
v
a
rio
u
s
lea
d
i
n
g
J
o
u
r
n
a
ls.
He
h
a
s
a
u
th
o
re
d
six
tex
t
b
o
o
k
s
a
n
d
ten
b
o
o
k
c
h
a
p
ters
.
His
re
se
a
rc
h
in
tere
sts
a
re
wire
les
s
se
n
so
r
n
e
two
rk
s,
c
o
m
p
u
ter
n
e
two
rk
s,
d
e
e
p
lea
rn
i
n
g
,
m
a
c
h
i
n
e
lea
rn
i
n
g
a
n
d
a
rti
ficia
l
in
telli
g
e
n
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
jv
n
ra
m
e
sh
@g
m
a
il
.
c
o
m
.
Ra
m
e
sh
Elu
r
i
re
c
e
iv
e
d
t
h
e
B.
Tec
h
.
d
e
g
re
e
i
n
CS
IT
fro
m
NIET
,
G
u
n
tu
r,
I
n
d
ia,
in
2
0
0
5
a
n
d
t
h
e
M
.
Tec
h
.
in
C
S
E
fro
m
RVR&
JC
Co
ll
e
g
e
o
f
E
n
g
in
e
e
rin
g
,
G
u
n
t
u
r
in
2
0
1
0
.
Cu
rre
n
tl
y
,
h
e
is
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
a
t
t
h
e
De
p
a
rtme
n
t
o
f
CS
E,
RVR&
JC
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
G
u
n
tu
r,
I
n
d
ia.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
in
ter
n
e
t
o
f
th
i
n
g
s
a
n
d
b
i
g
d
a
ta
a
n
a
ly
ti
c
s a
n
d
m
o
re
o
v
e
r
m
a
c
h
i
n
e
l
e
a
rn
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
e
lu
ri.
r@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.