I
n
t
e
r
n
at
ion
al
Jou
r
n
a
l
of
I
n
f
o
r
m
at
ics
an
d
Com
m
u
n
icat
ion
T
e
c
h
n
ol
ogy
(
I
J
-
I
CT
)
Vo
l
.
1
4
,
N
o
.
3
,
De
c
e
m
b
e
r
20
2
5
,
pp.
941
~
949
I
S
S
N:
2252
-
8776
,
DO
I
:
10
.
11591/i
ji
c
t
.
v
1
4
i
3
.
pp
94
1
-
949
941
Jou
r
n
al
h
o
m
e
page
:
ht
tp:
//
ij
ict
.
iaes
c
or
e
.
c
om
E
m
p
ow
e
r
in
g l
ow
-
r
e
sou
r
c
e
l
a
n
gu
age
s:
a
m
ac
h
i
n
e
l
e
ar
n
in
g
ap
p
r
oac
h
t
o
T
a
m
i
l
se
n
t
i
m
e
n
t
c
la
ssi
f
ic
at
io
n
S
al
e
e
m
Raj
a
Abd
u
l
S
am
ad
1
,
P
r
ad
e
e
p
a
Gan
e
s
an
1
,
Ju
s
t
in
Raj
as
e
k
a
r
an
1
,
M
ad
h
u
b
al
a
Radh
ak
r
i
s
h
n
an
1
,
P
e
e
r
b
as
h
a
S
h
e
b
b
e
e
r
B
as
h
a
2
,
Var
al
a
k
s
h
m
i
K
u
p
p
u
s
am
y
3
1
I
n
f
o
r
ma
ti
o
n
T
e
c
hn
ol
o
g
y
D
e
pa
r
t
me
nt
, C
o
ll
e
g
e
of
C
o
mput
in
g a
nd I
n
f
o
r
ma
ti
o
n S
c
i
e
n
c
e
s
,
U
ni
ve
r
s
it
y
of
T
e
c
hn
o
l
o
g
y
a
nd A
ppl
i
e
d S
c
i
e
nc
e
s
,
S
hi
na
s
, O
ma
n
2
D
e
pa
r
tm
e
nt
of
C
o
mpu
te
r
S
c
ie
n
c
e
, J
a
ma
l
M
o
ha
me
d
C
o
ll
e
g
e
,
T
ir
uc
hi
r
a
ppa
ll
i,
I
ndi
a
3
D
e
pa
r
tm
e
nt
of
C
o
mpu
te
r
S
c
ie
n
c
e
a
nd E
ngi
n
e
e
r
in
g, S
R
M
U
ni
ve
r
s
it
y
, C
he
nna
i,
I
nd
ia
Ar
t
ic
l
e
I
n
f
o
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
i
ve
d
S
e
p
18,
2024
R
e
vi
s
e
d
M
a
y
18,
2025
A
c
c
e
pt
e
d
J
u
l
1,
2025
Sen
t
i
m
en
t
a
n
al
y
s
i
s
i
s
e
s
s
e
n
t
i
a
l
f
o
r
d
ec
i
p
h
e
r
i
n
g
p
u
b
l
i
c
o
p
i
n
i
o
n
,
g
u
i
d
i
n
g
d
eci
s
i
o
n
s
,
an
d
r
e
fi
n
i
n
g
m
ar
k
e
t
i
n
g
s
t
rat
e
g
i
e
s
.
I
t
p
l
a
y
s
a
c
ru
c
i
a
l
ro
l
e
i
n
mo
n
i
t
o
ri
n
g
p
u
b
l
i
c
s
e
n
t
i
men
t
,
f
o
s
t
e
ri
n
g
c
u
s
t
o
me
r
en
g
a
g
eme
n
t
,
an
d
en
h
a
n
c
i
n
g
re
l
at
i
o
n
s
h
i
p
s
w
i
t
h
b
u
s
i
n
e
s
s
e
s
'
t
arg
e
t
au
d
i
en
ce
s
b
y
a
n
al
y
zi
n
g
em
o
t
i
o
n
a
l
t
o
n
e
s
an
d
at
t
i
t
u
d
e
s
i
n
v
as
t
t
e
x
t
u
al
d
at
a.
S
e
n
t
i
men
t
an
al
y
s
i
s
i
s
e
x
t
re
mel
y
l
i
mi
t
ed
,
p
art
i
c
u
l
ar
l
y
fo
r
l
an
g
u
a
g
e
s
l
i
k
e
T
ami
l
,
d
u
e
t
o
l
i
m
i
t
e
d
a
p
p
l
i
c
at
i
o
n
i
n
d
i
v
e
rs
e
l
i
n
g
u
i
s
t
i
c
c
o
n
t
e
x
t
s
w
i
t
h
f
ew
e
r
r
e
s
o
u
r
ce
s
.
G
i
v
e
n
i
t
s
g
l
o
b
al
i
m
p
ac
t
a
n
d
l
i
n
g
u
i
s
t
i
c
d
i
v
e
rs
i
t
y
,
ad
d
r
e
s
s
i
n
g
t
h
i
s
g
ap
i
s
c
ru
ci
al
f
o
r
a
mo
r
e
n
u
a
n
c
ed
u
n
d
e
rs
t
an
d
i
n
g
o
f
s
en
t
i
me
n
t
s
i
n
In
d
i
a.
I
n
t
h
e
co
n
t
e
x
t
o
f
T
am
i
l
,
t
h
e
n
eed
fo
r
s
e
n
t
i
me
n
t
a
n
al
y
s
i
s
mo
d
el
s
i
s
p
art
i
cu
l
ar
l
y
c
ru
ci
al
d
u
e
t
o
i
t
s
s
t
at
u
s
as
o
n
e
o
f
t
h
e
cl
as
s
i
c
a
l
l
a
n
g
u
ag
e
s
s
p
o
k
e
n
b
y
m
i
l
l
i
o
n
s
.
T
h
e
cu
l
t
u
r
al
,
s
o
c
i
a
l
,
a
n
d
h
i
s
t
o
ri
c
al
n
u
an
ce
s
em
b
e
d
d
e
d
i
n
T
a
m
i
l
l
an
g
u
a
g
e
u
s
ag
e
r
e
q
u
i
r
e
t
ai
l
o
r
e
d
s
e
n
t
i
me
n
t
an
a
l
y
s
i
s
ap
p
ro
a
c
h
e
s
t
h
at
c
a
n
c
ap
t
u
r
e
t
h
e
s
u
b
t
l
e
t
i
e
s
o
f
s
en
t
i
me
n
t
e
x
p
re
s
s
i
o
n
.
T
h
i
s
p
ap
e
r
i
n
t
ro
d
u
ce
s
a
n
o
v
e
l
me
t
h
o
d
t
h
at
as
s
e
s
s
e
s
t
h
e
p
e
rfo
r
m
an
ce
o
f
v
ar
i
o
u
s
t
e
x
t
e
m
b
ed
d
i
n
g
me
t
h
o
d
s
i
n
c
o
n
j
u
n
c
t
i
o
n
w
i
t
h
a
ran
g
e
o
f
m
a
ch
i
n
e
l
e
arn
i
n
g
(ML
)
al
g
o
r
i
t
h
m
s
t
o
en
h
a
n
c
e
s
e
n
t
i
me
n
t
c
l
as
s
i
fi
c
at
i
o
n
fo
r
T
am
i
l
t
e
x
t
,
w
i
t
h
a
s
p
e
ci
fi
c
fo
cu
s
o
n
l
y
ri
c
s
.
E
x
p
e
r
i
me
n
t
s
n
o
t
ab
l
y
em
p
h
as
i
z
e
Fas
t
T
e
x
t
w
o
r
d
em
b
e
d
d
i
n
g
as
t
h
e
mo
s
t
e
ff
ec
t
i
v
e
me
t
h
o
d
,
s
h
o
w
c
a
s
i
n
g
s
u
p
e
ri
o
r
r
e
s
u
l
t
s
w
i
t
h
a
r
em
ark
ab
l
e
7
8
%
a
cc
u
ra
cy
w
h
e
n
c
o
u
p
l
e
d
w
i
t
h
t
h
e
s
u
p
p
o
rt
v
ec
t
o
r
c
l
as
s
i
fi
c
at
i
o
n
(SV
C)
mo
d
el
.
K
e
y
w
o
r
d
s
:
F
a
s
t
T
e
x
t
Na
t
ur
a
l
l
a
n
gua
ge
pr
o
c
e
s
s
i
n
g
T
a
m
i
l
s
e
n
t
i
m
e
n
t
c
l
a
s
s
if
i
c
a
t
i
o
n
T
e
x
t
e
m
b
e
dd
i
ng
W
o
r
d
e
m
be
dd
i
ng
W
o
r
d2Ve
c
Th
i
s
i
s
a
n
o
p
en
a
c
ces
s
a
r
t
i
c
l
e
u
n
d
e
r
t
h
e
CC
B
Y
-
SA
l
i
cen
s
e.
C
or
r
e
s
pon
din
g
A
u
th
or
:
P
e
e
r
b
a
s
ha
S
h
e
bb
e
e
r
B
a
s
h
a
De
pa
r
t
m
e
n
t
o
f
C
o
m
put
e
r
S
c
i
e
n
c
e
,
J
a
m
a
l
M
o
h
a
m
e
d
C
o
l
l
e
ge
,
T
i
r
uc
hi
r
a
ppa
ll
i
T
a
m
i
l
Na
du.
I
n
d
i
a
E
m
a
i
l
:
b
a
s
ha
pe
e
r
2003
@
g
m
a
il
.
c
o
m
1.
I
NT
RODU
C
T
I
ON
T
a
m
i
l
i
s
o
n
e
o
f
t
h
e
wo
r
l
d
'
s
o
l
d
e
s
t
a
n
c
i
e
n
t
l
a
n
gua
g
e
s
,
w
i
t
h
a
gr
e
a
t
l
i
t
e
r
a
r
y
l
e
ga
c
y
s
pa
nni
ng
t
h
o
us
a
n
d
s
o
f
y
e
a
r
s
.
T
h
e
I
n
d
i
a
n
s
t
a
t
e
s
o
f
T
a
m
il
Na
du,
P
uduc
he
r
r
y
,
a
n
d
S
r
i
L
a
n
ka
a
l
l
u
s
e
T
a
mi
l
a
s
t
h
e
i
r
o
f
f
i
c
i
a
l
lan
gua
g
e
.
I
t
s
s
i
g
nif
i
c
a
n
c
e
t
r
a
n
s
c
e
n
ds
ge
o
gr
a
phi
c
a
l
l
i
mi
t
a
t
i
o
ns
,
a
s
t
h
e
r
e
e
xi
s
t
s
a
wo
r
l
dw
i
de
T
a
m
il
-
s
pe
a
k
i
n
g
d
i
a
s
po
r
a
[
1]
.
T
a
m
i
l
li
t
e
r
a
t
ur
e
s
e
r
v
e
s
a
s
a
c
r
uc
i
a
l
r
e
po
s
i
t
or
y
f
o
r
t
h
e
c
u
l
t
ur
a
l
he
r
i
t
a
ge
o
f
t
h
e
T
a
mi
l
-
s
pe
a
k
i
ng
c
o
mm
u
ni
t
y
,
c
o
m
pr
i
s
i
ng
pr
o
s
e
,
p
o
e
t
r
y
,
a
n
d
a
n
c
i
e
n
t
s
c
r
i
pt
ur
e
s
.
S
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
i
s
p
a
r
a
m
o
un
t
i
n
to
da
y
's
da
ta
-
dr
i
ve
n
l
a
n
d
s
c
a
pe
,
e
n
a
bli
ng
o
r
ga
ni
z
a
t
i
o
ns
to
de
c
i
p
he
r
a
nd
r
e
s
po
n
d
to
t
h
e
s
e
n
t
i
m
e
n
t
s
e
x
pr
e
s
s
e
d
i
n
v
a
s
t
v
o
l
u
m
e
s
o
f
t
e
x
t
ua
l
da
t
a
.
Us
i
n
g
n
a
t
ur
a
l
l
a
n
gu
a
ge
pr
o
c
e
s
s
i
n
g
(
NL
P
)
t
e
c
hni
que
s
,
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
e
x
t
r
a
c
t
s
v
a
l
ua
bl
e
i
ns
i
g
h
t
s
f
r
o
m
c
us
t
o
m
e
r
r
e
vi
e
w
s
,
s
o
c
i
a
l
m
e
d
i
a
i
n
t
e
r
a
c
t
i
o
n
s
,
a
n
d
ot
h
e
r
t
e
x
t
ua
l
s
o
ur
c
e
s
,
pr
o
vi
d
i
n
g
bus
i
ne
s
s
e
s
w
i
t
h
a
n
ua
nc
e
d
un
de
r
s
t
a
n
d
i
ng
o
f
publi
c
o
p
i
ni
o
n
.
T
hi
s
i
nf
o
r
m
a
t
i
o
n
i
s
i
ns
t
r
u
m
e
n
t
a
l
i
n
s
ha
p
i
n
g
s
t
r
a
t
e
gi
c
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
1
4
,
N
o.
3
,
De
c
e
m
be
r
20
2
5
:
941
-
949
942
de
c
i
s
i
o
n
s
,
e
nh
a
n
c
i
ng
b
r
a
n
d
pe
r
c
e
pt
i
o
n
,
a
n
d
i
m
p
r
o
vi
n
g
c
us
to
m
e
r
s
a
t
i
s
f
a
c
t
i
o
n
.
F
r
o
m
m
a
r
ke
t
r
e
s
e
a
r
c
h
a
nd
pr
o
duc
t
de
v
e
l
o
p
m
e
n
t
to
b
r
a
n
d
r
e
put
a
t
i
o
n
m
a
na
ge
m
e
n
t
a
n
d
po
l
i
t
i
c
a
l
a
na
l
y
s
i
s
,
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
i
s
a
p
o
we
r
f
u
l
too
l
a
c
r
o
s
s
v
a
r
i
o
us
do
m
a
i
ns
,
f
o
s
t
e
r
i
n
g
i
nf
o
r
m
e
d
de
c
i
s
i
o
n
-
m
a
k
i
ng
a
n
d
r
e
s
po
n
s
i
ve
c
o
m
m
u
ni
c
a
t
i
o
n
i
n
a
r
a
pi
d
ly
e
v
o
l
vi
ng
d
i
g
i
t
a
l
e
nvi
r
o
nm
e
n
t
[
2]
,
[
3]
.
I
n
c
o
r
p
o
r
a
t
i
n
g
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
s
pe
c
if
i
c
a
ll
y
f
o
r
T
a
m
i
l
i
s
o
f
pr
o
f
o
un
d
s
i
g
ni
f
i
c
a
n
c
e
,
o
f
f
e
r
i
ng
a
n
ua
n
c
e
d
c
o
m
pr
e
he
n
s
i
o
n
o
f
e
m
o
t
i
o
ns
a
n
d
o
p
i
ni
o
n
s
w
i
t
hi
n
t
hi
s
vi
b
r
a
n
t
l
i
ngu
i
s
t
i
c
c
o
m
m
u
ni
t
y
.
A
m
o
r
e
r
e
f
i
ne
d
un
de
r
s
t
a
n
d
i
ng
e
m
e
r
ge
s
by
a
pp
l
yi
ng
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
t
o
T
a
m
il
t
e
x
t
,
e
n
a
bl
i
ng
e
f
f
e
c
t
i
v
e
c
o
m
muni
c
a
t
i
o
n
s
t
r
a
t
e
gi
e
s
,
c
o
n
t
e
n
t
pe
r
s
o
n
a
l
i
z
a
t
i
o
n
,
a
n
d
t
a
r
ge
t
e
d
de
c
i
s
i
o
n
-
m
a
k
i
ng
[
4]
.
B
us
i
n
e
s
s
e
s
c
a
n
l
e
v
e
r
a
g
e
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
o
n
T
a
m
il
r
e
vi
e
ws
a
n
d
s
o
c
i
a
l
m
e
d
i
a
t
o
t
a
i
l
o
r
t
h
e
i
r
pr
o
duc
t
s
a
n
d
s
e
r
vi
c
e
s
,
r
e
s
u
l
t
i
n
g
i
n
e
l
e
v
a
t
e
d
c
us
t
o
m
e
r
s
a
t
i
s
f
a
c
t
i
o
n
.
M
o
r
e
o
v
e
r
,
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
i
n
T
a
m
il
h
o
l
ds
c
o
ns
i
de
r
a
bl
e
i
m
po
r
t
a
n
c
e
i
n
po
l
i
t
i
c
a
l
a
n
d
s
o
c
i
a
l
r
e
a
lm
s
,
pr
o
vi
d
i
ng
po
l
i
c
ym
a
k
e
r
s
a
n
d
r
e
s
e
a
r
c
h
e
r
s
w
i
t
h
i
nva
l
u
a
bl
e
i
n
s
i
g
h
t
s
i
n
to
publ
i
c
s
e
n
t
i
m
e
n
t
.
T
hi
s
,
i
n
t
ur
n
,
c
o
n
tr
i
b
ut
e
s
to
m
o
r
e
i
nf
o
r
m
e
d
a
n
d
i
ns
i
g
h
t
f
u
l
d
e
c
i
s
i
o
n
-
m
a
k
i
ng
pr
o
c
e
s
s
e
s
[
5]
.
T
h
e
r
e
s
e
a
r
c
h
e
r
s
h
a
ve
pr
e
s
e
n
t
e
d
a
v
a
r
i
e
t
y
o
f
m
e
t
ho
d
o
l
o
g
i
e
s
;
h
o
we
ve
r
,
t
h
e
c
h
a
ll
e
n
ge
s
pe
r
s
i
s
t
due
to
t
h
e
s
h
o
r
t
a
ge
o
f
l
a
b
e
l
e
d
da
t
a
a
n
d
t
h
e
i
n
t
r
i
c
a
t
e
n
a
t
ur
e
o
f
t
h
e
T
a
m
il
l
a
n
gua
g
e
.
T
h
e
i
n
t
r
o
du
c
t
i
o
n
o
f
c
o
de
-
m
i
xi
ng,
i
n
t
e
gr
a
t
i
n
g
m
u
l
t
i
p
l
e
l
a
n
gua
ge
s
i
n
c
o
m
m
u
ni
c
a
t
i
o
n,
a
dds
c
o
m
p
l
e
xi
t
y
to
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
by
i
nc
o
r
po
r
a
t
i
n
g
d
i
v
e
r
s
e
li
ngu
i
s
t
i
c
e
l
e
m
e
n
t
s
.
A
ddr
e
s
s
i
n
g
t
h
e
s
e
o
b
s
t
a
c
l
e
s
de
m
a
n
ds
s
p
e
c
i
a
li
z
e
d
a
ppr
o
a
c
h
e
s
t
h
a
t
a
c
c
o
un
t
f
o
r
t
h
e
i
n
t
r
i
c
a
c
i
e
s
o
f
b
o
t
h
t
h
e
T
a
m
il
l
a
n
gua
ge
a
n
d
c
o
de
-
m
i
xe
d
t
e
x
t
,
un
de
r
s
c
o
r
i
n
g
t
h
e
n
e
c
e
s
s
i
t
y
f
o
r
de
d
i
c
a
t
e
d
r
e
s
e
a
r
c
h
a
n
d
m
e
t
h
o
do
l
o
g
i
e
s
i
n
t
hi
s
d
i
s
t
i
nc
t
i
ve
do
m
a
i
n
.
T
hi
s
pa
pe
r
us
e
s
w
o
r
d
e
m
be
dd
i
n
g
m
e
t
h
o
ds
a
n
d
m
a
c
hi
n
e
l
e
a
r
ni
ng
(
M
L
)
t
o
c
l
a
s
s
i
f
y
T
a
mi
l
ly
r
i
c
a
l
t
we
e
t
s
tat
e
m
e
n
t
s
.
E
x
pe
r
i
m
e
n
t
s
n
o
t
a
bl
y
e
m
p
h
a
s
i
z
e
F
a
s
t
T
e
x
t
wo
r
d
e
m
b
e
dd
i
ng
a
s
t
h
e
m
o
s
t
e
f
f
e
c
t
i
v
e
m
e
t
h
o
d,
s
h
o
wc
a
s
i
ng
s
upe
r
i
o
r
r
e
s
u
l
t
s
wi
t
h
a
r
e
m
a
r
ka
bl
e
78%
a
c
c
ur
a
c
y
whe
n
c
o
upl
e
d
w
i
t
h
t
h
e
s
uppo
r
t
v
e
c
t
or
c
l
a
s
s
i
f
i
c
a
t
i
o
n
(
S
V
C
)
m
o
de
l
.
T
h
e
s
u
bs
e
que
n
t
s
e
c
t
i
o
ns
o
f
t
h
e
pa
p
e
r
a
r
e
s
t
r
uc
t
ur
e
d
a
s
f
o
l
l
o
w
s
:
s
e
c
t
i
o
n
1
de
li
ne
a
t
e
s
t
h
e
n
e
c
e
s
s
i
t
y
o
f
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
f
o
r
t
h
e
T
a
m
il
l
a
n
gua
ge
a
n
d
i
d
e
n
t
i
f
i
e
s
r
e
s
e
a
r
c
h
ga
ps
.
S
e
c
t
i
o
n
2
pr
o
vi
de
s
a
n
o
v
e
r
vi
e
w
o
f
r
e
c
e
n
t
r
e
s
e
a
r
c
h
e
n
de
a
v
o
r
s
.
S
e
c
t
i
o
n
3
o
u
t
l
i
ne
s
t
h
e
pr
o
p
o
s
e
d
m
e
t
h
o
do
l
o
g
y
.
S
e
c
t
i
o
n
4
s
h
o
wc
a
s
e
s
e
x
pe
r
i
m
e
n
t
a
l
r
e
s
u
l
t
s
a
n
d
e
n
ga
ge
s
i
n
d
i
s
c
u
s
s
i
o
n
.
T
h
e
pa
pe
r
c
o
n
c
l
ude
s
i
n
s
e
c
t
i
o
n
5.
2.
M
E
T
HO
D
T
hi
s
s
e
c
t
i
o
n
o
f
f
e
r
s
a
n
o
ut
l
i
ne
o
f
c
ur
r
e
n
t
r
e
s
e
a
r
c
h
e
f
f
o
r
t
s
i
n
t
h
e
do
m
a
i
n
o
f
T
a
m
il
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
.
Se
e
t
al.
[
6
]
u
t
i
li
z
e
d
ML
a
l
go
r
i
t
hm
s
,
i
n
c
l
ud
i
ng
s
u
ppo
r
t
v
e
c
t
or
m
a
c
hi
ne
(
S
VM
)
,
M
a
x
e
n
t
c
l
a
s
s
if
i
e
r
,
de
c
i
s
i
o
n
t
r
e
e
(
DT
)
,
a
n
d
Na
i
v
e
B
a
y
e
s
,
to
c
l
a
s
s
if
y
T
a
mi
l
m
o
vi
e
r
e
vi
e
w
s
i
n
t
o
p
o
s
i
t
i
v
e
a
n
d
n
e
ga
t
i
v
e
c
a
t
e
gor
i
e
s
.
T
h
e
da
t
a
s
e
t,
c
o
l
l
e
c
t
e
d
f
r
o
m
v
a
r
i
o
us
we
b
s
o
ur
c
e
s
,
i
nc
o
r
p
or
a
t
e
d
f
e
a
t
ur
e
s
f
r
o
m
T
a
m
il
S
e
n
t
i
wo
r
dn
e
t
,
wi
t
h
S
VM
de
m
o
ns
t
r
a
t
i
n
g
s
upe
r
i
o
r
pe
r
f
o
r
m
a
n
c
e
,
a
c
hi
e
vi
ng
a
n
a
c
c
ur
a
c
y
o
f
75.
9%
.
T
h
a
va
r
e
e
s
a
n
a
n
d
M
a
h
e
s
a
n
[
7]
c
r
i
t
i
c
a
ll
y
a
n
a
ly
z
e
r
e
c
e
n
t
l
i
t
e
r
a
t
ur
e
o
n
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
e
m
p
l
o
yi
ng
T
a
m
il
t
e
x
t
,
c
o
n
c
l
ud
i
ng
t
h
a
t
S
VM
a
n
d
r
e
c
ur
r
e
n
t
n
e
ur
a
l
n
e
t
wo
r
k
(
R
NN
)
c
l
a
s
s
if
i
e
r
s
u
s
i
ng
ter
m
f
r
e
que
n
c
y
-
i
nve
r
s
e
do
c
u
m
e
n
t
f
r
e
que
n
c
y
(
TF
-
I
DF
)
a
n
d
W
o
r
d2v
e
c
f
e
a
t
ur
e
s
o
u
t
pe
r
f
o
r
m
gr
a
m
m
a
r
r
u
l
e
-
b
a
s
e
d
c
l
a
s
s
if
i
c
a
t
i
o
n
s
a
n
d
ot
h
e
r
c
l
a
s
s
i
f
i
e
r
s
.
Us
i
n
g
d
i
f
f
e
r
e
n
t
c
o
r
p
or
a
a
n
d
f
e
a
t
ur
e
r
e
pr
e
s
e
n
t
a
t
i
o
n
t
e
c
hni
que
s
,
T
h
a
v
a
r
e
e
s
a
n
a
n
d
M
a
h
e
s
a
n
[
8]
e
x
pe
r
im
e
n
t
e
d
w
i
t
h
v
a
r
i
o
us
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
a
ppr
o
a
c
he
s
,
i
n
c
l
ud
i
ng
l
e
xi
c
o
n
-
b
a
s
e
d,
s
upe
r
vi
s
e
d
ML
,
hy
b
r
i
d,
a
n
d
c
l
us
t
e
r
i
n
g
w
i
t
h
ba
g
o
f
wo
r
d
m
e
t
h
o
ds
.
A
m
a
xi
m
u
m
a
c
c
ur
a
c
y
o
f
79%
wa
s
a
tt
a
i
n
e
d
f
o
r
t
h
e
UJ
_C
o
r
pus
_Opi
ni
o
ns
_No
un
s
c
o
r
pus
us
i
n
g
F
a
s
t
T
e
x
t
i
n
t
h
e
s
upe
r
vi
s
e
d
ML
a
ppr
o
a
c
h
,
i
n
c
o
r
por
a
t
i
n
g
b
ot
h
b
a
s
i
c
a
n
d
t
r
a
di
t
i
o
n
a
l
f
e
a
t
ur
e
s
.
B
a
b
u
a
nd
S
r
i
[
9]
i
n
t
r
o
duc
e
d
hy
b
r
i
d
de
e
p
l
e
a
r
ni
n
g
a
ppr
o
a
c
h
e
s
,
i
nc
l
ud
i
ng
c
o
nv
o
l
ut
i
o
na
l
n
e
ur
a
l
n
e
t
wo
r
k
-
bi
d
i
r
e
c
t
i
o
n
a
l
l
o
n
g
s
h
o
r
t
-
t
e
r
m
m
e
m
o
r
y
(
C
NN
-
B
i
L
S
T
M
)
,
C
NN
-
l
o
n
g
s
h
o
r
t
-
t
e
r
m
m
e
m
o
r
y
(
L
S
T
M
)
,
a
n
d
C
NN
-
bi
d
i
r
e
c
t
i
o
na
l
ga
t
e
d
r
e
c
ur
r
e
n
t
uni
t
(
B
i
G
R
U
)
,
l
e
ve
r
a
g
i
n
g
t
oo
l
s
s
uppo
r
ti
ng
t
h
e
T
a
m
i
l
l
a
n
gua
ge
f
o
r
da
t
a
pr
e
pa
r
a
t
i
o
n
.
T
h
e
m
o
de
l
s
we
r
e
e
v
a
l
ua
t
e
d
b
a
s
e
d
o
n
m
e
t
r
i
c
s
l
i
k
e
a
c
c
ur
a
c
y
,
r
e
c
a
l
l
,
a
n
d
F
1,
r
e
v
e
a
li
ng
t
h
a
t
C
NN
-
B
i
L
S
T
M
a
c
hiev
e
d
t
h
e
hi
g
h
e
s
t
a
c
c
ur
a
c
y
(
80.
2%
)
a
n
d
F
1
-
s
c
o
r
e
(
0.
64
)
c
o
m
pa
r
e
d
to
ot
h
e
r
m
o
de
l
s
,
e
f
f
e
c
t
i
v
e
ly
c
l
a
s
s
if
yi
ng
s
e
n
t
i
m
e
n
t
s
i
n
T
a
m
i
l
m
o
vi
e
r
e
vi
e
ws
.
Ki
s
h
o
r
e
e
t
al.
[
10]
e
m
p
l
o
ye
d
ML
m
o
de
l
s
f
o
r
s
e
n
t
i
m
e
n
t
a
na
l
y
s
i
s
i
n
T
a
m
il
a
n
d
T
u
l
u
l
a
n
gua
ge
s
,
ut
i
l
i
z
i
ng
a
c
o
de
-
m
i
xe
d
da
t
a
s
e
t
f
r
o
m
s
o
c
i
a
l
m
e
d
i
a
.
A
c
hi
e
vi
ng
64%
a
c
c
ur
a
c
y
a
n
d
a
43%
m
a
c
r
o
F
1
s
c
o
r
e
f
o
r
T
a
m
il
a
n
d
66%
a
c
c
ur
a
c
y
a
n
d
51%
m
a
c
r
o
F
1
s
c
o
r
e
f
o
r
T
ul
u
w
i
t
h
T
F
-
I
DF
f
e
a
t
ur
e
e
x
t
r
a
c
t
i
o
n
,
t
h
e
i
r
s
t
udy
hi
g
hl
i
g
h
t
s
t
h
e
e
f
f
i
c
a
c
y
o
f
t
h
e
T
F
-
I
DF
wi
t
h
l
o
g
i
s
t
i
c
r
e
gr
e
s
s
i
o
n
(
L
R
)
m
o
de
l
,
e
m
p
h
a
s
i
z
i
ng
i
t
s
pot
e
n
t
i
a
l
a
pp
l
i
c
a
t
i
o
ns
i
n
a
dd
r
e
s
s
i
ng
s
o
c
i
a
l
i
s
s
ue
s
a
n
d
f
o
s
t
e
r
i
n
g
i
nc
l
us
i
v
i
t
y
o
nl
i
ne
.
T
h
e
r
e
s
e
a
r
c
h
f
i
nd
i
ngs
u
n
e
qu
i
v
o
c
a
ll
y
i
nd
i
c
a
t
e
t
h
a
t
c
o
m
bi
n
i
ng
ML
m
o
de
l
s
w
i
t
h
wo
r
d
e
m
b
e
dd
i
ng
s
pr
o
duc
e
s
b
e
tt
e
r
r
e
s
u
l
t
s
.
T
h
e
pr
o
p
o
s
e
d
m
e
t
h
o
d
i
s
s
t
r
uc
t
u
r
e
d
i
n
t
o
t
w
o
di
s
t
i
n
c
t
i
v
e
p
h
a
s
e
s
.
I
n
t
h
e
i
ni
t
i
a
l
p
h
a
s
e
,
wo
r
d
e
m
b
e
dd
i
ng
s
a
r
e
ge
n
e
r
a
t
e
d
f
o
r
e
a
c
h
wo
r
d
i
n
T
a
m
il
t
e
x
t
us
i
n
g
f
o
ur
di
v
e
r
s
e
e
m
be
dd
i
ng
m
e
t
h
o
ds
:
c
o
un
t
,
T
F
-
I
DF
,
Ha
s
hi
ng,
W
o
r
d2Ve
c
,
a
n
d
F
a
s
t
T
e
x
t
.
T
h
e
s
e
t
e
c
hni
qu
e
s
a
r
e
e
m
p
l
o
y
e
d
to
v
e
c
t
or
i
z
e
t
h
e
T
a
m
il
t
e
x
t
,
p
r
o
v
i
d
i
ng
a
c
o
m
pr
e
h
e
ns
i
ve
r
e
pr
e
s
e
n
t
a
t
i
o
n
o
f
t
h
e
s
e
m
a
n
t
i
c
a
n
d
c
o
n
t
e
x
t
ua
l
i
n
f
o
r
m
a
t
i
o
n
pr
e
s
e
n
t
i
n
t
h
e
l
a
n
gua
ge
.
M
o
vi
n
g
t
o
t
h
e
s
e
c
o
n
d
ph
a
s
e
,
e
i
g
h
t
di
s
t
i
n
c
t
ML
m
e
t
h
o
ds
a
r
e
e
m
p
l
o
y
e
d.
E
a
c
h
m
e
t
h
o
d
i
s
i
nd
i
v
i
dua
ll
y
t
r
a
i
n
e
d
a
n
d
t
e
s
t
e
d
to
e
v
a
l
ua
t
e
i
t
s
c
l
a
s
s
if
i
c
a
t
i
o
n
pe
r
f
o
r
m
a
nc
e
,
t
h
e
r
e
by
e
n
a
bli
ng
a
t
h
o
r
o
ugh
a
s
s
e
s
s
m
e
n
t
o
f
t
h
e
e
f
f
e
c
t
i
ve
n
e
s
s
o
f
t
h
e
pr
o
p
o
s
e
d
a
ppr
o
a
c
h
,
a
s
de
pi
c
t
e
d
i
n
F
i
gur
e
1.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
E
mpo
w
e
r
ing
lo
w
-
r
e
s
our
c
e
languages
:
a
mac
hine
lear
ning
appr
oac
h
to
…
(
Salee
m
R
aja
A
bdul
Sama
d
)
943
F
i
gur
e
1.
P
r
o
p
o
s
e
d
m
e
t
h
o
d
2.
1.
Dat
as
e
t
T
h
e
da
t
a
s
e
t
c
o
m
pr
i
s
e
s
1,
000
t
we
e
t
s
s
o
ur
c
e
d
f
r
o
m
T
w
i
t
t
e
r
,
e
a
c
h
l
a
b
e
l
e
d
"
Ha
pp
y
"
o
r
"
S
a
d.
"
T
hi
s
da
t
a
s
e
t
pr
i
m
a
r
i
ly
a
im
s
t
o
f
a
c
il
i
t
a
t
e
bi
na
r
y
c
l
a
s
s
if
i
c
a
t
i
o
n
,
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
,
a
n
d
ot
h
e
r
NL
P
t
a
s
ks
.
N
otably
,
t
h
e
d
i
s
t
r
i
b
ut
i
o
n
o
f
l
a
b
e
l
s
i
s
b
a
l
a
n
c
e
d,
w
i
t
h
50%
o
f
t
h
e
t
we
e
t
s
c
a
t
e
gor
i
z
e
d
a
s
"
S
a
d"
a
n
d
t
h
e
r
e
m
a
i
n
i
ng
50%
a
s
"
Ha
pp
y
.
"
T
hi
s
b
a
l
a
n
c
e
d
r
e
pr
e
s
e
n
t
a
t
i
o
n
e
ns
ur
e
s
t
h
e
da
t
a
s
e
t
i
s
we
l
l
-
s
u
i
t
e
d
f
o
r
t
r
a
i
ni
ng
a
n
d
e
va
l
u
a
t
i
n
g
m
o
de
l
s
i
n
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
a
n
d
r
e
l
a
t
e
d
NL
P
a
pp
l
i
c
a
t
i
o
n
s
[
11]
.
2.
2
.
Dat
a
c
l
e
an
in
g
Da
t
a
c
l
e
a
ni
ng
i
n
t
h
e
c
o
n
t
e
x
t
o
f
T
a
m
il
t
e
x
t
(
l
yr
i
c
s
)
i
nv
o
l
v
e
s
t
h
e
r
e
m
o
v
a
l
o
f
s
pe
c
i
a
l
s
ym
b
o
l
s
,
a
l
p
h
a
b
e
t
s
,
a
n
d
n
u
m
be
r
s
to
e
n
s
ur
e
a
r
e
f
i
ne
d
a
n
d
s
t
a
n
da
r
d
i
z
e
d
da
t
a
s
e
t
.
T
hi
s
pr
o
c
e
s
s
e
nh
a
n
c
e
s
t
h
e
qua
l
it
y
o
f
t
h
e
t
e
x
t
da
t
a
by
e
l
im
i
na
t
i
n
g
unn
e
c
e
s
s
a
r
y
e
l
e
m
e
n
t
s
t
h
a
t
m
a
y
n
o
t
c
o
n
t
r
i
b
ut
e
to
t
h
e
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
tas
k.
T
h
e
c
l
e
a
ni
ng
s
t
e
ps
t
y
p
i
c
a
ll
y
i
nc
l
ude
s
t
r
i
pp
i
ng
a
wa
y
p
un
c
t
ua
t
i
o
n
m
a
r
ks
,
s
pe
c
i
a
l
c
h
a
r
a
c
t
e
r
s
,
a
n
d
n
u
m
e
r
ic
v
a
l
ue
s
,
l
e
a
vi
ng
b
e
hi
nd
a
pr
e
pr
o
c
e
s
s
e
d
t
e
x
t
m
o
r
e
c
o
n
duc
i
ve
to
a
c
c
ur
a
t
e
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
.
T
hi
s
m
e
t
i
c
u
l
o
us
c
l
e
a
ni
ng
a
i
d
s
i
n
c
r
e
a
t
i
n
g
a
s
t
r
e
a
m
li
ne
d
a
n
d
u
ni
f
o
r
m
da
t
a
s
e
t
,
o
p
t
i
mi
z
i
ng
t
h
e
s
u
bs
e
que
n
t
a
n
a
ly
s
i
s
a
n
d
m
o
de
l
tr
a
i
ni
n
g
s
t
a
ge
s
.
2.
3
.
Ve
c
t
or
iz
in
g
o
r
e
m
b
e
d
d
in
g
Ve
c
to
r
i
z
i
ng
o
r
e
m
be
dd
i
n
g
T
a
mi
l
t
e
x
t
i
nv
o
l
ve
s
t
r
a
n
s
f
o
r
m
i
ng
t
e
x
t
ua
l
da
t
a
i
n
t
o
n
u
m
e
r
i
c
a
l
r
e
pr
e
s
e
n
t
a
t
i
o
ns
t
h
a
t
c
a
p
t
ur
e
s
e
m
a
n
t
i
c
a
n
d
c
o
n
t
e
x
t
ua
l
i
nf
o
r
m
a
t
i
o
n
.
Va
r
i
o
us
t
e
c
h
ni
que
s
,
s
uc
h
a
s
c
o
un
t
v
e
c
t
o
r
i
z
a
t
i
o
n
,
T
F
-
I
DF
,
Ha
s
hi
ng,
W
o
r
d2Ve
c
,
a
n
d
F
a
s
t
T
e
x
t
,
a
r
e
e
m
p
l
o
y
e
d
t
o
c
o
n
v
e
r
t
e
a
c
h
wo
r
d
o
r
d
o
c
um
e
n
t
i
n
t
o
a
c
o
r
r
e
s
p
o
n
d
i
n
g
ve
c
t
or
i
n
a
hi
g
h
-
d
i
m
e
ns
i
o
n
a
l
s
pa
c
e
[
12]
,
[
13
]
.
T
h
e
s
e
v
e
c
t
or
i
z
a
t
i
o
n
m
e
t
h
o
ds
a
r
e
c
r
uc
i
a
l
i
n
pr
e
p
a
r
i
n
g
t
h
e
T
a
m
il
t
e
x
t
f
o
r
ML
m
o
de
l
s
,
f
a
c
il
i
t
a
t
i
n
g
t
a
s
ks
l
i
ke
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
.
B
y
r
e
pr
e
s
e
n
t
i
ng
wor
ds
o
r
d
o
c
um
e
n
t
s
a
s
n
u
m
e
r
i
c
a
l
v
e
c
t
o
r
s
,
t
h
e
s
e
t
e
c
hni
que
s
e
n
a
bl
e
a
l
go
r
i
t
hm
s
t
o
p
r
o
c
e
s
s
a
n
d
u
n
de
r
s
t
a
n
d
t
h
e
i
nhe
r
e
n
t
pa
tt
e
r
n
s
a
n
d
r
e
l
a
t
i
o
ns
hi
ps
w
i
t
hi
n
t
h
e
l
a
n
gua
ge
,
c
o
n
t
r
i
b
ut
i
n
g
to
m
o
r
e
e
f
f
e
c
t
i
v
e
a
n
d
a
c
c
ur
a
t
e
c
o
m
put
a
t
i
o
n
a
l
a
n
a
ly
s
i
s
o
f
T
a
m
il
t
e
x
t
ua
l
da
t
a
.
2.
3.
1
.
Coun
t
v
e
c
t
or
iz
e
r
C
o
un
t
v
e
c
t
or
i
z
a
t
i
o
n
i
s
a
s
i
m
p
l
e
t
e
c
hni
qu
e
f
o
r
t
r
a
n
s
f
o
r
m
i
ng
t
e
x
t
da
t
a
i
n
t
o
n
u
m
e
r
i
c
a
l
f
o
r
m
a
t
[
14
]
.
I
t
r
e
pr
e
s
e
n
t
s
e
a
c
h
do
c
u
m
e
n
t
a
s
a
v
e
c
to
r
o
f
t
e
r
m
f
r
e
que
n
c
i
e
s
.
F
o
r
T
a
m
i
l
s
e
n
t
i
m
e
n
t
c
l
a
s
s
if
i
c
a
t
i
o
n
,
e
a
c
h
uni
que
wo
r
d
i
n
t
h
e
c
o
r
pus
i
s
a
s
s
i
g
n
e
d
a
n
i
nde
x
,
a
n
d
t
h
e
c
o
un
t
o
f
o
c
c
ur
r
e
n
c
e
s
o
f
e
a
c
h
wo
r
d
i
s
us
e
d
to
c
o
n
s
t
r
uc
t
a
v
e
c
t
o
r
r
e
pr
e
s
e
n
t
a
t
i
o
n
.
(
,
)
=
2.
3.
2
.
TF
-
I
DF
v
e
c
t
or
i
z
e
r
T
h
e
T
F
-
I
DF
a
ppr
o
a
c
h
a
s
s
e
s
s
e
s
a
wo
r
d'
s
s
i
g
nif
i
c
a
n
c
e
i
n
a
do
c
u
m
e
n
t
a
b
o
ut
a
gr
o
up
o
f
do
c
u
m
e
n
t
s
[
15]
.
I
t
a
ppl
i
e
s
we
i
g
h
t
s
to
w
o
r
ds
us
i
n
g
T
F
a
n
d
I
DF.
(
,
,
)
=
(
,
)
(
,
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
1
4
,
N
o.
3
,
De
c
e
m
be
r
20
2
5
:
941
-
949
944
W
h
e
r
e
:
TF
(
w
,
d
)
=
N
u
m
b
e
r
of
oc
c
u
r
e
nc
e
s
of
w
or
d
in
d
oc
u
m
e
nt
T
ot
a
l
nu
m
b
e
r
of
w
or
d
s
in
I
DF
(
w
,
d
)
=
log
(
T
ot
a
l
nu
m
b
e
r
of
d
oc
u
m
e
nt
s
in
N
u
m
b
e
r
of
d
oc
u
m
e
nt
s
c
ont
a
i
ni
ng
w
or
d
)
2.
3.
3
.
Has
h
in
g
v
e
c
t
or
i
z
e
r
Ha
s
hi
ng
v
e
c
t
or
i
z
e
r
i
s
a
t
e
x
t
v
e
c
t
or
i
z
a
t
i
o
n
t
e
c
hnique
t
h
a
t
e
m
p
l
o
y
s
a
ha
s
h
f
u
n
c
t
i
o
n
to
m
a
p
wo
r
ds
d
i
r
e
c
t
l
y
t
o
f
e
a
t
ur
e
i
n
d
i
c
e
s
,
c
o
nv
e
r
t
i
n
g
t
h
e
m
i
n
t
o
f
i
x
e
d
-
s
i
z
e
v
e
c
t
o
r
s
[
15
]
.
2.
3.
4
.
Wor
d
2Ve
c
(
c
on
t
in
u
ou
s
b
ag
of
wor
d
s
)
W
o
r
d2v
e
c
i
s
a
p
o
pul
a
r
wo
r
d
e
m
be
dd
i
n
g
t
e
c
hni
qu
e
us
e
d
i
n
NL
P
t
a
s
ks
,
s
uc
h
a
s
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
[
16]
.
I
n
t
h
e
c
o
n
t
e
x
t
o
f
T
a
m
il
s
e
n
t
i
m
e
n
t
c
l
a
s
s
if
i
c
a
t
i
o
n
,
W
o
r
d2Ve
c
e
m
p
l
o
y
s
t
h
e
c
o
n
t
i
n
uo
us
b
a
g
o
f
wo
r
d
s
(
C
B
O
W
)
m
o
de
l
.
C
B
O
W
pr
e
d
i
c
t
s
a
t
a
r
ge
t
wor
d
b
a
s
e
d
o
n
i
t
s
c
o
n
t
e
x
t,
a
i
mi
ng
to
un
de
r
s
t
a
n
d
t
h
e
di
s
t
r
i
but
i
o
n
a
l
s
e
m
a
n
t
i
c
s
o
f
wo
r
ds
.
2.
3.
5
.
F
as
t
T
e
x
t
F
a
s
t
T
e
x
t
i
s
a
n
e
x
t
e
n
s
i
o
n
o
f
W
o
r
d2Ve
c
t
h
a
t
c
o
n
s
i
de
r
s
s
u
b
-
wo
r
d
i
nf
o
r
m
a
t
i
o
n
.
I
t
b
r
e
a
ks
wo
r
ds
i
n
t
o
s
m
a
l
l
e
r
n
-
gr
a
m
s
u
b
-
wo
r
ds
a
n
d
r
e
pr
e
s
e
n
t
s
t
h
e
m
a
s
t
h
e
s
u
m
o
f
t
h
e
s
e
s
u
b
-
wo
r
d
e
m
b
e
dd
i
ngs
[
1
7]
.
T
h
i
s
pa
r
t
i
c
u
l
a
r
l
y
b
e
n
e
f
i
t
s
l
a
n
gua
ge
s
l
i
ke
T
a
m
il
,
wh
e
r
e
wo
r
ds
c
a
n
h
a
v
e
c
o
m
p
l
e
x
m
o
r
ph
o
l
o
gi
c
a
l
s
t
r
uc
t
ur
e
s
.
2.
4.
Cr
os
s
va
l
id
at
ion
an
d
p
e
r
f
o
r
m
an
c
e
e
va
l
u
at
ion
F
o
l
l
o
w
i
ng
t
h
e
v
e
c
to
r
i
z
a
t
i
o
n
o
r
e
m
b
e
dd
i
ng
pr
o
c
e
s
s
,
a
c
o
m
pr
e
h
e
n
s
i
ve
10
-
f
o
l
d
c
r
o
s
s
-
v
a
l
i
da
t
i
o
n
[
18]
i
s
c
o
n
duc
t
e
d
us
i
n
g
e
i
g
h
t
d
i
v
e
r
s
e
M
L
s
c
h
e
m
e
s
,
s
u
c
h
a
s
S
VM
,
LR
,
Na
i
ve
B
a
y
e
s
,
r
a
n
do
m
f
o
r
e
s
t
(
R
F
)
,
DT
,
gr
a
d
i
e
n
t
b
oo
s
t
i
n
g
(
GB
)
,
e
x
t
r
e
m
e
gr
a
d
i
e
n
t
b
oo
s
t
i
ng
(
XG
B
)
,
a
n
d
A
da
B
o
o
s
t
[
19
]
-
[
23
]
.
T
h
i
s
m
e
t
i
c
u
l
o
us
e
v
a
l
ua
t
i
o
n
a
s
s
e
s
s
e
s
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
e
a
c
h
m
o
de
l
i
n
t
h
e
c
o
n
t
e
x
t
o
f
T
a
m
il
s
e
n
t
i
m
e
n
t
c
l
a
s
s
if
i
c
a
t
i
o
n
.
T
h
e
pe
r
f
o
r
m
a
n
c
e
i
s
m
e
a
s
ur
e
d
a
c
r
o
s
s
v
a
r
i
o
us
e
v
a
l
ua
t
i
o
n
m
e
t
r
i
c
s
,
i
n
c
l
ud
i
ng
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
a
n
d
F
1
s
c
o
r
e
.
E
a
c
h
ML
m
o
de
l
u
n
de
r
go
e
s
r
i
go
r
o
us
t
e
s
t
i
n
g
a
n
d
t
r
a
i
ni
ng
a
c
r
o
s
s
t
h
e
10
f
o
l
ds
,
e
n
s
ur
i
ng
a
r
o
b
us
t
a
s
s
e
s
s
m
e
n
t
o
f
i
t
s
e
f
f
i
c
a
c
y
i
n
h
a
n
d
li
ng
t
h
e
c
o
m
p
l
e
xi
t
i
e
s
o
f
T
a
m
il
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
.
T
h
e
c
h
o
s
e
n
e
va
l
ua
t
i
o
n
m
e
t
r
i
c
s
pr
o
vi
d
e
a
h
o
l
i
s
t
i
c
vi
e
w
o
f
t
h
e
m
o
de
l
'
s
pe
r
f
o
r
m
a
n
c
e
,
a
c
c
o
un
t
i
n
g
f
o
r
a
s
pe
c
t
s
s
uc
h
a
s
o
v
e
r
a
ll
c
o
r
r
e
c
t
n
e
s
s
(
a
c
c
ur
a
c
y
)
,
c
a
pa
bil
i
t
y
t
o
a
ppr
o
pr
i
a
t
e
l
y
i
de
n
t
i
f
y
po
s
i
t
i
ve
i
n
s
t
a
n
c
e
s
(
p
r
e
c
i
s
i
o
n
)
,
c
a
pa
bi
li
t
y
t
o
s
e
i
z
ur
e
a
l
l
po
s
i
t
i
ve
i
ns
t
a
nc
e
s
(
r
e
c
a
ll
)
,
a
n
d
t
h
e
h
a
r
m
o
ni
c
m
e
a
n
o
f
pr
e
c
i
s
i
o
n
a
n
d
r
e
c
a
l
l
(
F
1
s
c
o
r
e
)
[
24
]
-
[
30]
.
T
hi
s
m
u
l
t
if
a
c
e
t
e
d
e
v
a
l
ua
t
i
o
n
s
t
r
a
t
e
g
y
h
e
l
ps
i
de
n
t
i
f
y
t
h
e
a
ppr
o
pr
i
a
t
e
ML
m
o
de
l
f
o
r
a
c
hi
e
vi
ng
o
p
t
i
m
a
l
s
e
n
t
i
m
e
n
t
c
l
a
s
s
i
f
i
c
a
t
i
o
n
r
e
s
u
l
t
s
i
n
t
h
e
T
a
m
i
l
c
o
n
t
e
x
t
.
3.
RE
S
UL
T
S
AN
D
DI
S
CU
S
S
I
ON
T
h
e
e
x
pe
r
im
e
n
t
a
l
r
e
s
u
l
t
s
o
f
t
h
e
pr
o
p
o
s
e
d
m
e
t
h
o
d
we
r
e
c
o
n
duc
t
e
d
us
i
n
g
P
y
t
h
o
n
a
n
d
J
up
y
t
e
r
Not
e
b
oo
k,
l
e
v
e
r
a
g
i
ng
t
h
e
po
pu
l
a
r
S
Kl
e
a
r
n
pa
c
ka
g
e
f
o
r
ML
f
u
n
c
t
i
o
n
a
li
t
i
e
s
.
E
i
g
h
t
d
i
s
t
i
n
c
t
ML
m
o
de
l
s
,
n
a
m
e
ly
LR
,
S
VM
,
Na
i
ve
B
a
y
e
s
,
DT
,
RF
,
XGB
,
GB
,
a
n
d
A
da
B
o
o
s
t
,
we
r
e
e
m
p
l
o
y
e
d
f
o
r
e
v
a
l
u
a
t
i
o
n
.
T
a
bl
e
1
pr
e
s
e
n
t
s
t
h
e
e
x
pe
r
i
m
e
n
t
a
l
r
e
s
u
l
t
s
f
o
r
t
h
e
c
o
un
t
v
e
c
to
r
i
z
e
r
.
S
ub
s
e
que
n
t
t
a
bl
e
s
,
T
a
bl
e
s
2
to
5
,
s
h
o
wc
a
s
e
t
h
e
o
u
t
c
o
m
e
s
o
f
T
F
-
I
DF
,
Ha
s
hi
ng
v
e
c
t
o
r
i
z
e
r
,
W
o
r
d2Ve
c
,
a
n
d
F
a
s
t
T
e
x
t
e
m
be
dd
i
ngs
,
r
e
s
pe
c
t
i
v
e
ly
.
T
h
e
s
e
t
a
bl
e
s
c
o
l
l
e
c
t
i
v
e
ly
pr
o
vi
de
a
c
o
m
pr
e
h
e
n
s
i
v
e
o
v
e
r
vi
e
w
o
f
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
d
i
f
f
e
r
e
n
t
v
e
c
t
or
i
z
a
t
i
o
n
t
e
c
h
ni
que
s
a
n
d
wo
r
d
e
m
b
e
dd
i
ngs
i
n
t
h
e
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
t
a
s
k
f
o
r
t
h
e
T
a
m
il
l
a
n
gua
ge
.
E
a
c
h
t
a
bl
e
e
n
c
a
ps
u
l
a
t
e
s
t
h
e
e
v
a
l
ua
t
i
o
n
m
e
t
r
i
c
s
,
i
n
c
l
ud
i
ng
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
a
n
d
F
1
s
c
o
r
e
,
o
f
f
e
r
i
ng
i
ns
igh
t
s
i
n
t
o
t
h
e
e
f
f
e
c
t
i
v
e
ne
s
s
o
f
t
h
e
c
o
r
r
e
s
po
n
d
i
n
g
m
e
t
h
o
do
l
o
gi
e
s
.
T
a
bl
e
1.
P
e
r
f
o
r
m
a
nc
e
o
f
c
o
un
t
v
e
c
to
r
i
z
e
r
M
o
de
l
A
c
c
u
r
a
c
y
P
r
e
c
is
i
o
n
R
e
c
a
ll
F1
-
s
c
o
r
e
LR
68.38
68.56
71.11
69.20
S
V
C
68.59
68.54
73.64
70.12
G
N
B
57.36
62.36
32.62
42.25
DT
63.75
64.48
64.82
63.92
RF
70.45
73.78
69.13
69.86
GB
69.17
69.38
75.21
70.92
A
da
B
oo
s
t
64.65
65.57
66.02
64.21
X
G
B
67.30
68.24
68.75
67.52
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
E
mpo
w
e
r
ing
lo
w
-
r
e
s
our
c
e
languages
:
a
mac
hine
lear
ning
appr
oac
h
to
…
(
Salee
m
R
aja
A
bdul
Sama
d
)
945
F
a
s
t
T
e
x
t
,
a
p
o
we
r
f
u
l
wo
r
d
e
m
b
e
dd
i
ng
t
e
c
h
ni
qu
e
,
l
e
v
e
r
a
ge
s
pr
e
-
t
r
a
i
n
e
d
m
o
de
l
s
f
o
r
T
a
m
il
t
e
x
t
,
a
c
c
e
s
s
i
bl
e
o
n
t
h
e
F
a
s
t
T
e
x
t
we
b
s
i
t
e
.
T
h
e
pe
r
f
o
r
m
a
n
c
e
r
e
s
u
l
t
s
i
nd
i
c
a
t
e
t
h
a
t
F
a
s
t
T
e
x
t
w
or
d
e
m
be
dd
i
n
g
s
o
u
t
s
hi
n
e
o
t
h
e
r
m
e
t
h
o
ds
,
de
m
o
ns
t
r
a
t
i
n
g
s
up
e
r
i
o
r
e
f
f
e
c
t
i
ve
n
e
s
s
.
S
pe
c
i
f
i
c
a
ll
y
,
w
i
t
h
t
h
e
S
V
C
m
o
de
l
,
F
a
s
t
T
e
x
t
a
c
hi
e
ve
s
a
n
im
pr
e
s
s
i
ve
78%
a
c
c
ur
a
c
y
a
n
d
F
1
-
s
c
o
r
e
,
un
de
r
s
c
o
r
i
n
g
i
t
s
pr
o
we
s
s
i
n
c
a
pt
ur
i
n
g
n
u
a
n
c
e
d
s
e
m
a
n
t
i
c
s
a
n
d
c
o
n
t
r
i
b
ut
i
n
g
s
i
g
ni
f
i
c
a
n
t
l
y
t
o
t
h
e
s
uc
c
e
s
s
o
f
s
e
nt
i
m
e
n
t
a
n
a
ly
s
i
s
i
n
t
h
e
T
a
m
il
l
a
n
gua
ge
.
T
a
bl
e
2.
P
e
r
f
o
r
m
a
nc
e
o
f
T
F
-
I
DF
v
e
c
t
or
i
z
e
r
M
o
de
l
A
c
c
u
r
a
c
y
P
r
e
c
is
i
o
n
R
e
c
a
ll
F1
-
s
c
o
r
e
L
o
gR
68.59
68.60
71.89
69.57
S
V
C
67.89
67.45
72.08
69.14
G
N
B
57.26
62.01
36.75
45.51
DT
62.16
63.34
64.02
62.56
RF
68.89
69.08
71.69
69.53
GB
69.57
69.09
75.21
71.05
A
da
B
oo
s
t
66.91
68.15
67.38
66.80
X
G
B
65.43
66.30
66.58
65.37
T
a
bl
e
3.
P
e
r
f
o
r
m
a
nc
e
o
f
Ha
s
hi
ng
v
e
c
t
or
i
z
e
r
M
o
de
l
A
c
c
u
r
a
c
y
P
r
e
c
is
i
o
n
R
e
c
a
ll
F1
-
s
c
o
r
e
L
o
gR
66.23
66.98
68.35
66.98
S
V
C
65.93
66.83
67.76
66.61
G
N
B
58.83
59.14
54.63
56.14
DT
58.92
60.49
56.76
57.90
RF
67.51
69.08
67.38
67.38
GB
68.77
69.33
74.23
70.53
A
da
B
oo
s
t
64.05
65.71
63.47
63.22
X
G
B
65.04
65.81
66.78
65.51
T
a
bl
e
4.
P
e
r
f
o
r
m
a
nc
e
o
f
W
o
r
d2Ve
c
e
m
be
dd
i
n
g
M
o
de
l
A
c
c
u
r
a
c
y
P
r
e
c
is
i
o
n
R
e
c
a
ll
F1
-
s
c
o
r
e
L
o
gR
63.68
64.98
56.76
60.49
S
V
C
66.39
72.49
50.46
59.25
G
N
B
59.12
71.24
27.10
38.91
DT
56.91
55.75
58.53
56.99
RF
64.91
65.20
61.26
63.04
GB
66.52
66.41
63.78
64.98
A
da
B
oo
s
t
59.49
59.07
57.01
57.86
X
G
B
62.46
61.53
63.29
62.26
T
a
bl
e
5.
P
e
r
f
o
r
m
a
nc
e
o
f
F
a
s
t
T
e
x
t
e
m
b
e
dd
i
ng
M
o
de
l
A
c
c
u
r
a
c
y
P
r
e
c
is
i
o
n
R
e
c
a
ll
F1
-
S
c
o
r
e
L
o
gR
75.00
76.00
73.00
75.00
S
V
C
78.00
78.00
77.00
78.00
G
N
B
71.00
74.00
66.00
69.00
DT
63.00
64.00
63.00
63.00
RF
74.00
76.00
72.00
74.00
GB
74.00
75.00
73.00
74.00
A
da
B
oo
s
t
71.00
71.00
70.00
71.00
X
G
B
75.00
76.00
74.00
75.00
F
i
gur
e
2
i
ll
us
t
r
a
t
e
s
t
h
e
r
e
c
e
i
v
e
r
o
pe
r
a
t
i
n
g
c
h
a
r
a
c
ter
i
s
t
i
c
(
R
OC
)
a
r
e
a
un
de
r
t
h
e
c
ur
v
e
(
A
UC
)
[
24]
,
[
25]
f
o
r
F
a
s
t
T
e
x
t
w
or
d
e
m
b
e
dd
i
ngs
c
o
up
l
e
d
w
i
t
h
t
h
e
S
VC
m
o
de
l
.
On
t
h
e
ot
h
e
r
h
a
n
d,
F
i
gur
e
3
pr
e
s
e
n
t
s
t
h
e
c
o
nf
us
i
o
n
m
a
t
r
i
x
a
s
s
o
c
i
a
t
e
d
w
i
t
h
t
hi
s
c
o
nf
i
gur
a
t
i
o
n
.
T
h
e
s
e
vi
s
u
a
l
i
z
a
t
i
o
n
s
o
f
f
e
r
i
ns
i
g
h
t
f
u
l
i
n
f
o
r
m
a
t
i
o
n
i
n
t
o
t
h
e
m
o
de
l
's
d
i
s
c
r
im
i
na
t
o
r
y
po
we
r
a
n
d
i
t
s
pe
r
f
o
r
m
a
n
c
e
i
n
d
i
s
t
i
n
gu
i
s
hi
ng
b
e
t
we
e
n
d
if
f
e
r
e
n
t
s
e
n
t
i
m
e
n
t
c
l
a
s
s
e
s
i
n
T
a
m
i
l
t
e
x
t
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
1
4
,
N
o.
3
,
De
c
e
m
be
r
20
2
5
:
941
-
949
946
F
i
gur
e
2.
R
OC
-
A
UC
c
ur
ve
f
o
r
F
a
s
t
T
e
x
t
w
o
r
d
e
m
be
dd
i
n
g
w
i
t
h
S
VC
m
o
de
l
F
i
gur
e
3.
C
o
nf
u
s
i
o
n
m
a
t
r
i
x
f
o
r
F
a
s
t
T
e
x
t
w
o
r
d
e
m
be
dd
i
n
g
w
i
t
h
S
VC
m
o
de
l
4.
CONC
L
USI
ON
T
h
e
pr
o
p
o
s
e
d
m
e
t
h
o
do
l
o
g
y
s
y
s
t
e
m
a
t
i
c
a
l
ly
e
v
a
l
u
a
t
e
s
di
v
e
r
s
e
t
e
x
t
e
m
b
e
dd
i
ng
m
e
t
h
o
ds
a
l
o
n
gs
i
de
v
a
r
i
o
us
ML
a
l
go
r
i
t
hm
s
t
o
e
n
h
a
n
c
e
s
e
n
t
i
m
e
n
t
c
l
a
s
s
if
i
c
a
t
i
o
n
f
o
r
T
a
m
il
t
e
x
t
,
f
o
c
us
i
ng
pa
r
t
i
c
u
l
a
r
l
y
o
n
ly
r
i
c
s
.
Our
f
i
nd
i
n
g
s
u
n
de
r
s
c
o
r
e
t
h
e
e
f
f
e
c
t
i
v
e
n
e
s
s
o
f
F
a
s
t
T
e
x
t
wo
r
d
e
m
b
e
dd
i
ngs
t
h
r
o
ugh
e
x
t
e
n
s
i
ve
e
x
p
e
r
i
men
t
a
t
i
o
n
,
s
h
o
wc
a
s
i
ng
s
upe
r
i
o
r
pe
r
f
o
r
m
a
nc
e
w
i
t
h
a
n
o
t
a
bl
e
78%
a
c
c
ur
a
c
y
w
he
n
e
m
p
l
o
y
e
d
w
i
t
h
t
h
e
S
VC
m
o
de
l
.
T
h
e
r
e
s
u
l
t
s
a
f
f
i
r
m
t
h
e
s
i
g
nif
i
c
a
n
c
e
o
f
l
e
v
e
r
a
g
i
ng
F
a
s
t
T
e
x
t
e
m
b
e
dd
i
ngs
f
o
r
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
i
n
T
a
m
il
ly
r
i
c
s
,
e
m
p
h
a
s
i
z
i
ng
t
h
e
i
r
po
t
e
n
t
i
a
l
t
o
c
a
p
t
ur
e
n
ua
nc
e
d
li
n
gu
i
s
t
i
c
n
u
a
n
c
e
s
a
n
d
a
c
hi
e
v
e
c
o
m
m
e
n
d
a
bl
e
c
l
a
s
s
if
i
c
a
t
i
o
n
a
c
c
ur
a
c
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
E
mpo
w
e
r
ing
lo
w
-
r
e
s
our
c
e
languages
:
a
mac
hine
lear
ning
appr
oac
h
to
…
(
Salee
m
R
aja
A
bdul
Sama
d
)
947
F
UN
DI
NG
I
N
F
ORM
AT
I
ON
A
ut
h
o
r
s
s
t
a
t
e
n
o
f
u
n
d
i
ng
i
nv
o
l
v
e
d.
AU
T
HO
R
CONT
RI
B
UT
I
ONS
S
T
AT
E
M
E
NT
Nam
e
of
Aut
h
or
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
S
a
l
e
e
m
R
a
j
a
Ab
du
l
S
a
m
a
d
P
r
a
de
e
pa
Ga
n
e
s
a
n
J
us
t
i
n
R
a
j
a
s
e
k
a
r
a
n
M
a
d
h
u
b
a
l
a
R
a
d
h
a
kr
i
s
hn
a
n
P
e
e
r
b
a
s
ha
S
h
e
bb
e
e
r
B
a
s
h
a
Va
r
a
l
a
k
s
hm
i
K
uppu
s
a
my
C
:
C
o
n
c
e
pt
ua
li
z
a
ti
o
n
M
:
M
e
th
o
d
o
l
o
g
y
So
:
So
f
twa
r
e
Va
:
Va
li
da
ti
o
n
Fo
:
Fo
r
ma
l
a
na
l
y
s
is
I
:
I
nve
s
ti
ga
ti
o
n
R
:
R
e
s
o
u
r
c
e
s
D
:
D
a
ta
C
ur
a
ti
o
n
O
:
W
r
it
in
g
-
O
r
ig
in
a
l
D
r
a
f
t
E
:
W
r
it
in
g
-
R
e
v
i
e
w
&
E
di
ti
ng
Vi
:
Vi
s
ua
li
z
a
ti
o
n
Su
:
Su
pe
r
v
is
io
n
P
:
P
r
o
j
e
c
t
a
dmi
ni
s
tr
a
ti
o
n
Fu
:
Fu
ndi
ng a
c
qui
s
it
i
o
n
CONF
L
I
CT
OF
I
NT
E
RE
S
T
S
T
AT
E
M
E
NT
A
ut
h
o
r
s
de
c
l
a
r
e
n
o
c
o
nf
li
c
t
o
f
i
n
t
e
r
e
s
t
s
DA
T
A
AV
AI
L
AB
I
L
I
T
Y
T
h
e
da
t
a
t
h
a
t
s
upp
o
r
t
t
h
e
f
i
nd
i
n
g
s
o
f
t
hi
s
s
t
ud
y
a
r
e
a
v
a
i
l
a
bl
e
f
r
o
m
t
h
e
c
o
r
r
e
s
p
o
n
d
i
n
g
a
ut
h
o
r
,
up
o
n
r
e
a
s
o
n
a
bl
e
r
e
que
s
t
.
RE
F
E
R
E
NC
E
S
[
1]
B
.
K
r
is
hna
mur
ti
, “
T
a
mi
l
la
ngua
g
e
,”
B
r
it
anni
c
a
. ht
tp
s
:/
/ww
w
.br
it
a
nni
c
a
.c
o
m
/t
o
pi
c
/
T
a
mi
l
-
la
ngua
ge
(
a
c
c
e
s
s
e
d F
e
b. 26, 2024)
.
[
2]
Q
.
A
.
X
u,
V
.
C
ha
ng,
a
nd
C
.
J
a
y
n
e
,
“
A
s
y
s
t
e
ma
ti
c
r
e
vi
e
w
of
s
oc
ia
l
m
e
di
a
-
ba
s
e
d
s
e
nt
im
e
nt
a
na
l
y
s
is
:
e
m
e
r
gi
ng
t
r
e
nds
a
nd
c
ha
ll
e
ng
e
s
,”
D
e
c
is
io
n A
nal
y
ti
c
s
J
our
nal
, v
o
l.
3, p. 100073, J
un.
2022, do
i:
10.1016/j
.da
j
o
u
r
.2022.100073.
[
3]
“
S
e
nt
im
e
nt
a
na
l
y
s
is
e
x
pl
a
in
e
d
:
f
r
o
m
th
e
o
r
y
t
o
r
e
a
l
-
w
o
r
ld
a
ppl
ic
a
ti
o
ns
,”
A
r
c
hi
v
e
,
2023.
ht
tp
s
:/
/a
r
c
hi
ve
.
c
o
m/
bl
o
g/
s
e
n
ti
m
e
nt
-
a
na
l
y
s
is
(
a
c
c
e
s
s
e
d F
e
b. 26, 2024)
.
[
4]
R
.
P
a
dma
ma
la
a
nd
V
.
P
r
e
ma
,
“
S
e
nt
im
e
nt
a
na
l
y
s
is
of
o
nl
in
e
T
a
mi
l
c
o
n
te
nt
s
us
in
g
r
e
c
ur
s
i
v
e
n
e
ur
a
l
ne
twor
k
mo
d
e
ls
a
ppr
o
a
c
h
f
o
r
T
a
mi
l
la
ngua
ge
,”
in
2017
I
E
E
E
I
nt
e
r
nat
io
nal
C
onf
e
r
e
n
c
e
on
Sm
ar
t
T
e
c
hnol
ogi
e
s
and
M
anage
m
e
nt
f
o
r
C
om
put
i
ng,
C
om
m
uni
c
at
io
n, C
ont
r
ol
s
, E
ne
r
gy
and M
at
e
r
ia
ls
(
I
C
ST
M
)
, A
ug. 2017, pp. 28
–
31, do
i:
10.1109/
I
C
S
T
M
.2017.8089122.
[
5]
S
.
A
nbukka
r
a
s
i
a
nd
S
.
V
a
r
a
dha
ga
na
pa
th
y
,
“
A
na
l
y
z
in
g
s
e
nt
im
e
nt
in
T
a
mi
l
tw
e
e
ts
us
in
g
de
e
p
ne
u
r
a
l
ne
two
r
k,”
in
2020
F
o
ur
th
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
C
o
m
put
in
g
M
e
th
odol
ogi
e
s
and
C
om
m
uni
c
at
io
n
(
I
C
C
M
C
)
,
M
a
r
.
2020,
pp.
449
–
453,
do
i:
10.1109/
I
C
C
M
C
48092.2020.I
C
C
M
C
-
00084.
[
6]
S
.
S
e
,
R
.
V
in
a
y
a
kuma
r
,
M
.
A
.
K
uma
r
,
a
nd
K
.
P
.
S
o
ma
n,
“
P
r
e
di
c
ti
ng
th
e
s
e
nt
im
e
nt
a
l
r
e
v
i
e
w
s
in
T
a
mi
l
m
ov
i
e
us
in
g
ma
c
hi
ne
le
a
r
ni
ng a
lg
o
r
it
h
ms
,”
I
ndi
an J
our
nal
of
Sc
ie
n
c
e
and T
e
c
hnol
og
y
, vo
l.
9, n
o
. 45, D
e
c
. 2016, d
o
i:
10.17485
/i
js
t/
2016/
v
9i
45/
1064
82.
[
7]
S
.
T
ha
v
a
r
e
e
s
a
n
a
nd
S
.
M
a
he
s
a
n,
“
R
e
v
ie
w
o
n
s
e
nt
im
e
nt
a
na
ly
s
is
in
T
a
mi
l
t
e
x
ts
,”
J
our
nal
o
f
Sc
ie
nc
e
,
v
ol
.
9,
no
.
2,
pp.
1
–
9,
D
e
c
. 2018, d
oi
:
10.4038/j
s
c
.
v
9i
2.14.
[
8]
S
.
T
ha
v
a
r
e
e
s
a
n
a
nd
S
.
M
a
he
s
a
n,
“
S
e
nt
im
e
nt
a
na
l
y
s
is
in
T
a
mi
l
te
x
ts
:
a
s
tu
d
y
o
n
ma
c
hi
n
e
le
a
r
n
in
g
te
c
hni
qu
e
s
a
nd
f
e
a
t
ur
e
re
pr
e
s
e
n
t
a
ti
o
n,”
in
2019
14t
h
C
onf
e
r
e
nc
e
on
I
ndu
s
tr
ia
l
an
d
I
nf
or
m
at
io
n
Sy
s
te
m
s
(
I
C
I
I
S)
,
D
e
c
.
2019,
pp.
320
–
325,
do
i:
10.1109/I
C
I
I
S
47346.2019.9063341.
[
9]
R
.
B
a
bu
a
nd
S
.
S
r
i,
“
S
e
nt
im
e
nt
a
na
l
y
s
is
in
T
a
mi
l
la
ngua
g
e
us
in
g
h
y
br
id
de
e
p
l
e
a
r
ni
ng
a
ppr
o
a
c
h,”
N
a
ti
o
na
l
C
o
ll
e
g
e
of
I
r
e
la
nd,
2022.
[
10]
K
.
K
.
P
o
nnus
a
m
y
,
C
.
R
a
jk
uma
r
,
P
.
K
.
K
uma
r
e
s
a
n,
E
.
S
he
r
l
y
,
a
nd
R
.
P
r
i
y
a
dha
r
s
hi
ni
,
“
V
E
L
@
D
r
a
v
id
ia
n
L
a
ng
T
e
c
h:
s
e
nt
i
me
nt
a
na
l
y
s
is
o
f
T
a
mi
l
a
nd
T
ul
u,”
in
D
r
av
id
ia
nL
angT
e
c
h
2023
-
3r
d
W
or
k
s
hop
on
Spe
e
c
h
and
L
anguage
T
e
c
hnol
ogi
e
s
f
or
D
r
a
v
i
di
an
L
anguage
s
,
as
s
o
c
ia
te
d
w
it
h
14t
h
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
R
e
c
e
nt
A
dv
anc
e
s
in
N
at
u
r
al
L
anguage
P
r
oc
e
s
s
in
g,
R
A
N
L
P
20
23
-
P
r
oc
e
e
di
ngs
, 2023, pp. 211
–
216, do
i:
10.26615/978
-
954
-
452
-
0
85
-
4_030.
[
11]
R
.
C
.
M
o
or
e
,
D
.
P
.
W
.
E
ll
is
,
E
.
F
o
ns
e
c
a
,
S
.
H
e
r
s
he
y
,
A
.
J
a
ns
e
n,
a
nd
M
.
P
la
ka
l,
“
D
a
ta
s
e
t
ba
la
nc
in
g
c
a
n
hur
t
m
o
d
e
l
p
e
r
f
or
ma
n
c
e
,”
in
I
C
A
SS
P
2023
-
2023
I
E
E
E
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
A
c
ous
ti
c
s
,
Spe
e
c
h
and
Si
gnal
P
r
oc
e
s
s
in
g
(
I
C
A
SSP
)
,
J
un.
2023,
pp. 1
–
5, do
i
:
10.1109/
I
C
A
S
S
P
49357.2023.10095255.
[
12]
S
.
R
.
A
.
S
a
ma
d
e
t
al
.
,
“
A
na
ly
s
is
o
f
th
e
pe
r
f
or
ma
n
c
e
im
pa
c
t
of
f
in
e
-
tu
n
e
d
ma
c
hi
n
e
l
e
a
r
ni
ng
m
o
de
l
f
or
phi
s
h
in
g
U
R
L
d
e
t
e
c
ti
on,”
E
le
c
tr
oni
c
s
, v
o
l.
12, n
o
. 7, p. 1642, M
a
r
. 2023, d
o
i:
10.3390/
e
l
e
c
tr
o
ni
c
s
12071642.
[
13]
S
.
R
.
A
.
S
a
ma
d,
P
.
G
a
ne
s
a
n,
J
.
R
a
ja
s
e
ka
r
a
n,
M
.
R
a
dha
kr
is
hna
n,
H
.
A
mm
a
ip
pa
n,
a
nd
V
.
R
a
ma
mur
th
y
,
“
S
mi
s
h
G
ua
r
d:
le
ve
r
a
gi
ng
ma
c
hi
ne
le
a
r
n
in
g
a
nd
na
tu
r
a
l
la
ngua
ge
pr
oc
e
s
s
in
g
f
o
r
s
mi
s
hi
n
g
de
t
e
c
t
i
o
n,”
I
nt
e
r
nat
io
nal
J
our
nal
of
A
dv
anc
e
d
C
om
put
e
r
S
c
i
e
nc
e
and A
ppl
ic
at
i
ons
, vo
l.
14, n
o
. 11, pp. 586
–
593, 2023, d
o
i
:
10.1
4569/I
J
A
C
S
A
.2023.0141160.
[
14]
A
.
S
.
S
.
R
a
ja
,
G
.
P
r
a
de
e
pa
,
S
.
M
a
ha
la
ks
hmi
,
a
nd
M
.
S
.
J
a
y
a
k
uma
r
,
“
N
a
tu
r
a
l
la
ngua
ge
ba
s
e
d
ma
li
c
io
us
d
o
ma
in
de
t
e
c
ti
o
n
us
in
g
ma
c
hi
ne
l
e
a
r
ni
ng
a
nd
de
e
p
le
a
r
ni
ng,”
Sc
ie
nt
if
ic
and
T
e
c
hni
c
al
J
our
nal
o
f
I
n
f
or
m
at
io
n
T
e
c
hnol
ogi
e
s
,
M
e
c
hani
c
s
and
O
pt
ic
s
,
vo
l.
23, n
o
. 2, pp. 304
–
312, Apr
. 2023, d
o
i
:
10.17586/2226
-
149
4
-
2023
-
23
-
2
-
304
-
312.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
1
4
,
N
o.
3
,
De
c
e
m
be
r
20
2
5
:
941
-
949
948
[
15]
A
. S
.
R
a
ja
, S
. P
e
e
r
ba
s
ha
b, Y
. M
.
I
qba
l,
B
. S
unda
r
v
a
di
v
a
z
ha
ga
n, a
nd M
. M
.
S
ur
put
he
e
n, “
S
t
r
uc
tu
r
a
l
a
na
l
y
s
is
of
U
R
L
f
o
r
ma
li
c
i
o
us
U
R
L
d
e
t
e
c
t
i
o
n
us
in
g
ma
c
hi
n
e
le
a
r
n
in
g,”
J
our
nal
O
f
A
dv
anc
e
d
A
ppl
ie
d
Sc
ie
nt
if
ic
R
e
s
e
a
r
c
h
,
v
o
l.
5,
n
o
.
4,
pp.
28
–
41,
J
ul
.
2023,
do
i:
10.46947/j
o
a
a
s
r
542023679.
[
16]
S
. S
i
v
a
kuma
r
,
L
. S
.
V
id
e
la
,
T
.
R
a
je
s
h
K
uma
r
, J
. N
a
ga
r
a
j,
S
.
I
tn
a
l,
a
nd D
.
H
a
r
it
ha
, “
R
e
v
i
e
w
o
n
W
or
d2V
e
c
w
or
d
e
mb
e
ddi
ng n
e
ur
a
l
n
e
t,
”
in
2020
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
Sm
a
r
t
E
le
c
tr
o
ni
c
s
and
C
om
m
uni
c
at
io
n
(
I
C
O
SE
C
)
,
S
e
p.
2020,
pp.
282
–
290,
do
i:
10.1109/
I
C
O
S
E
C
49089.2020.9215319.
[
17]
N
.
B
a
dr
i,
F
.
K
b
o
ubi
,
a
nd
A
.
H
.
C
ha
ib
i,
“
C
o
mbi
ni
ng
F
a
s
t
T
e
xt
a
nd
G
l
ove
W
o
r
d
e
mb
e
ddi
ng
f
or
of
f
e
ns
i
ve
a
nd
ha
te
s
p
e
e
c
h
te
x
t
de
t
e
c
t
i
o
n,”
P
r
oc
e
di
a C
om
put
e
r
Sc
ie
n
c
e
, v
o
l.
207, pp. 769
–
778,
2022, do
i:
10.1016/j
.p
r
oc
s
.2022.09.132.
[
18]
J
.
K
a
li
a
ppa
n,
A
. R
.
B
a
ge
pa
ll
i,
S
.
A
lm
a
l,
R
. M
is
hr
a
,
Y
.
-
C
.
H
u,
a
nd
K
.
S
r
in
i
v
a
s
a
n,
“
I
mpa
c
t
of
c
r
o
s
s
-
v
a
li
da
ti
o
n
o
n
ma
c
hi
n
e
l
e
a
r
ni
ng
mo
d
e
ls
f
o
r
e
a
r
l
y
d
e
t
e
c
ti
o
n
of
in
t
r
a
ut
e
r
in
e
f
e
ta
l
de
mi
s
e
,”
D
ia
gnos
ti
c
s
,
v
o
l.
13,
n
o
.
10,
p.
1692,
M
a
y
2
023,
do
i:
10.3390/di
a
gn
o
s
ti
c
s
13101692.
[
19]
P
.
D
ha
na
la
ks
hmi
,
G
.
A
.
K
uma
r
,
B
.
S
.
S
a
twi
k,
K
.
S
r
e
e
r
a
nga
,
A
.
T
.
S
a
i,
a
nd
G
.
J
a
s
hw
a
nt
h,
“
S
e
nt
im
e
nt
a
na
l
y
s
is
us
in
g
V
A
D
E
R
a
nd
lo
gi
s
ti
c
r
e
gr
e
s
s
io
n
te
c
hni
qu
e
s
,”
in
2023
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
I
nt
e
ll
ig
e
nt
Sy
s
te
m
s
f
o
r
C
om
m
uni
c
at
io
n,
I
oT
and
Se
c
ur
it
y
(
I
C
I
SC
oI
S)
, F
e
b. 2023, pp. 139
–
144, d
o
i:
10.1109/
I
C
I
S
C
o
I
S
5
6
541.2023.10100565.
[
20]
M
.
A
hma
d,
S
.
A
f
ta
b,
M
.
S
a
lm
a
n,
a
nd
N
.
H
a
me
e
d,
“
S
e
nt
im
e
nt
a
na
l
y
s
is
us
in
g
S
V
M
:
a
s
y
s
te
ma
ti
c
li
t
e
r
a
tu
r
e
r
e
v
i
e
w
,”
I
nt
e
r
nat
io
nal
J
our
nal
of
A
dv
an
c
e
d C
om
put
e
r
Sc
ie
nc
e
and A
ppl
ic
at
io
ns
, vo
l.
9, no
. 2, 2018, d
o
i:
10.14569/
I
J
A
C
S
A
.2018.09022
6.
[
21]
P
.
P
.
S
ur
y
a
a
nd
B
.
S
ubbula
ks
hmi
,
“
S
e
nt
im
e
nt
a
l
a
na
l
y
s
is
us
i
n
g
N
a
iv
e
B
a
y
e
s
c
la
s
s
i
f
i
e
r
,”
in
2019
I
n
te
r
nat
io
nal
C
onf
e
r
e
n
c
e
on
V
is
io
n
T
ow
ar
ds
E
m
e
r
gi
ng
T
r
e
nds
in
C
om
m
uni
c
at
io
n
and
N
e
tw
or
k
in
g
(
V
i
T
E
C
oN
)
,
M
a
r
.
2019,
pp.
1
–
5,
do
i:
10.1109/Vi
T
E
C
o
N
.2019.889961
8.
[
22]
M
.
A
uf
a
r
,
R
.
A
ndr
e
s
w
a
r
i,
a
nd
D
.
P
r
a
m
e
s
ti
,
“
S
e
nt
i
me
nt
a
na
l
y
s
is
o
n
Y
o
u
tu
be
s
oc
ia
l
me
d
ia
us
in
g
de
c
is
io
n
t
r
e
e
a
nd
r
a
nd
o
m
f
or
e
s
t
a
lg
o
r
it
h
m:
a
c
a
s
e
s
tu
d
y
,”
in
2020
I
nt
e
r
nat
io
nal
C
onf
e
r
e
n
c
e
on
D
at
a
Sc
ie
nc
e
and
I
ts
A
ppl
ic
at
io
ns
(
I
C
oD
SA
)
,
A
ug.
2020,
pp.
1
–
7
,
do
i:
10.1109/
I
C
o
D
S
A
50139.2020.9213078.
[
23]
A
.
S
a
w
a
r
n,
A
nki
t,
a
nd
M
.
G
upt
a
,
“
C
o
mpa
r
a
ti
ve
a
na
l
y
s
is
of
b
a
ggi
ng
a
nd
bo
o
s
ti
ng
a
lg
o
r
it
h
ms
f
or
s
e
nt
im
e
nt
a
na
l
y
s
is
,”
P
r
oc
e
di
a
C
om
put
e
r
Sc
ie
n
c
e
, v
o
l.
173, pp. 210
–
215, 2020, d
o
i:
10.1016
/j
.
pr
oc
s
.2020.06.025.
[
24]
F
.
S
.
N
a
hm,
“
R
e
c
e
i
v
e
r
o
p
e
r
a
ti
ng
c
ha
r
a
c
t
e
r
is
ti
c
c
u
r
ve
:
ove
r
v
i
e
w
a
nd
pr
a
c
ti
c
a
l
us
e
f
or
c
li
ni
c
ia
ns
,”
K
or
e
an
J
our
nal
of
A
ne
s
th
e
s
io
lo
gy
, v
o
l.
75, n
o
. 1, pp. 25
–
36,
F
e
b. 2022, d
o
i
:
10.40
97/
kj
a
.21209.
[
25]
S
.
V
B
a
ls
he
twa
r
,
A
.
R
S
,
a
nd
D
.
J
.
R
,
“
F
a
k
e
n
e
w
s
d
e
te
c
ti
o
n
in
s
o
c
ia
l
m
e
di
a
ba
s
e
d
o
n
s
e
n
ti
m
e
nt
a
na
l
y
s
is
us
in
g
c
la
s
s
if
ie
r
te
c
hni
que
s
,”
M
ul
ti
m
e
di
a T
oo
ls
and A
ppl
ic
at
io
ns
, vo
l.
82, n
o
. 2
3, pp. 35781
–
35811, S
e
p. 2023, d
o
i:
10.1007/s
11042
-
023
-
1488
3
-
3.
[
26]
S
.
A
mi
r
ip
a
r
ia
n
e
t
al
.
,
“
T
h
e
M
uS
e
2024
mul
ti
m
o
da
l
s
e
nt
im
e
nt
a
na
l
y
s
is
c
ha
ll
e
ng
e
:
s
oc
ia
l
p
e
r
c
e
pt
i
o
n
a
nd
hum
or
r
e
c
o
gni
ti
o
n,”
ar
x
iv
pr
e
p
r
in
t:
2406.07753
, J
un. 2024, do
i:
10.48550/ar
X
i
v
.24
06.07753.
[
27]
J
.
C
a
be
z
a
s
,
D
.
M
o
c
te
z
uma
,
A
.
F
e
r
ná
nd
e
z
-
I
s
a
be
l,
a
nd
I
.
M
a
r
tí
n
de
D
ie
g
o
,
“
D
e
t
e
c
ti
ng
e
m
ot
i
o
na
l
e
vo
lu
ti
o
n
o
n
T
w
i
tt
e
r
du
r
in
g
th
e
C
O
V
I
D
-
19
pa
nde
mi
c
us
in
g
te
x
t
a
na
l
y
s
is
,”
I
nt
e
r
nat
io
nal
J
our
nal
of
E
nv
ir
onm
e
nt
al
R
e
s
e
a
r
c
h
and
P
ubl
ic
H
e
al
th
,
v
o
l.
18,
n
o
.
13,
p. 6981, J
un. 2021, do
i:
10.3390/i
j
e
r
ph18136981.
[
28]
A
.
G
a
ndhi
,
K
.
A
dh
v
a
r
y
u,
S
.
P
o
r
ia
,
E
.
C
a
mbr
ia
,
a
n
d
A
.
H
us
s
a
in
,
“
M
ul
ti
mo
da
l
s
e
nt
i
me
nt
a
na
l
y
s
is
:
a
s
y
s
t
e
ma
ti
c
r
e
v
i
e
w
of
hi
s
t
o
r
y
,
da
ta
s
e
ts
,
mul
ti
mo
da
l
f
us
i
o
n
m
e
th
o
ds
,
a
ppl
ic
a
ti
o
ns
,
c
ha
ll
e
ng
e
s
a
nd
f
ut
ur
e
di
r
e
c
t
i
o
ns
,”
I
nf
o
r
m
at
io
n
F
us
io
n
,
vo
l.
91,
pp.
424
–
4
44,
2023, do
i:
10.1016/j
.
in
f
f
us
.2022.09.025.
[
29]
R
.
G
e
e
th
a
nj
a
li
a
nd
A
.
V
a
la
r
ma
th
i,
“
A
no
ve
l
h
y
br
id
d
e
e
p
le
a
r
ni
ng
I
C
hO
A
-
C
N
N
-
L
S
T
M
m
o
d
e
l
f
o
r
m
o
da
li
t
y
-
e
nr
ic
h
e
d
a
nd
mul
ti
li
ngua
l
e
m
o
ti
o
n
r
e
c
o
gni
ti
o
n
in
s
oc
ia
l
m
e
di
a
,”
Sc
ie
nt
if
ic
R
e
por
ts
,
v
o
l.
14,
n
o
.
1,
p.
22270,
S
e
p.
20
24,
do
i:
10.1038/s
41598
-
024
-
73452
-
2.
[
30]
K
.
F
o
unt
o
ul
a
ki
s
e
t
al
.
,
“
S
e
l
f
-
r
e
p
or
te
d
c
ha
nge
s
in
a
nx
i
e
t
y
,
d
e
pr
e
s
s
io
n
a
nd
s
ui
c
id
a
li
t
y
dur
in
g
th
e
C
O
V
I
D
-
19
lo
c
kd
o
w
n
in
G
r
e
e
c
e
,”
J
our
nal
of
a
ff
e
c
ti
v
e
di
s
o
r
de
r
s
, v
o
l.
279, pp. 624
–
629, 2021,
[
O
nl
in
e
]
. A
v
a
il
a
bl
e
:
ht
tp
s
:/
/p
ubm
e
d.n
c
bi
.nl
m.ni
h.g
ov
/3
3190113/.
B
I
OG
RA
P
HI
E
S
OF
AU
T
HO
RS
Sa
l
eem
R
a
ja
A
bd
ul
Sa
m
a
d
i
s
a
facu
l
t
y
memb
e
r
i
n
t
h
e
I
T
D
e
p
art
men
t
,
U
n
i
v
e
rs
i
t
y
o
f
T
ec
h
n
o
l
o
g
y
an
d
A
p
p
l
i
e
d
S
c
i
en
ce
s
,
S
h
i
n
as
,
Su
l
t
an
at
e
o
f
O
m
a
n
.
H
e
h
o
l
d
h
i
s
Ph
.
D
.
d
eg
r
ee
i
n
2
0
1
7
i
n
t
h
e
b
ro
ad
ar
e
a
o
f
d
at
a
m
i
n
i
n
g
an
d
M.
T
ec
h
–
i
n
f
o
r
m
at
i
o
n
t
ec
h
n
o
l
o
g
y
d
eg
r
ee
fr
o
m
B
h
arat
h
i
d
as
an
U
n
i
v
e
rs
i
t
y
,
T
ami
l
N
a
d
u
,
In
d
i
a.
H
e
h
as
o
v
e
r
1
8
y
e
ars
o
f
t
e
a
c
h
i
n
g
an
d
r
e
s
e
ar
c
h
e
x
p
e
ri
en
ce
.
D
e
l
i
v
e
r
ed
t
ec
h
n
i
c
a
l
t
al
k
o
n
n
at
u
ral
l
an
g
u
a
g
e
p
ro
ce
s
s
i
n
g
,
d
at
a
s
c
i
en
c
e,
mo
b
i
l
e
p
ro
g
ra
mm
i
n
g
,
a
n
d
I
o
T
.
H
e
h
as
b
een
s
u
p
e
rv
i
s
i
n
g
ap
p
l
i
e
d
r
e
s
e
ar
ch
p
ro
j
ec
t
s
an
d
g
ra
d
u
at
e
s
t
u
d
e
n
t
p
ro
j
ec
t
s
i
n
cy
b
e
r
s
ec
u
r
i
t
y
.
H
e
h
as
c
o
m
p
l
e
t
e
d
C
CN
A
,
H
C
A
I
,
a
n
d
Mi
c
r
o
s
o
ft
A
s
s
o
c
i
at
e
ce
rt
i
fi
c
at
i
o
n
s
.
H
e
h
as
p
u
b
l
i
s
h
ed
mo
r
e
t
h
a
n
5
5
r
e
s
e
ar
ch
p
ap
e
rs
i
n
i
n
t
e
rn
at
i
o
n
a
l
a
n
d
n
at
i
o
n
a
l
j
o
u
rn
al
s
,
co
n
f
e
r
en
ce
s
,
an
d
b
o
o
k
ch
ap
t
e
rs
.
H
i
s
re
s
e
a
rc
h
i
n
t
e
r
e
s
t
s
i
n
c
l
u
d
e
cy
b
e
r
s
ecu
ri
t
y
,
m
a
c
h
i
n
e
l
e
arn
i
n
g
,
d
ee
p
l
e
ar
n
i
n
g
,
n
a
t
u
ra
l
l
a
n
g
u
ag
e
p
ro
ce
s
s
i
n
g
,
i
m
a
g
e
p
ro
ce
s
s
i
n
g
,
a
n
d
t
h
e
Io
T
.
H
e
c
an
b
e
co
n
t
a
c
t
ed
at
em
a
i
l
:
s
al
eem
.
ab
d
u
l
s
a
m
ad
@
u
t
as
.
e
d
u
.
o
m
.
P
ra
deepa
Ga
n
es
a
n
i
s
a
fa
cu
l
t
y
mem
b
e
r
i
n
t
h
e
I
T
D
ep
art
m
e
n
t
at
t
h
e
U
n
i
v
e
rs
i
t
y
o
f
T
e
ch
n
o
l
o
g
y
an
d
A
p
p
l
i
e
d
S
ci
e
n
ce
s
,
Sh
i
n
as
,
Su
l
t
an
at
e
o
f
O
m
an
.
Sh
e
h
o
l
d
s
h
e
r
MCA
d
eg
r
ee
fro
m
Ma
d
u
ra
i
K
a
m
araj
U
n
i
v
e
rs
i
t
y
,
T
a
m
i
l
n
ad
u
,
I
n
d
i
a
,
h
e
r
M.
Ph
i
l
d
e
g
r
ee
fro
m
B
h
arat
h
i
d
as
an
U
n
i
v
e
rs
i
t
y
,
T
ami
l
n
ad
u
,
I
n
d
i
a,
an
d
h
e
r
Ph
.
D
.
fro
m
V
el
s
I
n
s
t
i
t
u
t
e
o
f
S
c
i
en
ce
,
T
ech
n
o
l
o
g
y
a
n
d
A
d
v
a
n
ce
d
St
u
d
i
e
s
,
T
a
m
i
l
n
a
d
u
,
I
n
d
i
a.
S
h
e
h
as
2
0
y
e
ars
o
f
t
e
a
ch
i
n
g
e
x
p
e
r
i
en
ce
.
H
e
r
r
e
s
e
ar
ch
i
n
t
e
r
e
s
t
s
i
n
c
l
u
d
e
cy
b
e
rs
ec
u
r
i
t
y
,
n
at
u
ra
l
l
an
g
u
a
g
e
p
ro
ce
s
s
i
n
g
,
m
a
ch
i
n
e
l
e
arn
i
n
g
,
an
d
d
ee
p
l
e
ar
n
i
n
g
.
Sh
e
c
an
b
e
co
n
t
a
c
t
ed
at
em
a
i
l
:
p
rad
ee
p
a.
g
a
n
e
s
an
@
u
t
as
.
e
d
u
.
o
m.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
E
mpo
w
e
r
ing
lo
w
-
r
e
s
our
c
e
languages
:
a
mac
hine
lear
ning
appr
oac
h
to
…
(
Salee
m
R
aja
A
bdul
Sama
d
)
949
J
u
s
ti
n
R
a
ja
s
ek
a
ra
n
i
s
w
o
rk
i
n
g
as
a
facu
l
t
y
mem
b
e
r
i
n
U
n
i
v
e
rs
i
t
y
o
f
T
ec
h
n
o
l
o
g
y
an
d
A
p
p
l
i
ed
S
ci
e
n
ce
s
,
S
h
i
n
as
,
O
m
an
.
H
e
h
as
au
t
h
o
r
e
d
s
e
v
e
ra
l
re
s
e
ar
c
h
p
ap
e
rs
a
n
d
c
h
ap
t
e
rs
i
n
re
p
u
t
ed
n
at
i
o
n
a
l
an
d
i
n
t
e
rn
at
i
o
n
al
j
o
u
rn
a
l
s
an
d
p
re
s
en
t
e
d
re
s
e
ar
c
h
p
ap
e
rs
i
n
n
at
i
o
n
a
l
an
d
i
n
t
e
r
n
at
i
o
n
al
c
o
n
f
e
r
e
n
ce
s
u
n
d
e
r
v
ar
i
o
u
s
d
o
m
ai
n
s
v
i
z
.
C
l
o
u
d
co
m
p
u
t
i
n
g
i
n
s
m
art
far
m
i
n
g
an
d
i
t
s
ap
p
l
i
c
at
i
o
n
,
s
t
u
d
en
t
s
'
p
e
rfo
r
m
a
n
ce
u
s
i
n
g
d
at
a
m
i
n
i
n
g
t
e
ch
n
i
q
u
e
s
,
m
o
b
i
l
e
ap
p
l
i
c
at
i
o
n
t
e
s
t
i
n
g
,
m
al
i
c
i
o
u
s
l
i
n
k
d
e
t
ec
t
i
o
n
u
s
i
n
g
n
at
u
ra
l
l
a
n
g
u
ag
e
p
ro
ces
s
i
n
g
.
H
e
h
as
p
art
i
c
i
p
at
e
d
i
n
v
ari
o
u
s
s
e
mi
n
ars
,
w
o
rk
s
h
o
p
s
,
an
d
Facu
l
t
y
D
ev
e
l
o
p
men
t
Pro
g
ram
s
.
H
e
h
as
al
s
o
p
art
i
ci
p
at
e
d
i
n
d
e
s
i
g
n
i
n
g
c
u
rr
i
c
u
l
u
m
f
o
r
A
I
an
d
d
at
a
s
ci
e
n
ce
.
H
e
c
a
n
b
e
c
o
n
t
ac
t
e
d
at
em
ai
l
:
j
u
s
t
i
n
.
ra
j
as
ek
aran
@
u
t
as
.
ed
u
.
o
m
.
M
a
dhu
ba
l
a
R
a
dh
a
k
ri
s
hn
a
n
cu
rr
e
n
t
l
y
s
e
rv
e
s
as
a
L
ec
t
u
r
e
r
i
n
t
h
e
I
T
D
e
p
art
men
t
at
t
h
e
U
n
i
v
e
rs
i
t
y
o
f
T
ec
h
n
o
l
o
g
y
an
d
A
p
p
l
i
e
d
S
c
i
en
ce
–
Sh
i
n
as
i
n
O
m
a
n
.
S
h
e
e
ar
n
e
d
h
e
r
D
o
c
t
o
r
o
f
P
h
i
l
o
s
o
p
h
y
d
e
g
r
ee
fro
m
V
el
s
I
n
s
t
i
t
u
t
e
o
f
S
c
i
en
ce
,
T
ec
h
n
o
l
o
g
y
a
n
d
A
p
p
l
i
ed
S
ci
e
n
ce
,
I
n
d
i
a
2
0
2
1
.
Re
s
e
ar
ch
i
n
t
e
r
e
s
t
s
i
n
cl
u
d
e
cl
o
u
d
c
o
m
p
u
t
i
n
g
,
art
i
fi
ci
al
i
n
t
e
l
l
i
g
e
n
ce
,
n
e
t
w
o
rk
s
,
I
o
T
,
s
e
rv
i
ce
-
o
ri
en
t
ed
ar
ch
i
t
ec
t
u
r
e
,
an
d
d
at
a
s
t
ru
c
t
u
r
e
s
.
S
h
e
's
b
ee
n
a
t
e
a
c
h
e
r
fo
r
t
w
e
n
t
y
-
f
o
u
r
y
e
ars
.
H
e
r
r
e
s
e
ar
c
h
h
as
b
ee
n
p
r
e
s
en
t
ed
at
co
n
f
e
r
en
ce
s
,
i
n
b
o
o
k
c
h
ap
t
e
rs
,
an
d
i
n
t
h
i
rt
ee
n
i
n
t
e
rn
at
i
o
n
a
l
j
o
u
rn
al
s
.
S
h
e
h
as
b
ee
n
s
e
rv
i
n
g
as
rev
i
ew
er
fo
r
s
e
v
e
ra
l
r
e
p
u
t
ed
j
o
u
rn
a
l
s
.
Sh
e
c
an
b
e
co
n
t
a
c
t
ed
at
em
ai
l
:
b
al
a
m
a
d
h
@
g
m
a
i
l
.
c
o
m
.
P
eerba
s
h
a
Sh
eb
beer
Ba
s
h
a
i
s
a
n
A
s
s
i
s
t
an
t
Pro
fe
s
s
o
r
o
f
Co
m
p
u
t
e
r
S
ci
e
n
ce
D
e
p
art
men
t
at
J
am
al
Mo
h
a
med
Co
l
l
e
g
e,
A
ffi
l
i
at
e
d
w
i
t
h
Bh
arat
h
i
d
as
an
U
n
i
v
e
rs
i
t
y
,
T
ami
l
N
ad
u
.
In
d
i
a.
H
e
h
as
1
4
y
e
ars
o
f
t
e
a
c
h
i
n
g
e
x
p
e
ri
en
ce
i
n
c
l
u
d
i
n
g
o
n
e
y
ear
o
f
i
n
t
e
r
n
at
i
o
n
a
l
e
x
p
e
ri
en
ce
as
a
s
e
n
i
o
r
l
ec
t
u
r
e
r
h
an
d
l
i
n
g
I
T
c
o
u
rs
e
o
f
S
o
u
t
h
e
r
n
Cr
o
s
s
U
n
i
v
e
rs
i
t
y
,
A
u
s
t
ral
i
a.
H
e
h
o
l
d
s
h
i
s
Ph
.
D
.
d
eg
r
ee
an
d
q
u
al
i
fi
ed
w
i
t
h
N
E
T
an
d
S
E
T
i
n
co
m
p
u
t
e
r
s
c
i
en
c
e
an
d
ap
p
l
i
c
at
i
o
n
s
.
H
e
h
o
l
d
s
MCA
,
M.
P
h
i
l
,
MBA
,
an
d
M
.
T
ec
h
.
H
e
h
as
rece
i
v
e
d
In
d
o
A
s
i
an
Mar
v
i
n
Mi
n
s
k
y
D
i
s
t
i
n
g
u
i
s
h
e
d
I
n
n
o
v
at
i
v
e
R
e
s
e
ar
ch
e
r
A
w
ar
d
i
n
co
m
p
u
t
e
r
s
ci
e
n
ce
.
H
e
h
as
p
u
b
l
i
s
h
ed
mo
r
e
t
h
a
t
w
e
l
v
e
r
e
s
e
ar
c
h
art
i
cl
e
s
i
n
r
e
p
u
t
e
d
i
n
t
e
rn
at
i
o
n
a
l
co
m
p
u
t
e
r
s
ci
e
n
ce
j
o
u
r
n
al
s
.
H
i
s
ar
e
a
o
f
re
s
e
ar
ch
e
x
p
e
rt
i
s
e
i
n
c
l
u
d
e
s
m
a
ch
i
n
e
l
e
arn
i
n
g
a
n
d
d
ee
p
l
e
arn
i
n
g
.
H
e
i
s
a
r
ev
i
ew
e
r
a
n
d
e
d
i
t
o
ri
a
l
b
o
ard
mem
b
e
r
fo
r
m
an
y
i
n
t
e
r
n
at
i
o
n
al
j
o
u
rn
al
s
r
e
l
at
e
d
w
i
t
h
co
m
p
u
t
e
r
s
c
i
en
ce
,
e
n
g
i
n
ee
ri
n
g
an
d
i
n
fo
r
m
at
i
o
n
t
ech
n
o
l
o
g
y
.
H
e
c
an
b
e
co
n
t
a
c
t
ed
at
em
ai
l
:
b
as
h
ap
e
e
r2
0
0
3
@
g
m
a
i
l
.
c
o
m
.
V
a
r
a
l
a
k
s
hm
i
K
u
pp
u
s
a
m
y
h
o
l
d
s
a
B.
T
ech
.
a
n
d
an
M.
T
ech
.
i
n
i
n
fo
r
m
at
i
o
n
t
e
ch
n
o
l
o
g
y
.
S
h
e
h
as
s
e
rv
ed
as
a
l
ec
t
u
r
e
r
at
A
n
n
a
U
n
i
v
e
rs
i
t
y
-
A
ffi
l
i
at
e
d
Co
l
l
eg
e
s
an
d
SRM
U
n
i
v
e
rs
i
t
y
.
I
n
h
e
r
a
c
a
d
em
i
c
c
ar
ee
r,
s
h
e
h
as
g
u
i
d
ed
n
u
me
ro
u
s
B.
T
ec
h
.
a
n
d
M.
T
ec
h
.
s
t
u
d
en
t
p
ro
j
ec
t
s
,
fo
cu
s
i
n
g
o
n
ar
e
as
s
u
c
h
as
art
i
fi
c
i
a
l
i
n
t
el
l
i
g
en
ce
,
i
m
ag
e
p
ro
ce
s
s
i
n
g
,
n
e
t
w
o
rk
i
n
g
,
an
d
d
at
a
s
t
ru
c
t
u
re
s
.
H
e
r
e
x
t
e
n
s
i
v
e
e
x
p
e
ri
en
ce
i
n
t
e
a
ch
i
n
g
an
d
men
t
o
ri
n
g
h
as
m
a
d
e
s
i
g
n
i
f
i
c
an
t
c
o
n
t
ri
b
u
t
i
o
n
s
t
o
t
h
e
a
c
ad
emi
c
an
d
p
ro
f
e
s
s
i
o
n
a
l
g
r
o
w
t
h
o
f
h
e
r
s
t
u
d
e
n
t
s
.
Sh
e
c
an
b
e
c
o
n
t
ac
t
e
d
at
em
ai
l
:
v
ara
mk
e
l
ra
n
g
a@
g
m
ai
l
.
co
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.