I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
,
p
p
.
2
5
8
5
~
2
5
9
2
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
9
i
4
.
p
p
2
5
8
5
-
2592
2585
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
H
ea
rt
ra
te
e
nca
ps
ula
tion a
nd
r
espo
nse
t
o
o
l using
s
enti
m
en
t
a
na
ly
sis
Na
nd
y
a
la
Sruja
na
Reddy
1
,
P
ra
ba
dev
i B
.
2
,
Dee
pa
B
3
1
,2
S
c
h
o
o
l
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
a
n
d
En
g
i
n
e
e
rin
g
,
V
e
ll
o
re
In
st
it
u
te o
f
T
e
c
h
n
o
lo
g
y
,
In
d
ia
3
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
S
ri
S
a
ira
m
In
stit
u
te
o
f
T
e
c
h
n
o
l
o
g
y
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
27
,
2
0
1
7
R
ev
i
s
ed
Mar
4
,
2
0
1
9
A
cc
ep
ted
Mar
6
,
2
0
1
9
Us
e
rs
o
f
e
v
e
r
y
s
y
ste
m
e
x
p
e
c
t
it
to
g
e
t
b
e
tt
e
r.
P
ro
v
id
i
n
g
f
e
e
d
b
a
c
k
to
th
e
o
w
n
e
rs
o
f
th
e
s
y
ste
m
w
a
s
d
iff
icu
lt
b
u
t
w
it
h
th
e
a
d
v
e
n
t
o
f
t
e
c
h
n
o
l
o
g
y
,
it
h
a
s
b
e
c
o
m
e
h
a
n
d
y
.
U
se
rs
c
a
n
n
o
w
p
o
st
t
h
e
ir
c
o
m
m
e
n
ts
th
ro
u
g
h
o
n
li
n
e
b
l
o
g
s,
a
n
d
ro
i
d
a
p
p
s
a
n
d
w
e
b
sites
.
Du
e
to
th
e
e
n
o
rm
o
u
s
d
a
ta
p
il
in
g
u
p
e
v
e
r
y
se
c
o
n
d
,
it
h
a
s
b
e
c
o
m
e
a
p
ro
b
lem
in
a
n
a
ly
z
in
g
it
.
In
th
is
p
a
p
e
r,
se
n
t
im
e
n
t
a
n
a
ly
sis
is
u
se
d
f
o
r
a
n
a
ly
z
in
g
c
o
m
m
e
n
ts
a
n
d
re
v
iew
s
p
o
ste
d
b
y
u
se
rs.
T
h
e
e
x
p
e
rime
n
ts
a
re
d
o
n
e
w
it
h
d
y
n
a
m
ic
a
n
d
re
a
l
d
a
ta
.
T
h
e
to
o
ls,
a
lg
o
rit
h
m
s
a
n
d
m
e
th
o
d
o
l
o
g
y
th
a
t
c
o
u
ld
f
e
tch
a
c
c
u
ra
te
re
su
lt
s
a
re
d
e
sc
rib
e
d
.
Ex
p
e
rim
e
n
tal
re
su
lt
s
in
d
ica
te
9
0
%
o
f
a
c
c
u
ra
c
y
in
p
r
o
p
o
se
d
s
y
ste
m
.
T
h
e
re
v
ie
w
re
p
o
rt
g
e
n
e
ra
ted
w
o
u
ld
h
e
lp
t
h
e
h
o
sp
i
tal
m
a
n
a
g
e
m
e
n
t
to
id
e
n
ti
f
y
th
e
p
o
siti
v
e
a
n
d
n
e
g
a
ti
v
e
f
e
e
d
b
a
c
k
w
h
ich
f
u
rth
e
r
a
ss
ists
th
e
m
in
imp
ro
v
in
g
t
h
e
ir
f
a
c
il
it
ies
th
a
t
c
o
u
l
d
n
o
t
o
n
ly
c
re
a
te cu
sto
m
e
r
sa
ti
s
f
a
c
ti
o
n
b
u
t
a
l
so
e
n
h
a
n
c
e
d
b
u
sin
e
ss
p
r
o
c
e
ss
e
s.
K
ey
w
o
r
d
s
:
C
o
m
m
e
n
ts
Feed
b
ac
k
Hea
lth
ca
r
e
d
ata
NL
P
NL
T
K
Sen
ti
m
e
n
t
a
n
a
l
y
s
is
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
P
r
ab
a
d
ev
i B
.
,
Sch
o
o
l o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
a
n
d
E
n
g
in
ee
r
i
n
g
,
VI
T
Un
iv
er
s
it
y
,
Vello
r
e,
T
am
i
l N
ad
u
,
I
n
d
ia
.
E
m
ail:
p
r
ab
ad
ev
i.b
@
v
it.a
c.
in
1.
I
NT
RO
D
UCT
I
O
N
Hea
lth
ca
r
e
i
n
d
u
s
tr
ie
s
li
k
e
h
o
s
p
itals
,
p
h
ar
m
ac
ie
s
,
lab
o
r
ato
r
ies,
s
o
f
t
w
ar
e
s
o
lu
tio
n
s
ar
e
g
r
o
w
i
n
g
tr
e
m
en
d
o
u
s
l
y
w
h
ich
i
s
lead
i
n
g
to
ex
p
o
n
e
n
tial
g
r
o
w
th
o
f
d
a
ta.
C
o
n
ti
n
u
o
u
s
ad
v
an
ce
m
e
n
t
o
f
all
t
h
ese
f
ac
il
ities
is
n
ec
es
s
ar
y
as
t
h
e
y
d
ea
l
w
i
th
h
ea
lt
h
o
f
t
h
e
h
u
m
an
.
T
h
e
zo
n
es
o
f
en
h
an
ce
m
e
n
t
ar
e
id
en
ti
f
ied
th
r
o
u
g
h
o
b
s
er
v
atio
n
,
e
x
p
er
ien
ce
an
d
f
ee
d
b
ac
k
o
f
th
e
u
s
e
r
s
.
T
h
e
w
o
r
d
f
ee
d
b
ac
k
r
e
f
er
s
to
t
h
e
r
ea
cti
o
n
to
a
p
r
o
d
u
ct
t
h
at
w
o
u
ld
ac
t a
s
a
m
ai
n
i
n
g
r
ed
ie
n
t
in
i
m
p
r
o
v
e
m
e
n
t.
T
h
e
tech
n
ica
l b
o
o
m
h
a
s
let
th
e
u
s
er
s
d
eli
v
e
r
th
eir
f
ee
d
b
ac
k
at
an
y
p
o
in
t i
n
ti
m
e.
Ho
s
p
ital
s
co
n
s
id
er
th
i
s
as a
n
i
m
p
o
r
tan
t p
ar
a
m
eter
in
p
r
o
v
id
i
n
g
c
ar
e
[
1
]
.
Up
s
u
r
g
e
in
t
h
e
p
atie
n
ts
d
ir
ec
ted
to
d
iv
er
s
e
v
ie
w
s
an
d
i
n
s
i
g
h
t
s
w
it
h
r
esp
ec
t
to
cli
n
ical
a
m
en
ities
.
T
h
ese
ar
e
ca
r
r
ied
to
th
e
i
n
f
ir
m
ar
y
th
r
o
u
g
h
a
n
d
r
o
id
ap
p
s
u
b
m
is
s
io
n
s
,
m
ai
ls
a
n
d
w
eb
s
ite
s
[
2
]
.
Su
r
v
e
y
r
e
v
ea
l
s
th
at
8
5
%
o
f
i
n
d
iv
id
u
als
u
s
e
web
s
ites
a
n
d
b
lo
g
s
to
p
o
s
t
t
h
eir
co
m
m
en
t
s
[
3
]
.
T
h
er
e
is
a
w
i
d
e
an
g
le
to
an
a
l
y
z
e
b
u
t
it
h
a
s
b
ec
o
m
e
d
i
f
f
icu
lt
a
s
th
e
d
ata
is
u
n
s
tr
u
ct
u
r
ed
.
O
w
i
n
g
to
t
h
is
,
a
n
i
n
s
tan
t
ac
tio
n
c
an
n
o
t
b
e
ap
p
lied
to
ad
d
r
ess
th
e
is
s
u
e
a
n
d
co
r
r
ec
t
th
e
co
n
d
itio
n
.
T
h
is
w
o
u
ld
r
esu
l
t
in
lo
s
s
o
f
tr
u
s
t
a
m
o
n
g
t
h
e
u
s
er
s.
Ma
n
u
a
l
s
cr
u
ti
n
y
m
ig
h
t
d
r
a
w
p
r
ec
is
e
r
esu
lts
b
u
t
w
o
u
ld
r
eq
u
ir
e
p
r
o
f
u
s
e
m
an
p
o
w
er
an
d
ti
m
e.
Si
n
ce
h
ea
lt
h
in
f
o
r
m
atio
n
is
s
en
s
iti
v
e,
m
is
u
s
in
g
it c
o
u
ld
ca
u
s
e
d
r
asti
c
e
f
f
ec
ts
.
Hen
ce
t
h
e
a
s
s
o
ciate
d
d
ata
i
s
to
b
e
co
llected
in
th
e
u
t
m
o
s
t
ef
f
icie
n
t
w
a
y
th
a
t
w
o
u
ld
else
r
esu
lt
in
i
m
p
r
o
p
er
d
ata.
T
h
e
f
ee
d
b
ac
k
s
u
b
m
itt
ed
is
an
ex
p
r
ess
iv
e
s
tate
m
en
t
o
f
t
h
e
u
s
er
w
h
ic
h
aid
s
as
a
g
r
ad
e
s
h
ee
t
f
o
r
th
e
h
o
s
p
ital.
T
h
e
u
s
ag
e
o
f
th
e
w
o
r
d
s
is
d
iv
er
s
e
i
n
n
u
m
er
o
u
s
ca
s
es
f
o
r
w
h
ich
t
h
e
alg
o
r
ith
m
s
ar
e
in
te
n
d
ed
w
it
h
m
a
n
y
r
es
tr
ai
n
t
s
lik
e
te
n
s
e,
co
n
tex
t,
s
u
b
s
tit
u
te
s
,
ad
j
ac
en
t
w
o
r
d
s
.
So
m
e
f
ee
d
b
a
ck
is
s
e
n
s
it
iv
e
a
n
d
h
en
ce
s
e
n
t
th
r
o
u
g
h
e
m
a
ils
.
T
h
e
d
ata
i
s
e
n
ca
p
s
u
lated
s
o
it
is
n
o
t
ex
p
lo
ited
.
T
h
e
r
esp
o
n
s
e
t
o
o
l
p
r
o
p
o
s
ed
in
th
is
p
ap
er
is
b
u
ilt
to
ex
p
a
n
d
th
e
h
ea
lt
h
ca
r
e
co
m
m
er
ciall
y
[
4
]
,
ae
s
th
et
icall
y
a
n
d
to
in
cr
ea
s
e
u
s
er
s
atis
f
ac
tio
n
[
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
:
2
5
8
5
-
2592
2586
T
h
e
f
ee
d
b
ac
k
p
ass
ed
v
ia
i
n
ter
n
et
i
s
av
ai
lab
le
an
d
ca
n
b
e
ac
ce
s
s
ed
in
s
n
ap
s
h
o
t.
A
s
u
r
v
e
y
s
u
g
g
e
s
ted
th
at
2
5
%
o
f
p
eo
p
le
r
ea
d
th
e
f
ee
d
b
ac
k
p
o
s
ted
a
n
d
m
ak
e
th
eir
d
ec
is
io
n
s
[
6
]
w
h
ic
h
s
tate
s
th
e
i
m
p
o
r
tan
ce
o
f
p
er
f
o
r
m
in
g
s
e
n
ti
m
en
t
an
al
y
s
i
s
o
n
th
e
h
u
g
e
d
ata
av
ailab
le.
I
t
is
d
o
n
e
f
o
r
f
r
ee
o
f
co
s
t
at
an
y
ti
m
e
b
y
u
s
i
n
g
th
e
tech
n
o
lo
g
ies
ac
ce
s
s
ib
le
[
7
]
.
I
t
in
v
o
l
v
es
t
w
o
s
tag
e
s
w
h
er
e
th
e
d
ata
is
in
itiall
y
co
llected
an
d
th
en
an
al
y
ze
d
u
s
i
n
g
th
e
al
g
o
r
ith
m
s
.
-
Data
co
llectio
n
:
Si
n
ce
th
e
d
at
a
e
m
a
n
ates
f
r
o
m
d
i
f
f
er
en
t
s
o
u
r
ce
s
a
n
d
v
ar
io
u
s
f
o
r
m
s
,
it
i
s
to
b
e
ca
p
tu
r
ed
ca
p
ab
ly
.
R
e
tr
iev
i
n
g
f
ee
d
b
ac
k
f
r
o
m
a
n
d
r
o
id
ap
p
licatio
n
s
,
w
eb
s
ites
a
n
d
m
ail
s
is
d
e
m
o
n
s
tr
ate
d
.
-
Sen
ti
m
e
n
t
An
al
y
s
i
s
:
T
h
e
i
n
f
o
r
m
atio
n
co
llected
i
s
d
ir
ec
ted
to
s
en
ti
m
e
n
t
m
o
d
u
le
w
h
ic
h
p
r
o
v
id
es
p
o
s
itiv
e
an
d
n
e
g
ati
v
e
f
ee
d
b
ac
k
s
tate
m
en
t.
T
h
e
alg
o
r
ith
m
s
ar
e
ex
p
lai
n
ed
an
d
r
esu
lts
o
b
tain
ed
a
f
ter
i
m
p
le
m
en
ta
tio
n
ar
e
d
em
o
n
s
tr
ated
.
T
h
e
f
o
llo
w
i
n
g
m
ac
h
i
n
e
lear
n
in
g
b
a
s
ed
alg
o
r
ith
m
s
p
a
v
e
a
w
a
y
f
o
r
p
r
ed
ictiv
e
an
al
y
s
is
.
T
h
is
w
o
u
ld
aid
th
e
o
r
g
an
izatio
n
in
m
a
k
in
g
p
r
ec
is
e
ch
o
ices a
t r
ig
h
t ti
m
e
b
y
est
i
m
ati
n
g
r
i
s
k
s
an
d
as
s
ess
in
g
t
h
e
m
.
2.
P
RO
P
O
SE
D
M
E
T
H
O
DO
L
O
G
Y
AND
AP
P
L
I
CA
T
I
O
N
O
F
SE
NT
I
M
E
NT
ANA
L
YS
I
S
2
.
1
.
Da
t
a
c
o
llect
io
n f
r
o
m
Andro
i
d a
pp
s
Stag
e
1
id
en
tify
i
n
g
th
e
d
ata
th
at
is
r
eq
u
ir
ed
f
o
r
an
al
y
s
is
:
C
o
n
s
id
er
a
n
a
n
d
r
o
id
ap
p
licatio
n
u
s
ed
b
y
t
h
e
u
s
er
s
to
p
r
o
v
id
e
f
ee
d
b
ac
k
.
T
h
is
ap
p
m
ig
h
t
co
n
tai
n
th
e
f
ie
ld
s
f
o
r
ev
er
y
f
ea
t
u
r
e
lik
e
h
o
s
p
italit
y
,
a
m
b
ie
n
ce
,
tr
ea
t
m
e
n
t,
co
s
t.
T
h
er
e
a
r
e
f
ew
ap
p
s
w
h
er
e
th
e
d
ata
is
p
o
s
ted
in
a
s
in
g
le
f
r
ee
tex
t
co
m
m
en
t
f
ield
w
h
ic
h
r
eq
u
ir
es sp
ec
ial
atte
n
tio
n
.
T
h
e
d
ata
th
a
t c
o
u
ld
ad
d
v
al
u
e
to
t
h
e
a
n
al
y
s
i
s
i
s
d
is
c
u
s
s
ed
w
it
h
t
h
e
m
a
n
ag
e
m
e
n
t a
n
d
co
n
s
id
er
ed
.
T
h
e
d
ata
c
o
llectio
n
f
lo
w
c
h
ar
t is d
ep
icted
in
Fi
g
u
r
e
1
.
Stag
e
2
co
n
n
ec
ti
n
g
t
h
e
a
n
d
r
o
id
ap
p
licatio
n
to
th
e
M
y
SQ
L
d
atab
ase
:
T
h
e
d
ata
is
to
b
e
co
llect
ed
f
r
o
m
th
e
an
d
r
o
id
ap
p
licatio
n
s
an
d
s
to
r
ed
in
d
atab
ase.
A
s
y
n
ctas
k
i
s
i
m
p
o
r
ted
in
th
e
A
n
d
r
o
id
ap
p
licatio
n
to
p
ass
th
e
d
ata
th
r
o
u
g
h
in
ter
n
et.
Http
lib
r
ar
ies
ar
e
im
p
o
r
ted
to
co
n
n
ec
t
th
e
an
d
r
o
id
ap
p
to
th
e
d
atab
ase.
T
h
e
d
ata/c
o
m
m
e
n
t
s
ar
e
s
en
t
t
o
th
e
s
er
v
er
u
s
i
n
g
t
h
e
A
s
y
n
c
T
ask
p
ac
k
ag
e.
An
y
d
ata
p
o
s
ted
th
r
o
u
g
h
t
h
e
ap
p
w
o
u
ld
b
e
u
p
d
ated
d
y
n
a
m
ical
l
y
.
Fig
u
r
e
1
.
Data
co
llectio
n
Flo
w
ch
ar
t
2
.
2
.
Web
s
cr
a
pin
g
t
o
re
t
riev
e
da
t
a
Stag
e
1
id
en
ti
f
y
t
h
e
w
eb
s
ite
s
to
b
e
s
cr
ap
e
d
:
T
h
er
e
ar
e
s
ev
er
al
w
eb
s
ite
s
av
ai
lab
le
w
h
er
e
th
e
r
ev
ie
w
s
ar
e
p
o
s
ted
.
T
h
e
o
n
es
th
at
ar
e
o
f
ten
u
s
ed
an
d
v
ie
w
ed
b
y
t
h
e
u
s
er
s
ar
e
id
en
tif
ied
u
s
in
g
th
e
co
u
n
t
o
f
v
ie
ws
r
u
n
n
i
n
g
i
n
t
h
e
b
ac
k
g
r
o
u
n
d
.
I
t c
o
u
ld
also
b
e
d
o
n
e
u
s
in
g
t
h
e
Go
o
g
le
A
P
I
’
s
.
Stag
e
2
s
cr
ap
e
th
e
id
en
tif
ied
w
eb
p
ag
e
:
W
eb
p
ag
es
ar
e
co
d
e
d
w
ith
n
u
m
er
o
u
s
tag
s
w
h
er
e
a
s
p
ec
if
ic
f
ield
h
o
ld
s
th
e
co
m
m
en
t
s
ec
ti
o
n
.
T
h
e
ad
m
in
o
f
t
h
e
w
eb
p
ag
e
ca
n
r
etr
iev
e
th
e
co
m
m
en
t
s
f
r
o
m
t
h
e
d
atab
ase.
As
an
a
n
al
y
s
t,
o
n
e
co
u
ld
s
cr
ap
e
th
e
d
ata
b
y
in
s
p
ec
tin
g
th
e
p
a
g
e
s
o
u
r
ce
.
T
h
e
co
m
m
e
n
t
f
ield
ca
n
b
e
id
en
t
if
ied
b
y
in
s
p
ec
ti
n
g
th
e
ele
m
e
n
t.
B
ea
u
t
if
u
lSo
u
p
i
n
P
y
th
o
n
is
u
s
ed
to
p
ar
s
e
th
e
tag
s
a
n
d
s
cr
ap
e
th
e
d
ata
an
d
is
th
en
s
to
r
ed
in
to
a
tex
t f
ile.
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
-
8708
Hea
r
t ra
te
en
ca
p
s
u
la
tio
n
a
n
d
r
esp
o
n
s
e
to
o
l u
s
in
g
s
en
timen
t
a
n
a
lysi
s
(
N
a
n
d
ya
la
S
r
u
ja
n
a
R
ed
d
y)
2587
2
.
3
.
Co
ll
ec
t
f
ee
db
a
ck
s
e
nt
t
hro
ug
h
m
a
i
ls
Ma
n
y
o
r
g
a
n
izat
io
n
s
h
a
v
e
s
p
ec
if
ic
m
ail
s
w
h
er
e
f
ee
d
b
ac
k
ca
n
b
e
p
o
s
ted
.
Mo
s
t o
f
th
e
u
s
er
s
d
o
th
is
as i
t
is
o
f
f
icial.
An
al
y
zin
g
e
v
er
y
m
ail
is
a
ted
io
u
s
p
r
o
ce
s
s
.
He
n
ce
th
e
d
ata
is
co
llected
an
d
s
to
r
ed
in
ex
ce
l
w
h
er
e
it
ca
n
b
e
co
n
v
er
ted
to
tex
t
f
ile.
T
h
is
p
r
o
ce
s
s
is
d
o
n
e
u
s
i
n
g
t
h
e
Mic
r
o
s
o
f
t
A
z
u
r
e
clo
u
d
an
d
Of
f
ice
3
6
5
Flo
w
tech
n
o
lo
g
y
.
2
.
4
.
Senti
m
ent
Ana
ly
s
is
T
h
e
s
tep
s
in
v
o
l
v
ed
in
s
e
n
ti
m
e
n
t a
n
al
y
s
is
i
s
d
ep
icted
in
Fig
u
r
e
2
.
Stag
e
1
c
o
n
v
er
t
w
o
r
d
s
to
to
k
en
s
:
E
ac
h
w
o
r
d
is
a
to
k
e
n
w
h
e
n
a
s
en
ten
ce
is
"
to
k
e
n
ized
"
in
to
w
o
r
d
s
[
8
]
.
E
ac
h
s
en
te
n
ce
ca
n
also
b
e
a
to
k
en
,
if
t
h
e
p
ar
ag
r
a
p
h
is
to
k
e
n
ized
in
to
s
e
n
te
n
ce
s
.
S
en
t
to
k
e
n
iz
e
an
d
w
o
r
d
_
to
k
en
ize
f
r
o
m
n
lt
k
.
to
k
e
n
ize
ar
e
to
b
e
i
m
p
o
r
ted
.
T
h
e
tex
t
is
p
as
s
ed
as
a
p
ar
a
m
ete
r
in
to
o
n
e
o
f
t
h
ese
f
u
n
ctio
n
s
w
h
er
e
w
o
r
d
s
ar
e
r
etu
r
n
ed
as to
k
e
n
s
.
T
h
e
s
p
lit d
ata
is
f
u
r
th
er
p
r
o
ce
s
s
ed
u
s
in
g
d
is
p
ar
ate
alg
o
r
ith
m
s
.
Stag
e
2
s
te
m
m
i
n
g
w
o
r
d
s
:
Sar
ca
s
tical
l
y
u
s
ed
w
o
r
d
s
ar
e
s
to
r
ed
in
a
li
s
t
w
h
er
e
th
e
r
ea
l
d
ata
ca
n
b
e
co
m
p
ar
ed
ag
a
in
s
t.
I
f
th
e
d
ata
h
as
s
u
c
h
w
o
r
d
s
,
t
h
e
y
ar
e
r
e
m
o
v
ed
as
t
h
e
y
d
o
n
’
t
ca
r
r
y
a
n
y
m
ea
n
in
g
a
n
d
ar
e
n
o
t
u
s
e
f
u
l
f
o
r
s
en
ti
m
e
n
t
an
al
y
s
is
.
Ste
m
m
i
n
g
[
9
]
is
a
k
i
n
d
o
f
n
o
r
m
al
izatio
n
w
h
er
e
t
h
e
w
o
r
d
s
th
at
h
o
ld
t
h
e
s
a
m
e
m
ea
n
in
g
b
u
t
d
if
f
er
ed
b
y
ten
s
e
ar
e
id
en
ti
f
ied
an
d
s
eg
r
eg
ated
.
T
h
is
w
o
u
ld
r
e
m
o
v
e
u
n
n
ec
es
s
ar
y
an
d
r
ed
u
n
d
an
t d
ata.
Stag
e
3
p
ar
ts
o
f
s
p
ee
ch
tag
g
in
g
:
T
ag
g
i
n
g
th
e
w
o
r
d
s
w
i
th
p
ar
ts
o
f
s
p
ee
ch
h
elp
s
in
ca
p
tu
r
in
g
t
h
e
e
m
o
tio
n
s
o
f
u
s
er
s
a
n
d
its
’
i
n
te
n
s
it
y
[
1
0
]
.
T
h
e
w
o
r
d
s
p
r
esen
t
in
co
r
p
o
r
a
ar
e
u
tili
ze
d
to
co
m
p
ar
e
an
d
s
eg
r
eg
ate.
T
h
e
n
o
u
n
s
an
d
ad
j
ec
tiv
es a
r
e
ass
i
g
n
ed
h
ig
h
s
co
r
e.
Stag
e
4
c
h
u
n
k
i
n
g
an
d
ch
in
k
i
n
g
d
ata:
T
h
e
m
ai
n
g
o
al
o
f
ch
u
n
k
i
n
g
i
s
to
g
r
o
u
p
to
k
e
n
s
i
n
to
"
n
o
u
n
p
h
r
ases
.
"
I
t
is
d
o
n
e
b
y
co
m
b
in
in
g
t
h
e
p
ar
t
o
f
s
p
ee
c
h
ta
g
s
w
i
th
r
e
g
u
lar
e
x
p
r
ess
io
n
s
[
1
1
].
A
f
ter
a
lo
t
o
f
ch
u
n
k
in
g
,
th
er
e
w
o
u
ld
s
till
b
e
s
o
m
e
w
o
r
d
s
in
ch
u
n
k
th
at
ar
e
a
m
b
i
g
u
o
u
s
.
C
h
i
n
k
i
n
g
h
elp
s
in
r
e
m
o
v
i
n
g
u
n
c
h
u
n
k
ed
d
ata
f
r
o
m
c
h
u
n
k
s
.
Stag
e
5
l
e
m
m
atizi
n
g
th
e
d
ata
:
L
e
m
m
atizi
n
g
is
s
i
m
ilar
to
s
t
e
m
m
in
g
,
b
u
t
s
te
m
m
i
n
g
ca
n
o
f
te
n
cr
ea
te
n
o
n
-
ex
is
te
n
t
w
o
r
d
s
,
w
h
er
ea
s
le
m
m
as
ar
e
ac
tu
a
l
w
o
r
d
s
.
I
t
tak
es
p
ar
t
o
f
s
p
ee
ch
a
s
p
ar
am
eter
a
n
d
p
u
ll
s
t
h
e
r
esu
lt.
W
o
r
d
NetL
e
m
m
atize
r
is
i
m
p
o
r
ted
f
r
o
m
n
lt
k
.
s
te
m
.
T
h
e
tex
t
is
p
as
s
ed
as
a
p
ar
am
e
ter
in
to
W
o
r
d
NetL
e
m
m
atize
r
.
le
m
m
at
i
ze
(
)
.
R
esu
lta
n
t
w
o
r
d
s
ar
e
ca
r
r
ied
o
v
er
f
o
r
cr
ea
tin
g
s
e
n
ti
m
e
n
t
m
o
d
u
le.
Stag
e
6
c
o
r
p
o
r
a
m
atc
h
i
n
g
:
T
h
e
NL
T
K
co
r
p
u
s
is
a
h
u
g
e
h
e
ap
o
f
all
k
i
n
d
s
o
f
n
a
t
u
r
al
lan
g
u
a
g
e
d
at
a
s
ets.
T
h
e
co
r
p
u
s
m
i
g
h
t
b
e
te
x
t
f
ile
s
o
r
X
ML
d
ata.
I
t
h
elp
s
in
h
it
tin
g
th
e
s
y
n
o
n
y
m
s
a
n
d
p
r
o
v
id
in
g
r
ele
v
a
n
c
y
i
n
th
e
an
a
l
y
s
is
.
G
u
te
n
b
er
g
f
r
o
m
n
lt
k
-
co
r
p
u
s
is
i
m
p
o
r
ted
.
Gu
t
en
b
er
g
-
B
ib
le
i
s
a
tex
t
f
ile
w
it
h
in
P
y
th
o
n
lib
r
ar
y
.
T
h
is
co
r
p
u
s
h
elp
s
i
n
id
en
ti
f
y
i
n
g
th
e
r
ele
v
an
t
w
o
r
d
s
i
n
t
h
e
r
ea
l
w
o
r
ld
f
o
r
an
al
y
zi
n
g
t
h
e
d
ata.
T
h
e
d
ata
is
p
ass
ed
an
d
co
m
p
ar
ed
w
it
h
co
r
p
u
s
w
h
ich
h
elp
s
in
id
e
n
ti
f
icatio
n
o
f
u
s
ef
u
l
w
o
r
d
s
.
Stag
e
7
n
aï
v
e
B
a
y
es
C
la
s
s
i
f
ic
atio
n
:
I
t
is
a
s
u
p
er
v
i
s
ed
r
u
le
m
in
i
n
g
w
h
er
e
w
e
f
ee
d
t
h
e
m
ac
h
in
e
s
tati
n
g
w
h
ic
h
is
p
o
s
iti
v
e
an
d
n
e
g
ati
v
e.
T
h
e
d
ata
is
f
ea
t
u
r
ed
i
n
to
tr
ain
i
n
g
d
ata
a
n
d
r
u
n
o
n
n
a
ïv
e
b
ay
e
s
cla
s
s
i
f
icatio
n
.
T
h
is
p
r
o
v
id
es
th
e
p
er
ce
n
ta
g
e
o
f
p
o
s
itiv
e
a
n
d
n
e
g
ati
v
e
d
ata.
T
h
e
d
ata
f
o
r
w
h
ich
y
o
u
w
an
t
to
tr
ain
an
d
te
s
t
t
h
e
class
i
f
ier
i
s
f
ir
s
tl
y
s
p
lit.
T
r
ain
in
g
i
s
d
o
n
e
th
r
o
u
g
h
class
i
f
ier
s
b
y
p
ass
i
n
g
t
h
e
tr
ain
i
n
g
s
et
i
n
to
n
lt
k
.
Naiv
eB
a
y
es
C
las
s
i
f
ier
.
tr
ain
().
Stag
e
8
Scik
it
-
L
ea
r
n
in
g
:
W
o
r
d
s
ar
e
p
r
o
ce
s
s
ed
to
t
o
k
en
s
an
d
co
n
v
er
ted
to
f
ea
tu
r
es.
Scik
it
-
lear
n
[
1
2
]
is
a
p
ac
k
ag
e
o
f
v
ar
io
u
s
clas
s
i
f
i
er
s
lik
e
S
u
p
p
o
r
t V
ec
to
r
Ma
ch
i
n
(
SVM)
a
n
d
Ga
u
s
s
ia
n
.
T
h
e
al
g
o
r
ith
m
i
s
ap
p
lied
to
r
etr
iev
e
th
e
f
u
zz
y
d
ata.
T
h
e
d
ata
f
o
ld
er
is
p
ass
ed
as
a
p
ar
a
m
eter
w
i
th
p
o
s
an
d
n
e
g
s
u
b
-
f
o
ld
er
s
w
h
er
e
t
h
e
p
o
s
itiv
e
an
d
n
eg
at
iv
e
r
e
f
er
en
c
ed
d
ata
ar
e
p
r
esen
t.
Stag
e
9
C
r
ea
tio
n
o
f
Sen
ti
m
e
n
t
Mo
d
u
le
:
Si
n
ce
t
h
e
d
ata
to
b
e
an
al
y
ze
d
is
co
llected
a
n
d
p
r
e
-
p
r
o
ce
s
s
ed
,
s
en
ti
m
e
n
t
m
o
d
u
le
i
s
cr
ea
ted
w
h
ic
h
it
i
s
co
llecti
v
el
y
lo
ad
ed
f
o
r
an
al
y
s
is
.
T
h
e
d
ata
f
ed
is
s
p
lit
i
n
to
w
o
r
d
s
/to
k
e
n
s
a
n
d
P
ar
ts
o
f
s
p
ee
ch
tag
g
in
g
i
s
d
o
n
e.
P
o
s
itiv
e
an
d
n
eg
ati
v
e
w
o
r
d
lib
r
ar
ie
s
ar
e
o
p
en
ed
an
d
ass
i
g
n
ed
to
a
v
ar
iab
le
th
at
is
f
u
r
t
h
er
r
ef
er
r
ed
.
C
lass
i
f
icati
o
n
o
f
d
ata
is
d
o
n
e
u
s
i
n
g
t
h
e
p
ick
led
alg
o
r
ith
m
s
.
f
ea
t
u
r
esets
.
p
ic
k
le
(
)
an
d
B
er
n
o
u
lli_
class
if
ier
.
p
ick
le
(
)
ar
e
i
m
p
o
r
ted
w
h
er
e
th
e
alg
o
r
it
h
m
s
ar
e
f
ed
.
Op
en
th
e
p
ick
led
alg
o
r
it
h
m
s
s
av
ed
i
n
d
o
cu
m
e
n
ts
.
p
ic
k
le.
N
L
T
K
p
r
o
v
id
es
a
f
u
n
c
tio
n
ali
t
y
o
f
cla
s
s
i
f
y
in
g
th
e
d
ata
as
p
er
th
e
p
ick
le.
T
h
e
d
ataset
is
s
h
u
f
f
led
an
d
s
p
lit
to
tr
ain
i
n
g
d
ata
an
d
test
i
n
g
d
ata
th
a
t
ar
e
p
ass
ed
to
th
e
class
if
ier
s
f
o
r
an
al
y
s
i
s
.
Nltk
cla
s
s
i
f
y
.
ac
cu
r
ac
y
(
cla
s
s
i
f
ier
,
test
in
g
s
et
*
1
0
0
)
g
iv
e
s
th
e
ac
c
u
r
ac
y
p
er
ce
n
t
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
:
2
5
8
5
-
2592
2588
Fig
u
r
e
2
.
Sen
ti
m
e
n
t
an
al
y
s
is
f
l
o
w
c
h
ar
t
2
.
5
.
Alg
o
rit
h
m
I
n
p
u
t:
Da
ta
f
r
o
m
An
d
r
o
id
ap
p
licatio
n
s
,
b
lo
g
s
an
d
w
eb
s
ites
r
elate
d
to
h
ea
lt
h
ca
r
e
in
d
u
s
tr
i
es
.
Ou
tp
u
t
:
Sen
ti
m
e
n
t I
n
d
e
x
o
f
th
e
r
e
v
ie
ws
w
h
ic
h
d
en
o
tes t
h
e
p
o
s
iti
v
e
a
n
d
n
e
g
ativ
e
i
m
p
r
es
s
io
n
o
f
t
h
e
u
s
er
s
/c
u
s
to
m
er
s
.
1.
C
o
m
p
ile
t
h
e
d
ata
f
r
o
m
M
y
SQ
L
DB
an
d
test
f
ile
s
in
to
a
s
i
n
g
l
e
f
r
ee
tex
t
f
ile.
2.
P
r
e
-
P
r
o
ce
s
s
in
g
:
a.
C
o
n
v
er
t t
h
e
w
o
r
d
s
to
to
k
e
n
s
u
s
i
n
g
N
L
T
K
lib
r
ar
y
b
.
I
d
en
tify
s
to
p
w
o
r
d
s
an
d
cle
ar
th
e
m
.
3.
T
ag
th
e
w
o
r
d
s
w
it
h
P
ar
ts
o
f
S
p
ee
ch
(
No
u
n
a
n
d
A
d
j
ec
tiv
e)
4.
Ma
tch
t
h
e
w
o
r
d
s
w
it
h
t
h
e
co
r
p
o
r
a
av
ailab
le
in
th
e
N
L
T
K
p
ac
k
ag
e.
5.
Fo
r
ea
ch
w
o
r
d
in
t
h
e
d
ata
s
et(
w
o
r
d
s
(
i)
)
{
I
f
(
if
(
w
o
r
d
s
(
i)
)
==
p
o
s
itiv
e
an
d
w
o
r
d
s
(
i
-
1
)
!
=
n
o
t/n
o
)
{
P
o
s
itiv
eW
o
r
d
C
o
u
n
t++
}
E
ls
e
{
Neg
ativ
eW
o
r
d
C
o
u
n
t++
}
6
.
Sto
r
e
th
e
P
o
s
iti
v
eW
o
r
d
C
o
u
n
t
an
d
Ne
g
ati
v
eW
o
r
d
C
o
u
n
t
o
f
th
e
w
o
r
d
s
to
tr
ain
th
e
s
e
n
ti
m
en
t
Mo
d
u
le
to
d
eter
m
in
Se
n
ti
m
e
n
tI
n
d
e
x
3.
E
XP
E
R
I
M
E
NT
a.
P
o
s
t d
ata
th
r
o
u
g
h
An
d
r
o
id
A
p
p
licatio
n
An
an
d
r
o
id
ap
p
licatio
n
is
cr
ea
ted
w
it
h
th
e
f
ield
s
r
eq
u
ir
ed
an
d
h
o
s
ted
lo
ca
ll
y
.
A
s
u
r
v
e
y
h
as
b
ee
n
co
n
d
u
cted
o
n
th
e
r
ev
ie
w
s
a
n
d
co
m
m
e
n
ts
s
u
b
m
itted
b
y
th
e
u
s
er
s
.
T
h
e
d
ata
is
f
etch
e
d
in
to
th
e
My
SQ
L
Data
b
ase
d
y
n
a
m
ical
l
y
.
T
h
e
s
n
ap
s
h
o
t
o
f
s
u
b
m
i
tti
n
g
co
m
m
e
n
ts
th
r
o
u
g
h
an
d
r
o
id
ap
p
,
s
to
r
i
n
g
d
ata
in
d
atab
ase,
w
eb
s
cr
ap
in
g
co
m
m
e
n
ts
f
r
o
m
in
ter
n
et
co
n
ten
t
s
,
o
u
tp
u
t
o
f
co
m
m
e
n
t
s
a
f
ter
w
eb
s
cr
ap
i
n
g
,
id
en
ti
f
y
in
g
w
o
r
d
s
an
d
f
ea
tu
r
es
o
f
d
ata
an
d
s
en
ti
m
en
tal
i
n
d
ex
o
b
tain
ed
b
y
ap
p
ly
in
g
s
e
n
ti
m
en
tal
a
n
al
y
s
i
s
ar
e
d
ep
icted
in
Fi
g
u
r
e
3
th
r
o
u
g
h
F
ig
u
r
e
7
.
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
-
8708
Hea
r
t ra
te
en
ca
p
s
u
la
tio
n
a
n
d
r
esp
o
n
s
e
to
o
l u
s
in
g
s
en
timen
t
a
n
a
lysi
s
(
N
a
n
d
ya
la
S
r
u
ja
n
a
R
ed
d
y)
2589
Fig
u
r
e
3
.
Su
b
m
i
tti
n
g
co
m
m
e
n
t
s
th
r
o
u
g
h
an
d
r
o
id
ap
p
licatio
n
b.
Sto
r
e
co
m
m
e
n
ts
to
d
atab
ase
Fig
u
r
e
4
.
T
h
e
s
u
b
m
itted
co
m
m
en
ts
s
to
r
ed
in
d
atab
ase
c.
W
eb
s
cr
ap
in
g
co
m
m
en
t
s
f
r
o
m
w
eb
s
ite
s
an
d
b
lo
g
s
Fig
u
r
e
5
.
Ou
tp
u
t o
f
co
m
m
en
t
s
af
ter
w
eb
-
s
cr
ap
i
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
:
2
5
8
5
-
2592
2590
d.
Fin
d
i
n
g
w
o
r
d
s
an
d
f
ea
tu
r
e
s
Fig
u
r
e
6
.
I
d
en
tify
in
g
w
o
r
d
s
an
d
f
ea
tu
r
es o
f
t
h
e
d
ata
Fig
u
r
e
7
.
Sen
ti
m
e
n
t I
n
d
ex
o
b
t
ain
ed
af
ter
p
er
f
o
r
m
i
n
g
s
e
n
ti
m
en
t a
n
al
y
s
is
4.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
h
e
d
ata
co
llected
in
to
d
esti
n
a
tio
n
is
lo
ad
ed
to
a
tex
t f
ile
an
d
p
r
o
ce
s
s
ed
f
o
r
s
en
ti
m
e
n
t a
n
al
y
s
is
.
Si
n
ce
th
e
d
ata
is
u
n
s
tr
u
c
tu
r
ed
,
th
e
d
ata
is
p
r
o
ce
s
s
ed
u
s
in
g
th
e
ab
o
v
e
s
tated
alg
o
r
it
h
m
s
.
T
h
e
d
ata
co
llectio
n
is
d
o
n
e
au
to
m
at
icall
y
u
s
in
g
t
h
e
ab
o
v
e
p
r
o
ce
s
s
es.
T
h
e
d
ata
s
o
u
r
ce
an
d
its
d
esti
n
atio
n
is
g
i
v
en
i
n
T
ab
le
1
.
An
d
r
o
id
Stu
d
io
A
P
I
2
1
is
u
s
ed
to
p
u
s
h
th
e
co
m
m
e
n
ts
i
n
t
o
d
atab
ase
d
y
n
a
m
icall
y
.
P
ag
e
s
o
u
r
ce
o
f
d
esire
d
w
eb
s
i
te
i
s
s
cr
ap
ed
an
d
w
r
itte
n
to
tex
t
f
iles
.
Flo
w
is
p
r
o
ce
s
s
ed
b
y
o
b
tain
i
n
g
a
to
k
en
I
D
f
o
r
Mic
r
o
s
o
f
t
A
z
u
r
e
a
n
d
w
r
itte
n
to
E
x
ce
l
Fil
e
s
w
h
ic
h
r
es
u
lt
s
i
n
s
tr
u
ctu
r
ed
d
ata.
T
h
e
d
ata
co
llec
ted
is
s
tr
ip
p
ed
o
f
u
n
n
ec
es
s
ar
y
d
ata
u
s
in
g
p
r
e
-
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
e
s
.
T
h
e
e
m
ai
ls
ar
e
r
etr
iev
ed
as
P
o
w
er
B
I
s
e
t
w
h
ic
h
ca
n
f
u
r
th
er
b
e
u
s
ed
f
o
r
p
r
ed
ictiv
e
an
al
y
s
i
s
.
T
h
is
co
u
ld
also
b
e
s
en
t f
o
r
tex
t a
n
al
y
tic
s
i
n
Flo
w
(
Of
f
ice
3
6
5
Po
w
er
ap
p
s
)
.
T
ab
le
1
.
D
ata
s
o
u
r
ce
an
d
co
r
r
e
s
p
o
n
d
in
g
Desti
n
atio
n
D
a
t
a
S
o
u
r
c
e
D
e
st
i
n
a
t
i
o
n
A
n
d
r
o
i
d
a
p
p
s
M
y
S
Q
L
D
a
t
a
b
a
se
W
e
b
si
t
e
s
T
e
x
t
f
i
l
e
s
Emai
l
s
Ex
c
e
l
S
t
r
u
c
t
u
r
e
d
D
a
t
a
i
s
p
r
o
d
u
c
e
d
C
o
mb
i
n
e
d
a
n
d
st
o
r
e
d
i
n
a
s
i
n
g
l
e
t
e
x
t
f
i
l
e
T
im
e
ta
k
e
n
to
co
llect
d
ata
f
r
o
m
ea
ch
s
o
u
r
ce
m
a
n
u
all
y
a
n
d
b
y
u
s
in
g
m
ac
h
i
n
e
b
ased
al
g
o
r
ith
m
s
is
r
ec
o
r
d
e
d
an
d
p
lo
tted
in
m
in
u
tes
as
s
h
o
w
n
i
n
F
ig
u
r
e
8
.
P
r
e
-
p
r
o
ce
s
s
i
n
g
t
h
e
d
ata
i
s
i
m
p
l
e
m
en
ted
in
P
y
th
o
n
u
s
i
n
g
NL
T
K
lib
r
ar
y
.
A
s
en
t
i
m
en
t
m
o
d
u
le
w
a
s
in
itiall
y
b
u
ilt
in
to
w
h
ich
t
h
e
d
ata
co
llected
is
f
ed
.
Fig
u
r
e
9
s
h
o
w
s
th
e
ti
m
e
ta
k
en
to
p
er
f
o
r
m
s
en
ti
m
en
t
an
al
y
s
is
o
n
ea
ch
s
et
o
f
d
ata,
m
an
u
all
y
a
n
d
b
y
u
s
i
n
g
m
ac
h
i
n
e
b
ased
alg
o
r
ith
m
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Hea
r
t ra
te
en
ca
p
s
u
la
tio
n
a
n
d
r
esp
o
n
s
e
to
o
l u
s
in
g
s
en
timen
t
a
n
a
lysi
s
(
N
a
n
d
ya
la
S
r
u
ja
n
a
R
ed
d
y)
2591
Fig
u
r
e
8
.
Ma
ch
in
e
b
ased
v
s
m
an
u
al
p
r
o
ce
s
s
f
o
r
Data
C
o
llectio
n
F
ig
u
r
e
9
.
Ma
ch
in
e
b
ased
v
s
m
an
u
al
p
r
o
ce
s
s
f
o
r
Sen
ti
m
e
n
t a
n
a
l
y
s
is
Sen
ti
m
e
n
t
an
al
y
s
is
g
en
er
ate
s
a
r
ep
o
r
t
w
it
h
p
o
s
itiv
e
a
n
d
n
e
g
a
tiv
e
a
s
p
ec
ts
o
f
th
e
f
ee
d
b
ac
k
.
T
h
e
r
an
k
i
n
g
s
f
o
r
t
h
e
s
tr
u
ct
u
r
ed
r
ev
ie
w
is
g
i
v
e
n
as:
e
x
ce
lle
n
t
-
5
,
g
o
o
d
-
4
,
av
er
ag
e
-
3
,
p
o
o
r
-
4
,
w
o
r
s
t
-
5.
T
h
e
s
en
ti
m
en
t
i
s
ca
lcu
lated
as
p
er
th
e
n
u
m
b
er
o
f
r
ev
ie
w
s
an
d
r
an
k
i
n
g
s
[
1
2
]
.
A
s
u
r
v
e
y
w
a
s
co
n
d
u
cted
i
n
f
e
w
h
o
s
p
ital
s
w
h
er
e
t
h
e
p
atie
n
t
s
w
er
e
as
k
ed
to
p
o
s
t
th
eir
f
ee
d
b
ac
k
eit
h
er
th
r
o
u
g
h
w
eb
s
i
tes,
m
a
ils
o
r
ap
p
s
.
T
h
e
f
ee
d
b
ac
k
w
a
s
co
lle
cted
w
h
ich
r
ep
o
r
ted
ab
o
u
t
9
4
%
ac
cu
r
ac
y
w
h
en
co
m
p
ar
e
a
g
ai
n
s
t
m
a
n
u
al
a
n
d
m
ac
h
in
e
b
ased
an
a
l
y
s
is
.
T
h
e
r
esu
lta
n
t
p
o
s
it
iv
e
an
d
n
e
g
ati
v
e
w
o
r
d
s
ar
e
g
i
v
e
n
i
n
T
ab
le
2
.
Ho
s
p
ital
r
ev
ie
w
d
ata
s
et
co
llected
an
d
m
o
v
ie
d
ataset
p
r
esen
t
w
it
h
i
n
th
e
N
L
T
K
m
o
d
u
le
ar
e
ex
p
er
i
m
e
n
ted
a
n
d
co
m
p
ar
ed
.
Su
r
v
e
y
[
1
3
]
s
u
g
g
e
s
ts
th
at
h
o
s
p
ital
m
a
n
a
g
e
m
e
n
t
is
r
ea
d
y
to
co
n
s
id
er
m
ac
h
i
n
e
-
b
ased
s
en
t
i
m
e
n
t
an
a
l
y
s
is
as
a
f
ac
to
r
to
i
m
p
r
o
v
e
t
h
eir
f
ac
i
liti
es
i
n
h
ea
lt
h
ca
r
e.
I
n
f
ac
t,
t
h
e
y
h
av
e
co
m
e
u
p
w
it
h
m
o
r
e
u
s
es
t
h
at
s
en
t
i
m
e
n
t
an
a
l
y
s
i
s
co
u
ld
p
r
o
v
id
e.
I
t
i
s
s
tated
th
at
p
o
s
iti
v
e
a
n
d
n
eg
a
tiv
e
w
o
r
d
s
ca
teg
o
r
ized
f
o
r
ev
er
y
d
o
m
ai
n
co
u
ld
h
e
lp
th
e
m
r
ec
o
g
n
ize
th
e
ar
ea
s
o
f
p
r
o
s
an
d
co
n
s
[
1
4
]
.
T
h
e
w
o
r
d
s
ar
e
co
llected
an
d
s
to
r
ed
as
p
o
s
iti
v
e
a
n
d
n
eg
at
iv
e
w
o
r
d
s
[
1
5
]
as
p
er
t
h
e
u
s
a
g
e
o
f
p
e
o
p
le
all
o
v
er
.
T
h
e
y
also
in
cl
u
d
e
co
m
m
o
n
l
y
u
s
ed
p
h
r
ases
i
n
s
o
cial
m
ed
ia
w
h
ic
h
ar
e
co
n
s
id
er
ed
as r
ef
er
en
ce
wh
ile
an
a
l
y
s
i
n
g
t
h
e
d
ata.
T
ab
le
2
.
R
esu
lta
n
t p
o
s
itiv
e
a
n
d
n
eg
ati
v
e
w
o
r
d
s
P
a
t
i
e
n
t
F
e
e
d
b
a
c
k
P
o
si
t
i
v
e
N
e
g
a
t
i
v
e
R
e
g
a
r
d
i
n
g
h
o
s
p
i
t
a
l
i
t
y
o
f
t
h
e
h
o
sp
i
t
a
l
man
a
g
e
me
n
t
c
l
e
a
r
w
o
r
k
good
b
e
l
o
v
e
d
g
r
e
a
t
w
e
l
l
b
e
st
mi
sco
n
c
e
p
t
i
o
n
f
r
u
st
r
a
t
i
o
n
h
a
n
d
i
c
a
p
p
e
d
r
u
d
e
u
n
k
i
n
d
h
o
r
r
i
b
l
e
d
i
sg
u
st
i
n
g
p
a
t
h
e
t
i
c
C
o
st
a
n
d
v
a
l
u
e
o
f
t
h
e
t
r
e
a
t
me
n
t
w
o
r
t
h
b
e
st
sw
e
e
t
b
a
d
f
r
a
u
d
En
v
i
r
o
n
me
n
t
c
l
e
a
r
b
e
a
u
t
y
c
o
n
sc
i
o
u
s
n
o
i
sy
v
u
l
n
e
r
a
b
l
e
p
a
t
h
e
t
i
c
f
o
u
l
Ma
n
u
a
l
a
n
al
y
s
is
i
n
v
o
l
v
es
f
i
n
d
in
g
o
f
p
o
s
iti
v
e
a
n
d
n
eg
at
iv
e
w
o
r
d
s
i
n
th
e
r
ev
ie
w
s
.
T
h
e
s
a
m
e
p
er
ce
p
tio
n
is
i
m
p
le
m
en
ted
in
P
y
th
o
n
t
h
at
r
e
s
u
l
ted
in
8
5
%
ac
cu
r
ac
y
.
I
n
ac
cu
r
ac
y
i
s
ca
u
s
e
d
d
u
e
to
t
h
e
u
s
a
g
e
an
d
co
n
te
x
t.
Hen
ce
,
t
h
e
al
g
o
r
ith
m
s
a
n
d
class
if
ier
s
ar
e
i
m
p
le
m
en
ted
to
s
en
s
e
t
h
e
u
s
ag
e
a
n
d
e
m
o
tio
n
s
b
y
r
ati
n
g
th
e
ad
j
ec
tiv
es
w
h
ic
h
led
to
m
o
r
e
ac
cu
r
ate
r
esu
lt
s
.
I
t
h
a
s
b
ee
n
test
ed
f
o
r
m
a
n
y
d
ata
s
ets.
Acc
u
r
ac
y
p
er
ce
n
ta
g
e
is
c
h
ec
k
ed
f
o
r
ev
er
y
cla
s
s
i
f
ier
w
h
ic
h
r
ep
o
r
ted
a
s
i
m
ilar
ac
cu
r
ac
y
as
d
ep
icted
in
Fi
g
u
r
e
1
0
.
T
h
e
d
ata
co
llected
f
r
o
m
t
h
e
s
o
u
r
ce
s
is
p
a
s
s
ed
t
h
r
o
u
g
h
s
e
n
ti
m
e
n
t
m
o
d
u
le
a
n
d
i
m
p
le
m
en
ted
in
P
y
th
o
n
.
T
h
e
v
ar
io
u
s
clas
s
i
f
ier
s
d
is
cu
s
s
ed
ab
o
v
e
ar
e
u
s
ed
in
s
e
n
ti
m
en
t a
n
al
y
s
is
.
NL
T
K
[
3
]
is
a
lar
g
e
f
a
m
il
y
wh
er
e
an
y
an
al
y
tical
al
g
o
r
ith
m
s
co
u
ld
b
e
b
u
ilt
e
f
f
ec
ti
v
el
y
.
W
h
en
d
ata
i
s
s
en
t
t
h
r
o
u
g
h
t
h
e
m
,
t
h
e
ac
cu
r
ac
y
p
er
ce
n
t
d
if
f
er
s
f
o
r
ev
er
y
d
ataset.
E
x
p
er
i
m
en
ta
l
r
esu
lt
s
o
n
t
w
o
r
ec
o
r
d
s
et
p
r
o
v
id
ed
6
5
-
7
0
%
ac
cu
r
ac
y
.
T
h
is
a
s
s
u
r
es
t
h
at
ac
cu
r
ac
y
is
m
o
r
e
th
an
5
0
%
w
h
ich
ca
n
ac
t
a
s
a
m
aj
o
r
b
u
s
in
e
s
s
-
d
ec
is
io
n
m
a
k
i
n
g
s
tate
m
e
n
t.
T
h
e
co
m
m
e
n
t
s
w
er
e
co
llected
f
r
o
m
th
e
w
eb
s
ite
s
,
ap
p
s
an
d
m
ail
s
an
d
s
to
r
ed
in
tex
t
f
ile.
T
h
e
g
iv
en
g
r
ap
h
s
m
ea
s
u
r
e
t
h
e
ac
c
u
r
ac
y
o
f
m
a
n
u
al
a
n
al
y
s
is
v
s
m
ac
h
in
e
b
ased
s
e
n
ti
m
e
n
t
a
n
al
y
s
is
.
Fro
m
Fi
g
u
r
e
1
1
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
:
2
5
8
5
-
2592
2592
t
h
e
ac
c
u
r
ac
y
s
ca
le
d
e
n
o
tes
th
e
i
m
p
ac
t
o
f
m
ac
h
i
n
e
b
ased
al
g
o
r
ith
m
s
t
h
at
is
b
ein
g
d
o
n
e
in
n
o
ti
m
e.
T
h
e
r
es
u
lt
s
s
u
g
g
e
s
t
a
m
ec
h
an
is
m
to
ad
d
r
ess
t
h
e
f
lo
w
in
g
d
ata
esp
ec
i
all
y
f
ee
d
b
ac
k
w
h
ic
h
is
co
n
s
id
er
ed
an
ass
et
o
f
u
p
g
r
ad
in
g
b
u
s
i
n
es
s
.
T
h
is
ca
n
b
e
ad
v
an
ce
d
to
r
ep
lace
tr
ad
itio
n
al
an
al
y
s
is
.
T
h
e
f
ig
u
r
e
s
h
o
w
s
t
h
e
ac
cu
r
ac
y
o
f
s
en
ti
m
e
n
t a
n
al
y
s
is
e
m
p
lo
y
ed
o
n
th
e
d
ata
s
ets ac
q
u
ir
ed
.
Fig
u
r
e
1
0
.
C
lass
i
f
ier
B
ased
ac
cu
r
ac
y
Fig
u
r
e
1
1
.
A
cc
u
r
ac
y
m
ea
s
u
r
e
o
f
s
en
ti
m
e
n
t a
n
al
y
s
i
s
5.
C
O
NCLU
SI
O
N
Hea
lth
ca
r
e
i
s
t
h
e
f
ield
t
h
at
h
as
g
a
in
ed
atte
n
tio
n
all
o
v
er
t
h
e
w
o
r
ld
as
i
t
i
s
i
m
p
o
r
ta
n
t
f
o
r
s
u
r
v
i
v
al.
Sin
ce
t
h
e
f
ee
d
b
ac
k
is
p
r
o
v
id
ed
in
d
ig
ital
f
o
r
m
,
th
er
e
is
an
u
r
g
e
n
t
n
ee
d
in
an
a
u
to
m
ated
an
al
y
s
is
.
T
h
is
p
ap
er
d
em
o
n
s
tr
ated
t
h
e
k
e
y
p
r
o
ce
s
s
es
o
f
Data
co
llec
t
io
n
a
n
d
Se
n
ti
m
en
t
a
n
al
y
s
is
.
T
h
is
p
la
y
s
an
i
m
m
en
s
e
r
o
le
i
n
s
tr
ea
m
-
li
n
i
n
g
t
h
e
b
u
s
i
n
es
s
p
r
o
ce
s
s
es.
Feed
b
ac
k
is
co
llec
ted
f
r
o
m
o
n
li
n
e
w
eb
s
ites
,
ap
p
s
a
n
d
m
ail
s
a
n
d
te
s
ted
in
r
ea
l
-
en
v
ir
o
n
m
e
n
t.
Se
n
ti
m
e
n
t
a
n
al
y
s
is
is
d
o
n
e
o
n
t
h
e
li
v
e
-
d
ata
p
r
o
cu
r
ed
an
d
r
ep
o
r
ted
.
A
l
l
t
h
e
al
g
o
r
ith
m
s
h
av
e
b
ee
n
i
m
p
le
m
en
ted
i
n
P
y
t
h
o
n
an
d
ac
cu
r
ate
r
es
u
lt
s
h
av
e
b
ee
n
g
e
n
er
ated
.
Gr
ap
h
ical
r
ep
r
esen
tatio
n
s
h
o
w
i
n
g
v
ar
iatio
n
s
h
a
s
b
ee
n
p
r
o
v
id
ed
f
o
r
a
w
id
e
-
a
n
g
le
v
ie
w.
I
n
f
u
t
u
r
e,
d
ata
co
llectio
n
w
o
u
ld
b
e
d
o
n
e
d
y
n
a
m
icall
y
f
r
o
m
w
eb
s
i
tes
w
h
er
e
a
ti
m
er
w
o
u
ld
b
e
s
et
f
o
r
ev
er
y
n
e
w
co
m
m
en
t.
A
s
er
v
ic
e
b
ased
s
ch
ed
u
le
w
o
u
ld
b
e
d
ev
elo
p
ed
f
o
r
th
e
s
a
m
e.
Se
n
ti
m
en
t
a
n
al
y
s
i
s
w
o
u
ld
b
e
th
en
d
o
n
e
o
n
e
v
er
y
s
in
g
le
r
ev
ie
w
a
n
d
u
p
d
ated
.
A
l
s
o
,
an
e
x
tr
e
m
e
o
p
ti
m
izatio
n
is
b
ein
g
p
lan
n
ed
to
in
cr
ea
s
e
th
e
ac
cu
r
ac
y
o
f
t
h
e
s
e
n
ti
m
en
t
an
al
y
s
is
.
An
a
u
to
m
at
ic
aler
t
w
o
u
ld
b
e
s
en
t
to
t
h
e
h
o
s
p
ita
l
i
f
t
h
er
e
is
a
n
i
n
cr
ea
s
ed
n
e
g
ati
v
it
y
f
o
r
a
f
e
atu
r
e.
T
h
is
is
cu
r
r
en
tl
y
i
n
d
ev
elo
p
m
en
t
w
h
ic
h
u
s
e
s
MSG
9
1
as
A
P
I
to
s
en
d
au
to
m
atic
m
es
s
ag
e
s
.
T
h
is
co
u
ld
h
elp
in
ad
d
r
ess
in
g
t
h
e
i
s
s
u
e
at
th
e
ea
r
l
iest
.
T
h
is
h
elp
s
t
h
e
h
o
s
p
ital to
co
n
ce
n
tr
ate
o
n
a
n
y
d
o
m
a
in
i
n
a
r
ig
h
t
w
a
y
.
RE
F
E
R
E
NC
E
S
[1
]
B
.
S
tev
e
n
,
e
t
a
l
.
,
“
Na
tu
ra
l
L
a
n
g
u
a
g
e
P
ro
c
e
ss
in
g
w
it
h
P
y
th
o
n
,
”
pp.
1
6
,
2
7
,
79
,
2
0
0
9
.
[2
]
G
a
o
G
.
G
.
,
e
t
a
l
.
,
“
A
c
h
a
n
g
in
g
lan
d
sc
a
p
e
o
f
p
h
y
sic
ian
q
u
a
li
ty
re
p
o
rti
n
g
:
a
n
a
ly
sis
o
f
p
a
ti
e
n
ts'
o
n
li
n
e
ra
ti
n
g
s
o
f
th
e
ir
p
h
y
sic
ian
s o
v
e
r
a
p
e
rio
d
,”
2
0
1
2
.
[3
]
G
re
a
v
e
s
F
.
a
n
d
M
il
lett
C.
,
“
Co
n
siste
n
tl
y
in
c
re
a
sin
g
n
u
m
b
e
rs
o
f
o
n
li
n
e
r
a
ti
n
g
s
o
f
h
e
a
lt
h
c
a
re
in
E
n
g
lan
d
,”
J
M
e
d
In
ter
n
e
t
Res
,
v
o
l/
iss
u
e
:
1
4
(3
)
,
p
p
.
e
9
4
,
2
0
1
2
.
[4
]
P
.
Ye
rp
u
d
e
,
e
t
a
l
.
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
n
N
a
t
u
ra
l
L
a
n
g
u
a
g
e
Co
mp
u
ti
n
g
(
IJ
NL
C)
,
v
ol
/i
ss
u
e
:
4
(
4
)
,
2
0
1
5
.
[5
]
G
re
a
v
e
s
F
.
,
e
t
a
l
.
,
“
A
ss
o
c
iatio
n
s
b
e
tw
e
e
n
In
tern
e
t
-
b
a
se
d
p
a
ti
e
n
t
ra
ti
n
g
s
a
n
d
c
o
n
v
e
n
ti
o
n
a
l
su
rv
e
y
s
o
f
p
a
ti
e
n
t
e
x
p
e
rien
c
e
in
th
e
E
n
g
li
sh
NH
S
:
a
n
o
b
se
rv
a
ti
o
n
a
l
stu
d
y
,”
BM
J
Qu
a
l
S
a
f
.
,
v
o
l/
issu
e
:
2
1
(7
)
,
p
p
.
6
0
0
-
5
,
2
0
1
2
.
[6
]
F
o
x
S
.
,
“
T
h
e
S
o
c
ial
L
if
e
o
f
H
e
a
lt
h
In
f
o
rm
a
ti
o
n
,”
W
a
sh
in
g
to
n
,
DC:
P
e
w
Re
se
a
rc
h
Ce
n
ter
,
2
0
1
1
.
[7
]
Ku
m
a
r
P
.
K.
a
n
d
Na
n
d
a
g
o
p
a
la
n
S
,
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
ol
/i
ss
u
e
:
7
(
5
)
,
p
p
.
2
8
1
8
-
2
8
2
2
,
2
0
1
7
.
[8
]
M
.
Ch
rist
o
p
h
e
r
D.
a
n
d
S
.
Hin
r
ich
,
“
F
o
u
n
d
a
ti
o
n
s
o
f
S
tatisti
c
a
l
Na
tu
r
a
l
L
a
n
g
u
a
g
e
P
ro
c
e
ss
in
g
,
”
Ch
4
,
p
p
.
5
7
5
,
2
0
0
3
.
[9
]
P
.
A
ro
ra
,
e
t
a
l
.
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
te
r
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
ol
/i
ss
u
e
:
7
(
2
)
,
p
p
.
9
6
7
-
974
,
2
0
1
7
.
[1
0
]
R
.
M
á
rio
a
n
d
T
.
A
n
tó
n
io
,
“
A
d
v
a
n
c
e
d
A
p
p
li
c
a
ti
o
n
s
o
f
Na
tu
ra
l
L
a
n
g
u
a
g
e
P
ro
c
e
ss
in
g
f
o
r
P
e
rf
o
rm
in
g
,
”
Ch
1
,
2,
4
.
[1
1
]
F.
Je
ff
re
y
E.
F.
,
“
M
a
ste
rin
g
Re
g
u
lar E
x
p
re
ss
io
n
s
,
”
2
0
0
6
.
[1
2
]
S
c
ik
it
-
lea
rn
.
h
tt
p
:/
/sc
ik
it
-
lea
rn
.
o
rg
/stab
le/
[1
3
]
X
.
F
a
n
g
a
n
d
J
.
Z
h
a
n
,
J
o
u
rn
a
l
o
f
B
ig
Da
t
a
,
v
o
l.
2
,
p
p
.
5
,
2
0
1
5
.
[1
4
]
L
.
R.
Na
ir,
e
t
a
l
.
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
t
e
r
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
ol
/i
ss
u
e
:
7
(
1
)
,
p
p
.
4
0
2
-
407
,
2
0
1
7
.
[1
5
]
L
iu
B
.,
“
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis a
n
d
Op
in
i
o
n
M
in
in
g
.
S
y
n
th
e
sis L
e
c
tu
re
s o
n
Hu
m
a
n
L
a
n
g
u
a
g
e
T
e
c
h
n
o
lo
g
ies
,
”
2
0
1
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.