I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
4
,
A
u
g
u
s
t
20
25
,
p
p
.
3
8
4
3
~
3
8
5
0
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
4
.
pp
3
8
4
3
-
3
8
5
0
3843
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Rea
l
-
time
ma
chin
e learning
-
ba
sed
po
sture corre
ctio
n f
o
r
enha
nced e
x
er
cis
e perf
o
rma
nc
e
Anis
h K
ha
dta
re
,
Va
s
is
t
ha
Ved,
H
im
a
ns
hu
K
o
t
a
k,
Ak
hil
J
a
in,
P
ink
i V
is
hwa
k
a
rma
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
S
h
a
h
a
n
d
A
n
c
h
o
r
K
u
t
c
h
h
i
E
n
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
M
u
m
b
a
i
,
M
a
h
a
r
a
s
h
t
r
a
,
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
8
,
2
0
2
4
R
ev
is
ed
Ap
r
1
2
,
2
0
2
5
Acc
ep
ted
Ma
y
2
4
,
2
0
2
5
P
o
o
r
p
o
stu
re
a
n
d
a
ss
o
c
iate
d
p
h
y
sic
a
l
h
e
a
lt
h
p
r
o
b
lem
s
h
a
v
e
g
r
o
wn
m
o
re
c
o
m
m
o
n
a
s
tec
h
n
o
lo
g
y
u
se
in
c
r
e
a
se
s,
e
sp
e
c
i
a
ll
y
d
u
r
in
g
wo
r
k
o
u
t
se
ss
io
n
s.
M
a
in
tain
i
n
g
p
r
o
p
e
r
p
o
st
u
re
is
e
ss
e
n
ti
a
l
to
in
c
re
a
sin
g
th
e
e
ffica
c
y
o
f
y
o
u
r
wo
rk
o
u
ts
a
n
d
a
v
o
i
d
in
g
in
ju
ri
e
s.
Th
e
re
se
a
rc
h
p
a
p
e
r
p
re
s
e
n
ts
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
a
m
a
c
h
in
e
-
lea
rn
in
g
m
o
d
e
l
d
e
sig
n
e
d
to
p
ro
v
i
d
e
re
a
l
-
ti
m
e
p
o
stu
re
c
o
rre
c
ti
o
n
a
n
d
fe
e
d
b
a
c
k
f
o
r
e
x
e
rc
ise
s
su
c
h
a
s
s
q
u
a
ts
a
n
d
p
l
a
n
k
s.
Th
e
m
o
d
e
l
u
se
s
M
e
d
iaP
ip
e
fo
r
p
re
c
is
e
re
a
l
-
ti
m
e
p
o
stu
re
e
stim
a
ti
o
n
a
n
d
Op
e
n
CV
fo
r
a
n
a
ly
z
i
n
g
v
i
d
e
o
fra
m
e
s.
It
d
e
tec
ts
p
o
o
r
p
o
stu
re
a
n
d
p
ro
v
i
d
e
s
u
se
rs
with
in
sta
n
t
c
o
rre
c
ti
v
e
fe
e
d
b
a
c
k
o
n
t
h
e
ir
p
o
st
u
re
b
y
e
x
a
m
in
i
n
g
th
e
a
n
g
le
s b
e
twe
e
n
imp
o
rtan
t
b
o
d
y
p
a
rts,
s
u
c
h
a
s
th
e
a
rm
s,
k
n
e
e
s,
b
a
c
k
,
a
n
d
h
ip
s.
T
h
is
in
n
o
v
a
ti
v
e
m
e
th
o
d
e
n
a
b
les
a
th
o
r
o
u
g
h
e
v
a
lu
a
ti
o
n
o
f
f
o
rm
wit
h
o
u
t
re
q
u
iri
n
g
f
ace
-
to
-
fa
c
e
su
p
e
rv
isio
n
,
o
p
e
n
i
n
g
it
u
p
to
a
wi
d
e
r
a
u
d
ien
c
e
.
Th
e
m
o
d
e
l
is
train
e
d
o
n
re
a
l
-
wo
rl
d
wo
r
k
o
u
t
d
a
tas
e
ts
o
f
p
e
o
p
le
p
e
rfo
rm
in
g
e
x
e
rc
ise
s
in
d
iffere
n
t
p
o
siti
o
n
s
a
n
d
p
o
stu
re
s
to
e
n
su
re
th
a
t
p
o
stu
re
d
e
tec
ti
o
n
is
re
li
a
b
le
u
n
d
e
r
v
a
rio
u
s u
se
r
c
ircu
m
sta
n
c
e
s
.
Th
e
sy
ste
m
u
ti
li
z
e
s
c
u
tt
in
g
-
e
d
g
e
m
a
c
h
in
e
-
lea
rn
in
g
a
l
g
o
rit
h
m
s
to
d
e
m
o
n
str
a
te
sc
a
lab
il
it
y
a
n
d
a
d
a
p
tab
il
it
y
fo
r
fu
t
u
re
train
in
g
t
y
p
e
s
b
e
y
o
n
d
sq
u
a
ts
a
n
d
p
lan
k
s.
T
h
e
m
a
in
g
o
a
l
is
t
o
p
ro
v
id
e
u
se
rs
with
a
m
o
d
e
l
t
h
a
t
i
n
c
re
a
se
s
th
e
e
ffica
c
y
o
f
w
o
rk
o
u
ts,
lo
we
rs
t
h
e
risk
o
f
in
ju
r
y
,
a
n
d
e
n
c
o
u
ra
g
e
s
b
e
tt
e
r
e
x
e
rc
ise
h
a
b
it
s.
T
h
e
m
o
d
e
l'
s
e
m
p
h
a
sis
o
n
u
sa
b
il
it
y
a
n
d
a
c
c
e
ss
ib
il
it
y
m
a
k
e
s it
p
o
te
n
ti
a
ll
y
a
v
it
a
l
t
o
o
l
f
o
r
a
n
y
o
n
e
lo
o
k
i
n
g
to
e
n
h
a
n
c
e
th
e
ir
p
o
st
u
re
a
n
d
g
e
n
e
ra
l
fit
n
e
ss
lev
e
ls.
K
ey
w
o
r
d
s
:
Hu
m
an
p
o
s
e
esti
m
atio
n
Ma
ch
in
e
lear
n
in
g
Me
d
iaPip
e
Op
en
C
V
T
en
s
o
r
f
lo
w
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
:
An
is
h
Kh
ad
tar
e
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
,
Sh
a
h
a
n
d
An
ch
o
r
Ku
t
ch
h
i E
n
g
i
n
ee
r
in
g
C
o
lleg
e
Mu
m
b
ai
-
4
0
0
0
8
8
,
Ma
h
a
r
ash
tr
a
,
I
n
d
ia
E
m
ail:
an
is
h
.
k
h
ad
tar
e1
5
6
3
6
@
s
ak
ec
.
ac
.
in
1.
I
NT
RO
D
UCT
I
O
N
Ma
in
tain
in
g
a
p
r
o
p
er
p
o
s
tu
r
e
wh
en
ex
er
cisi
n
g
is
cr
u
cial
f
o
r
m
ax
im
izin
g
p
h
y
s
ical
p
e
r
f
o
r
m
an
ce
an
d
lo
wer
in
g
th
e
ch
a
n
ce
o
f
in
ju
r
y
[
1
]
.
R
eg
u
lar
p
h
y
s
ical
ac
tiv
ity
is
b
en
ef
icial
f
o
r
ca
r
d
io
v
ascu
lar
h
ea
lth
,
m
u
s
cu
la
r
s
tr
en
g
th
,
an
d
g
en
er
al
well
-
b
ei
n
g
,
ac
co
r
d
in
g
to
s
ev
er
al
s
tu
d
i
es.
Acc
o
r
d
in
g
to
th
e
W
o
r
ld
H
ea
lth
Or
g
an
izatio
n
,
n
ea
r
ly
3
1
%
o
f
th
e
wo
r
l
d
'
s
ad
u
lt
p
o
p
u
latio
n
,
am
o
u
n
tin
g
to
o
v
er
1
.
8
b
illi
o
n
ad
u
lts
,
ar
e
p
h
y
s
ically
in
ac
tiv
e
[
2
]
.
Ho
wev
er
,
esp
ec
ially
f
o
r
th
o
s
e
wh
o
ar
e
n
ew
to
e
x
er
cisi
n
g
,
p
o
o
r
e
x
er
cise
p
r
ac
tices
ca
n
r
e
s
u
lt
in
a
v
ar
iety
o
f
d
if
f
icu
lties
,
s
u
ch
as
ac
u
te
in
ju
r
ies
an
d
lo
n
g
-
ter
m
m
u
s
cu
lo
s
k
eleta
l
co
n
ce
r
n
s
.
T
h
is
em
p
h
asizes
h
o
w
cr
u
cial
it
i
s
to
m
ain
tain
p
r
o
p
er
f
o
r
m
,
p
ar
ti
cu
lar
ly
wh
ile
p
er
f
o
r
m
i
n
g
b
asi
c
ex
er
cises
lik
e
p
lan
k
s
an
d
s
q
u
ats.
T
ec
h
n
o
lo
g
ical
d
e
v
elo
p
m
e
n
ts
h
av
e
m
a
d
e
it
ea
s
ier
to
d
ev
elo
p
tech
n
o
lo
g
y
f
o
r
t
r
ac
k
in
g
an
d
ad
ju
s
tin
g
p
o
s
tu
r
e
wh
ile
e
x
er
cisi
n
g
.
R
ec
en
t
s
tu
d
ies
h
av
e
p
r
o
p
o
s
ed
m
ac
h
in
e
lear
n
in
g
a
n
d
c
o
m
p
u
te
r
v
is
io
n
tech
n
iq
u
es
s
u
ch
as
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
etwo
r
k
s
(
C
NN)
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVM)
,
Me
d
iaPip
e
p
o
s
e,
an
d
Dee
p
Po
s
e
ar
e
u
s
ed
to
d
e
v
elo
p
m
o
d
els
f
o
r
a
n
aly
zin
g
an
d
e
x
a
m
in
in
g
h
u
m
an
b
o
d
y
p
o
s
tu
r
e
.
Ma
n
y
o
f
t
h
e
cu
r
r
en
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
25
:
3
8
4
3
-
3850
3844
s
o
lu
tio
n
s
,
h
o
we
v
er
,
n
ee
d
m
o
d
er
n
tech
n
o
lo
g
y
o
r
s
k
illed
p
e
r
s
o
n
n
el,
wh
ich
m
ay
r
estrict
ac
c
ess
ib
ilit
y
f
o
r
p
e
o
p
le
in
T
ier
2
a
n
d
T
ie
r
3
cities wh
er
e
th
ese
r
eso
u
r
ce
s
m
ig
h
t n
o
t
b
e
ea
s
ily
ac
ce
s
s
ib
le
[
3
]
–
[
5
]
.
E
v
en
with
g
r
ea
t
ad
v
an
ce
m
en
t
s
,
th
er
e
ar
e
s
till
d
if
f
icu
lties
in
d
ev
elo
p
i
n
g
r
e
al
-
tim
e
f
ee
d
b
ac
k
s
y
s
tem
s
th
at
let
u
s
er
s
ex
am
in
e
th
eir
b
o
d
y
p
o
s
tu
r
e
d
u
r
in
g
wo
r
k
o
u
ts
o
n
th
eir
o
wn
with
o
u
t
ex
p
er
t
s
u
p
er
v
is
io
n
.
Fo
r
th
o
s
e
wh
o
wan
t
to
g
et
f
itter
in
d
is
tan
t
o
r
d
is
ad
v
an
tag
e
d
lo
ca
tio
n
s
,
t
r
ad
itio
n
al
tr
ain
in
g
tech
n
iq
u
es
s
o
m
etim
es
n
ee
d
in
-
p
er
s
o
n
in
s
tr
u
ctio
n
,
wh
ich
c
an
b
e
a
b
a
r
r
ier
.
R
ec
en
t
r
esear
ch
s
h
o
ws
th
at
o
n
e
o
f
t
h
e
m
ain
r
ea
s
o
n
s
p
e
o
p
le
ar
e
h
esit
an
t
to
wo
r
k
o
u
t
o
r
e
n
g
ag
e
in
weig
h
t
tr
ain
in
g
liv
in
g
in
T
ier
2
o
r
T
ier
3
cities
is
th
e
h
ig
h
co
s
t
ass
o
ciate
d
with
th
e
tr
ain
er
f
ee
,
in
ad
d
itio
n
to
th
e
e
x
p
en
s
iv
e
g
y
m
m
em
b
er
s
h
ip
f
ee
s
.
I
n
o
u
r
m
o
d
el
to
s
o
lv
e
th
ese
ch
allen
g
es,
p
o
s
e
esti
m
atio
n
tech
n
iq
u
es
s
u
ch
as
Me
d
iaPip
e
ar
e
u
s
ed
wh
ich
d
etec
t
u
p
to
3
3
k
e
y
p
o
in
ts
s
u
ch
as
lef
t
h
ip
,
r
ig
h
t
h
ip
lef
t
k
n
ee
,
an
d
r
ig
h
t
k
n
ee
in
t
h
e
h
u
m
an
b
o
d
y
f
o
r
an
aly
zin
g
th
e
h
u
m
an
b
o
d
y
p
o
s
tu
r
e
[
6
]
,
[
7
]
.
T
o
tr
ain
o
u
r
m
o
d
el,
a
cu
s
to
m
d
atase
t
was
co
m
p
iled
wh
ich
co
n
s
is
ted
o
f
p
eo
p
le
p
er
f
o
r
m
in
g
ex
er
cises
s
u
ch
as sq
u
ats an
d
p
lan
k
s
in
d
if
f
er
e
n
t p
o
s
itio
n
s
in
v
id
eo
f
o
r
m
at.
T
h
e
m
o
d
el
a
n
aly
ze
s
th
e
an
g
les
b
e
twee
n
v
ar
io
u
s
h
u
m
an
b
o
d
y
jo
in
t
p
o
in
ts
to
e
x
am
in
e
th
e
co
r
r
ec
tn
ess
o
f
p
o
s
tu
r
e
d
u
r
in
g
a
wo
r
k
o
u
t.
T
h
e
m
o
d
el
n
ar
r
o
ws
th
e
g
ap
b
etwe
en
th
e
n
ee
d
f
o
r
p
r
o
f
ess
io
n
al
tr
ain
in
g
an
d
th
e
ec
o
n
o
m
ic
ch
allen
g
es
th
at
ar
e
f
ac
ed
b
y
p
eo
p
le
liv
in
g
in
r
em
o
te
ar
ea
s
wh
er
e
s
u
ch
p
r
o
f
ess
io
n
al
tr
ain
i
n
g
s
er
v
ices
ar
e
n
o
t
av
ailab
le.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
Rela
t
ed
w
o
rk
Yan
g
et
a
l.
[
8
]
p
r
o
p
o
s
ed
a
s
y
s
tem
wh
ich
h
elp
s
in
an
al
y
zin
g
h
u
m
a
n
b
o
d
y
p
o
s
tu
r
e
w
h
ile
p
er
f
o
r
m
in
g
ex
er
cise.
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
ex
am
in
es
th
e
h
u
m
an
b
o
d
y
p
o
s
tu
r
e
b
y
an
aly
zi
n
g
th
e
ca
p
t
u
r
ed
v
id
e
o
o
f
th
e
u
s
er
u
s
in
g
Op
en
C
V.
T
h
e
s
y
s
tem
h
elp
s
in
g
en
er
atin
g
s
u
g
g
esti
o
n
s
f
o
r
t
h
e
u
s
er
s
to
p
e
r
f
o
r
m
th
e
e
x
er
cise
co
r
r
ec
tly
b
y
an
al
y
zin
g
th
e
c
o
o
r
d
in
ate
lo
ca
tio
n
o
f
k
e
y
p
o
in
ts
o
f
th
e
h
u
m
an
b
o
d
y
.
I
t
u
s
es
Op
en
Po
s
e
f
o
r
p
er
f
o
r
m
in
g
p
o
s
e
esti
m
atio
n
f
o
r
ex
e
r
cises
s
u
ch
as sq
u
ats an
d
p
u
s
h
-
u
p
s
.
Flo
r
es
et
a
l.
[
9
]
p
r
esen
ted
an
ap
p
licatio
n
,
wh
ich
r
ec
o
r
d
s
u
s
er
s
wo
r
k
in
g
o
u
t
u
s
in
g
th
e
c
am
er
as
o
n
th
eir
s
m
ar
tp
h
o
n
es
an
d
u
s
es
a
f
u
zz
y
in
f
er
en
ce
s
y
s
tem
(F
I
S)
to
class
if
y
wo
r
k
o
u
t
p
er
f
o
r
m
an
ce
af
ter
s
k
eleto
n
izin
g
th
e
u
s
er
an
d
ex
tr
ac
tin
g
jo
in
t a
n
g
les.
Ajay
et
a
l.
[
1
0
]
p
r
esen
ted
a
d
ee
p
lea
r
n
in
g
m
o
d
el
th
at
m
a
k
es
u
s
e
o
f
Me
d
ia
P
ip
e,
a
m
ac
h
in
e
lear
n
in
g
a
n
d
co
m
p
u
ter
v
is
io
n
s
o
lu
tio
n
,
a
n
d
B
laze
Po
s
e,
a
r
ea
l
-
tim
e
p
o
s
e
esti
m
atio
n
m
o
d
el
th
at
an
aly
z
es
ex
er
cise
m
o
v
em
en
ts
an
d
g
iv
es
u
s
er
s
im
m
ed
iate
f
ee
d
b
ac
k
,
m
ak
in
g
at
-
h
o
m
e
wo
r
k
o
u
ts
s
af
er
an
d
m
o
r
e
p
r
o
d
u
ctiv
e
b
y
co
n
f
ir
m
in
g
p
o
s
tu
r
e
an
d
p
r
o
v
id
in
g
r
ec
o
m
m
en
d
at
io
n
s
f
o
r
co
r
r
ec
tio
n
.
Mo
r
eo
v
er
,
it lo
wer
s
th
e
ex
p
en
s
e
o
f
h
ir
in
g
q
u
alif
ied
p
e
r
s
o
n
al
tr
ain
er
s
an
d
im
p
r
o
v
es a
cc
ess
ib
ilit
y
.
Dso
u
za
et
a
l.
[
1
1
]
h
i
g
h
lig
h
ted
th
e
d
ev
elo
p
m
en
t
o
f
a
s
m
ar
t
g
y
m
tr
ai
n
er
p
r
o
g
r
a
m
th
at
u
s
es
co
m
p
u
ter
v
is
io
n
an
d
m
ac
h
in
e
lear
n
in
g
to
esti
m
ate
h
u
m
an
p
o
s
itio
n
.
T
h
e
tech
n
o
lo
g
y
o
f
f
er
s
r
ea
l
-
tim
e
f
ee
d
b
ac
k
u
s
in
g
d
ee
p
l
ea
r
n
in
g
an
d
C
NNs
b
y
co
m
p
a
r
in
g
a
u
s
er
'
s
ac
tiv
ity
with
th
at
o
f
a
p
r
o
f
ess
io
n
al
at
h
lete,
m
ak
in
g
at
-
h
o
m
e
wo
r
k
o
u
ts
s
af
er
a
n
d
m
o
r
e
ef
f
icien
t.
L
o
v
an
s
h
i
an
d
T
iwar
i
[
1
2
]
ass
ess
ed
d
ee
p
lear
n
in
g
-
b
ased
h
u
m
an
p
o
s
tu
r
e
esti
m
ate
m
eth
o
d
s
,
in
clu
d
in
g
Op
en
Po
s
e,
ViT
Po
s
e
-
B
,
H
R
N
et,
Alp
h
aPo
s
e,
Den
s
eNe
t,
E
f
f
icien
tPo
s
e,
Den
s
ePo
s
e,
an
d
Ho
u
r
g
lass
u
s
in
g
th
e
C
OC
O
an
d
MPI
I
d
atasets
.
M
etr
ics
s
u
ch
as
av
er
ag
e
ac
cu
r
ac
y
(
AP)
an
d
p
r
o
b
ab
ilit
y
o
f
a
cc
u
r
ate
k
ey
p
o
i
n
ts
(
PC
K)
ar
e
th
e
m
ain
f
o
c
u
s
o
f
th
e
ass
ess
m
en
t.
On
th
e
C
OC
O
d
ataset,
ViT
Po
s
e
-
B
p
er
f
o
r
m
s
b
etter
in
AP,
a
n
d
Ho
u
r
g
lass
p
er
f
o
r
m
s
b
etter
in
P
C
K
o
n
MPI
I
.
Ag
r
awa
l
et
a
l.
[
1
3
]
u
s
ed
m
ac
h
in
e
lear
n
in
g
to
id
en
tif
y
y
o
g
a
p
o
s
es.
Fo
r
1
0
p
o
s
es,
YOGI
h
ad
5
4
5
9
p
ictu
r
es.
T
h
e
tf
-
p
o
s
e
-
esti
m
atio
n
alg
o
r
ith
m
g
en
e
r
ated
t
h
e
s
k
eleto
n
o
f
th
e
p
r
ac
titi
o
n
e
r
to
g
e
t
1
2
an
g
les
f
o
r
th
e
p
o
s
e
d
etec
tio
n
an
d
co
r
r
ec
tio
n
alg
o
r
ith
m
.
Six
class
if
icatio
n
m
o
d
els ac
h
iev
ed
a
n
ac
cu
r
ac
y
o
f
9
4
.
2
8
%.
Z
h
o
n
g
et
a
l.
[
1
4
]
p
r
esen
ted
DSPNet,
a
d
ee
p
s
u
p
er
v
is
io
n
p
y
r
am
id
n
etwo
r
k
with
a
m
in
im
al
co
m
p
u
tatio
n
al
c
o
s
t
th
at
is
in
t
en
d
ed
f
o
r
h
u
m
an
p
o
s
tu
r
e
esti
m
atio
n
.
I
t
tack
les
th
e
p
r
o
b
lem
o
f
ex
is
tin
g
p
o
s
tu
r
e
esti
m
atio
n
alg
o
r
ith
m
s
'
h
ig
h
co
m
p
u
tin
g
b
u
r
d
e
n
,
wh
ich
r
en
d
e
r
s
th
em
u
n
s
u
itab
le
f
o
r
d
ev
ices w
ith
lo
w
r
eso
u
r
ce
s
.
T
h
e
s
u
g
g
ested
DSPNet
en
h
an
ce
s
m
u
lti
-
s
ca
le
g
ettin
g
ca
p
ab
ilit
ies
with
o
u
t
ad
d
in
g
m
o
r
e
p
ar
am
eter
s
b
y
co
m
b
in
in
g
a
d
ee
p
s
u
p
er
v
is
io
n
p
y
r
am
id
d
esig
n
with
a
lig
h
tweig
h
t u
p
s
am
p
lin
g
u
n
it.
W
an
g
et
a
l.
[
1
5
]
p
r
o
p
o
s
ed
d
ee
p
lear
n
in
g
-
b
ased
m
eth
o
d
s
f
o
r
3
D
h
u
m
an
p
o
s
e
esti
m
atio
n
th
a
t
tak
e
in
to
ac
co
u
n
t
a
v
ar
iety
o
f
i
n
p
u
t
f
o
r
m
ats,
in
clu
d
in
g
o
n
e
o
r
m
o
r
e
v
iews,
o
n
e
o
r
m
o
r
e
p
h
o
t
o
s
,
an
d
o
n
e
o
r
m
o
r
e
in
d
iv
id
u
als.
I
t
talk
s
ab
o
u
t
b
o
d
y
f
o
r
m
r
e
p
r
esen
tatio
n
u
s
in
g
p
ar
am
etr
ic
m
o
d
els
s
u
ch
as
S
C
APE,
S
MPL
,
an
d
Den
s
ePo
s
e,
an
d
it
d
iv
id
es
3
D
p
o
s
e
esti
m
atio
n
tech
n
iq
u
es
in
t
o
s
in
g
le
-
s
tag
e,
two
-
s
tag
e
(
to
p
-
d
o
wn
a
n
d
b
o
tto
m
-
u
p
)
,
an
d
d
ir
ec
t
esti
m
atio
n
m
eth
o
d
s
.
Mu
n
ea
et
a
l.
[
1
6
]
p
r
o
p
o
s
ed
th
at
2
D
h
u
m
an
p
o
s
e
esti
m
atio
n
d
iv
id
es
2
D
h
u
m
an
p
o
s
tu
r
e
esti
m
ate
in
to
t
wo
ca
teg
o
r
ies:
s
in
g
le
-
p
e
r
s
o
n
an
d
m
u
lti
-
p
er
s
o
n
.
I
t
co
v
er
s
m
an
y
m
eth
o
d
s
,
u
s
es,
d
if
f
icu
lties
,
an
d
s
ig
n
if
ican
t
s
tu
d
ies
co
n
d
u
cte
d
in
th
is
ar
e
a.
B
y
an
aly
zin
g
c
u
r
r
en
t
a
p
p
r
o
ac
h
es
an
d
th
ei
r
s
h
o
r
tco
m
in
g
s
,
th
e
r
ev
iew
s
ee
k
s
to
p
r
o
v
id
e
n
o
v
ices
with
b
asic
k
n
o
wled
g
e
an
d
d
ir
ec
t
r
ese
ar
ch
er
s
in
cr
ea
tin
g
b
etter
m
o
d
els.
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
R
ea
l
-
time
ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
p
o
s
tu
r
e
co
r
r
ec
tio
n
fo
r
en
h
a
n
ce
d
…
(
A
n
is
h
K
h
a
d
ta
r
e
)
3845
B
in
et
a
l.
[
1
7
]
e
x
p
lain
ed
a
s
tu
d
y
o
n
h
u
m
an
p
o
s
e
esti
m
atio
n
,
to
f
u
r
th
er
en
h
an
ce
lo
ca
lizatio
n
p
er
f
o
r
m
an
ce
,
it
is
d
esira
b
le
to
r
ep
r
esen
t
th
e
s
tr
u
ctu
r
al
lin
k
ag
es
b
etwe
en
b
o
d
y
k
ey
p
o
in
t
s
b
ec
au
s
e
th
ey
a
r
e
in
ter
co
n
n
ec
ted
.
I
n
th
is
s
tu
d
y
,
a
n
o
v
el
m
o
d
el
is
o
f
f
er
ed
ca
lled
p
o
s
tu
r
e
g
r
ap
h
co
n
v
o
lu
tio
n
al
n
etwo
r
k
(
PGC
N)
,
to
lev
er
ag
e
th
ese
s
ig
n
if
ican
t
ass
o
ciatio
n
s
f
o
r
p
o
s
tu
r
e
esti
m
atio
n
.
I
t
is
b
u
ilt
o
n
o
r
i
g
in
al
g
r
ap
h
c
o
n
v
o
lu
tio
n
a
l
n
etwo
r
k
s
.
C
h
en
et
a
l.
[
1
8
]
p
r
esen
ted
a
s
tu
d
y
th
at
d
ea
ls
with
o
n
e
o
f
th
e
m
o
s
t
b
asic
an
d
d
if
f
icu
l
t
is
s
u
es
in
co
m
p
u
ter
v
is
io
n
is
v
is
io
n
-
b
ased
m
o
n
o
cu
lar
h
u
m
a
n
p
o
s
e
esti
m
atio
n
,
wh
ich
s
ee
k
s
to
d
et
er
m
in
e
th
e
h
u
m
an
b
o
d
y
'
s
p
o
s
tu
r
e
f
r
o
m
in
p
u
t
p
ic
tu
r
es
o
r
v
id
e
o
s
eq
u
en
ce
s
.
T
h
e
d
ee
p
lear
n
i
n
g
-
b
ased
2
D
an
d
3
D
h
u
m
an
p
o
s
tu
r
e
esti
m
atio
n
tech
n
iq
u
es
r
e
leased
s
in
ce
2
0
1
4
ar
e
r
ev
iewe
d
in
-
d
e
p
th
in
th
is
s
tu
d
y
.
T
h
e
d
if
f
icu
lties
,
k
e
y
f
r
am
ewo
r
k
s
,
b
en
c
h
m
ar
k
d
at
asets
,
ass
e
s
s
m
en
t
m
ea
s
u
r
es,
p
er
f
o
r
m
an
ce
co
m
p
ar
is
o
n
,
an
d
s
o
m
e
ex
citin
g
p
r
o
s
p
ec
ts
f
o
r
f
u
tu
r
e
s
tu
d
y
ar
e
o
u
tlin
ed
in
t
h
is
p
ap
er
.
Srijan
et
a
l.
[
1
9
]
p
r
o
v
id
e
d
an
an
aly
s
is
o
f
an
in
d
iv
id
u
al'
s
ev
e
r
y
d
ay
p
o
s
tu
r
e
an
d
h
o
w
it
im
p
ac
ts
th
eir
b
o
n
e
h
ea
lth
.
T
h
is
ar
ticle
ass
em
b
led
a
s
tu
d
y
o
n
p
o
s
tu
r
e.
T
o
b
etter
u
n
d
er
s
tan
d
h
o
w
to
p
r
e
v
en
t
v
ar
io
u
s
m
u
s
cu
lo
s
k
eleta
l
d
is
ea
s
es
in
t
h
e
g
en
er
al
p
o
p
u
latio
n
,
th
is
s
tu
d
y
co
n
d
u
cts
a
p
ilo
t
r
e
v
iew
an
d
an
aly
ze
s
s
ev
er
al
p
r
ev
io
u
s
r
esear
ch
s
tu
d
ies
o
n
p
o
s
tu
r
e
d
etec
tio
n
an
d
co
r
r
e
ctio
n
u
s
in
g
m
ac
h
i
n
e
lear
n
in
g
an
d
d
ee
p
lear
n
i
n
g
ap
p
r
o
ac
h
es.
Kim
et
a
l.
[
2
0
]
s
u
g
g
ested
a
r
ea
l
-
tim
e
Pil
ates
p
o
s
tu
r
e
d
etec
tio
n
s
y
s
tem
o
n
a
s
m
ar
tp
h
o
n
e
f
o
r
wo
r
k
o
u
t
m
o
n
ito
r
in
g
.
T
h
e
eig
h
t
Pil
ates
ex
er
cises
th
at
we
wer
e
tr
y
in
g
to
id
en
tify
wer
e
th
e
B
r
id
g
e,
Hea
d
r
o
ll
-
u
p
,
Hu
n
d
r
ed
,
R
o
ll
-
u
p
,
T
ea
s
er
,
Pla
n
k
,
T
h
ig
h
s
tr
etch
,
an
d
Swan
.
I
n
itially
,
b
o
d
y
jo
in
t
ch
ar
ac
te
r
is
tics
ar
e
ex
tr
ac
ted
u
s
in
g
th
e
B
laze
p
o
s
e
m
o
d
el.
N
ex
t,
u
s
in
g
th
e
b
o
d
y
tr
aits
th
at
wer
e
r
etr
iev
ed
,
we
cr
ea
ted
a
d
ee
p
n
eu
r
al
n
etwo
r
k
m
o
d
el
th
at
ca
n
id
en
tify
Pil
ates
.
Ao
n
ty
et
a
l.
[
2
1
]
p
r
esen
ted
a
g
r
o
u
p
-
b
ased
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
m
o
d
el
u
s
ed
to
p
r
esen
t
a
h
u
m
an
p
o
s
tu
r
e
esti
m
atio
n
tec
h
n
iq
u
e.
T
h
e
s
u
g
g
ested
tech
n
i
q
u
e
u
s
es
a
b
o
tt
o
m
-
u
p
p
ar
s
in
g
ap
p
r
o
ac
h
to
p
r
o
v
id
e
ch
ar
ac
ter
is
tics
f
o
r
th
e
e
x
tr
ac
tio
n
o
f
th
e
h
u
m
an
b
o
d
y
'
s
s
k
elet
al
im
p
o
r
tan
t
p
o
in
ts
.
Fu
r
th
e
r
m
o
r
e,
it
u
s
es
th
e
n
on
-
p
ar
am
etr
ic
d
escr
ip
tio
n
f
o
r
th
e
k
ey
p
o
in
t
ass
o
ciatio
n
v
ec
to
r
f
ield
to
g
r
o
u
p
an
at
o
m
ical
k
ey
p
o
in
ts
f
o
r
ea
c
h
p
er
s
o
n
.
Su
p
an
ich
et
a
l.
[
2
2
]
p
r
esen
te
d
a
m
ac
h
in
e
lear
n
in
g
-
b
ased
p
o
s
tu
r
e
class
if
ier
s
y
s
tem
th
at
c
an
id
en
tify
di
f
f
er
en
t
ty
p
es
o
f
wo
r
k
o
u
t
p
o
s
tu
r
es.
T
h
e
o
b
jectiv
e
o
f
th
is
r
esear
ch
is
to
d
ev
elo
p
an
a
u
to
m
a
ted
m
o
d
el
th
at
ca
n
ac
cu
r
ately
ev
alu
ate
wo
r
k
o
u
t
p
o
s
tu
r
e
in
s
tead
o
f
h
ir
in
g
a
p
er
s
o
n
al
tr
ain
er
.
W
e
u
s
e
th
e
Me
d
iaPip
e
p
o
s
e
esti
m
atio
n
f
r
am
ewo
r
k
to
ex
tr
ac
t
b
o
d
y
s
k
eleto
n
s
e
q
u
en
ce
s
f
r
o
m
a
v
id
e
o
d
ata
s
o
u
r
ce
th
at
was
ca
p
tu
r
ed
b
y
a
f
itn
ess
s
p
ec
ialis
t u
s
in
g
a
b
asic w
eb
ca
m
er
a.
Kan
ch
an
ap
ae
tn
u
k
u
l
et
a
l.
[
2
3
]
ex
p
lain
e
d
a
s
tu
d
y
wh
o
s
e
p
u
r
p
o
s
e
is
to
p
r
o
v
id
e
a
m
eth
o
d
f
o
r
d
etec
tin
g
an
d
ev
alu
atin
g
T
ai
C
h
i
ex
er
cis
e
p
o
s
tu
r
es
to
ass
is
t
th
e
el
d
er
ly
in
p
r
ac
ticin
g
o
n
th
eir
o
wn
at
h
o
m
e
.
T
h
e
g
r
ap
h
ical
u
s
er
in
ter
f
ac
e
(
GUI
)
o
n
th
e
s
y
s
tem
r
ec
o
r
d
s
th
e
m
o
v
em
en
ts
o
f
s
en
io
r
citizen
s
p
er
f
o
r
m
in
g
T
ai
C
h
i,
an
d
T
ai
C
h
i v
id
eo
clip
s
ar
e
av
ailab
le
f
o
r
p
r
esen
tatio
n
.
Usi
n
g
two
Kin
ec
t c
am
e
r
as,
th
e
s
y
s
te
m
will id
en
tify
an
d
ev
alu
ate
th
e
o
ld
p
er
s
o
n
'
s
m
o
v
em
en
t to
d
eter
m
i
n
e
if
it is
r
ig
h
t o
r
n
o
t.
Han
d
e
et
a
l.
[
2
4
]
aim
ed
to
in
v
esti
g
ate
h
o
w
r
ec
en
t
ad
v
an
ce
m
en
ts
in
p
o
s
e
esti
m
atio
n
,
co
r
r
ec
tio
n
,
an
d
r
ec
o
g
n
itio
n
ar
e
ap
p
licab
le
to
c
alcu
late
ex
er
c
is
e
p
o
s
tu
r
es
an
d
o
f
f
er
in
s
ig
h
tf
u
l
f
ee
d
b
ac
k
o
n
m
eth
o
d
s
to
id
e
n
tify
p
ar
ticu
lar
ap
p
r
o
ac
h
is
s
u
es
li
n
k
ed
to
a
s
ig
n
if
ican
t
lik
elih
o
o
d
o
f
in
ju
r
y
f
o
r
co
m
m
o
n
ex
er
cises
.
Actio
n
r
ec
o
g
n
itio
n
will
b
e
in
ch
ar
g
e
o
f
g
ath
er
in
g
,
ca
teg
o
r
izin
g
,
an
d
o
r
g
an
izin
g
th
e
d
ata
in
ad
d
i
tio
n
to
tr
ain
in
g
an
d
co
m
b
in
in
g
it with
r
ea
l
-
tim
e
d
a
ta
to
g
iv
e
f
ee
d
b
ac
k
t
o
th
e
u
s
er
.
Sin
g
h
al
et
a
l.
[
2
5
]
s
u
g
g
ested
a
m
o
d
el
p
r
o
v
id
in
g
t
h
e
u
s
er
with
r
ea
l
-
tim
e,
lig
h
tweig
h
t
f
au
lt
p
o
in
t
id
en
tific
atio
n
.
T
o
ass
is
t th
e
u
s
er
in
m
ak
in
g
t
h
e
n
ec
ess
ar
y
co
r
r
ec
tio
n
s
,
th
e
wr
o
n
g
lo
ca
tio
n
is
s
h
o
wn
in
r
ea
l tim
e
o
n
to
p
o
f
t
h
ei
r
v
id
eo
s
tr
ea
m
.
T
h
e
u
s
er
r
ec
eiv
es
th
e
n
ec
ess
ar
y
in
f
o
r
m
atio
n
b
y
b
ein
g
in
f
o
r
m
ed
wh
en
th
ey
ar
e
s
itti
n
g
in
an
im
p
r
o
p
er
p
o
s
tu
r
e
an
d
b
y
s
ee
in
g
th
e
to
tal
am
o
u
n
t
o
f
tim
e
s
p
en
t
in
an
im
p
r
o
p
er
p
o
s
tu
r
e
d
u
r
in
g
th
e
s
ess
io
n
an
d
ad
d
r
ess
es
th
e
p
r
ev
alen
t
p
r
o
b
lem
o
f
p
r
iv
ac
y
co
n
ce
r
n
s
b
y
en
h
a
n
cin
g
th
e
h
a
n
d
g
estu
r
e
r
ec
o
g
n
itio
n
f
u
n
ctio
n
with
f
ed
er
ated
lear
n
i
n
g
an
d
p
er
s
o
n
aliza
tio
n
,
wh
ile
s
till
en
ab
lin
g
u
s
er
s
to
tailo
r
th
eir
ex
p
er
ien
ce
.
Neg
i
et
a
l.
[
2
6
]
ex
p
lain
ed
a
s
tu
d
y
w
h
o
s
e
p
u
r
p
o
s
e
is
to
d
e
v
elo
p
a
m
ac
h
in
e
lear
n
i
n
g
m
o
d
el
wh
ic
h
an
aly
s
es
r
ea
l
-
tim
e
h
u
m
an
p
o
s
tu
r
e
u
s
in
g
Op
en
Po
s
e
f
o
cu
s
s
in
g
o
n
b
o
d
y
jo
in
t
p
r
ed
ictio
n
s
in
d
if
f
er
en
t
p
o
s
es
lik
e
T
-
p
o
s
e,
W
ar
r
io
r
p
o
s
e,
T
r
ee
-
p
o
s
e.
2
.
2
.
P
ro
po
s
ed
wo
rk
T
h
e
ap
p
r
o
ac
h
f
o
r
th
e
p
o
s
tu
r
e
an
aly
s
is
b
eg
in
s
with
co
n
s
tr
u
ctin
g
a
c
u
s
to
m
d
ataset
b
y
co
m
b
in
in
g
m
u
ltip
le
p
u
b
lic
d
atasets
.
Key
b
o
d
y
lan
d
m
ar
k
s
ar
e
ex
tr
ac
te
d
d
u
r
in
g
p
r
ep
r
o
ce
s
s
in
g
,
lab
el
led
,
an
d
s
to
r
ed
f
o
r
m
o
d
el
tr
ain
in
g
.
Af
ter
lab
ellin
g
,
th
e
lan
d
m
ar
k
s
ar
e
tr
a
n
s
f
o
r
m
ed
in
to
f
ea
t
u
r
e
v
ec
t
o
r
s
to
cl
ass
if
y
p
o
s
es.
Fin
ally
,
th
e
m
o
d
el
p
r
o
v
id
es
r
ea
l
-
tim
e
f
ee
d
b
ac
k
b
y
co
m
p
a
r
in
g
u
s
er
p
o
s
es
to
p
r
e
d
ef
in
ed
ex
er
cises
,
aid
in
g
i
n
ac
cu
r
at
e
ex
er
cise p
er
f
o
r
m
an
ce
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
25
:
3
8
4
3
-
3850
3846
2
.
2
.
1
.
Da
t
a
c
o
llect
io
n
A
n
ew
d
ataset
was
cr
ea
ted
b
y
co
m
b
in
in
g
m
u
ltip
le
d
ata
s
o
u
r
ce
s
s
p
ec
if
ically
d
esig
n
ed
f
o
r
ex
er
cise
p
o
s
e
d
etec
tio
n
,
with
an
em
p
h
asis
o
n
s
q
u
ats
an
d
p
lan
k
s
—
two
ac
tiv
ities
th
at
n
ee
d
ex
ac
t
p
o
s
tu
r
e
f
o
r
p
r
o
p
er
ex
ec
u
tio
n
.
E
x
er
cise
v
id
eo
s
w
er
e
r
ec
o
r
d
ed
in
a
v
ar
iety
o
f
s
ettin
g
s
to
ca
p
t
u
r
e
a
wid
e
r
an
g
e
o
f
b
o
d
y
ty
p
es
a
n
d
m
o
v
em
en
t
v
a
r
iatio
n
s
.
Key
p
o
s
e
f
ea
tu
r
es,
r
ep
r
esen
ted
as
f
lo
atin
g
-
p
o
in
t
v
al
u
es
r
ep
r
esen
tin
g
jo
in
t
co
o
r
d
in
ates
an
d
lim
b
an
g
les,
wer
e
co
llected
f
r
o
m
ea
c
h
m
o
v
ie
an
d
co
m
b
in
ed
in
to
s
tr
u
ct
u
r
ed
C
SV
f
iles
th
at
co
m
p
r
is
ed
in
p
u
t
v
ec
to
r
s
(
f
latten
ed
p
o
s
e
p
ar
am
eter
s
)
a
n
d
o
u
tp
u
t
v
ec
to
r
s
(
lab
els
in
d
icatin
g
co
r
r
ec
t
p
o
s
tu
r
e)
.
T
h
e
d
ataset
was
th
o
r
o
u
g
h
ly
c
h
ec
k
ed
to
en
s
u
r
e
th
at
th
e
in
p
u
t
a
n
d
o
u
tp
u
t
item
s
wer
e
alig
n
ed
,
a
n
d
t
h
en
d
iv
id
ed
in
to
tr
ain
in
g
(
8
0
%)
an
d
test
in
g
(
2
0
%)
s
ets.
2
.
2
.
2
.
P
re
pro
ce
s
s
ing
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase
en
t
ailed
s
tan
d
ar
d
izin
g
th
e
v
id
eo
d
ata
to
a
u
n
if
o
r
m
f
r
am
e
r
ate
o
f
1
2
f
r
am
es
p
er
s
ec
o
n
d
an
d
s
ca
lin
g
it
to
7
2
0
×
1
2
8
0
p
ix
els
to
en
s
u
r
e
p
o
s
e
d
etec
tio
n
ac
cu
r
ac
y
.
T
h
e
Me
d
iaPip
e
lib
r
ar
y
was
u
s
ed
to
r
ec
o
g
n
ize
m
ajo
r
b
o
d
y
lan
d
m
ar
k
s
in
s
id
e
ea
ch
f
r
a
m
e,
allo
win
g
ess
en
tial
p
o
s
itio
n
in
f
o
r
m
atio
n
to
b
e
ex
tr
ac
ted
q
u
ic
k
ly
.
T
h
e
lan
d
m
a
r
k
s
wer
e
o
r
g
a
n
ized
in
to
N
u
m
Py
ar
r
ay
s
an
d
s
av
ed
as
C
SV
f
iles
f
o
r
q
u
ick
ac
ce
s
s
d
u
r
in
g
m
o
d
el
t
r
ain
in
g
.
2
.
2
.
3
.
L
a
belin
g
T
h
e
lab
ellin
g
s
tep
is
n
ec
ess
ar
y
f
o
r
tr
ai
n
in
g
th
e
p
o
s
tu
r
e
esti
m
atio
n
m
o
d
el.
E
ac
h
f
r
am
e
r
et
r
iev
ed
f
r
o
m
th
e
tr
ain
in
g
f
ilm
s
was
p
ain
s
t
ak
in
g
ly
ev
alu
ated
b
y
ce
r
tifie
d
f
itn
ess
s
p
ec
iali
s
ts
,
wh
o
lab
elled
th
e
p
o
s
tu
r
e
as
co
r
r
ec
t
o
r
in
co
r
r
ec
t.
T
h
is
ex
p
er
t
an
n
o
tatio
n
a
p
p
r
o
ac
h
g
u
a
r
an
tees
th
at
th
e
d
ataset
ap
p
r
o
p
r
iately
r
ep
r
esen
ts
s
u
itab
le
wo
r
k
o
u
t te
c
h
n
i
q
u
es,
l
ay
in
g
a
g
o
o
d
f
o
u
n
d
atio
n
f
o
r
m
o
d
el
tr
ain
in
g
.
I
n
ad
d
itio
n
to
th
e
p
r
im
ar
y
lab
els,
m
etad
ata
f
o
r
ea
ch
s
tan
ce
was
d
o
cu
m
en
ted
,
s
u
ch
as
p
o
s
tu
r
e
ca
teg
o
r
y
,
in
te
n
s
ity
lev
el,
an
d
v
ar
ian
ts
.
T
h
is
co
n
tex
tu
al
i
n
f
o
r
m
atio
n
im
p
r
o
v
es
th
e
d
at
aset
'
s
u
s
ab
ili
ty
b
y
en
ab
lin
g
m
o
r
e
d
etailed
an
aly
s
is
an
d
u
n
d
er
s
tan
d
in
g
o
f
o
u
tco
m
es.
C
o
n
s
is
ten
cy
ch
ec
k
s
wer
e
d
o
n
e
t
h
r
o
u
g
h
o
u
t
th
e
lab
ellin
g
p
r
o
ce
s
s
to
en
s
u
r
e
h
ig
h
d
ata
in
teg
r
ity
,
an
d
a
n
y
an
o
m
alies
wer
e
ad
d
r
ess
ed
s
wif
tly
.
T
h
is
th
o
r
o
u
g
h
lab
ellin
g
ap
p
r
o
ac
h
is
cr
itical
f
o
r
g
en
er
atin
g
a
d
ep
e
n
d
ab
le
m
ac
h
in
e
-
lear
n
in
g
m
o
d
el
ca
p
ab
le
o
f
ac
cu
r
ate
p
o
s
tu
r
e
r
ec
o
g
n
itio
n
an
d
c
o
r
r
ec
tio
n
.
2
.
2
.
4
.
P
o
s
e
e
s
t
im
a
t
io
n
A
T
en
s
o
r
Flo
w
m
o
d
el
is
u
s
ed
to
esti
m
ate
p
o
s
e
an
d
class
if
y
wo
r
k
o
u
t
p
o
s
tu
r
es
b
ased
o
n
lan
d
m
ar
k
co
o
r
d
in
ates
f
r
o
m
th
e
Me
d
iaP
ip
e
f
r
am
ewo
r
k
.
T
h
e
p
r
o
ce
d
u
r
e
s
tar
ts
with
tr
an
s
f
o
r
m
in
g
lan
d
m
ar
k
d
ata
in
to
a
Featu
r
e
Vec
to
r
,
wh
ich
is
ac
co
m
p
lis
h
ed
b
y
ce
n
ter
in
g
th
e
p
o
s
tu
r
e
at
th
e
o
r
ig
in
,
s
ca
lin
g
it
to
a
s
tan
d
ar
d
s
ca
le,
an
d
f
latten
in
g
th
e
co
o
r
d
in
ates
in
to
a
o
n
e
-
d
im
en
s
io
n
al
ar
r
ay
.
T
h
e
Me
d
iaPip
e
lib
r
ar
y
d
etec
ts
p
o
s
es
in
r
ea
l
tim
e,
ex
tr
ac
tin
g
ess
en
tial
b
o
d
y
lan
d
m
ar
k
s
f
r
o
m
p
ictu
r
es
o
r
v
id
eo
f
r
am
es.
T
h
e
n
e
u
r
al
n
etwo
r
k
ar
ch
itectu
r
e
in
clu
d
es
an
in
p
u
t
lay
er
with
3
4
n
eu
r
o
n
s
wh
ich
co
r
r
esp
o
n
d
to
t
h
e
f
latte
n
ed
co
o
r
d
in
ates,
two
h
id
d
e
n
l
ay
er
s
with
1
2
8
an
d
6
4
n
eu
r
o
n
s
(
b
o
th
u
s
in
g
th
e
R
eL
U6
ac
tiv
atio
n
f
u
n
ctio
n
)
,
an
d
a
d
r
o
p
o
u
t
lay
er
with
a
0
.
5
d
r
o
p
o
u
t
r
ate
to
r
ed
u
c
e
o
v
er
f
itti
n
g
.
T
h
e
o
u
tp
u
t
lay
er
u
s
es
th
e
So
f
tMa
x
ac
tiv
atio
n
f
u
n
ctio
n
t
o
d
iv
i
d
e
th
e
p
o
s
e
in
t
o
s
ev
er
al
ca
teg
o
r
ies.
T
r
ain
in
g
is
ca
r
r
ied
o
u
t
u
s
in
g
an
ap
p
r
o
p
r
iately
la
b
elled
d
ata
s
et
lo
ad
ed
with
th
e
d
ata
d
iv
id
ed
in
to
b
atc
h
es
f
o
r
o
p
tim
u
m
p
r
o
ce
s
s
in
g
.
T
o
r
ed
u
c
e
er
r
o
r
s
in
class
if
icatio
n
,
th
e
m
o
d
el
u
tili
ze
s
a
ca
teg
o
r
ical
en
tr
o
p
y
cr
o
s
s
as a
lo
s
s
f
u
n
ctio
n
,
wh
ich
is
iter
ated
n
u
m
er
o
u
s
tim
es
o
v
er
.
Per
f
o
r
m
an
ce
ev
alu
atio
n
in
clu
d
es
p
ar
am
eter
s
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
tr
ain
in
g
p
r
o
ce
s
s
v
is
u
aliza
tio
n
,
as
well
as
th
e
cr
ea
tio
n
o
f
a
co
n
f
u
s
io
n
m
atr
ix
to
p
r
o
v
id
e
a
f
u
ll a
s
s
ess
m
en
t o
f
th
e
m
o
d
el'
s
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
2
.
2
.
5
.
E
rr
o
r
estim
a
t
i
o
n a
nd
f
ee
db
a
ck
T
h
e
f
ee
d
b
ac
k
m
ec
h
an
is
m
is
an
ess
en
tial
co
m
p
o
n
en
t
o
f
th
e
ap
p
licatio
n
,
g
iv
in
g
u
s
er
s
r
ea
l
-
tim
e
ass
is
tan
ce
to
ad
j
u
s
t
th
eir
p
o
s
tu
r
e
d
u
r
in
g
ex
e
r
ci
s
e.
Af
ter
g
at
h
er
in
g
k
ey
p
o
i
n
ts
f
r
o
m
th
e
u
s
er
'
s
v
id
eo
f
ee
d
,
th
e
m
o
d
el
c
o
m
p
ar
es
th
em
to
a
p
r
e
s
et
lis
t
o
f
k
e
y
p
o
in
ts
f
o
r
o
p
tim
al
p
o
s
tu
r
e.
T
h
is
c
o
m
p
ar
is
o
n
g
i
v
es
an
e
r
r
o
r
s
co
r
e,
wh
ich
m
ea
s
u
r
es th
e
u
s
er
'
s
p
o
s
tu
r
e
d
ev
iatio
n
f
r
o
m
th
e
co
r
r
ec
t
s
tan
d
ar
d
.
W
h
en
lar
g
e
d
ev
iatio
n
s
ar
e
n
o
ticed
,
th
e
u
s
er
in
ter
f
ac
e
p
r
o
v
id
es
f
ast
f
ee
d
b
ac
k
.
T
h
is
f
ee
d
b
ac
k
co
n
tain
s
v
is
u
al
clu
es
an
d
co
r
r
ec
tio
n
in
s
tr
u
ctio
n
s
th
at
h
elp
u
s
er
s
alter
th
eir
p
o
s
tu
r
e
ef
f
ec
tiv
ely
.
T
h
e
r
ea
l
-
tim
e
n
atu
r
e
o
f
th
is
f
ee
d
b
ac
k
m
o
tiv
ates
u
s
er
s
to
p
ar
ticip
ate
ac
tiv
ely
in
t
h
eir
wo
r
k
o
u
t
r
eg
im
en
s
,
r
esu
ltin
g
in
im
p
r
o
v
e
d
tech
n
iq
u
e
a
n
d
r
ed
u
ce
d
ch
an
ce
o
f
in
j
u
r
y
.
B
y
o
f
f
e
r
in
g
r
a
p
id
co
r
r
ec
tio
n
s
,
th
e
a
p
p
licati
o
n
ass
is
ts
u
s
er
s
in
ad
o
p
tin
g
ef
f
ec
tiv
e
wo
r
k
o
u
t te
ch
n
iq
u
es,
u
ltima
tely
im
p
r
o
v
in
g
p
er
f
o
r
m
an
ce
a
n
d
s
af
ety
.
3.
RE
SU
L
T
S AN
D
D
I
SC
U
SS
I
O
N
T
h
e
m
o
d
el
d
e
m
o
n
s
tr
ated
ef
f
e
ctiv
en
ess
in
an
aly
zin
g
an
d
s
u
g
g
esti
n
g
r
ea
l
-
tim
e
f
ee
d
b
ac
k
d
u
r
in
g
p
la
n
k
an
d
s
q
u
at
wo
r
k
o
u
t
ex
er
cises
,
ac
h
iev
in
g
o
v
er
7
2
%
ac
cu
r
ac
y
in
id
en
tify
in
g
co
r
r
ec
t
b
o
d
y
alig
n
m
en
t.
T
h
is
r
esu
lt
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
R
ea
l
-
time
ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
p
o
s
tu
r
e
co
r
r
ec
tio
n
fo
r
en
h
a
n
ce
d
…
(
A
n
is
h
K
h
a
d
ta
r
e
)
3847
v
alid
ates
th
e
o
r
ig
in
al
th
e
o
r
y
t
h
at
ex
er
cise
p
o
s
tu
r
e
c
o
r
r
ec
tio
n
co
u
ld
b
e
im
p
r
o
v
ed
b
y
a
m
a
ch
in
e
lear
n
in
g
-
b
ased
tech
n
iq
u
e.
Acc
u
r
ate
p
o
s
tu
r
e
a
n
aly
s
is
th
at
s
u
p
p
o
r
ts
th
e
g
o
als
o
f
th
e
s
tu
d
y
was
m
a
d
e
p
o
s
s
ib
le
b
y
th
e
p
r
ec
is
e
esti
m
atio
n
o
f
jo
in
t a
n
g
les m
ad
e
p
o
s
s
ib
le
b
y
th
e
i
n
teg
r
atio
n
o
f
th
e
Me
d
ia
P
ip
e
f
r
a
m
ewo
r
k
.
Fig
u
r
e
1
s
h
o
ws
th
e
s
ig
n
if
ic
an
t
in
s
ig
h
ts
r
eg
a
r
d
in
g
o
u
r
m
ac
h
in
e
lear
n
in
g
m
o
d
el'
s
p
er
f
o
r
m
a
n
ce
o
b
tain
ed
f
r
o
m
tr
ain
in
g
it
o
v
e
r
2
0
0
ep
o
c
h
s
.
T
h
e
tr
ain
in
g
ac
c
u
r
ac
y
ev
o
lu
tio
n
is
d
ep
icted
in
Fig
u
r
e
1
,
wh
er
e
th
e
ac
cu
r
ac
y
in
cr
ea
s
es
q
u
ic
k
ly
f
r
o
m
1
0
%
to
7
0
%
in
th
e
f
ir
s
t
2
5
ep
o
ch
s
b
e
f
o
r
e
g
r
ad
u
ally
im
p
r
o
v
in
g
to
7
2
%
i
n
th
e
en
d
.
Acc
o
r
d
in
g
l
y
,
Fig
u
r
e
2
s
h
o
ws
th
e
tr
ain
in
g
lo
s
s
,
wh
ich
g
r
ad
u
ally
co
n
v
er
g
e
d
to
a
b
o
u
t
0
.
1
af
te
r
d
r
o
p
p
i
n
g
s
h
ar
p
ly
f
r
o
m
1
.
2
to
0
.
2
in
th
e
f
ir
s
t
2
5
ep
o
ch
s
.
T
h
ese
o
u
tc
o
m
es
d
em
o
n
s
tr
ated
th
e
m
o
d
el'
s
ef
f
ec
t
iv
e
lear
n
in
g
ca
p
ac
ity
,
esp
ec
ially
i
n
th
e
f
ir
s
t
p
h
ases
o
f
tr
ain
in
g
.
A
f
in
al
t
r
ain
in
g
ac
c
u
r
ac
y
o
f
7
2
%
s
u
g
g
e
s
ts
th
at
th
e
tr
ain
in
g
d
ata
was im
p
lem
en
ted
ef
f
ec
tiv
ely
.
Fig
u
r
e
1.
T
r
ain
in
g
ac
c
u
r
ac
y
a
n
d
tr
ain
in
g
lo
s
s
g
r
ap
h
o
f
t
h
e
m
o
d
el
Fig
u
r
e
2
.
Mo
d
els’
p
er
f
o
r
m
a
n
c
e
o
n
d
if
f
er
en
t
b
o
d
y
p
o
s
itio
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.
15
,
No
.
4
,
Au
g
u
s
t
20
25
:
3
8
4
3
-
3850
3848
Fig
u
r
e
2
d
e
m
o
n
s
tr
ates
th
e
m
o
d
el
ab
ilit
y
to
a
n
aly
ze
th
e
h
u
m
an
b
o
d
y
p
o
s
tu
r
e
a
n
d
g
iv
e
co
r
r
ec
tiv
e
in
s
tr
u
ctio
n
s
wh
ile
p
er
f
o
r
m
in
g
ex
er
cises
in
d
if
f
er
en
t
p
o
s
itio
n
s
.
B
ased
o
n
an
aly
s
is
o
f
th
e
b
o
d
y
p
o
s
tu
r
e
th
e
m
o
d
el
g
iv
es r
ea
l tim
e
s
u
g
g
esti
o
n
s
to
im
p
r
o
v
e
it.
I
n
co
n
tr
ast
to
ea
r
lier
r
esear
c
h
,
th
e
r
esu
lts
alig
n
with
th
e
b
o
d
y
o
f
liter
atu
r
e
em
p
h
asizin
g
th
e
b
en
ef
its
o
f
em
p
lo
y
in
g
s
o
p
h
is
ticated
m
eth
o
d
s
f
o
r
p
o
s
tu
r
e
co
r
r
ec
tio
n
.
T
h
e
ef
f
icien
cy
o
f
d
ee
p
lear
n
in
g
m
eth
o
d
s
in
r
ea
l
-
tim
e
ap
p
licatio
n
s
,
f
o
r
ex
am
p
le,
was
also
m
en
tio
n
ed
in
p
r
ev
io
u
s
s
tu
d
i
es.
T
h
e
s
tu
d
y
'
s
s
tr
en
g
th
lies
in
th
e
co
m
b
in
atio
n
o
f
Me
d
ia
P
ip
e
f
o
r
lan
d
m
ar
k
d
etec
tio
n
with
T
en
s
o
r
Flo
w
f
o
r
p
o
s
tu
r
e
class
if
icati
o
n
,
wh
ich
p
r
o
v
id
es
a
m
o
r
e
r
eliab
le
s
o
lu
tio
n
t
h
an
co
n
v
en
tio
n
al
tech
n
iq
u
es.
Ho
wev
er
,
th
er
e
wer
e
s
ev
e
r
al
d
r
awb
ac
k
s
,
s
u
ch
as
v
ar
iatio
n
s
in
u
s
er
r
esp
o
n
s
es
ac
co
r
d
in
g
o
n
b
o
d
y
s
h
ap
e
an
d
b
ac
k
g
r
o
u
n
d
lig
h
tin
g
co
n
d
it
io
n
s
.
Fu
r
th
er
m
o
r
e
,
b
ased
o
n
th
e
r
esp
o
n
s
es
g
iv
e
n
,
u
s
er
s
r
ep
o
r
ted
h
a
v
in
g
d
if
f
icu
lties
f
itti
n
g
th
eir
wh
o
le
-
b
o
d
y
p
o
s
tu
r
e,
wh
ich
p
r
esen
ted
an
u
n
an
ticip
ated
o
b
s
tacle
an
d
h
ig
h
lig
h
te
d
ar
ea
s
f
o
r
u
s
er
in
ter
f
ac
e
d
esig
n
d
e
v
elo
p
m
en
t.
I
n
c
o
n
clu
s
io
n
,
th
e
s
tu
d
y
s
u
cc
e
s
s
f
u
lly
s
h
o
wed
h
o
w
m
ac
h
in
e
l
ea
r
n
in
g
im
p
r
o
v
es
e
x
er
cise
p
e
r
f
o
r
m
an
ce
b
y
ac
cu
r
ately
r
ec
o
g
n
izin
g
p
o
s
tu
r
e.
T
h
ese
r
esu
lts
h
ig
h
lig
h
t
h
o
w
cr
u
cial
it
is
to
p
r
o
v
id
e
r
ea
l
-
tim
e
f
ee
d
b
ac
k
in
f
itn
ess
p
r
o
g
r
am
s
.
T
o
in
c
r
ea
s
e
u
s
er
en
g
ag
em
e
n
t
an
d
ef
f
icac
y
,
f
u
tu
r
e
s
tu
d
ies
s
h
o
u
ld
c
o
n
ce
n
tr
ate
o
n
ex
p
a
n
d
in
g
th
e
d
ataset
to
en
co
m
p
ass
a
wid
er
v
ar
iety
o
f
b
o
d
y
s
h
ap
es
an
d
p
o
s
tu
r
es
an
d
ex
p
lo
r
in
g
ad
d
itio
n
al
f
ee
d
b
ac
k
m
ec
h
an
is
m
s
.
4.
CO
NCLU
SI
O
N
W
ith
an
ac
cu
r
ac
y
o
f
m
o
r
e
th
a
n
7
2
%
in
an
aly
zin
g
an
d
d
eter
m
in
in
g
th
e
co
r
r
ec
t
b
o
d
y
p
o
s
tu
r
e
f
o
r
t
h
e
u
s
er
wh
ile
p
er
f
o
r
m
in
g
ex
e
r
ci
s
es
lik
e
s
q
u
ats
an
d
p
lan
k
s
,
th
e
r
esear
ch
h
as
s
h
o
wn
th
e
e
f
f
ec
tiv
en
ess
o
f
o
u
r
m
o
d
el
f
o
r
r
ea
l
-
tim
e
c
o
r
r
ec
tio
n
o
f
p
o
s
tu
r
e.
T
h
ese
r
esu
lts
d
em
o
n
s
tr
ate
th
at
in
co
r
p
o
r
atin
g
c
u
t
tin
g
-
ed
g
e
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
in
to
f
itn
ess
ap
p
s
ca
n
g
r
ea
tly
im
p
r
o
v
e
u
s
er
s
'
ca
p
ac
ity
to
m
ain
tain
c
o
r
r
ec
t
b
o
d
y
p
o
s
tu
r
e
.
W
h
ich
in
tu
r
n
lo
we
r
s
th
e
ch
an
ce
o
f
in
ju
r
y
an
d
b
o
o
s
ts
th
e
ef
f
i
ca
cy
o
f
wo
r
k
o
u
ts
o
v
er
all.
T
h
ese
f
in
d
in
g
s
h
av
e
s
ig
n
if
ica
n
ce
f
o
r
m
o
r
e
th
an
ju
s
t
in
d
iv
i
d
u
al
f
itn
ess
en
th
u
s
iast
s
;
th
ey
also
s
h
o
w
h
o
w
tech
n
o
lo
g
y
-
d
r
iv
e
n
s
o
lu
ti
o
n
s
m
ay
h
elp
co
m
m
u
n
ities
ad
o
p
t
h
ea
lth
y
ex
er
cise
p
r
ac
tices.
Peo
p
le
wh
o
d
o
n
o
t
h
av
e
th
e
m
ea
n
s
f
o
r
ex
p
er
t
tr
ain
in
g
o
r
d
ir
ec
tio
n
ca
n
u
tili
ze
it
s
in
ce
th
e
r
ea
l
-
tim
e
f
ee
d
b
ac
k
m
eth
o
d
en
a
b
les
u
s
er
s
to
o
b
tain
p
r
o
m
p
t
r
em
e
d
i
al
ad
v
ice.
T
h
is
ap
p
licatio
n
ca
n
s
av
e
h
ea
lth
ca
r
e
e
x
p
en
s
es
co
n
n
ec
ted
to
e
x
er
cise
-
r
elate
d
in
ju
r
ies an
d
p
r
o
m
o
te
p
r
o
p
er
e
x
er
cise p
r
ac
tices,
b
o
t
h
o
f
wh
ich
h
av
e
lo
n
g
-
ter
m
h
ea
lt
h
ad
v
a
n
tag
es.
Ad
d
itio
n
ally
,
t
h
is
s
tu
d
y
o
p
en
s
th
e
way
f
o
r
s
ev
er
al
u
p
co
m
i
n
g
e
x
p
an
s
io
n
s
a
n
d
a
p
p
licatio
n
s
.
Fu
tu
r
e
v
er
s
io
n
s
o
f
th
e
s
o
f
twar
e
co
u
ld
in
clu
d
e
ex
e
r
cises
o
th
er
th
an
p
lan
k
s
an
d
s
q
u
ats,
m
a
k
in
g
it
s
u
itab
le
f
o
r
a
g
r
ea
ter
v
ar
iety
o
f
p
h
y
s
ical
ac
tiv
ity
.
A
d
d
itio
n
ally
,
a
d
d
in
g
f
u
n
ctio
n
s
l
ik
e
p
r
o
g
r
ess
m
o
n
it
o
r
in
g
an
d
c
u
s
to
m
ized
ex
er
cise
r
o
u
tin
es
m
ig
h
t
im
p
r
o
v
e
u
s
er
m
o
tiv
atio
n
a
n
d
en
g
a
g
em
en
t.
T
o
im
p
r
o
v
e
th
e
f
ee
d
b
ac
k
s
y
s
tem
s
an
d
g
u
ar
a
n
tee
th
at
th
e
f
ee
d
b
ac
k
g
iv
en
is
u
s
ef
u
l
an
d
ef
f
icien
t,
p
ar
tn
er
s
h
ip
s
with
f
itn
ess
in
s
tr
u
cto
r
s
an
d
m
ed
ical
s
p
ec
ialis
t
s
m
ig
h
t
also
b
e
i
n
v
esti
g
ated
.
I
n
th
e
en
d
,
th
e
r
esu
lts
h
ig
h
lig
h
t
h
o
w
im
p
o
r
tan
t
tec
h
n
o
lo
g
y
c
an
b
e
to
th
e
f
itn
ess
s
ec
to
r
,
esp
ec
ially
wh
en
it
co
m
es
to
im
p
r
o
v
i
n
g
ac
ce
s
s
ib
ilit
y
an
d
cu
s
to
m
izin
g
th
e
u
s
e
r
ex
p
er
ien
ce
.
T
h
is
r
esear
ch
o
p
e
n
s
th
e
d
o
o
r
f
o
r
cr
ea
tiv
e
s
o
lu
tio
n
s
th
at
s
u
p
p
o
r
t
p
h
y
s
ical
h
ea
lth
an
d
well
-
b
e
in
g
in
a
v
ar
iety
o
f
g
r
o
u
p
s
b
y
tack
lin
g
u
n
an
s
wer
e
d
p
r
o
b
le
m
s
ab
o
u
t
u
s
er
in
ter
f
a
ce
d
esig
n
an
d
th
e
m
o
d
el'
s
ad
a
p
tatio
n
to
d
if
f
er
e
n
t
b
o
d
y
t
y
p
es.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
s
th
an
k
our
co
lle
ag
u
es
f
r
o
m
Sh
ah
a
n
d
An
c
h
o
r
Ku
tch
h
i
E
n
g
in
ee
r
in
g
C
o
l
leg
e
wh
o
p
r
o
v
id
e
d
in
s
ig
h
t
an
d
ass
is
ta
n
ce
th
at
co
n
s
p
icu
o
u
s
ly
ass
is
ted
th
e
r
esear
ch
ca
r
r
ied
b
y
u
s
.
W
ith
o
u
t
th
eir
p
er
s
is
ten
t su
p
p
o
r
t,
co
n
d
u
ctin
g
r
esear
ch
wo
u
ld
n
o
t h
a
v
e
b
ee
n
p
o
s
s
ib
le.
RE
F
E
R
E
NC
E
S
[
1
]
G.
-
P
.
B
o
t
i
l
i
a
s
a
n
d
C
.
S
t
y
l
i
o
s,
“
A
p
p
f
o
r
p
h
y
s
i
c
a
l
f
i
t
n
e
ss
i
mp
r
o
v
e
me
n
t
b
a
se
d
o
n
p
h
y
si
c
a
l
a
c
t
i
v
i
t
y
g
u
i
d
e
l
i
n
e
s
a
n
d
se
l
f
-
t
e
st
i
n
g
t
o
o
l
s,
”
i
n
2
0
2
2
I
EEE
-
E
MB
S
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
We
a
ra
b
l
e
a
n
d
I
m
p
l
a
n
t
a
b
l
e
Bo
d
y
S
e
n
s
o
r
N
e
t
w
o
r
k
s
(
BS
N
)
,
S
e
p
.
2
0
2
2
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
B
S
N
5
6
1
6
0
.
2
0
2
2
.
9
9
2
8
5
2
4
.
[
2
]
S
.
A
r
v
i
n
d
,
K
.
L.
H
e
ma
l
a
t
h
a
,
B
.
P
.
U
p
e
n
d
r
a
R
o
y
,
K
.
S
.
S
a
n
d
e
e
p
,
a
n
d
P
.
K
.
P
a
r
e
e
k
,
“
A
d
v
a
n
c
e
d
sp
o
r
t
s
p
e
r
f
o
r
ma
n
c
e
a
n
a
l
y
si
s
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
p
o
s
t
u
r
e
a
n
d
mo
v
e
m
e
n
t
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
i
n
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
D
a
t
a
S
c
i
e
n
c
e
a
n
d
N
e
t
w
o
rk
S
e
c
u
ri
t
y
,
I
C
D
S
N
S
2
0
2
3
,
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
S
N
S
5
8
4
6
9
.
2
0
2
3
.
1
0
2
4
5
5
4
4
.
[
3
]
R
.
G
u
p
t
a
,
D
.
S
a
i
n
i
,
a
n
d
S
.
M
i
s
h
r
a
,
“
P
o
s
t
u
r
e
d
e
t
e
c
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
t
i
m
e
seri
e
s
d
a
t
a
,
”
i
n
2
0
2
0
T
h
i
rd
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
m
a
rt
S
y
st
e
m
s
a
n
d
I
n
v
e
n
t
i
v
e
T
e
c
h
n
o
l
o
g
y
(
I
C
S
S
I
T
)
,
A
u
g
.
2
0
2
0
,
p
p
.
7
4
0
–
7
4
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
S
I
T4
8
9
1
7
.
2
0
2
0
.
9
2
1
4
2
2
3
.
[
4
]
M
.
B
e
n
G
a
mr
a
a
n
d
M
.
A
.
A
k
h
l
o
u
f
i
,
“
A
r
e
v
i
e
w
o
f
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
2
D
a
n
d
3
D
h
u
ma
n
p
o
se
e
s
t
i
m
a
t
i
o
n
,
”
I
m
a
g
e
a
n
d
Vi
si
o
n
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
1
4
,
p
.
1
0
4
2
8
2
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
ma
v
i
s
.
2
0
2
1
.
1
0
4
2
8
2
.
[
5
]
L.
S
o
n
g
,
G
.
Y
u
,
J.
Y
u
a
n
,
a
n
d
Z.
Li
u
,
“
H
u
ma
n
p
o
se
e
s
t
i
m
a
t
i
o
n
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
t
o
a
c
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
:
A
s
u
r
v
e
y
,
”
J
o
u
rn
a
l
o
f
Vi
su
a
l
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
I
m
a
g
e
Re
p
res
e
n
t
a
t
i
o
n
,
v
o
l
.
7
6
,
p
.
1
0
3
0
5
5
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
v
c
i
r
.
2
0
2
1
.
1
0
3
0
5
5
.
[
6
]
P
.
Y
a
n
g
,
Z.
-
L.
P
e
n
g
,
a
n
d
W
.
-
L.
W
a
n
g
,
“
S
i
t
t
i
n
g
p
o
s
t
u
r
e
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
b
a
se
d
o
n
K
e
r
a
s
f
r
a
mew
o
r
k
,
”
i
n
2
0
2
2
3
rd
I
n
t
e
r
n
a
t
i
o
n
a
l
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
R
ea
l
-
time
ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
p
o
s
tu
r
e
co
r
r
ec
tio
n
fo
r
en
h
a
n
ce
d
…
(
A
n
is
h
K
h
a
d
ta
r
e
)
3849
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
,
I
m
a
g
e
a
n
d
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
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s (
C
VI
D
L
& I
C
C
E
A)
,
M
a
y
2
0
2
2
,
p
p
.
1
7
0
–
1
7
4
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
I
D
L
I
C
C
EA
5
6
2
0
1
.
2
0
2
2
.
9
8
2
4
1
6
4
.
[
7
]
V
.
S
.
P
.
B
h
a
mi
d
i
p
a
t
i
,
I
.
S
a
x
e
n
a
,
D
.
S
a
i
sa
n
t
h
i
y
a
,
a
n
d
M
.
R
e
t
n
a
d
h
a
s
,
“
R
o
b
u
st
i
n
t
e
l
l
i
g
e
n
t
p
o
st
u
r
e
e
st
i
ma
t
i
o
n
f
o
r
a
n
A
I
G
y
m
Tr
a
i
n
e
r
u
si
n
g
M
e
d
i
a
p
i
p
e
a
n
d
O
p
e
n
C
V
,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
N
e
t
w
o
rk
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
(
I
C
N
W
C
)
,
A
p
r
.
2
0
2
3
,
p
p
.
1
–
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
N
W
C
5
7
8
5
2
.
2
0
2
3
.
1
0
1
2
7
2
6
4
.
[
8
]
L.
Y
a
n
g
,
Y
.
Li
,
D
.
Ze
n
g
,
a
n
d
D
.
W
a
n
g
,
“
H
u
m
a
n
e
x
e
r
c
i
se
p
o
st
u
r
e
a
n
a
l
y
s
i
s b
a
s
e
d
o
n
p
o
s
e
e
st
i
ma
t
i
o
n
,
”
i
n
2
0
2
1
I
E
EE
5
t
h
A
d
v
a
n
c
e
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
E
l
e
c
t
r
o
n
i
c
a
n
d
A
u
t
o
m
a
t
i
o
n
C
o
n
t
r
o
l
C
o
n
f
e
ren
c
e
(
I
AEA
C
)
,
M
a
r
.
2
0
2
1
,
p
p
.
1
7
1
5
–
1
7
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
A
EA
C
5
0
8
5
6
.
2
0
2
1
.
9
3
9
0
8
7
0
.
[
9
]
A
.
F
l
o
r
e
s,
B
.
H
a
l
l
,
L.
C
a
r
t
e
r
,
M
.
La
n
u
m,
R
.
N
a
r
a
h
a
r
i
,
a
n
d
G
.
G
o
o
d
m
a
n
,
“
V
e
r
u
m
f
i
t
n
e
ss
:
A
n
A
I
p
o
w
e
r
e
d
m
o
b
i
l
e
f
i
t
n
e
ss
safe
t
y
a
n
d
i
mp
r
o
v
e
me
n
t
a
p
p
l
i
c
a
t
i
o
n
,
”
i
n
2
0
2
1
I
E
EE
3
3
r
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
T
o
o
l
s
w
i
t
h
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
I
C
T
AI
)
,
N
o
v
.
2
0
2
1
,
p
p
.
9
8
0
–
9
8
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
TA
I
5
2
5
2
5
.
2
0
2
1
.
0
0
1
5
6
.
[
1
0
]
L.
A
j
a
y
,
V
.
G
.
B
i
r
a
d
a
r
,
M
.
C
h
a
n
d
u
,
a
n
d
J.
B
.
B
h
a
r
a
t
h
,
“
A
I
t
o
o
l
a
s
a
f
i
t
n
e
ss
t
r
a
i
n
e
r
u
si
n
g
h
u
m
a
n
p
o
se
e
st
i
mat
i
o
n
,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
N
e
t
w
o
rk,
M
u
l
t
i
m
e
d
i
a
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
N
MIT
C
O
N
)
,
S
e
p
.
2
0
2
3
,
p
p
.
1
–
1
2
,
d
o
i
:
1
0
.
1
1
0
9
/
N
M
I
TC
O
N
5
8
1
9
6
.
2
0
2
3
.
1
0
2
7
6
3
2
0
.
[
1
1
]
G
.
D
s
o
u
z
a
,
D
.
M
a
u
r
y
a
,
a
n
d
A
.
P
a
t
e
l
,
“
S
mart
g
y
m
t
r
a
i
n
e
r
u
si
n
g
H
u
ma
n
p
o
s
e
e
st
i
ma
t
i
o
n
,
”
i
n
2
0
2
0
I
E
EE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
f
o
r
I
n
n
o
v
a
t
i
o
n
i
n
T
e
c
h
n
o
l
o
g
y
(
I
N
O
C
O
N
)
,
N
o
v
.
2
0
2
0
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
N
O
C
O
N
5
0
5
3
9
.
2
0
2
0
.
9
2
9
8
2
1
2
.
[
1
2
]
M
.
L
o
v
a
n
sh
i
a
n
d
V
.
Ti
w
a
r
i
,
“
H
u
ma
n
p
o
s
e
e
s
t
i
m
a
t
i
o
n
:
B
e
n
c
h
mar
k
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
met
h
o
d
s,”
i
n
2
0
2
2
I
EE
E
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
r
d
i
sci
p
l
i
n
a
r
y
Ap
p
r
o
a
c
h
e
s
i
n
T
e
c
h
n
o
l
o
g
y
a
n
d
M
a
n
a
g
e
m
e
n
t
f
o
r
S
o
c
i
a
l
I
n
n
o
v
a
t
i
o
n
(
I
ATM
S
I
)
,
D
e
c
.
2
0
2
2
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
A
TM
S
I
5
6
4
5
5
.
2
0
2
2
.
1
0
1
1
9
3
2
4
.
[
1
3
]
Y
.
A
g
r
a
w
a
l
,
Y
.
S
h
a
h
,
a
n
d
A
.
S
h
a
r
m
a
,
“
I
mp
l
e
me
n
t
a
t
i
o
n
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
f
o
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
Y
o
g
a
P
o
s
e
s,”
i
n
2
0
2
0
I
EEE
9
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
s
t
e
m
s
a
n
d
N
e
t
w
o
rk
T
e
c
h
n
o
l
o
g
i
e
s
(
C
S
N
T
)
,
A
p
r
.
2
0
2
0
,
p
p
.
4
0
–
4
3
,
d
o
i
:
1
0
.
1
1
0
9
/
C
S
N
T
4
8
7
7
8
.
2
0
2
0
.
9
1
1
5
7
5
8
.
[
1
4
]
F
.
Z
h
o
n
g
,
M
.
Li
,
K
.
Zh
a
n
g
,
J.
H
u
,
a
n
d
L.
Li
u
,
“
D
S
P
N
e
t
:
A
l
o
w
c
o
m
p
u
t
a
t
i
o
n
a
l
-
c
o
s
t
n
e
t
w
o
r
k
f
o
r
h
u
ma
n
p
o
s
e
e
st
i
ma
t
i
o
n
,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
4
2
3
,
p
p
.
3
2
7
–
3
3
5
,
Ja
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m
.
2
0
2
0
.
1
1
.
0
0
3
.
[
1
5
]
J.
W
a
n
g
e
t
a
l
.
,
“
D
e
e
p
3
D
h
u
m
a
n
p
o
s
e
e
st
i
ma
t
i
o
n
:
A
r
e
v
i
e
w
,
”
C
o
m
p
u
t
e
r
V
i
si
o
n
a
n
d
I
m
a
g
e
U
n
d
e
rst
a
n
d
i
n
g
,
v
o
l
.
2
1
0
,
p
.
1
0
3
2
2
5
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
v
i
u
.
2
0
2
1
.
1
0
3
2
2
5
.
[
1
6
]
T.
L.
M
u
n
e
a
,
Y
.
Z
.
Jem
b
r
e
,
H
.
T.
W
e
l
d
e
g
e
b
r
i
e
l
,
L
.
C
h
e
n
,
C
.
H
u
a
n
g
,
a
n
d
C
.
Y
a
n
g
,
“
T
h
e
p
r
o
g
r
e
ss
o
f
h
u
ma
n
p
o
se
e
st
i
ma
t
i
o
n
:
A
su
r
v
e
y
a
n
d
t
a
x
o
n
o
m
y
o
f
m
o
d
e
l
s
a
p
p
l
i
e
d
i
n
2
D
h
u
ma
n
p
o
se
e
st
i
ma
t
i
o
n
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
3
3
3
3
0
–
1
3
3
3
4
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
1
0
2
4
8
.
[
1
7
]
Y
.
B
i
n
,
Z.
-
M
.
C
h
e
n
,
X
.
-
S
.
W
e
i
,
X
.
C
h
e
n
,
C
.
G
a
o
,
a
n
d
N
.
S
a
n
g
,
“
S
t
r
u
c
t
u
r
e
-
a
w
a
r
e
h
u
ma
n
p
o
se
e
s
t
i
m
a
t
i
o
n
w
i
t
h
g
r
a
p
h
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
t
w
o
r
k
s,”
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
,
v
o
l
.
1
0
6
,
p
.
1
0
7
4
1
0
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
2
0
.
1
0
7
4
1
0
.
[
1
8
]
Y
.
C
h
e
n
,
Y
.
T
i
a
n
,
a
n
d
M
.
H
e
,
“
M
o
n
o
c
u
l
a
r
h
u
m
a
n
p
o
se
e
s
t
i
m
a
t
i
o
n
:
A
su
r
v
e
y
o
f
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
m
e
t
h
o
d
s,
”
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
I
m
a
g
e
U
n
d
e
rst
a
n
d
i
n
g
,
v
o
l
.
1
9
2
,
p
.
1
0
2
8
9
7
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
v
i
u
.
2
0
1
9
.
1
0
2
8
9
7
.
[
1
9
]
S
r
i
j
a
n
,
M
a
l
l
i
k
a
,
A
l
p
a
n
a
,
a
n
d
P
.
G
u
p
t
a
,
“
A
r
e
v
i
e
w
o
n
p
o
st
u
r
e
d
e
t
e
c
t
i
o
n
a
n
d
c
o
r
r
e
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
2
S
e
c
o
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
N
e
x
t
G
e
n
e
r
a
t
i
o
n
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
(
I
C
N
G
I
S
)
,
J
u
l
.
2
0
2
2
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
N
G
I
S
5
4
9
5
5
.
2
0
2
2
.
1
0
0
7
9
7
2
6
.
[
2
0
]
H
.
K
i
m
e
t
a
l
.
,
“
R
e
a
l
-
t
i
me
p
i
l
a
t
e
s
p
o
s
t
u
r
e
r
e
c
o
g
n
i
t
i
o
n
s
y
st
e
m
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
,
”
2
0
2
3
,
p
p
.
3
–
1
5
.
[
2
1
]
S
.
S
.
A
o
n
t
y
,
K
.
D
e
b
,
M
.
S
e
n
S
a
r
ma,
P
.
K
.
D
h
a
r
,
a
n
d
T.
S
h
i
mam
u
r
a
,
“
M
u
l
t
i
-
p
e
r
s
o
n
p
o
s
e
e
st
i
ma
t
i
o
n
u
si
n
g
g
r
o
u
p
-
b
a
se
d
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
m
o
d
e
l
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
4
2
3
4
3
–
4
2
3
6
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
7
1
5
9
3
.
[
2
2
]
W
.
S
u
p
a
n
i
c
h
,
S
.
K
u
l
k
a
r
i
n
e
e
t
h
a
m,
P
.
S
u
k
p
h
o
k
h
a
,
a
n
d
P
.
W
i
s
a
r
n
sar
t
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
e
x
e
r
c
i
s
e
p
o
s
t
u
r
e
r
e
c
o
g
n
i
t
i
o
n
s
y
s
t
e
m
u
si
n
g
M
e
d
i
a
P
i
p
e
P
o
se
e
s
t
i
mat
i
o
n
f
r
a
mew
o
r
k
,
”
i
n
2
0
2
3
9
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
st
e
m
s
(
I
C
A
C
C
S
)
,
M
a
r
.
2
0
2
3
,
p
p
.
2
0
0
3
–
2
0
0
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
C
S
5
7
2
7
9
.
2
0
2
3
.
1
0
1
1
2
7
2
6
.
[
2
3
]
S
.
K
a
n
c
h
a
n
a
p
a
e
t
n
u
k
u
l
,
R
.
A
u
n
k
a
e
w
,
P
.
C
h
a
r
e
r
n
m
o
o
l
,
M
.
D
a
o
u
d
i
,
K
.
S
a
r
a
u
b
o
n
,
a
n
d
P
.
V
i
s
u
t
s
a
k
,
“
T
a
i
C
h
i
e
x
e
r
c
i
s
e
p
o
s
t
u
r
e
d
e
t
e
c
t
i
o
n
a
n
d
a
sses
sme
n
t
f
o
r
t
h
e
El
d
e
r
l
y
u
s
i
n
g
B
P
N
N
a
n
d
2
K
i
n
e
c
t
c
a
m
e
r
a
s,”
i
n
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
T
e
c
h
n
i
c
a
l
C
o
n
f
e
re
n
c
e
o
n
C
i
rc
u
i
t
s
/
S
y
st
e
m
s,
C
o
m
p
u
t
e
rs
,
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
(
I
T
C
-
C
S
C
C
)
,
Ju
n
.
2
0
2
3
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
TC
-
C
S
C
C
5
8
8
0
3
.
2
0
2
3
.
1
0
2
1
2
5
7
0
.
[
2
4
]
T.
H
a
n
d
e
,
B
.
K
a
k
i
r
w
a
r
,
A
.
V
.
B
h
a
r
a
d
w
a
j
a
,
P
.
K
s
h
i
r
sa
g
a
r
,
A
.
G
u
p
t
a
,
a
n
d
P
.
V
i
j
a
y
a
k
u
mar,
“
C
o
r
r
e
c
t
i
o
n
a
n
d
e
s
t
i
m
a
t
i
o
n
o
f
w
o
r
k
o
u
t
p
o
s
t
u
r
e
s
w
i
t
h
p
o
se
e
st
i
ma
t
i
o
n
u
s
i
n
g
A
I
,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
a
n
d
I
n
n
o
v
a
t
i
v
e
T
e
c
h
n
o
l
o
g
i
e
s
i
n
C
o
m
p
u
t
i
n
g
,
El
e
c
t
r
i
c
a
l
a
n
d
E
l
e
c
t
r
o
n
i
c
s (I
I
T
C
EE)
,
J
a
n
.
2
0
2
3
,
p
p
.
2
4
7
–
2
5
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
I
TC
EE5
7
2
3
6
.
2
0
2
3
.
1
0
0
9
0
4
6
3
.
[
2
5
]
R
.
S
i
n
g
h
a
l
,
H
.
M
o
d
i
,
S
.
S
r
i
h
a
r
i
,
A
.
G
a
n
d
h
i
,
C
.
O
.
P
r
a
k
a
s
h
,
a
n
d
S
.
Esw
a
r
a
n
,
“
B
o
d
y
p
o
s
t
u
r
e
c
o
r
r
e
c
t
i
o
n
a
n
d
h
a
n
d
g
e
s
t
u
r
e
d
e
t
e
c
t
i
o
n
u
si
n
g
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
a
n
d
M
e
d
i
a
P
i
p
e
,
”
i
n
2
0
2
3
2
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
f
o
r
I
n
n
o
v
a
t
i
o
n
i
n
T
e
c
h
n
o
l
o
g
y
(
I
N
O
C
O
N
)
,
M
a
r
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
N
O
C
O
N
5
7
9
7
5
.
2
0
2
3
.
1
0
1
0
1
1
2
4
.
[
2
6
]
S
.
N
e
g
i
,
M
.
G
a
r
g
,
H
.
M
a
i
n
d
o
l
a
,
V
.
K
a
n
s
a
l
,
U
.
Jai
n
,
a
n
d
S
.
B
h
a
t
l
a
,
“
R
e
a
l
-
t
i
me
h
u
m
a
n
p
o
s
e
e
st
i
ma
t
i
o
n
:
A
M
e
d
i
a
P
i
p
e
a
n
d
P
y
t
h
o
n
a
p
p
r
o
a
c
h
f
o
r
3
D
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
i
n
2
0
2
3
3
rd
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
T
e
c
h
n
o
l
o
g
i
c
a
l
Ad
v
a
n
c
e
m
e
n
t
s
i
n
C
o
m
p
u
t
a
t
i
o
n
a
l
S
c
i
e
n
c
e
s (I
C
T
A
C
S
)
,
N
o
v
.
2
0
2
3
,
p
p
.
1
2
8
–
1
3
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
TA
C
S
5
9
8
4
7
.
2
0
2
3
.
1
0
3
9
0
5
0
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ani
sh
K
h
a
d
ta
r
e
is
p
u
rsu
i
n
g
t
h
e
B.
En
g
d
e
g
re
e
i
n
c
o
m
p
u
ter
e
n
g
in
e
e
rin
g
fro
m
t
h
e
S
h
a
h
a
n
d
An
c
h
o
r
Ku
tc
h
h
i
En
g
in
e
e
rin
g
Co
ll
e
g
e
,
In
d
ia.
His
g
e
n
e
r
a
l
a
re
a
o
f
re
se
a
r
c
h
in
c
lu
d
e
s
m
a
c
h
in
e
lea
rn
in
g
,
M
e
d
iaPi
p
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
a
n
ish
.
k
h
a
d
tare
1
5
6
3
6
@s
a
k
e
c
.
a
c
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
25
:
3
8
4
3
-
3850
3850
Va
sistha
Ve
d
is
p
u
rsu
i
n
g
th
e
B.
En
g
d
e
g
re
e
i
n
c
o
m
p
u
ter
e
n
g
in
e
e
rin
g
fro
m
t
h
e
S
h
a
h
a
n
d
An
c
h
o
r
Ku
tc
h
h
i
En
g
in
e
e
rin
g
Co
ll
e
g
e
,
In
d
ia.
His
g
e
n
e
r
a
l
a
re
a
o
f
re
se
a
r
c
h
in
c
lu
d
e
s
m
a
c
h
in
e
lea
rn
in
g
.
He
c
a
n
b
e
c
o
n
t
a
c
ted
a
t
e
m
a
il
:
v
a
sisth
a
.
v
e
d
1
5
8
9
1
@s
a
k
e
c
.
a
c
.
in
.
H
im
a
n
sh
u
K
o
ta
k
is
p
u
rsu
i
n
g
th
e
B.
En
g
d
e
g
re
e
in
c
o
m
p
u
ter
e
n
g
in
e
e
rin
g
fro
m
th
e
S
h
a
h
a
n
d
An
c
h
o
r
Ku
tch
h
i
En
g
i
n
e
e
rin
g
C
o
ll
e
g
e
,
In
d
ia.
h
is
g
e
n
e
ra
l
a
re
a
o
f
re
se
a
rc
h
in
c
l
u
d
e
s
m
a
c
h
in
e
lea
rn
in
g
,
Ten
so
rfl
o
w
e
tc.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
ima
n
sh
u
.
k
o
tak
1
5
9
3
4
@s
a
k
e
c
.
a
c
.
in
.
Akh
il
J
a
in
is
p
u
rs
u
in
g
t
h
e
B.
En
g
d
e
g
re
e
in
c
o
m
p
u
ter
e
n
g
i
n
e
e
rin
g
fr
o
m
th
e
S
h
a
h
a
n
d
A
n
c
h
o
r
K
u
tch
h
i
En
g
in
e
e
rin
g
Co
ll
e
g
e
,
In
d
ia.
His g
e
n
e
ra
l
a
re
a
o
f
re
se
a
rc
h
in
c
l
u
d
e
s
m
a
c
h
i
n
e
lea
rn
in
g
,
Ten
so
rf
lo
w.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
k
h
il
.
jain
1
5
9
9
8
@s
a
k
e
c
.
a
c
.
in
.
Pi
n
k
i
Pra
k
a
sh
Vishwa
k
a
r
m
a
h
a
s
re
c
e
iv
e
d
th
e
P
h
D
d
e
g
r
e
e
fro
m
th
e
K
L
Un
iv
e
rsity
,
In
d
ia.
S
h
e
is
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
i
n
t
h
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
En
g
in
e
e
ri
n
g
,
S
h
a
h
a
n
d
An
c
h
o
r
K
u
tch
h
i
En
g
in
e
e
rin
g
Co
ll
e
g
e
,
M
u
m
b
a
i,
a
ffil
iate
d
to
Un
i
v
e
rsity
o
f
M
u
m
b
a
i,
In
d
ia.
He
r
g
e
n
e
ra
l
a
re
a
o
f
re
se
a
rc
h
in
c
l
u
d
e
s
m
o
b
il
e
c
o
m
m
e
rc
e
,
d
a
ta
m
in
in
g
,
d
a
ta
b
a
se
s,
d
a
ta
a
n
a
ly
ti
c
s
in
se
c
u
re
tran
sa
c
ti
o
n
,
d
a
ta
m
in
in
g
in
a
g
ric
u
lt
u
re
.
S
h
e
h
a
s
p
u
b
li
s
h
e
d
se
v
e
ra
l
p
a
p
e
rs
in
re
fe
rre
d
jo
u
rn
a
l
a
n
d
c
o
n
fe
re
n
c
e
p
ro
c
e
e
d
in
g
s
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
in
k
i.
v
ish
wa
k
a
rm
a
@s
a
k
e
c
.
a
c
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.