I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
,
p
p
.
2377
~
2
3
8
4
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
3
.
p
p
2
3
7
7
-
2
3
8
4
2377
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Lo
g
Reg
ress
io
n:
huma
n actio
n pat
t
ern re
co
g
nition
f
o
r yo
g
a
and
ka
v
a
y
a
t
for children
Va
nita
B
a
ba
nn
e
1
,
P
a
nk
a
j
M.
Ag
a
rka
r
2
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
V
i
sh
w
a
k
a
r
ma
I
n
st
i
t
u
t
e
o
f
I
n
f
o
r
ma
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
S
a
v
i
t
r
i
b
a
i
P
h
u
l
e
P
u
n
e
U
n
i
v
e
r
s
i
t
y
,
P
u
n
e
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
A
j
e
e
n
k
y
a
D
Y
P
a
t
i
l
S
c
h
o
o
l
o
f
En
g
i
n
e
e
r
i
n
g
,
P
u
n
e
,
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
Oct
1
5
,
2
0
2
4
R
ev
is
ed
Ma
r
7
,
2
0
2
6
Acc
ep
ted
Ap
r
2
2
,
2
0
2
6
P
o
se
s
o
f
h
u
m
a
n
p
a
tt
e
rn
re
c
o
g
n
i
ti
o
n
t
h
ro
u
g
h
m
a
c
h
in
e
lea
rn
in
g
is
an
e
ss
e
n
ti
a
l
fa
c
e
t
o
f
se
v
e
ra
l
a
p
p
li
c
a
ti
o
n
s,
i
n
c
lu
d
in
g
h
e
a
lt
h
,
s
u
rv
e
il
lan
c
e
,
a
n
d
sp
o
rts
a
n
a
ly
sis.
F
o
r
c
h
il
d
re
n
y
o
g
a
a
n
d
k
a
v
a
y
a
t
(m
o
c
k
d
r
il
l)
i
n
c
re
a
se
s
th
e
p
h
y
sic
a
l
a
s
we
ll
a
s
m
e
n
tal
h
e
a
lt
h
.
T
h
ro
u
g
h
th
e
a
n
a
l
y
sis
o
f
m
o
t
io
n
d
a
ta
th
is
wo
r
k
d
isc
rimin
a
tes
b
e
twe
e
n
v
a
rie
d
a
c
ti
o
n
s
wit
h
h
ig
h
p
re
c
isio
n
,
c
o
n
tri
b
u
ti
o
n
v
a
lu
e
d
in
si
g
h
ts
fo
r
m
o
n
it
o
rin
g
a
n
d
a
n
a
ly
sis
in
re
a
l
-
ti
m
e
.
He
re
,
t
h
is
sy
ste
m
th
a
t
in
fl
u
e
n
c
e
s
tec
h
n
iq
u
e
c
a
ll
e
d
a
s
m
a
c
h
in
e
lea
rn
in
g
s
p
e
c
ifi
c
a
ll
y
lo
g
isti
c
re
g
re
ss
io
n
,
to
p
re
c
ise
ly
d
isc
rimin
a
te
a
n
d
c
las
sify
p
h
y
sic
a
l
a
c
ti
o
n
p
a
tt
e
rn
s
(c
h
il
d
p
o
se
e
stim
a
ti
o
n
)
o
f
c
h
il
d
r
e
n
.
A
n
a
lo
g
o
u
s
t
o
t
h
e
p
ro
p
a
g
a
ti
o
n
o
f
fa
lse
in
fo
rm
a
ti
o
n
,
id
e
n
t
ify
i
n
g
p
h
y
sic
a
l
a
c
ti
o
n
s
is
e
ss
e
n
ti
a
l
f
o
r
u
p
h
o
ld
in
g
in
teg
rit
y
a
n
d
e
fficie
n
c
y
a
c
ro
ss
v
a
rio
u
s
d
o
m
a
in
s.
Th
e
n
o
v
e
l
sy
ste
m
d
e
m
o
n
stra
tes
a
to
we
rin
g
a
c
c
u
ra
c
y
o
f
9
8
.
0
0
%
,
h
i
g
h
li
g
h
t
in
g
it
s
e
ffe
c
ti
v
e
n
e
ss
i
n
re
c
o
g
n
izi
n
g
a
n
d
c
las
sify
in
g
p
h
y
sic
a
l
a
c
ti
o
n
p
a
tt
e
rn
s.
K
ey
w
o
r
d
s
:
C
o
m
p
u
ter
v
is
io
n
Hu
m
an
ac
tio
n
r
ec
o
g
n
itio
n
L
o
g
is
tic
r
eg
r
ess
io
n
Ma
ch
in
e
lear
n
in
g
Yo
g
a
an
d
k
av
ay
at
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
:
Van
ita
B
ab
an
n
e
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
,
Vis
h
wak
ar
m
a
I
n
s
titu
t
e
o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
Sav
itrib
ai
Ph
u
le
Pu
n
e
Un
iv
e
r
s
ity
Pu
n
e,
I
n
d
ia
E
m
ail:
v
an
ita.
g
ad
e
k
ar
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
e
wo
r
ld
o
f
f
itn
ess
an
d
e
x
er
cise,
d
o
in
g
ex
e
r
cises
co
r
r
ec
tly
is
s
u
p
er
im
p
o
r
tan
t
f
o
r
g
ettin
g
th
e
r
esu
lts
y
o
u
wan
t
an
d
s
tay
in
g
s
af
e
f
r
o
m
in
ju
r
ies.
W
h
eth
er
s
o
m
eo
n
e
is
liftin
g
weig
h
ts
,
d
o
i
n
g
y
o
g
a,
o
r
p
lay
in
g
s
p
o
r
ts
o
r
f
o
r
ch
ild
r
e
n
d
o
in
g
as
y
o
g
a
an
d
k
a
v
ay
at
s
o
m
etim
es
it
is
ca
lled
as
m
o
c
k
d
r
ill
.
Mo
c
k
d
r
ill
is
r
etain
in
g
ch
ild
r
en
f
it
a
n
d
h
ea
lth
y
,
h
o
w
m
o
v
e
m
atter
s
a
lo
t.
B
u
t
let'
s
b
e
r
ea
l,
it'
s
n
o
t
alwa
y
s
ea
s
y
to
k
ee
p
f
o
r
m
p
er
f
ec
t,
esp
ec
ially
if
d
o
n
'
t
h
av
e
s
o
m
e
o
n
e
tr
ain
ed
to
h
elp
.
T
h
at'
s
w
h
er
e
tech
n
o
lo
g
y
ca
n
s
tep
in
to
len
d
a
h
an
d
.
On
e
ex
citin
g
ar
ea
is
m
ac
h
in
e
lear
n
i
n
g
,
wh
ich
is
lik
e
s
m
ar
t te
ch
n
o
lo
g
y
th
at
ca
n
lear
n
f
r
o
m
lo
ts
o
f
d
ata.
B
y
s
tu
d
y
in
g
h
o
w
we
m
o
v
e,
th
ese
m
ac
h
in
e
s
ca
n
lear
n
to
r
ec
o
g
n
ize
wh
en
we'
r
e
d
o
in
g
ex
er
cises
r
ig
h
t
o
r
if
we
m
ig
h
t
b
e
at
r
is
k
o
f
g
ettin
g
h
u
r
t.
Her
e
s
tated
th
at
h
o
w
to
d
iv
es
in
to
h
o
w
th
is
r
ef
in
ed
tech
n
o
lo
g
y
ca
n
g
iv
e
u
s
f
ee
d
b
ac
k
an
d
g
u
id
an
ce
as we
wo
r
k
o
n
g
ettin
g
f
itter
an
d
b
etter
at
wh
at
we
d
o
.
In
th
e
r
ea
lm
o
f
p
h
y
s
ical
f
itn
e
s
s
,
co
n
v
en
tio
n
al
m
eth
o
d
s
o
f
r
ec
eiv
in
g
f
ee
d
b
ac
k
o
f
ten
h
in
g
e
u
p
o
n
th
e
p
r
esen
ce
o
f
a
q
u
alif
ied
tr
ain
er
wh
o
ca
n
o
b
s
er
v
e
an
d
o
f
f
er
g
u
id
an
ce
o
n
o
u
r
ex
er
cise
tec
h
n
iq
u
es.
Ho
wev
er
,
th
e
ac
ce
s
s
ib
ilit
y
o
f
p
er
s
o
n
al
tr
ain
er
s
r
em
ain
s
a
p
r
iv
ileg
e
n
o
t
af
f
o
r
d
ed
to
ev
e
r
y
o
n
e,
an
d
ev
en
f
o
r
th
o
s
e
wh
o
d
o
h
av
e
ac
ce
s
s
,
th
e
lim
itatio
n
s
o
f
tim
e
a
n
d
a
v
ailab
ilit
y
p
e
r
s
is
t.
Her
ein
lies
th
e
u
tili
ty
o
f
m
ac
h
in
e
lear
n
in
g
tech
n
o
lo
g
y
.
T
h
r
o
u
g
h
th
e
u
tili
za
tio
n
o
f
s
p
ec
ialized
s
en
s
o
r
s
a
n
d
ca
m
er
as,
th
ese
in
tellig
en
t
s
y
s
tem
s
ar
e
ca
p
ab
le
o
f
m
o
n
ito
r
in
g
o
u
r
m
o
v
em
en
ts
an
d
p
r
o
m
p
tly
p
r
o
v
id
i
n
g
f
ee
d
b
ac
k
o
n
th
e
c
o
r
r
ec
tn
ess
o
f
o
u
r
ac
tio
n
s
.
W
h
eth
er
it
in
v
o
lv
es
r
ec
tify
in
g
m
in
o
r
er
r
o
r
s
in
a
s
q
u
at
o
r
r
ef
in
in
g
th
e
alig
n
m
en
t
o
f
a
y
o
g
a
p
o
s
e,
t
h
ese
s
y
s
tem
s
o
f
f
er
in
s
tan
tan
eo
u
s
g
u
id
an
ce
.
W
h
at
d
is
tin
g
u
is
h
es
th
ese
s
y
s
tem
s
is
th
eir
ca
p
ac
ity
f
o
r
co
n
tin
u
o
u
s
lear
n
in
g
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
3
7
7
-
2
3
8
4
2378
ad
ap
tatio
n
.
Ov
er
tim
e,
th
ey
ac
cu
m
u
late
in
s
ig
h
ts
in
to
o
u
r
u
n
iq
u
e
m
o
v
em
en
t
p
atter
n
s
an
d
ar
ea
s
wh
er
e
im
p
r
o
v
em
e
n
t
is
n
ee
d
ed
.
C
o
n
s
eq
u
en
tly
,
th
e
f
ee
d
b
ac
k
d
is
p
en
s
ed
b
ec
o
m
es
i
n
cr
ea
s
in
g
ly
p
er
s
o
n
alize
d
,
ak
i
n
to
th
e
g
u
id
a
n
ce
o
f
a
s
ea
s
o
n
ed
tr
ain
er
wh
o
p
o
s
s
ess
es
an
i
n
tim
ate
u
n
d
e
r
s
tan
d
in
g
o
f
o
u
r
ca
p
ab
ilit
ies
an
d
lim
itatio
n
s
.
T
h
is
p
er
s
o
n
alize
d
f
ee
d
b
ac
k
n
o
t
o
n
ly
e
n
h
an
ce
s
th
e
ef
f
icac
y
o
f
o
u
r
wo
r
k
o
u
ts
b
u
t
also
em
p
o
wer
s
u
s
with
g
r
ea
ter
au
to
n
o
m
y
o
v
er
o
u
r
f
itn
ess
en
d
ea
v
o
r
s
.
Ap
a
r
t
f
r
o
m
g
iv
in
g
u
s
f
ee
d
b
a
ck
d
u
r
i
n
g
wo
r
k
o
u
ts
,
th
ese
s
m
ar
t
s
y
s
tem
s
ca
n
d
o
a
lo
t
m
o
r
e.
T
h
ey
ca
n
k
e
ep
tr
ac
k
o
f
o
u
r
p
r
o
g
r
ess
an
d
tell
u
s
h
o
w
we'
r
e
im
p
r
o
v
in
g
.
T
h
ey
ca
n
also
war
n
u
s
if
we'
r
e
at
r
is
k
o
f
g
ettin
g
h
u
r
t,
wh
ich
h
el
p
s
u
s
s
tay
s
af
e
in
th
e
lo
n
g
r
u
n
.
An
d
if
th
at'
s
n
o
t
en
o
u
g
h
,
th
e
y
ca
n
ev
en
m
ak
e
ex
er
cisi
n
g
m
o
r
e
f
u
n
!
B
y
c
o
m
b
in
in
g
with
v
ir
tu
al
r
ea
lity
o
r
au
g
m
en
ted
r
ea
lity
,
th
ese
s
y
s
tem
s
ca
n
cr
ea
te
ex
cit
in
g
v
ir
t
u
al
wo
r
ld
s
f
o
r
u
s
to
tr
ain
in
.
I
t'
s
lik
e
p
lay
in
g
a
v
id
e
o
g
am
e,
b
u
t
in
s
tead
o
f
s
itti
n
g
ar
o
u
n
d
,
we'
r
e
m
o
v
i
n
g
an
d
g
ettin
g
f
it.
Usi
n
g
m
ac
h
i
n
e
lear
n
in
g
to
r
ec
o
g
n
ize
h
o
w
we
m
o
v
e
ca
n
m
ak
e
o
u
r
wo
r
k
o
u
ts
b
etter
an
d
s
af
er
.
I
t
g
iv
es
u
s
in
s
tan
t
f
ee
d
b
ac
k
,
tr
ac
k
s
o
u
r
p
r
o
g
r
ess
,
an
d
m
ak
es
ex
er
cisi
n
g
m
o
r
e
en
jo
y
ab
le.
B
u
t
to
m
ak
e
th
is
h
a
p
p
en
,
we
n
ee
d
to
wo
r
k
to
g
eth
er
,
th
in
k
a
b
o
u
t
th
e
eth
ics,
an
d
k
ee
p
im
p
r
o
v
in
g
th
e
tech
n
o
lo
g
y
.
W
ith
team
wo
r
k
a
n
d
in
n
o
v
atio
n
,
we
ca
n
m
a
k
e
e
x
er
cisi
n
g
s
m
ar
ter
an
d
m
o
r
e
f
u
n
f
o
r
e
v
er
y
o
n
e.
T
h
e
u
s
e
o
f
g
y
r
o
s
co
p
ic
s
en
s
o
r
s
[
1
]
an
d
ac
ce
ler
o
m
eter
s
in
m
o
b
ile
b
ased
h
u
m
a
n
ac
tio
n
r
ec
o
g
n
itio
n
,
to
r
ec
o
g
n
ize
th
e
ac
cu
r
ac
y
an
aly
z
ed
o
n
th
e
f
ea
tu
r
es
an
d
d
is
cu
s
s
ed
th
e
r
esu
lts
.
Hu
m
an
ac
tiv
ity
r
ec
o
g
n
itio
n
[
2
]
is
o
n
co
n
d
itio
n
th
at
d
if
f
er
e
n
t
ty
p
es
o
f
s
en
s
o
r
s
b
ein
g
u
s
ed
.
T
h
is
wo
r
k
s
u
f
f
er
ed
ev
alu
atio
n
a
n
d
tr
ain
in
g
u
s
in
g
a
d
ataset
o
p
en
av
ailab
le.
A
s
y
s
t
em
u
tili
ze
s
d
ee
p
lear
n
in
g
an
d
co
m
p
u
ter
v
is
io
n
f
o
r
r
ea
l
-
tim
e
p
o
s
tu
r
e
d
etec
tio
n
s
u
p
er
v
is
o
r
y
u
s
er
s
o
n
th
e
way
to
ac
cu
r
ate
p
o
s
tu
r
es
wh
ich
co
m
p
ar
is
o
n
with
ty
p
ical
y
o
g
a
p
o
s
es
[
3
]
.
Fu
r
th
er
m
o
r
e
,
am
alg
am
ate
f
ea
tu
r
es
th
is
wo
r
k
f
in
d
p
ath
f
o
r
g
y
m
ac
tiv
ities
f
r
o
m
v
ar
ie
d
p
o
s
tu
r
e
d
etec
tio
n
ap
p
licatio
n
s
o
n
to
a
co
m
b
i
n
ed
i
n
ter
f
ac
e.
R
o
le
o
f
c
am
er
a
as
a
v
is
i
o
n
-
b
ase
d
t
ec
h
n
i
q
u
e
ess
e
n
t
ial
f
o
r
t
h
e
a
p
p
r
eh
e
n
d
t
h
e
v
i
d
e
o
,
w
h
i
c
h
en
ca
m
p
s
wit
h
co
n
v
o
l
u
ti
o
n
al
n
e
u
r
al
n
et
wo
r
k
(
C
NN
)
a
n
d
c
o
n
v
o
lu
ti
o
n
al
lo
n
g
s
h
o
r
t
-
te
r
m
m
e
m
o
r
y
(
C
o
n
v
L
STM
)
[
4
]
.
I
t
p
r
o
p
o
s
es
t
h
e
u
n
iq
u
e
m
et
h
o
d
n
am
e
d
as
l
o
g
is
t
ic
r
e
g
r
ess
i
o
n
.
S
o
m
e
o
f
t
h
e
s
am
p
l
es
f
r
o
m
it
c
o
n
s
i
d
e
r
t
h
e
n
d
i
v
i
d
e
i
n
2
g
r
o
u
p
s
.
T
h
e
n
o
v
el
lo
g
is
tic
r
e
g
r
ess
i
o
n
al
g
o
r
it
h
m
v
ali
d
ates a
d
v
a
n
c
ed
ac
cu
r
ac
y
e
q
u
a
te
d
t
o
l
i
n
e
ar
r
eg
r
ess
io
n
[
5
]
.
Yo
u
o
n
l
y
l
o
o
k
a
t
c
o
e
f
f
i
cie
n
ts
(
YO
L
AC
T
)
-
te
m
p
o
r
a
l
r
el
ati
o
n
n
et
wo
r
k
ar
ch
ite
ct
u
r
e
(
T
R
N)
[
6
]
o
f
f
e
r
e
d
a
n
d
t
h
is
ar
ch
ite
ct
u
r
e
is
p
r
ec
is
el
y
in
te
n
d
e
d
f
o
r
a
ct
u
a
l
c
o
n
s
i
d
e
r
ate
o
f
h
an
d
a
cti
o
n
s
.
I
t
m
e
r
g
es
YO
L
AC
T
,
an
i
n
s
t
an
ce
s
eg
m
e
n
t
ati
o
n
m
et
h
o
d
o
lo
g
y
u
n
i
tin
g
i
n
r
e
al
ti
m
e
a
T
R
N
.
Mo
s
t
o
f
t
h
e
h
a
n
d
ac
t
io
n
u
n
d
e
r
s
t
an
d
t
h
r
o
u
g
h
t
h
e
T
R
N
.
T
wo
s
ep
ar
ate
ap
p
r
o
ac
h
es
d
ee
p
C
NN
[
7
]
:
p
r
im
ar
ily
,
u
n
til
th
e
en
d
o
f
tr
ain
in
g
o
n
th
e
R
GB
im
ag
e
d
ataset,
en
g
ag
in
g
tr
an
s
f
er
lea
r
n
in
g
to
class
if
y
p
o
s
itio
n
s
with
I
m
ag
eNe
t
c
o
u
n
t
in
n
u
m
b
er
f
iv
e
.
F
u
r
th
e
r
m
o
r
e
,
co
n
tr
o
l
ex
is
tin
g
q
u
alif
ied
(
p
o
s
e
esti
m
ato
r
)
d
ee
p
co
n
v
o
l
u
tio
n
al
n
etwo
r
k
d
em
o
n
s
tr
ate
ac
c
u
r
ac
y
.
Pre
s
en
tin
g
a
n
ew
way
to
s
h
o
w
th
e
th
r
ee
r
a
n
d
o
m
ly
co
n
n
ec
ted
in
s
tan
ce
s
c
o
m
b
in
ed
as
a
tr
ip
let.
W
h
ich
i
n
f
er
th
e
u
n
f
am
iliar
ac
tiv
ities
an
d
d
is
tin
g
u
is
h
in
g
ch
ar
ac
ter
is
tics
b
etwe
en
th
em
[
8
]
.
T
h
is
p
io
n
ee
r
in
g
m
eth
o
d
to
m
ea
s
u
r
e
ch
an
g
es
in
s
k
eleto
n
d
etec
tio
n
d
u
r
i
n
g
s
u
cc
ess
iv
e
ac
tiv
itie
s
is
k
n
o
wn
as
s
k
eleto
n
d
etec
tio
n
tech
n
iq
u
e.
I
t
o
p
er
ates
to
class
if
y
v
elo
city
lev
els
u
s
in
g
n
ea
r
est
n
eig
h
b
o
r
an
d
d
ir
ec
ts
t
h
e
s
p
atial
tem
p
o
r
al
g
r
a
p
h
c
o
n
v
o
lu
tio
n
al
n
etwo
r
k
s
(
ST
-
GC
N
)
m
o
d
el
to
co
n
cl
u
d
e
v
ar
iatio
n
s
in
s
tates
[
9
]
.
Acc
o
r
d
in
g
to
C
h
a
u
d
h
ar
i
et
a
l.
[
1
0
]
,
h
u
m
an
jo
in
ts
t
o
id
en
tify
d
is
cr
ep
an
cies
in
p
o
s
t
u
r
e
b
y
lo
ca
lizin
g
k
ey
p
o
i
n
ts
as
a
m
o
d
el,
th
is
p
r
ac
tice
u
s
ed
in
th
e
em
p
lo
y
s
C
NN
f
o
r
p
o
s
e
r
ec
o
g
n
itio
n
.
R
ec
en
t
p
r
o
g
r
ess
io
n
s
in
p
er
s
o
n
p
o
s
e
r
ec
o
g
n
itio
n
r
ea
lized
c
o
m
p
lete
th
e
e
n
titl
em
en
t
o
f
d
e
ep
lear
n
in
g
tech
n
iq
u
es
[
1
1
]
.
Dee
p
lear
n
in
g
h
as
r
ev
o
lu
tio
n
ized
p
o
s
e
ap
p
r
o
x
i
m
atio
n
b
y
a
p
p
r
o
v
i
n
g
th
e
g
r
o
wth
o
f
tr
em
en
d
o
u
s
ly
d
etailed
an
d
ef
f
icien
t
wo
r
k
th
at
g
r
ip
m
u
ltifa
c
eted
p
o
s
es
a
n
d
o
cc
lu
s
io
n
s
.
I
t
a
ttem
p
ted
th
r
ee
test
s
an
d
tr
ai
n
ed
th
e
f
r
am
ewo
r
k
wh
ich
d
is
tin
g
u
is
h
es
in
d
iv
id
u
ally
p
o
s
e
o
f
h
u
m
an
[
1
2
]
.
I
t
is
also
s
u
p
p
o
r
tiv
e
i
n
i
n
to
co
n
s
is
ten
t
p
atter
n
s
th
r
o
u
g
h
t
h
e
tr
an
s
f
o
r
m
atio
n
o
f
d
is
cr
ep
an
cies
o
f
d
is
s
im
ilar
ac
tiv
ities
.
I
t
d
ep
icts
ab
o
u
t
ac
tiv
ity
ac
k
n
o
wled
g
em
en
t
a
n
d
p
r
o
ce
s
s
in
g
o
f
im
ag
e
[
1
3
]
.
I
t
r
ec
eip
ts
s
in
g
le
d
ataset
an
d
e
x
am
in
es
th
e
p
er
f
o
r
m
an
ce
an
d
p
r
ec
is
io
n
.
Fra
m
es sep
ar
ated
in
to
im
ag
es.
I
t
v
id
eo
p
o
s
e3
D
f
o
r
h
u
m
a
n
ac
tiv
ity
r
eq
u
ir
e
th
e
v
er
y
less
d
ata
an
d
g
iv
es th
e
tr
ain
in
g
f
o
r
3
D
[
1
4
]
.
E
x
er
cise b
ased
p
o
s
t e
s
tim
atio
n
d
if
f
icu
lties
ca
n
b
e
wo
r
k
ed
.
On
e
ap
p
r
o
ac
h
[
1
5
]
u
tili
ze
s
a
s
tateless
d
y
n
am
ic
len
g
th
v
id
eo
d
ata
in
p
u
t
p
r
o
d
u
ce
r
,
alth
o
u
g
h
th
e
o
th
er
in
s
p
ec
ts
th
e
s
tate
d
ep
en
d
en
t
ca
p
ab
ilit
y
o
f
r
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
ch
ief
ly
u
s
ed
in
h
u
m
a
n
ac
tio
n
r
ec
o
g
n
itio
n
.
T
h
is
tactic
q
u
alif
ies
th
e
ar
ch
ety
p
al
to
f
o
ld
to
e
x
ce
r
p
t
i
n
e
q
u
itab
le
p
atter
n
s
f
r
o
m
p
r
ev
io
u
s
f
r
am
es
alth
o
u
g
h
co
n
s
er
v
in
g
m
em
o
r
y
i
n
teg
r
ity
.
Var
io
u
s
p
o
s
e
esti
m
atio
n
f
r
a
m
ewo
r
k
s
h
a
v
e
r
ec
e
n
tly
b
ee
n
s
cr
u
tin
ized
f
o
r
th
ei
r
ef
f
icac
y
in
class
if
y
in
g
tr
ad
iti
o
n
al
I
n
d
ian
p
h
y
s
ical
ac
tiv
itie
s
.
Sp
ec
if
ically
,
W
ah
ee
d
et
a
l.
[
2
]
u
s
in
g
d
if
f
er
e
n
t
ty
p
es
o
f
s
en
s
o
r
s
u
s
ed
to
r
ec
o
g
n
ize
th
e
ac
tiv
ity
o
f
h
u
m
a
n
.
T
h
e
cu
r
r
en
t
r
esear
ch
b
u
ild
s
u
p
o
n
th
is
f
o
u
n
d
atio
n
al
y
ar
d
s
tick
b
y
in
tr
o
d
u
cin
g
an
o
p
tim
ized
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el
to
en
h
an
ce
p
atter
n
r
ec
o
g
n
itio
n
ac
cu
r
a
cy
.
A
m
in
d
f
u
ln
ess
y
o
g
a
s
h
o
w
to
r
e
d
u
ce
th
e
ce
r
tain
an
x
iety
an
d
p
h
y
s
io
lo
g
ical
ar
o
u
s
al
(
p
u
ls
e
r
ate)
am
o
n
g
ch
ild
r
e
n
with
s
ch
o
o
l
r
ef
u
s
al
[
1
6
]
.
Acc
o
r
d
in
g
to
W
ilk
in
et
a
l.
[
1
7
]
,
ex
ec
u
tiv
e
f
u
n
ctio
n
o
f
3
-
to
7
-
y
e
ar
ch
ild
r
en
u
n
d
er
g
o
ch
an
g
es
an
d
lead
s
to
f
o
u
n
d
a
tio
n
o
f
ac
a
d
em
ics
,
em
o
tio
n
al
,
an
d
c
o
g
n
itiv
e
o
u
tco
m
es.
B
az
za
n
o
et
a
l.
[
1
8
]
m
in
d
f
u
ln
ess
in
ter
v
en
tio
n
p
lu
s
co
m
b
in
ed
y
o
g
a
r
esu
lts
in
to
s
o
m
e
ef
f
ec
ts
wer
e
s
m
all
an
d
co
n
tex
t
-
d
ep
en
d
en
t th
at
d
ec
r
ea
s
es
th
e
an
x
iety
a
n
d
d
ep
r
ess
io
n
.
L
iu
et
a
l.
[
1
9
]
f
o
cu
s
ed
o
n
3
D
p
o
s
e
an
d
m
esh
r
ec
o
v
er
y
m
eth
o
d
s
(
s
in
g
le
an
d
m
u
lti
-
p
er
s
o
n
)
,
d
atasets
an
d
tr
en
d
s
u
s
ef
u
l
if
y
o
u
r
p
ip
el
in
e
co
n
s
id
er
s
3
D
o
r
d
e
p
th
.
G
r
ap
h
co
n
v
o
l
u
tio
n
al
n
etwo
r
k
with
8
0
%
ac
cu
r
ac
y
u
s
ed
to
e
x
tr
ac
t
f
r
o
m
em
o
tio
n
al
f
ea
tu
r
es.
Fo
r
ac
tio
n
r
ec
o
g
n
itio
n
T
R
N
a
n
d
a
f
ac
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Lo
g
R
eg
r
ess
io
n
:
h
u
ma
n
a
ctio
n
p
a
tter
n
r
ec
o
g
n
itio
n
fo
r
yo
g
a
a
n
d
ka
va
ya
t fo
r
ch
ild
r
en
(
V
a
n
ita
B
a
b
a
n
n
e
)
2379
r
ec
o
g
n
itio
n
(
f
a
ce
r
ec
o
g
n
itio
n
b
ac
k
b
o
n
e
-
s
ec
u
r
ity
n
etwo
r
k
(
FR
B
-
SN
)
)
b
ased
s
ec
u
r
it
y
n
etwo
r
k
f
o
r
u
s
er
id
en
tific
atio
n
with
9
1
%
ac
cu
r
ac
y
an
d
m
ajo
r
co
n
ce
r
n
with
s
ec
u
r
ity
an
d
in
tu
itiv
e
in
ter
a
ctio
n
[
2
0
]
.
T
ab
le
1
co
m
p
ar
e
in
r
ea
l
tim
e
h
u
m
an
p
o
s
e
esti
m
atio
n
m
o
d
els
with
s
in
g
le
o
r
m
u
lti
p
er
s
o
n
with
d
if
f
er
en
t
k
ey
p
o
in
ts
d
etec
tio
n
to
th
e
s
y
s
tem
o
f
an
d
th
en
lo
g
r
ess
io
n
with
3
3
k
e
y
p
o
in
ts
s
tated
f
o
r
ch
ild
p
o
s
e
d
etec
tio
n
.
T
ab
le
1
.
H
u
m
a
n
p
o
s
e
esti
m
ati
o
n
m
o
d
els u
s
in
g
d
ee
p
lear
n
in
g
P
o
se
e
st
i
ma
t
i
o
n
m
o
d
e
l
K
e
y
p
o
i
n
t
F
u
n
c
t
i
o
n
i
n
g
A
p
p
r
o
a
c
h
S
i
n
g
l
e
/
m
a
n
y
O
p
e
n
p
o
se
25
R
e
a
l
-
t
i
me
B
o
t
t
o
m
-
up
S
i
n
g
l
e
a
n
d
m
a
n
y
p
e
r
s
o
n
M
a
s
k
-
R
N
N
11
R
e
a
l
-
t
i
me
B
o
t
t
o
m
-
up
M
a
n
y
p
e
r
so
n
A
l
p
h
a
P
o
se
12
R
e
a
l
-
t
i
me
To
p
-
up
M
a
n
y
p
e
r
so
n
D
e
e
p
c
u
t
17
R
e
a
l
-
t
i
me
B
o
t
t
o
m
-
up
M
a
n
y
p
e
r
so
n
I
t
e
r
a
t
i
v
e
e
r
r
o
r
f
e
e
d
b
a
c
k
13
R
e
a
l
-
t
i
me
To
p
-
up
S
i
n
g
l
e
a
n
d
m
a
n
y
p
e
r
s
o
n
Lo
g
R
e
g
r
e
s
si
o
n
33
R
e
a
l
-
t
i
me
To
p
-
up
S
i
n
g
l
e
2.
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
is
b
ased
o
n
a
p
p
r
e
h
en
d
in
g
th
e
v
i
d
eo
f
r
am
e
an
d
d
etec
tio
n
t
h
e
co
r
r
ec
t
h
u
m
an
ac
tio
n
u
s
in
g
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
.
Fig
u
r
e
1
illu
s
tr
ate
th
e
o
v
er
all
ar
ch
itectu
r
al
f
r
am
ewo
r
k
o
f
p
r
o
p
o
s
e
d
L
o
g
R
eg
r
ess
io
n
s
y
s
tem
f
o
r
r
e
co
g
n
izin
g
y
o
g
a
an
d
k
a
v
ay
at
p
atter
n
s
in
c
h
ild
r
en
.
T
h
e
f
l
o
wch
ar
t
d
etails
th
e
s
eq
u
en
tial stag
es f
r
o
m
v
id
e
o
i
n
p
u
t to
f
in
al
class
if
icatio
n
p
er
f
o
r
m
an
ce
o
f
th
e
s
y
s
tem
.
Fig
u
r
e
1
.
W
o
r
k
f
lo
w
d
iag
r
am
o
f
p
r
o
p
o
s
ed
L
o
g
R
eg
r
ess
io
n
s
y
s
tem
2
.
1
.
Arc
hite
ct
ure
T
h
is
is
p
r
o
p
o
s
ed
wo
r
k
f
lo
w
d
iag
r
am
to
illu
s
tr
ate
th
e
F
ig
u
r
e
1
,
w
h
ich
h
ig
h
lig
h
t
th
e
d
ataf
lo
w
an
d
in
teg
r
atio
n
o
f
ea
ch
c
o
m
p
o
n
en
t
as f
o
llo
ws:
i)
I
n
p
u
t:
t
h
e
in
p
u
t
to
th
e
s
y
s
tem
is
a
liv
e
d
ata
o
f
u
s
er
’
s
b
o
d
y
p
o
in
ts
.
T
h
e
d
ataset
co
n
tain
s
s
am
p
les
o
f
v
ar
io
u
s
p
h
y
s
ical
ac
tiv
ities
p
er
f
o
r
m
ed
b
y
th
e
c
h
ild
r
en
.
T
h
e
d
a
ta
is
ca
p
tu
r
ed
b
y
ca
m
er
a.
ii)
Pre
p
r
o
ce
s
s
in
g
:
th
e
r
aw
d
ata
is
p
r
e
-
p
r
o
ce
s
s
ed
to
e
r
ad
icate
n
o
is
e
an
d
i
n
ap
p
r
o
p
r
iate
i
n
f
o
r
m
atio
n
.
T
h
is
in
clu
d
es
tech
n
iq
u
es
s
u
ch
as
f
ilter
in
g
,
n
o
r
m
aliza
tio
n
,
a
n
d
s
eg
m
en
tatio
n
t
o
is
o
late
in
d
iv
i
d
u
al
ac
tiv
ities
.
Pre
p
r
o
ce
s
s
in
g
is
d
o
n
e
t
o
em
p
h
asize
th
e
s
ig
n
if
ican
ce
o
f
d
ata
q
u
ality
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
3
7
7
-
2
3
8
4
2380
iii)
Featu
r
e
ex
tr
ac
tio
n
:
it
in
cl
u
d
e
s
tr
an
s
f
o
r
m
in
g
a
n
d
s
elec
tin
g
u
n
p
r
o
ce
s
s
ed
d
ata
h
o
o
k
ed
o
n
v
alu
ab
le
a
n
d
in
s
ig
h
t
f
ea
tu
r
es
m
ay
r
o
u
tin
e
th
at
m
ac
h
in
e
lear
n
i
n
g
m
o
d
e
ls
f
o
r
co
r
r
ec
t
ac
k
n
o
wled
g
em
en
t
o
f
p
e
r
s
o
n
ac
tiv
ity
.
R
elev
an
t
f
ea
tu
r
es
ca
p
tu
r
e
in
f
o
r
m
atio
n
f
o
r
ac
tio
n
r
ec
o
g
n
itio
n
.
T
h
e
s
y
s
tem
u
s
es
co
o
r
d
in
ates
allo
ca
ted
o
n
t
h
e
b
o
d
y
a
n
d
f
a
ce
o
f
th
e
p
r
ac
titi
o
n
er
to
d
ete
ct
th
e
p
o
s
es.
A
d
ataset
o
f
c
h
ild
(
y
o
g
a
an
d
k
av
ay
at
)
p
o
s
es with
co
r
r
esp
o
n
d
in
g
co
o
r
d
in
ates f
o
r
ea
ch
p
o
s
e
with
k
ey
p
o
i
n
ts
.
iv
)
C
las
s
if
icatio
n
u
s
in
g
lo
g
is
tic
r
eg
r
ess
io
n
alg
o
r
ith
m
:
lo
g
is
ti
c
r
eg
r
ess
io
n
is
u
s
ed
f
o
r
class
if
icatio
n
o
f
m
u
ltip
le
task
s
.
I
t
m
o
d
els
th
e
p
r
o
b
a
b
ilit
y
o
f
ea
c
h
class
u
s
in
g
a
lo
g
is
tic
f
u
n
ctio
n
an
d
m
a
k
es
p
r
ed
ictio
n
s
b
ased
o
n
th
e
p
r
o
b
a
b
ilit
y
s
co
r
es.
T
h
e
d
ataset
was
p
r
ep
r
o
ce
s
s
ed
,
an
d
lo
g
is
tic
r
eg
r
ess
io
n
was
tr
ain
ed
to
class
if
y
th
e
p
o
s
es d
ep
en
d
o
n
t
h
e
o
b
tain
e
d
f
ea
tu
r
es.
v)
Dete
ct
h
u
m
an
ac
tiv
ity
:
af
ter
tr
ain
in
g
o
f
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el,
it
ca
n
b
e
u
s
ed
to
class
if
y
n
ew
in
s
tan
ce
s
o
f
s
en
s
o
r
d
ata
in
to
d
if
f
er
en
t
ac
tiv
ity
class
es.
T
h
e
m
o
d
el
p
r
ed
icts
th
e
g
r
ea
test
p
o
s
s
ib
le
ac
tiv
ity
wo
r
k
ed
o
n
th
e
e
x
tr
ac
ted
f
ea
t
u
r
es a
n
d
lear
n
ed
p
ar
am
eter
s
.
v
i)
E
v
alu
atio
n
:
m
et
r
ics
lik
e
ac
cu
r
ac
y
ar
e
u
s
ed
to
ev
alu
ate
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
o
d
el,
o
f
f
er
in
g
in
s
ig
h
ts
in
to
its
ab
ilit
y
to
ac
cu
r
ately
cl
ass
if
y
v
ar
io
u
s
ac
tiv
ities
.
2
.
2
.
P
r
o
po
s
ed
a
lg
o
rit
hm
L
o
g
is
tic
r
e
g
r
ess
i
o
n
:
t
h
is
a
lg
o
r
it
h
m
wh
ic
h
cl
ass
i
f
ies
t
h
e
ta
s
k
s
i
n
b
i
n
ar
y
n
u
m
b
e
r
s
.
G
r
o
u
p
o
f
i
n
p
u
t
f
e
at
u
r
es
1
,
2
,
3
,
…
,
.
Ou
tp
u
t
wi
ll
b
e
g
i
v
e
n
in
t
h
e
co
m
b
i
n
atio
n
o
f
0
a
n
d
1
.
Giv
en
a
d
at
ase
t w
it
h
i
n
p
u
t
f
ea
t
u
r
es
a
n
d
b
in
ar
y
la
b
els
,
is
e
it
h
er
0
o
r
1
an
d
,
is
a
v
ec
to
r
o
f
s
iz
e
.
I
n
iti
ali
ze
t
h
e
we
ig
h
ts
w
a
n
d
b
i
as
t
o
0
’
s
o
r
m
i
n
o
r
r
a
n
d
o
m
v
a
l
u
es
.
C
o
m
p
u
te
t
h
e
s
u
m
o
f
t
h
e
p
r
o
d
u
cts
o
f
co
r
r
es
p
o
n
d
i
n
g
wei
g
h
ts
a
n
d
i
n
p
u
t
f
ea
t
u
r
es
as
i
n
(
1
)
.
=
1
1
+
2
2
+
⋯
+
+
(
1
)
Ap
p
l
y
a
n
d
ca
lc
u
l
ate
t
h
e
l
o
g
is
t
ic
(
s
ig
m
o
i
d
)
f
u
n
cti
o
n
t
o
t
h
e
l
i
n
e
ar
co
m
b
i
n
at
io
n
t
o
g
e
t
t
h
e
p
r
ed
i
ct
ed
p
r
o
b
ab
ilit
y
.
Dete
r
m
i
n
e
t
h
e
l
o
s
s
,
o
r
e
r
r
o
r
,
b
y
c
o
m
p
ar
in
g
t
h
e
p
r
ed
ict
ed
p
r
o
b
a
b
il
it
y
t
o
t
h
e
ac
t
u
al
l
ab
el
,
t
y
p
ic
all
y
u
s
i
n
g
a
l
o
s
s
f
u
n
cti
o
n
l
ik
e
b
i
n
a
r
y
c
r
o
s
s
-
e
n
t
r
o
p
y
.
U
p
d
a
te
th
e
b
i
as
a
n
d
wei
g
h
t
t
o
m
i
n
i
m
i
ze
th
e
lo
s
s
f
u
n
c
tio
n
u
s
i
n
g
g
r
a
d
i
en
t
d
es
ce
n
t
as
i
n
(
2
)
.
=
−
(
2
)
R
ep
e
at
s
te
p
s
th
e
s
u
m
o
f
p
r
o
d
u
ct
an
d
u
p
d
a
te
t
h
e
b
ias
a
n
d
wei
g
h
t
f
o
r
a
q
u
a
n
ti
f
i
ed
n
u
m
b
e
r
o
f
it
er
ati
o
n
s
o
r
u
n
ti
l
co
n
v
e
r
g
e
n
c
e.
Us
e
t
h
e
t
r
a
in
e
d
wei
g
h
ts
a
n
d
b
ias
t
o
p
r
e
d
ict
o
u
tc
o
m
es
f
o
r
n
e
w
d
ata
,
a
c
h
ie
v
ed
b
y
a
p
p
l
y
i
n
g
th
e
lo
g
is
t
ic
f
u
n
ct
io
n
t
o
th
e
s
u
m
o
f
th
e
p
r
o
d
u
cts
o
f
i
n
p
u
t
f
e
at
u
r
es
a
n
d
t
h
eir
c
o
r
r
es
p
o
n
d
i
n
g
w
ei
g
h
ts
.
Fig
u
r
e
2
i
ll
u
s
tr
at
es
t
h
e
d
a
t
aset
co
m
p
il
ed
f
o
r
t
h
is
s
tu
d
y
,
w
h
i
c
h
d
is
ti
n
g
u
is
h
es
b
e
t
wee
n
t
h
e
h
i
g
h
-
p
r
ec
is
i
o
n
s
t
ati
c
r
e
q
u
i
r
e
m
en
ts
o
f
y
o
g
a
a
n
d
th
e
co
o
r
d
i
n
at
e
-
b
as
ed
m
o
v
e
m
e
n
ts
o
f
k
a
v
a
y
a
t
(
d
r
il
l)
.
W
h
il
e
y
o
g
a
p
o
s
es
em
p
h
asi
ze
m
a
in
tai
n
i
n
g
s
p
e
ci
f
ic
j
o
i
n
t
an
g
l
es,
k
a
v
a
y
at
a
cti
o
n
s
a
r
e
c
h
a
r
a
ct
er
i
ze
d
b
y
r
a
p
i
d
t
r
a
n
s
it
io
n
s
b
et
we
en
s
ta
n
d
a
r
d
p
o
s
it
io
n
s
.
T
ab
l
e
2
ill
u
s
t
r
ates
t
h
e
d
if
f
e
r
e
n
t
tec
h
n
i
q
u
es
u
s
e
d
wit
h
t
h
e
d
at
as
et
an
d
t
h
e
ac
c
u
r
ac
y
o
f
t
h
e
m
o
d
el.
T
o
e
n
s
u
r
e
a
b
al
an
ce
d
c
lass
i
f
i
ca
t
io
n
,
t
h
e
lo
g
is
t
ic
r
e
g
r
ess
i
o
n
m
o
d
el
was
tr
ai
n
ed
o
n
s
t
an
d
ar
d
i
ze
d
f
e
at
u
r
e
v
ec
to
r
s
ex
tr
ac
t
ed
f
r
o
m
Me
d
i
aPi
p
e
,
a
ll
o
wi
n
g
t
h
e
s
y
s
te
m
t
o
d
i
f
f
e
r
e
n
ti
ate
b
etw
ee
n
t
h
e
s
u
b
tl
e
a
n
g
u
la
r
d
e
v
i
ati
o
n
s
i
n
y
o
g
a
a
n
d
t
h
e
d
is
t
in
c
t s
p
a
tia
l s
h
i
f
ts
i
n
s
ch
o
o
l
d
r
i
l
ls
.
Fig
u
r
e
2
.
C
o
m
p
a
r
is
o
n
o
f
ex
er
c
is
e
p
o
s
es d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Lo
g
R
eg
r
ess
io
n
:
h
u
ma
n
a
ctio
n
p
a
tter
n
r
ec
o
g
n
itio
n
fo
r
yo
g
a
a
n
d
ka
va
ya
t fo
r
ch
ild
r
en
(
V
a
n
ita
B
a
b
a
n
n
e
)
2381
T
ab
le
2
.
Mo
d
el
s
ettin
g
s
with
d
ataset
u
s
ed
with
ac
cu
r
ac
y
Y
e
a
r
Tr
a
i
n
i
n
g
m
o
d
e
l
T
e
c
h
n
i
q
u
e
u
s
e
d
D
a
t
a
s
e
t
u
s
e
d
A
c
c
u
r
a
c
y
(
%)
2024
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
L
o
g
i
s
t
i
c
r
e
g
r
e
s
s
i
o
n
R
e
a
l
t
i
me
d
a
t
a
s
e
t
u
s
e
d
m
a
d
e
b
y
H
D
c
a
me
r
a
9
9
.
0
0
2023
D
e
e
p
l
e
a
r
n
i
n
g
B
l
a
z
e
P
o
s
e
G
H
U
M
3
D
[
2
1
]
R
G
B
i
m
a
g
e
d
a
t
a
s
e
t
9
6
.
9
0
2023
D
e
e
p
l
e
a
r
n
i
n
g
M
o
v
e
N
e
t
[
2
2
]
S
e
l
f
-
c
o
l
l
e
c
t
e
d
d
a
t
a
s
e
t
b
y
H
D
c
a
m
8
3
.
0
0
2022
D
e
e
p
l
e
a
r
n
i
n
g
P
o
s
e
N
e
t
[
2
3
]
C
O
C
O
a
n
d
M
P
I
I
h
u
m
a
n
p
o
se
d
a
t
a
s
e
t
9
7
.
6
0
2022
D
e
e
p
l
e
a
r
n
i
n
g
C
N
N
-
L
S
T
M
[
2
4
]
I
n
n
o
v
a
t
i
v
e
d
a
t
a
c
o
l
l
e
c
t
b
y
K
i
n
e
c
t
s
e
n
s
o
r
9
0
.
1
8
2020
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
D
e
n
se
N
e
t
[
2
5
]
YOGA
-
8
2
S
,
8
2
i
n
s
t
a
n
c
e
9
1
.
4
4
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Fo
r
th
e
d
etec
tio
n
o
f
h
u
m
an
a
ctio
n
r
ec
o
g
n
itio
n
,
a
ca
m
er
a
i
s
u
tili
ze
d
.
T
h
e
s
y
s
tem
p
r
o
ce
s
s
es
a
liv
e
d
ataset
to
d
etec
t
h
u
m
an
p
o
s
es.
T
h
e
ca
m
er
a
em
p
lo
y
ed
ca
n
b
e
em
b
ed
d
ed
i
n
a
lap
to
p
o
r
an
e
x
ter
n
al
ca
m
er
a
ca
n
b
e
u
s
ed
.
I
t
id
en
tifie
s
th
e
o
u
t
p
u
t
o
f
liv
e
p
o
s
es
b
y
co
m
p
a
r
in
g
th
em
with
o
r
i
g
in
al
d
ataset.
Ad
d
itio
n
ally
,
th
e
s
y
s
tem
p
r
o
v
id
es th
e
n
am
e
o
f
th
e
ac
tiv
ity
b
ein
g
p
er
f
o
r
m
e
d
.
Few
s
am
p
les
d
ep
icted
in
r
ea
l
-
tim
e
o
p
er
atio
n
al
ca
p
ab
ilit
y
o
f
t
h
e
s
y
s
tem
is
d
em
o
n
s
tr
ated
lik
e
Fig
u
r
e
3
wh
ich
illu
s
tr
ates
th
e
'
s
tan
d
in
g
d
r
ill
f
r
o
n
t'
(
k
av
ay
at
)
,
Fig
u
r
e
4
lef
ts
ize
war
r
io
r
p
o
s
e
,
Fig
u
r
e
5
s
ea
ted
s
ize
s
tr
etch
r
ec
o
g
n
itio
n
u
s
in
g
a
liv
e
ca
m
e
r
a
f
ee
d
.
As
th
e
c
h
ild
p
e
r
f
o
r
m
s
th
e
d
r
ill,
th
e
s
y
s
tem
u
tili
ze
s
a
f
r
a
m
e
-
by
-
f
r
am
e
p
r
o
ce
s
s
in
g
ap
p
r
o
ac
h
to
o
v
er
la
y
3
3
s
k
eleta
l
lan
d
m
ar
k
s
o
n
th
e
h
u
m
an
s
u
b
ject.
T
h
e
r
ea
l
-
tim
e
in
ter
f
ac
e
p
r
o
v
id
es
im
m
ed
iate
f
ee
d
b
ac
k
b
y
ca
lcu
latin
g
th
e
s
p
atial
c
o
o
r
d
in
ates
o
f
th
e
lim
b
s
.
Fo
r
th
e
s
tan
d
in
g
d
r
ill,
th
e
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el
s
p
ec
if
ically
m
o
n
ito
r
s
th
e
v
er
tical
alig
n
m
en
t o
f
th
e
to
r
s
o
an
d
th
e
p
r
o
x
im
it
y
o
f
th
e
ar
m
s
to
th
e
later
al
m
id
lin
e.
T
h
is
v
is
u
aliza
tio
n
co
n
f
ir
m
s
th
at
th
e
m
o
d
el
ca
n
m
ain
tain
tr
ac
k
in
g
s
tab
ilit
y
an
d
class
if
icatio
n
ac
cu
r
ac
y
ev
e
n
u
n
d
er
v
ar
y
in
g
l
ig
h
tin
g
co
n
d
itio
n
s
an
d
b
ac
k
g
r
o
u
n
d
n
o
is
e
ty
p
ical
in
f
r
o
n
t o
f
t
h
e
ca
m
er
a.
Fig
u
r
e
3
.
Stan
d
i
n
g
d
r
ill f
r
o
n
t
Fig
u
r
e
4
.
L
e
f
ts
ize
war
r
io
r
p
o
s
e
Fig
u
r
e
5
.
Seated
s
ize
s
tr
etch
3
.
1
.
Co
m
pa
riso
n o
f
e
x
er
cise da
t
a
T
h
e
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el
ac
h
iv
e
th
e
s
ig
n
if
ican
lt
o
u
tp
er
f
o
r
m
in
g
9
9
%
ac
cu
r
ac
y
wh
en
co
m
p
ar
in
g
with
o
th
er
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
attin
th
e
8
5
%
an
d
d
ec
is
io
n
tr
ee
7
5
%
wh
ile
h
an
d
lin
g
t
h
e
v
ar
iatio
n
s
o
f
th
e
p
o
s
e
p
atter
n
s
as
s
h
o
wn
in
th
e
Fig
u
r
e
2
.
T
h
e
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
l
o
g
is
tic
r
eg
r
ess
io
n
ef
f
ec
tiv
ely
h
an
d
les
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
3
7
7
-
2
3
8
4
2382
lin
ea
r
ly
s
ep
ar
ab
le
f
ea
tu
r
es
d
er
iv
ed
f
r
o
m
th
e
n
o
r
m
alize
d
p
o
s
es
k
ey
p
o
in
ts
.
I
t
wo
r
k
s
ex
ce
llen
t
in
th
e
r
ea
l
tim
e
p
o
s
e
class
if
icatio
n
wo
r
k
.
3
.
2
.
P
r
o
po
s
ed
m
a
t
he
m
a
t
ica
l
m
o
dellin
g
T
h
is
s
y
s
tem
u
s
es
th
e
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
as
a
lo
g
is
t
ic
r
eg
r
ess
io
n
.
Ou
tco
m
e
m
ea
s
u
r
e
in
f
o
r
m
o
f
0
a
n
d
1
.
L
o
g
f
u
n
ctio
n
f
in
d
p
r
o
b
a
b
ilit
ies
in
r
elatio
n
s
o
f
1
an
d
0
.
T
h
e
h
y
p
o
th
esis
f
u
n
ctio
n
g
iv
e
n
b
y
lo
g
is
tic
r
eg
r
ess
io
n
as in
(
3
)
.
ℎ
(
)
=
1
1
+
ⅇ
(
3
)
W
h
er
e
is
f
ea
tu
r
e
v
ec
to
r
,
ℎ
(
)
is
b
ased
p
r
o
b
ab
ilit
y
,
is
p
ar
am
et
er
s
o
f
v
ec
to
r
s
(
weig
h
ts
)
c
o
n
n
ec
ted
with
ev
er
y
f
ea
t
u
r
e,
is
lo
g
ar
ith
m
b
a
s
e
u
p
o
n
o
u
tco
m
e
t
h
e
v
alu
es o
f
,
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el
is
tr
ain
ed
.
I
n
lo
g
is
tic
r
eg
r
ess
io
n
,
t
h
e
co
s
t
f
u
n
ctio
n
is
d
e
f
in
ed
b
y
th
e
l
o
g
-
lik
elih
o
o
d
f
u
n
ctio
n
as in
(
4
)
.
(
)
=
−
1
∑
[
−
(
)
(
ℎ
(
(
)
)
)
+
(
1
−
(
)
)
(
1
−
ℎ
(
(
)
)
)
]
=
1
(
4
)
W
h
er
e
is
a
l
o
s
s
f
u
n
ctio
n
,
is
th
e
p
ar
am
ete
r
v
ec
t
o
r
t
h
at
d
e
f
in
es
th
e
weig
h
ts
o
f
t
h
e
m
o
d
el,
is
th
e
s
ize
o
f
s
am
p
le
in
th
e
d
ataset,
(
)
is
th
e
ac
tu
al
lab
el
o
f
th
e
th
s
am
p
le,
ℎ
(
(
)
)
is
th
e
f
o
r
eseen
p
r
o
b
ab
ilit
y
o
f
th
e
j
th
s
am
p
le
b
elo
n
g
in
g
to
th
e
p
o
s
itiv
e
class
,
(
)
is
th
e
th
s
am
p
le
in
t
h
e
d
ataset.
3
.
3
.
Da
t
a
c
o
llect
io
n pro
t
o
co
l
A
L
o
g
itech
C
9
2
0
HD
Pro
R
GB
ca
m
er
a
m
o
u
n
ted
,
g
r
asp
in
g
v
id
eo
s
at
a
f
r
am
e
r
ate
o
f
3
0
FPS
an
d
r
eso
lu
tio
n
o
f
1
9
2
0
×1
0
8
0
p
ix
el
s
.
Par
ticip
an
ts
p
o
s
itio
n
ed
ab
o
u
t
2
.
5
to
3
.
0
m
eter
s
o
u
t
o
f
s
ig
h
t
f
r
o
m
ca
m
er
a
with
m
o
d
if
icatio
n
s
co
m
p
leted
f
o
r
s
in
g
le
p
er
s
o
n
t
o
g
u
ar
an
tee
t
h
e
co
m
p
lete
b
o
d
y
p
o
in
ts
ca
n
v
is
ib
le.
T
h
e
ca
m
e
r
a
h
eig
h
t
o
f
ar
o
u
n
d
1
.
2
m
eter
s
o
n
tr
ip
o
d
s
o
th
at
t
h
e
p
ar
ticip
a
n
t
s
in
th
e
p
r
o
p
er
m
id
d
le.
T
h
e
p
a
r
ticip
an
ts
tau
g
h
t
to
s
tan
ce
o
n
a
n
o
ticea
b
le
lo
ca
tio
n
o
n
th
e
f
l
o
o
r
to
co
n
tin
u
e
r
eliab
le
d
is
tan
ce
a
n
d
alig
n
in
g
wit
h
th
e
ca
m
er
a.
E
v
er
y
p
ar
ticip
an
t
p
er
f
o
r
m
ed
s
eq
u
e
n
c
e
ac
tio
n
o
f
y
o
g
a
an
d
k
a
v
ay
at
d
r
ills
(
to
tal
1
0
class
es).
Mo
v
e
m
en
t
ex
ec
u
ted
th
r
ee
p
er
io
d
s
p
e
r
p
o
s
tu
r
e/ex
er
cise
t
o
ac
co
u
n
t
f
o
r
in
tr
a
-
p
ar
ticip
an
t
v
ar
iab
ilit
y
.
Data
g
ain
in
g
co
n
d
u
cted
in
a
p
r
ec
is
e
in
s
id
e
s
ettin
g
to
d
ec
r
ea
s
e
co
n
t
ex
tu
al
an
d
lig
h
tin
g
in
co
n
s
is
te
n
cy
.
T
o
av
o
id
v
is
u
al
d
is
tr
ac
tio
n
s
d
u
r
in
g
lan
d
m
ar
k
d
etec
tio
n
,
r
ec
o
r
d
in
g
s
wer
e
p
e
r
f
o
r
m
e
d
ag
ain
s
t
a
p
lain
,
tex
tu
r
e
-
f
r
ee
wall
with
u
n
if
o
r
m
am
b
ien
t
lig
h
tin
g
th
at
m
in
im
ized
s
h
ad
o
ws.
S
u
p
er
v
i
s
io
n
s
taf
f
co
n
f
i
r
m
ed
th
at
m
o
v
em
en
ts
d
ir
ec
ted
ca
r
e
f
u
lly
,
wit
h
s
atis
f
ac
to
r
y
b
r
ea
k
b
etwe
en
d
u
p
licatio
n
s
.
Mo
tio
n
f
itti
n
g
g
ar
m
e
n
ts
u
s
ed
s
o
d
o
n
o
t o
b
s
tr
u
ct
th
e
jo
in
ts
v
is
ib
ilit
y
.
T
ab
le
3
.
Data
s
et
s
tatis
tic
s
P
a
r
a
me
t
e
r
I
l
l
u
st
r
a
t
i
v
e
v
a
l
u
e
To
t
a
l
p
a
r
t
i
c
i
p
a
n
t
s (N
)
N
=
1
2
0
V
i
d
e
o
s
p
e
r
p
a
r
t
i
c
i
p
a
n
t
1
0
v
i
d
e
o
s
p
e
r
p
a
r
t
i
c
i
p
a
n
t
O
v
e
r
a
l
l
v
i
d
e
o
c
o
u
n
t
1
,
2
0
0
v
i
d
e
o
s
Ex
t
r
a
c
t
e
d
f
r
a
me
s
≈
1
1
,
5
0
0
f
r
a
mes
D
e
f
i
n
i
t
i
o
n
o
f
a
sam
p
l
e
1
sa
mp
l
e
=
1
f
r
a
me
(
p
o
se
i
n
st
a
n
c
e
)
4.
CO
NCLU
SI
O
N
Yo
g
a
an
d
k
av
ay
at
f
o
r
c
h
ild
r
en
lev
er
a
g
in
g
t
h
e
s
tu
d
y
d
ev
elo
p
e
d
,
ca
p
ab
le
o
f
r
ea
l
-
tim
e
ac
tio
n
r
ec
o
g
n
itio
n
,
p
r
o
v
id
in
g
f
ee
d
b
ac
k
s
o
u
n
d
b
y
wa
y
o
f
t
h
e
p
r
ed
icted
e
x
er
cise
n
am
e.
B
y
s
u
cc
ess
f
u
lly
im
p
lem
en
tatio
n
o
f
th
is
in
tellig
en
t
s
y
s
tem
ca
p
ab
le
o
f
r
ec
o
g
n
izin
g
h
u
m
an
ac
tio
n
s
in
f
r
o
n
t
o
f
th
e
ca
m
er
a,
t
h
is
wo
r
k
led
t
o
th
e
way
f
o
r
r
ev
o
lu
tio
n
ar
y
ap
p
licatio
n
s
in
th
e
f
ield
o
f
h
o
lis
tic
an
d
p
er
s
o
n
al
well
-
b
ein
g
.
T
h
is
ap
p
licatio
n
n
o
t o
n
ly
e
n
h
an
ce
s
th
e
f
itn
ess
ex
p
er
ien
ce
f
o
r
in
d
i
v
id
u
als
b
u
t
also
h
o
l
d
s
p
r
o
m
is
e
f
o
r
ap
p
licatio
n
s
in
s
p
o
r
t,
h
ea
lth
ca
r
e
,
an
d
p
e
r
s
o
n
a
l
tr
ain
in
g
.
T
h
e
im
p
lem
en
ted
s
y
s
tem
is
f
o
r
s
in
g
le
u
s
er
at
a
m
o
m
en
t
ca
p
t
u
r
e
with
Me
d
iaPip
e
Fra
m
ewo
r
k
with
lo
g
is
tic
r
eg
r
ess
io
n
alg
o
r
ith
m
.
T
h
is
tech
n
o
lo
g
y
-
g
u
id
ed
h
u
m
an
m
o
v
em
en
t,
au
g
m
en
t
its
en
g
ag
e
an
d
m
a
k
e
it
m
o
r
e
e
n
jo
y
a
b
le.
T
h
is
wo
r
k
ca
n
b
e
ex
te
n
d
ed
to
s
u
p
p
o
r
t
m
an
y
u
s
er
s
s
im
u
ltan
eo
u
s
ly
,
en
ab
lin
g
g
r
o
u
p
wo
r
k
o
u
ts
o
r
co
m
p
etitiv
e
s
ce
n
ar
io
s
.
I
n
teg
r
atio
n
with
v
i
r
tu
al
r
ea
lity
o
r
th
e
p
o
s
s
ib
le
to
u
p
g
r
ad
e
th
e
e
n
d
u
s
er
ex
p
er
ie
n
ce
with
s
u
p
er
io
r
te
ch
n
o
lo
g
y
ca
lled
as
au
g
m
en
ted
r
ea
lity
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Lo
g
R
eg
r
ess
io
n
:
h
u
ma
n
a
ctio
n
p
a
tter
n
r
ec
o
g
n
itio
n
fo
r
yo
g
a
a
n
d
ka
va
ya
t fo
r
ch
ild
r
en
(
V
a
n
ita
B
a
b
a
n
n
e
)
2383
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT
)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Van
ita
B
ab
an
n
e
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Pan
k
aj
M.
Ag
ar
k
a
r
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
n
o
co
n
f
lict o
f
in
ter
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
u
s
ed
in
th
is
s
tu
d
y
ar
e
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
[
VB
]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
Owin
g
to
p
r
iv
ac
y
co
n
ce
r
n
s
an
d
eth
ical
o
b
lig
atio
n
s
,
th
e
d
ataset,
wh
ich
in
clu
d
es
p
ar
ticip
an
t
ex
er
cise
v
id
eo
s
an
d
p
o
s
e
f
r
am
e
ex
tr
ac
ti
o
n
s
,
is
n
o
t p
u
b
licly
ac
ce
s
s
ib
le.
RE
F
E
R
E
NC
E
S
[
1
]
P
.
W
i
l
l
i
a
m,
G
.
R
.
La
n
k
e
,
D
.
B
o
r
d
o
l
o
i
,
A
.
S
h
r
i
v
a
st
a
v
a
,
A
.
P
.
S
r
i
v
a
st
a
v
a
a
,
a
n
d
S
.
V
.
D
e
s
h
m
u
k
h
,
“
A
ss
e
ssm
e
n
t
o
f
h
u
ma
n
a
c
t
i
v
i
t
y
r
e
c
o
g
n
i
t
i
o
n
b
a
s
e
d
o
n
i
m
p
a
c
t
o
f
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
,
”
i
n
2
0
2
3
4
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
I
n
t
e
l
l
i
g
e
n
t
En
g
i
n
e
e
ri
n
g
a
n
d
Ma
n
a
g
e
m
e
n
t
(
I
C
I
E
M)
,
M
a
y
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
EM
5
9
3
7
9
.
2
0
2
3
.
1
0
1
6
6
2
4
7
.
[
2
]
S
.
W
a
h
e
e
d
,
R
.
A
m
i
n
,
J
.
I
q
b
a
l
,
M
.
H
u
ssa
i
n
,
a
n
d
M
.
A
.
B
a
s
h
i
r
,
“
A
n
a
u
t
o
m
a
t
e
d
h
u
m
a
n
a
c
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
r
a
mew
o
r
k
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
3
4
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
p
u
t
i
n
g
,
M
a
t
h
e
m
a
t
i
c
s
a
n
d
E
n
g
i
n
e
e
r
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
(
i
C
o
ME
T
)
,
M
a
r
.
2
0
2
3
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
i
C
o
M
ET
5
7
9
9
8
.
2
0
2
3
.
1
0
0
9
9
1
9
0
.
[
3
]
I
.
C
h
a
u
d
h
a
r
y
,
N
.
T.
S
i
n
g
h
,
M
.
C
h
a
u
d
h
a
r
y
,
a
n
d
K
.
Y
a
d
a
v
,
“
R
e
a
l
-
t
i
m
e
y
o
g
a
p
o
s
e
d
e
t
e
c
t
i
o
n
u
si
n
g
O
p
e
n
C
V
a
n
d
M
e
d
i
a
P
i
p
e
,
”
i
n
2
0
2
3
4
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
f
o
r E
m
e
rg
i
n
g
T
e
c
h
n
o
l
o
g
y
(
I
N
C
ET)
,
M
a
y
2
0
2
3
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
N
C
ET
5
7
9
7
2
.
2
0
2
3
.
1
0
1
7
0
4
8
5
.
[
4
]
R
.
G
e
r
a
,
K
.
R
.
A
m
b
a
t
i
,
P
.
C
h
a
k
o
l
e
,
N
.
C
h
e
g
g
o
j
u
,
V
.
K
a
m
b
l
e
,
a
n
d
V
.
R
.
S
a
t
p
u
t
e
,
“
C
l
a
ssi
f
y
i
n
g
h
u
m
a
n
a
c
t
i
v
i
t
i
e
s
u
s
i
n
g
C
N
N
a
n
d
C
o
n
v
LST
M
i
n
v
i
d
e
o
se
q
u
e
n
c
e
s
,
”
i
n
2
0
2
3
2
n
d
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
Pa
r
a
d
i
g
m
S
h
i
f
t
s
i
n
C
o
m
m
u
n
i
c
a
t
i
o
n
s
Em
b
e
d
d
e
d
S
y
s
t
e
m
s,
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
a
n
d
S
i
g
n
a
l
Pro
c
e
ss
i
n
g
(
PC
E
M
S
)
,
A
p
r
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
P
C
E
M
S
5
8
4
9
1
.
2
0
2
3
.
1
0
1
3
6
0
4
3
.
[
5
]
S
.
B
.
P
r
a
k
a
s
h
,
V
.
A
mu
d
h
a
,
a
n
d
N
.
M
e
e
n
a
k
s
h
i
su
n
d
a
r
a
m
,
“
Ef
f
i
c
i
e
n
t
h
u
m
a
n
a
c
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
n
o
v
e
l
l
o
g
i
s
t
i
c
r
e
g
r
e
ss
i
o
n
c
o
m
p
a
r
e
d
o
v
e
r
l
i
n
e
a
r
r
e
g
r
e
ssi
o
n
w
i
t
h
i
mp
r
o
v
e
d
a
c
c
u
r
a
c
y
,
”
i
n
2
0
2
3
E
i
g
h
t
h
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
S
c
i
e
n
c
e
T
e
c
h
n
o
l
o
g
y
En
g
i
n
e
e
ri
n
g
a
n
d
Ma
t
h
e
m
a
t
i
c
s (I
C
O
N
S
T
EM
)
,
A
p
r
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
N
S
TE
M
5
6
9
3
4
.
2
0
2
3
.
1
0
1
4
2
5
6
7
.
[
6
]
V
.
K
e
t
s
o
i
,
M
.
R
a
z
a
,
H
.
C
h
e
n
,
a
n
d
X
.
Y
a
n
g
,
“
A
sec
u
r
e
a
p
p
r
o
a
c
h
f
o
r
h
u
m
a
n
c
o
mp
u
t
e
r
i
n
t
e
r
a
c
t
i
o
n
u
si
n
g
h
u
m
a
n
h
a
n
d
a
c
t
i
o
n
,
”
i
n
2
0
2
2
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
n
S
y
s
t
e
m
s,
M
a
n
,
a
n
d
C
y
b
e
r
n
e
t
i
c
s
(
S
M
C
)
,
O
c
t
.
2
0
2
2
,
p
p
.
9
6
8
–
9
7
4
,
d
o
i
:
1
0
.
1
1
0
9
/
S
M
C
5
3
6
5
4
.
2
0
2
2
.
9
9
4
5
4
0
5
.
[
7
]
A
.
S
h
a
r
ma,
P
.
S
h
a
r
ma,
D
.
P
i
n
c
h
a
,
a
n
d
P
.
J
a
i
n
,
“
S
u
r
y
a
N
a
m
a
s
k
a
r
:
r
e
a
l
-
t
i
m
e
a
d
v
a
n
c
e
d
p
o
s
e
r
e
c
o
g
n
i
t
i
o
n
a
n
d
c
o
r
r
e
c
t
i
o
n
f
o
r
smar
t
h
e
a
l
t
h
c
a
r
e
,
”
2
0
2
2
,
a
r
Xi
v
:
2
2
0
9
.
0
2
4
9
2
.
[
8
]
M
.
Le
e
a
n
d
S
.
B
.
K
i
m,
“
S
e
n
s
o
r
-
b
a
s
e
d
o
p
e
n
-
se
t
h
u
ma
n
a
c
t
i
v
i
t
y
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
r
e
p
r
e
s
e
n
t
a
t
i
o
n
l
e
a
r
n
i
n
g
w
i
t
h
m
i
x
u
p
t
r
i
p
l
e
t
s
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
1
1
9
3
3
3
–
1
1
9
3
4
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
2
2
1
4
2
5
.
[
9
]
M.
-
F
.
Tsa
i
a
n
d
C
.
-
H
.
C
h
e
n
,
“
S
p
a
t
i
a
l
t
e
m
p
o
r
a
l
v
a
r
i
a
t
i
o
n
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
(
S
TV
-
G
C
N
)
f
o
r
s
k
e
l
e
t
o
n
-
b
a
se
d
e
mo
t
i
o
n
a
l
a
c
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
3
8
7
0
–
1
3
8
7
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
5
2
2
4
6
.
[
1
0
]
A
.
C
h
a
u
d
h
a
r
i
,
O
.
D
a
l
v
i
,
O
.
R
a
ma
d
e
,
a
n
d
D
.
A
m
b
a
w
a
d
e
,
“
Y
o
g
-
G
u
r
u
:
r
e
a
l
-
t
i
m
e
y
o
g
a
p
o
s
e
c
o
r
r
e
c
t
i
o
n
s
y
st
e
m
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
met
h
o
d
s,
”
i
n
2
0
2
1
I
n
t
e
rn
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
i
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
p
u
t
i
n
g
T
e
c
h
n
o
l
o
g
y
(
I
C
C
I
C
T
)
,
J
u
n
.
2
0
2
1
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
I
C
T5
0
8
0
3
.
2
0
2
1
.
9
5
0
9
9
3
7
.
[
1
1
]
J.
J
i
,
“
A
c
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
b
a
se
d
o
n
h
u
m
a
n
p
o
se
e
s
t
i
mat
i
o
n
,
”
i
n
2
0
2
1
2
n
d
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
C
o
m
p
u
t
i
n
g
a
n
d
D
a
t
a
S
c
i
e
n
c
e
(
C
D
S
)
,
J
a
n
.
2
0
2
1
,
p
p
.
7
3
–
7
8
,
d
o
i
:
1
0
.
1
1
0
9
/
C
D
S
5
2
0
7
2
.
2
0
2
1
.
0
0
0
1
9
.
[
1
2
]
J.
R
y
u
,
A
.
K
.
P
a
t
i
l
,
B
.
C
h
a
k
r
a
v
a
r
t
h
i
,
A
.
B
a
l
a
su
b
r
a
m
a
n
y
a
m,
S
.
P
a
r
k
,
a
n
d
Y
.
C
h
a
i
,
“
A
n
g
u
l
a
r
f
e
a
t
u
r
e
s
-
b
a
s
e
d
h
u
m
a
n
a
c
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
sy
s
t
e
m
f
o
r
a
r
e
a
l
a
p
p
l
i
c
a
t
i
o
n
w
i
t
h
su
b
t
l
e
u
n
i
t
a
c
t
i
o
n
s,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
9
6
4
5
–
9
6
5
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
4
4
4
5
6
.
[
1
3
]
H
.
R
.
P
a
t
e
l
a
n
d
J
.
T
.
D
o
s
h
i
,
“
H
u
man
a
c
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
i
n
d
a
r
k
v
i
d
e
o
s,
”
i
n
2
0
2
1
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
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
M
a
c
h
i
n
e
V
i
si
o
n
(
AI
MV
)
,
S
e
p
.
2
0
2
1
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
A
I
M
V
5
3
3
1
3
.
2
0
2
1
.
9
6
7
0
9
2
3
.
[
1
4
]
H
.
B
a
i
,
“
A
t
r
a
i
n
i
n
g
met
h
o
d
f
o
r
V
i
d
e
o
P
o
s
e
3
D
w
i
t
h
i
d
e
o
l
o
g
y
o
f
a
c
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
,
”
i
n
2
0
2
1
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
i
g
n
a
l
Pro
c
e
ssi
n
g
a
n
d
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
(
C
O
N
F
-
S
P
ML)
,
N
o
v
.
2
0
2
1
,
p
p
.
1
6
9
–
1
7
4
,
d
o
i
:
1
0
.
1
1
0
9
/
C
O
N
F
-
S
P
M
L5
4
0
9
5
.
2
0
2
1
.
0
0
0
4
1
.
[
1
5
]
A
.
S
.
-
C
a
b
a
l
l
e
r
o
,
D
.
F
.
-
Ji
mé
n
e
z
,
a
n
d
C
.
L.
-
G
u
t
i
é
r
r
e
z
,
“
R
e
a
l
-
t
i
m
e
h
u
man
a
c
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
r
a
w
d
e
p
t
h
v
i
d
e
o
-
b
a
se
d
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
2
,
n
o
.
1
1
,
p
p
.
1
6
2
1
3
–
1
6
2
3
5
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
022
-
1
4
0
7
5
-
5.
[
1
6
]
M
.
A
m
i
t
a
n
i
e
t
a
l
.
,
“
Th
e
e
f
f
e
c
t
o
f
mi
n
d
f
u
l
n
e
ss
y
o
g
a
i
n
c
h
i
l
d
r
e
n
w
i
t
h
sc
h
o
o
l
r
e
f
u
sa
l
:
a
s
t
u
d
y
p
r
o
t
o
c
o
l
f
o
r
a
n
e
x
p
l
o
r
a
t
o
r
y
,
c
l
u
st
e
r
-
r
a
n
d
o
m
i
z
e
d
,
o
p
e
n
,
st
a
n
d
a
r
d
c
a
r
e
-
c
o
n
t
r
o
l
l
e
d
,
m
u
l
t
i
c
e
n
t
e
r
c
l
i
n
i
c
a
l
t
r
i
a
l
,
”
F
ro
n
t
i
e
rs
i
n
Pu
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
1
0
,
n
o
.
1
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
u
b
h
.
2
0
2
2
.
8
8
1
3
0
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
3
7
7
-
2
3
8
4
2384
[
1
7
]
K
.
W
i
l
k
i
n
,
G
.
A
.
-
B
a
k
e
r
,
a
n
d
C
.
T
h
o
r
n
t
o
n
,
“
Th
e
e
f
f
e
c
t
s
o
f
sc
h
o
o
l
-
b
a
se
d
y
o
g
a
o
n
t
h
e
e
x
e
c
u
t
i
v
e
f
u
n
c
t
i
o
n
i
n
g
sk
i
l
l
s
o
f
c
h
i
l
d
r
e
n
b
e
t
w
e
e
n
t
h
r
e
e
a
n
d
se
v
e
n
y
e
a
r
s
o
f
a
g
e
.
A
met
a
-
a
n
a
l
y
s
i
s
o
f
e
x
i
s
t
i
n
g
r
e
se
a
r
c
h
,
”
Me
n
t
a
l
H
e
a
l
t
h
a
n
d
P
h
y
s
i
c
a
l
Ac
t
i
v
i
t
y
,
v
o
l
.
2
7
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
h
p
a
.
2
0
2
4
.
1
0
0
6
4
3
.
[
1
8
]
A
.
N
.
B
a
z
z
a
n
o
e
t
a
l
.
,
“
Ef
f
e
c
t
o
f
y
o
g
a
a
n
d
mi
n
d
f
u
l
n
e
ss
i
n
t
e
r
v
e
n
t
i
o
n
o
n
sy
m
p
t
o
ms
o
f
a
n
x
i
e
t
y
a
n
d
d
e
p
r
e
ss
i
o
n
i
n
y
o
u
n
g
a
d
o
l
e
sc
e
n
t
s
a
t
t
e
n
d
i
n
g
mi
d
d
l
e
s
c
h
o
o
l
:
a
p
r
a
g
ma
t
i
c
c
o
mm
u
n
i
t
y
-
b
a
se
d
c
l
u
s
t
e
r
r
a
n
d
o
mi
z
e
d
c
o
n
t
r
o
l
l
e
d
t
r
i
a
l
i
n
a
r
a
c
i
a
l
l
y
d
i
v
e
r
s
e
u
r
b
a
n
se
t
t
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
n
v
i
ro
n
m
e
n
t
a
l
Re
s
e
a
r
c
h
a
n
d
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
1
9
,
n
o
.
1
9
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
e
r
p
h
1
9
1
9
1
2
0
7
6
.
[
1
9
]
Y
.
Li
u
,
C
.
Q
i
u
,
a
n
d
Z
.
Z
h
a
n
g
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
3
D
h
u
ma
n
p
o
se
e
st
i
m
a
t
i
o
n
a
n
d
mes
h
r
e
c
o
v
e
r
y
:
a
su
r
v
e
y
,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
5
9
6
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
2
4
.
1
2
8
0
4
9
.
[
2
0
]
M
.
M
o
h
i
u
d
d
i
n
,
S
.
M
.
M
.
H
o
ssa
i
n
,
S
.
K
h
a
n
a
m,
P
.
B
a
r
u
a
,
A
.
B
a
r
u
a
,
a
n
d
M
.
T.
H
o
ssa
i
n
,
“
I
n
t
e
g
r
a
t
i
n
g
sk
e
l
e
t
o
n
b
a
s
e
d
r
e
p
r
e
s
e
n
t
a
t
i
o
n
s
f
o
r
r
o
b
u
s
t
y
o
g
a
p
o
s
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
,
”
2
0
2
5
,
a
rXi
v
:
2
5
1
2
.
0
0
5
7
2
.
[
2
1
]
M
.
S
h
a
h
,
K
.
G
a
n
d
h
i
,
B
.
M
.
P
a
n
d
h
i
,
P
.
P
a
d
h
i
y
a
r
,
a
n
d
S
.
D
e
g
a
d
w
a
l
a
,
“
C
o
mp
u
t
e
r
v
i
s
i
o
n
&
d
e
e
p
l
e
a
r
n
i
n
g
b
a
s
e
d
r
e
a
l
t
i
m
e
a
n
d
p
r
e
-
r
e
c
o
r
d
e
d
h
u
ma
n
p
o
se
e
s
t
i
mat
i
o
n
,
”
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
re
n
c
e
o
n
Ap
p
l
i
e
d
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
C
o
m
p
u
t
i
n
g
(
I
C
AAIC)
,
M
a
y
2
0
2
3
,
p
p
.
3
1
3
–
3
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
A
I
C
5
6
8
3
8
.
2
0
2
3
.
1
0
1
4
1
2
7
9
.
[
2
2
]
N
.
F
.
Ja
n
b
i
a
n
d
N
.
A
l
mu
a
y
t
h
i
r
,
“
B
o
w
l
i
n
g
D
L
:
a
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
b
o
w
l
i
n
g
p
l
a
y
e
r
s
p
o
s
e
e
s
t
i
m
a
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
1
st
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
d
I
n
n
o
v
a
t
i
o
n
s
i
n
S
m
a
rt
C
i
t
i
e
s
(
I
C
AI
S
C
)
,
J
a
n
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
I
S
C
5
6
3
6
6
.
2
0
2
3
.
1
0
0
8
5
4
3
4
.
[
2
3
]
B
.
J
.
J
o
a
n
d
S
.
K
.
K
i
m
,
“
C
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
o
f
O
p
e
n
P
o
s
e
,
P
o
seN
e
t
,
a
n
d
M
o
v
e
N
e
t
mo
d
e
l
s
f
o
r
p
o
se
e
s
t
i
mat
i
o
n
i
n
mo
b
i
l
e
d
e
v
i
c
e
s,
”
T
r
a
i
t
e
m
e
n
t
d
u
S
i
g
n
a
l
,
v
o
l
.
3
9
,
n
o
.
1
,
p
p
.
1
1
9
–
1
2
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
8
2
8
0
/
t
s.
3
9
0
1
1
1
.
[
2
4
]
D
.
S
w
a
i
n
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
f
o
r
y
o
g
a
p
o
s
e
mo
n
i
t
o
r
i
n
g
,
”
A
l
g
o
r
i
t
h
m
s
,
v
o
l
.
1
5
,
n
o
.
1
1
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
1
5
1
1
0
4
0
3
.
[
2
5
]
M
.
V
e
r
ma
,
S
.
K
u
maw
a
t
,
Y
.
N
a
k
a
sh
i
ma,
a
n
d
S
.
R
a
ma
n
,
“
Y
o
g
a
-
8
2
:
a
n
e
w
d
a
t
a
se
t
f
o
r
f
i
n
e
-
g
r
a
i
n
e
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
h
u
m
a
n
p
o
s
e
s,
”
i
n
2
0
2
0
I
EEE
/
C
VF
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
Wo
r
k
s
h
o
p
s
(
C
VP
RW
)
,
Ju
n
.
2
0
2
0
,
p
p
.
4
4
7
2
–
4
4
7
9
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
W
5
0
4
9
8
.
2
0
2
0
.
0
0
5
2
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Va
n
ita
Ba
b
a
n
n
e
p
u
rs
u
in
g
D
o
c
to
r
o
f
P
h
il
o
so
p
h
y
i
n
C
o
m
p
u
ter
En
g
i
n
e
e
rin
g
fr
o
m
P
u
n
e
Un
i
v
e
rsity
a
n
d
h
o
l
d
m
a
ste
rs
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
-
I
T
fr
o
m
P
u
n
e
Un
iv
e
rsity
i
n
2
0
1
3
with
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
En
g
in
e
e
rin
g
fro
m
Dr.
Ba
b
a
sa
h
e
b
Am
b
e
d
k
a
r
M
a
ra
th
wa
d
a
Un
iv
e
rs
it
y
,
Au
ra
n
g
a
b
a
d
in
2
0
0
5
.
S
h
e
is
c
u
rre
n
tl
y
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
a
t
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
in
P
u
n
e
,
P
u
n
e
Un
iv
e
rsity
.
He
r
re
se
a
rc
h
in
c
lu
d
e
s
m
a
c
h
in
e
lea
rn
in
g
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
a
n
d
d
a
ta
m
i
n
in
g
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
o
v
e
r
2
8
p
a
p
e
rs
i
n
in
tern
a
ti
o
n
a
l
j
o
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
F
ro
m
F
e
b
2
0
2
2
to
J
u
ly
2
0
0
7
,
sh
e
is
a
re
se
a
rc
h
sc
h
o
la
r
in
Vish
wa
k
a
rm
a
In
stit
u
te
o
f
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
,
P
u
n
e
,
I
n
d
ia.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
a
n
it
a
.
g
a
d
e
k
a
r@g
m
a
il
.
c
o
m
.
Dr
.
Pa
n
k
a
j
M
.
Ag
a
r
k
a
r
is
p
ro
fe
ss
o
r
in
Aje
e
n
k
y
a
D.Y.
P
a
ti
l
S
c
h
o
o
l
o
f
En
g
i
n
e
e
rin
g
,
Lo
h
e
g
a
o
n
P
u
n
e
.
He
re
c
e
iv
e
d
th
e
P
h
.
D.
d
e
g
re
e
fro
m
S
h
ri
Ja
g
d
ish
p
ra
sa
d
Jh
a
b
a
rm
a
l
Ti
b
re
wa
la
Un
iv
e
rsity
,
Ra
jas
tan
c
u
rre
n
tl
y
w
o
rk
i
n
g
a
s
a
H
o
D
in
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
o
n
th
e
Aj
e
e
n
k
y
a
D.Y.
P
a
ti
l
E
n
g
in
e
e
rin
g
,
L
o
h
e
g
a
o
n
,
P
u
n
e
.
He
h
a
s
t
o
tal
2
4
y
e
a
rs ex
p
e
rien
c
e
in
tea
c
h
in
g
a
s we
ll
a
s
m
o
re
th
a
n
1
0
+
y
e
a
rs o
f
e
x
p
e
rien
c
e
a
s a
d
m
in
istrativ
e
e
x
p
e
rien
c
e
a
s
h
e
a
d
o
f
d
e
p
a
rtme
n
t
.
His
re
se
a
rc
h
a
re
a
s
o
f
in
tere
st
i
n
c
lu
d
e
c
lo
u
d
c
o
m
p
u
ti
n
g
a
n
d
a
rti
ficia
l
in
telli
g
e
n
t
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
m
a
g
a
rk
a
r@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.