I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
5
,
Octo
b
e
r
2
0
1
9
,
p
p
.
3
4
6
5
~
3
4
7
3
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
9
i
5
.
p
p
3
4
6
5
-
3473
3465
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
A si
m
pl
ifi
ed
m
a
c
hine learning
app
ro
a
ch
for recog
ni
z
ing
h
u
m
a
n ac
tivity
A
b
du
l
L
a
t
e
e
f
H
a
r
o
o
n
P
.
S
,
U
.
E
r
a
nn
a
D
e
p
a
r
tm
e
n
t
o
f
E
le
c
t
r
o
n
i
c
s
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
E
n
g
i
n
e
e
r
i
n
g
,
B
a
l
la
r
i
I
n
s
t
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
a
n
d
M
a
n
a
g
e
m
e
n
t
,
I
n
d
i
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
a
n
31
,
2
0
1
9
R
ev
i
s
ed
A
p
r
7
,
2
0
1
9
A
cc
ep
ted
A
p
r
19
,
2
0
1
9
W
it
h
th
e
w
id
e
ra
n
g
e
s
o
f
re
a
l
-
ti
m
e
e
v
e
n
t
f
e
e
d
c
a
p
tu
rin
g
d
e
v
ice
s
,
th
e
re
h
a
s
b
e
e
n
sig
n
if
ica
n
t
p
ro
g
re
ss
in
th
e
a
re
a
o
f
d
ig
it
a
l
i
m
a
g
e
p
ro
c
e
ss
in
g
to
w
a
rd
s
a
c
ti
v
it
y
d
e
te
c
ti
o
n
a
n
d
re
c
o
g
n
it
i
o
n
.
Ir
re
sp
e
c
ti
v
e
o
f
th
e
p
re
se
n
c
e
o
f
v
a
rio
u
s
su
c
h
d
e
v
ice
s,
th
e
y
a
re
n
o
t
a
d
e
q
u
a
te
to
m
e
e
t
d
y
n
a
m
i
c
m
o
n
it
o
rin
g
d
e
m
a
n
d
s
o
f
th
e
v
isu
a
l
su
rv
e
il
lan
c
e
sy
ste
m
,
a
n
d
th
e
ir
f
e
a
tu
re
s
a
re
h
ig
h
ly
li
m
it
e
d
to
w
a
rd
s
c
o
m
p
lex
h
u
m
a
n
a
c
ti
v
it
y
re
c
o
g
n
it
io
n
sy
ste
m
.
Re
v
ie
w
o
f
e
x
isti
n
g
sy
s
t
e
m
c
o
n
f
irms
th
a
t
stil
l
th
e
re
is
a
l
a
rg
e
sc
o
p
e
o
f
e
n
h
a
n
c
e
m
e
n
t
a
s
th
e
y
lac
k
a
p
p
li
c
a
b
il
i
ty
to
re
a
l
-
li
f
e
e
v
e
n
ts
a
n
d
a
lso
d
o
e
sn
'
t
o
f
f
e
r
o
p
ti
m
a
l
s
y
ste
m
p
e
rf
o
r
m
a
n
c
e
.
T
h
e
re
f
o
re
,
th
e
p
r
o
p
o
se
d
m
a
n
u
sc
rip
t
p
re
se
n
ts
a
m
o
d
e
l
f
o
r
a
c
ti
v
it
y
r
e
c
o
g
n
it
io
n
sy
ste
m
w
h
e
r
e
th
e
a
c
c
u
ra
c
y
o
f
re
c
o
g
n
it
io
n
o
p
e
ra
ti
o
n
a
n
d
s
y
ste
m
p
e
rf
o
r
m
a
n
c
e
a
re
r
e
tain
e
d
w
it
h
g
o
o
d
b
a
lan
c
e
.
T
h
e
stu
d
y
p
re
se
n
ts
a
sim
p
li
f
ied
f
e
a
tu
re
e
x
trac
ti
o
n
p
ro
c
e
ss
f
ro
m
sp
a
ti
a
l
a
n
d
te
m
p
o
ra
l
traits
o
f
th
e
e
v
e
n
t
f
e
e
d
s
th
a
t
is
f
u
rth
e
r
s
u
b
jec
ted
to
th
e
m
a
c
h
in
e
lea
rn
in
g
m
e
c
h
a
n
is
m
f
o
r
b
o
o
st
in
g
re
c
o
g
n
it
i
o
n
p
e
rf
o
rm
a
n
c
e
.
K
ey
w
o
r
d
s
:
A
cti
v
it
y
r
ec
o
g
n
itio
n
C
las
s
i
f
icatio
n
Featu
r
e
e
x
tr
ac
tio
n
Hu
m
an
a
cti
v
it
y
Ma
ch
i
n
e
l
ea
r
n
i
n
g
Co
p
y
rig
h
t
©
2
0
1
9
I
n
stit
u
te o
f
Ad
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
A
b
d
u
l
L
at
e
ef
H
a
r
o
o
n
P.
S
,
D
e
p
a
r
tm
en
t
o
f
E
l
ec
t
r
o
n
i
c
s
a
n
d
C
o
m
m
u
n
i
c
a
ti
o
n
E
n
g
in
e
e
r
i
n
g
,
B
a
l
l
a
r
i
I
n
s
t
i
tu
te
o
f
T
e
ch
n
o
l
o
g
y
a
n
d
M
an
ag
em
en
t
,
K
a
r
n
at
ak
a
,
I
n
d
i
a
.
E
-
M
ai
l
:
a
b
d
u
l
b
i
tm
@
g
m
a
i
l
.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
W
ith
t
h
e
i
n
cr
ea
s
i
n
g
u
s
a
g
e
o
f
s
m
ar
t
ap
p
lian
ce
s
,
tr
ac
k
i
n
g
a
n
d
m
o
n
ito
r
i
n
g
o
p
er
atio
n
s
h
a
v
e
b
ec
o
m
e
q
u
ite
in
e
v
itab
le
in
al
m
o
s
t
all
th
e
p
er
v
asiv
e
d
ev
ice
s
[
1
,
2
]
.
On
e
s
u
c
h
o
p
er
atio
n
is
ca
lled
a
h
u
m
a
n
ac
tiv
it
y
r
ec
o
g
n
itio
n
s
y
s
te
m
w
h
ic
h
i
s
a
b
o
u
t
tr
ac
k
i
n
g
a
n
y
s
p
ec
i
f
ic
m
o
b
ilit
y
p
atter
n
[
3
]
.
A
d
if
f
er
e
n
t
ap
p
licatio
n
o
f
it
i
s
alr
ea
d
y
o
n
t
h
e
co
m
m
er
cial
m
ar
k
ets,
e.
g
.
h
ea
l
th
ca
r
e,
v
id
eo
s
u
r
v
eilla
n
ce
,
an
d
in
ter
ac
tio
n
b
et
w
ee
n
h
u
m
a
n
an
d
s
m
ar
t
ap
p
lia
n
ce
(
co
m
p
u
ti
n
g
s
y
s
te
m
)
[
4
]
.
W
ith
th
e
u
p
g
r
ad
atio
n
o
f
m
o
d
er
n
i
m
a
g
i
n
g
tech
n
o
lo
g
ies,
t
h
er
e
i
s
also
an
i
m
p
r
o
v
e
m
e
n
t
i
n
t
h
e
p
r
o
ce
s
s
o
f
ca
p
t
u
r
in
g
t
h
e
f
ee
d
o
f
h
u
m
an
-
b
ased
ac
ti
v
it
ies.
Ho
w
e
v
er
,
th
er
e
ar
e
v
ar
io
u
s
ch
alle
n
g
e
s
as
s
o
ciate
d
w
it
h
s
u
ch
ac
ti
v
it
y
r
ec
o
g
n
itio
n
s
y
s
te
m
e.
g
.
v
ar
iatio
n
s
o
f
i
n
tr
a
-
c
las
s
es
a
n
d
s
i
m
ilar
it
y
o
f
in
ter
-
c
lass
e
s
,
in
ter
ac
tio
n
o
f
m
u
ltip
le
s
u
b
j
ec
ts
,
b
ac
k
g
r
o
u
n
d
co
m
p
lex
i
t
y
,
g
r
o
u
p
ac
ti
v
it
y
,
etc
[
5
]
.
T
h
er
e
h
av
e
b
ee
n
v
ar
io
u
s
atte
m
p
ts
to
w
ar
d
s
u
s
ag
e
o
f
m
ac
h
in
e
lear
n
in
g
-
b
ased
ap
p
r
o
ac
h
f
o
r
s
o
lv
in
g
class
if
icatio
n
p
r
o
b
lem
s
in
ac
ti
v
it
y
-
r
ec
o
g
n
it
io
n
s
y
s
te
m
,
e.
g
.
n
eu
r
al
n
et
w
o
r
k
,
d
ee
p
lear
n
i
n
g
,
s
u
p
p
o
r
t v
ec
to
r
m
ac
h
i
n
e,
etc
[6
-
1
0
]
.
Ho
w
e
v
er
,
v
er
y
less
w
o
r
k
h
as
co
n
s
id
er
ed
ac
cu
r
ac
y
as
t
h
e
p
r
o
m
in
e
n
t
p
er
f
o
r
m
a
n
ce
p
ar
a
m
eter
s
.
A
p
ar
t
f
r
o
m
t
h
is
,
ac
cu
r
ac
y
i
n
t
h
e
ac
tiv
it
y
r
ec
o
g
n
itio
n
s
y
s
te
m
is
n
o
t
an
ea
s
y
tas
k
to
b
e
ac
co
m
p
lis
h
ed
as
v
ar
io
u
s
p
ar
am
eter
s
co
n
tr
o
l
ac
cu
r
ac
y
,
an
d
o
n
e
p
r
o
m
i
n
en
t
p
ar
a
m
eter
in
t
h
is
r
e
g
ar
d
is
t
h
e
p
o
te
n
t
ial
f
ea
t
u
r
e.
On
e
o
f
t
h
e
s
ig
n
i
f
ica
n
t
f
ac
to
r
s
t
h
at
ar
e
i
g
n
o
r
ed
i
n
t
h
e
m
aj
o
r
ity
o
f
t
h
e
e
x
is
t
in
g
ap
p
r
o
ac
h
es
is
a
s
s
o
ciate
d
w
it
h
t
h
e
id
en
ti
f
icatio
n
o
f
t
h
e
in
d
e
x
attr
ib
u
te
in
th
e
h
u
m
a
n
b
o
d
y
th
a
t
is
ass
o
ciate
d
w
it
h
m
o
b
ili
t
y
an
d
d
is
p
lace
m
en
t.
I
f
s
u
c
h
i
n
d
ex
attr
ib
u
te
s
ar
e
id
en
ti
f
ied
,
t
h
en
it
o
f
f
er
s
e
n
r
ich
ed
i
n
f
o
r
m
at
io
n
to
w
ar
d
s
f
ea
t
u
r
e
e
x
tr
ac
tio
n
.
T
h
e
co
n
v
en
tio
n
al
p
r
o
ce
s
s
o
f
ca
p
tu
r
in
g
h
u
m
an
m
o
b
ilit
y
ca
n
b
e
ca
r
r
i
ed
o
u
t
o
n
an
y
d
ev
ices;
h
o
w
e
v
er
,
all
p
r
o
b
lem
s
s
h
o
o
t
u
p
af
ter
t
h
e
f
ee
d
is
ca
p
tu
r
ed
o
w
in
g
to
th
e
p
r
esen
ce
o
f
v
ar
io
u
s
p
r
o
b
le
m
s
,
e.
g
.
illu
m
i
n
atio
n
,
v
ar
iab
ilit
y
,
d
y
n
a
m
ic
it
y
o
f
m
o
v
e
m
en
t,
etc.
Fi
g
.
1
d
is
cu
s
s
e
s
ab
o
u
t
d
if
f
er
en
t
lev
e
ls
o
f
h
u
m
a
n
ac
tiv
it
y
r
ec
o
g
n
itio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
5
,
Octo
b
er
2
0
1
9
:
3
4
6
5
-
3
4
7
3
3466
s
y
s
te
m
w
i
th
m
u
ltip
le
asp
ec
t
s
o
f
ap
p
licab
ilit
y
o
n
co
m
m
er
cial
ap
p
licatio
n
s
(
h
ea
lt
h
ca
r
e,
r
ec
o
g
n
itio
n
o
f
ab
n
o
r
m
a
l
ac
tiv
i
t
y
,
etc)
.
T
h
eo
r
etica
ll
y
,
th
er
e
ar
e
th
r
ee
w
a
y
s
o
f
ca
p
tu
r
in
g
th
e
h
u
m
a
n
ac
tiv
it
y
f
o
r
an
al
y
zi
n
g
t
h
eir
b
eh
av
io
r
i
n
t
h
e
f
o
r
m
o
f
a
n
e
v
e
n
t.
I
n
th
e
b
o
tto
m
le
v
el
o
f
h
u
m
an
ac
ti
v
it
y
,
t
h
e
y
ar
e
q
u
ite
ato
m
ic
a
n
d
co
m
p
le
x
i
n
th
e
f
o
r
m
o
f
m
o
b
ilit
y
tr
aits
.
T
h
e
s
ec
o
n
d
le
v
el
co
n
s
is
t
s
o
f
all
s
o
r
ts
o
f
ac
t
io
n
s
o
r
t
h
e
ac
ti
v
itie
s
ass
o
ciate
d
w
it
h
it.
T
h
e
th
ir
d
le
v
el
is
f
u
r
th
er
co
m
p
licated
o
n
e
as
it
co
n
s
is
t
s
o
f
m
u
ltip
le
s
u
b
j
ec
ts
to
b
e
tr
ac
k
ed
o
r
m
o
n
ito
r
ed
.
T
h
e
im
p
le
m
e
n
tatio
n
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
ca
r
r
ied
o
u
t
u
s
i
n
g
v
ar
io
u
s
a
ctio
n
p
r
i
m
iti
v
e
s
o
f
th
e
s
ig
n
i
f
ica
n
t
li
m
b
s
o
f
t
h
e
s
u
b
j
ec
ts
w
i
th
d
if
f
er
en
t
m
o
b
ili
t
y
co
n
d
itio
n
s
o
f
th
eir
li
m
b
s
.
T
h
e
an
al
y
s
is
o
f
th
e
o
u
tco
m
e
i
s
p
er
f
o
r
m
ed
o
n
t
h
e
b
asi
s
o
f
s
u
c
h
ato
m
ic
ac
t
io
n
s
f
o
cu
s
ed
o
n
s
p
ec
if
ic
li
m
b
-
b
ased
ac
tio
n
s
t
h
a
t
co
n
s
is
t
o
f
v
ar
io
u
s
s
p
atial
an
d
te
m
p
o
r
al
d
ata
ar
r
an
g
ed
i
n
s
eq
u
e
n
ce
.
s
e
g
m
e
n
t
a
t
i
o
n
E
x
t
r
a
c
t
i
n
g
F
e
a
t
u
r
e
R
e
p
r
e
s
e
n
t
i
n
g
F
e
a
u
r
e
A
c
t
i
v
i
t
y
D
e
t
e
c
t
i
o
n
&
R
e
c
o
g
n
i
t
i
o
n
A
c
t
i
v
i
t
y
r
e
c
o
g
n
i
t
i
o
n
o
f
s
i
n
g
l
e
p
e
r
s
o
n
I
n
t
e
r
a
c
t
i
o
n
o
f
M
u
l
t
i
p
l
e
p
e
r
s
o
n
&
C
r
o
w
d
B
e
h
a
v
i
o
u
r
R
e
c
o
g
n
i
t
i
o
n
o
f
A
b
n
o
r
m
a
l
A
c
t
i
v
i
t
y
S
u
r
v
e
i
l
l
a
n
c
e
E
n
v
i
r
o
n
m
e
n
t
E
n
t
e
r
t
a
i
n
m
e
n
t
E
n
v
i
r
o
n
m
e
n
t
H
e
a
l
t
h
c
a
r
e
S
y
s
t
e
m
L
o
w
t
o
h
i
g
h
L
e
v
e
l
Fig
u
r
e
1
.
L
ev
el
s
o
f
h
u
m
a
n
ac
ti
v
it
y
r
ec
o
g
n
i
tio
n
s
y
s
te
m
T
h
er
ef
o
r
e,
th
e
p
r
im
e
o
b
j
ec
tiv
e
o
f
th
e
p
r
o
p
o
s
ed
r
esear
ch
w
o
r
k
i
s
to
o
f
f
er
s
i
m
p
lifie
d
m
o
d
eli
n
g
o
f
h
u
m
a
n
ac
tiv
i
t
y
r
ec
o
g
n
itio
n
s
y
s
t
e
m
w
h
er
e
t
h
e
co
r
e
em
p
h
a
s
is
is
g
iv
e
n
to
th
e
f
ea
t
u
r
e
ex
t
r
ac
tio
n
p
r
o
ce
s
s
an
d
ac
cu
r
ac
y
.
E
x
is
tin
g
r
e
s
ea
r
ch
-
b
ased
s
o
lu
tio
n
s
to
w
ar
d
s
ac
ti
v
it
y
r
ec
o
g
n
itio
n
ar
e
b
r
ief
ed
in
S
ec
tio
n
2
f
o
llo
w
ed
b
y
h
ig
h
li
g
h
ti
n
g
o
f
t
h
e
r
e
s
ea
r
ch
p
r
o
b
lem
i
n
s
ec
tio
n
3
.
Sec
tio
n
4
i
n
tr
o
d
u
ce
s
ab
o
u
t
th
e
ad
o
p
ted
m
et
h
o
d
o
lo
g
y
f
o
llo
w
ed
b
y
s
ec
tio
n
5
d
is
c
u
s
s
i
n
g
th
e
al
g
o
r
ith
m
i
m
p
le
m
en
tat
io
n
.
Dis
c
u
s
s
io
n
o
f
r
e
s
u
l
ts
o
b
t
ain
ed
is
ca
r
r
ied
o
u
t
in
Sectio
n
6
w
h
ile
t
h
e
co
n
cl
u
s
io
n
is
b
r
ief
ed
in
Sectio
n
7
.
Ou
r
p
r
io
r
r
ev
ie
w
w
o
r
k
h
a
s
o
f
f
er
ed
a
b
r
ief
id
ea
ab
o
u
t
t
h
e
r
esear
ch
w
o
r
k
to
w
ar
d
s
a
n
ac
ti
v
it
y
r
ec
o
g
n
itio
n
s
y
s
te
m
[
1
1
]
.
T
h
e
n
e
u
r
al
n
e
t
w
o
r
k
w
a
s
also
ad
o
p
ted
b
y
C
h
e
n
et
al.
[
1
2
]
f
o
r
ex
tr
ac
ti
n
g
m
o
r
e
in
f
o
r
m
atio
n
f
r
o
m
th
e
e
v
en
t
c
alled
as
k
n
o
w
led
g
e
d
is
til
latio
n
.
Ho
w
e
v
er
,
it
h
as
b
ee
n
s
ee
n
th
at
d
ataset
o
f
f
er
s
i
m
p
o
r
tan
ce
to
w
a
r
d
s
r
ec
o
g
n
it
io
n
s
y
s
te
m
.
A
d
o
p
tio
n
o
f
th
e
s
e
n
s
o
r
y
d
ataset
is
f
o
u
n
d
m
o
r
e
f
r
eq
u
en
t (
Fra
n
co
et
a
l.
[
1
3
]
)
.
P
lo
tz
an
d
Gu
an
[
1
4
]
h
a
v
e
d
is
c
u
s
s
ed
t
h
e
s
i
g
n
i
f
ican
ce
o
f
d
ee
p
lear
n
i
n
g
f
o
r
ac
ti
v
it
y
r
ec
o
g
n
itio
n
s
y
s
te
m
ass
o
ciate
d
w
it
h
t
h
e
m
o
b
ile
co
m
p
u
ti
n
g
s
y
s
te
m
.
T
h
e
m
o
s
t
r
ec
en
t
w
o
r
k
o
f
C
h
e
n
et
al.
[
1
5
]
h
as
u
s
ed
co
n
v
o
l
u
tio
n
n
eu
r
al
n
et
w
o
r
k
co
n
s
id
er
in
g
t
h
e
d
is
ta
n
ce
b
et
w
ee
n
j
o
in
t
s
o
f
in
ter
-
f
r
a
m
e
s
f
o
r
p
er
f
o
r
m
i
n
g
ac
tiv
it
y
r
ec
o
g
n
itio
n
s
y
s
te
m
o
v
er
t
h
e
n
e
w
d
ata
s
et.
T
h
er
e
ar
e
also
g
o
o
d
n
u
m
b
er
s
o
f
r
esear
c
h
w
h
er
e
r
ec
o
g
n
iti
o
n
o
f
g
est
u
r
e
an
d
ac
tiv
it
y
is
ca
p
tu
r
ed
f
r
o
m
Ki
n
ec
t
(
Gav
r
ilo
v
a
et
al.
[
1
6
]
)
.
T
h
e
w
o
r
k
o
f
He
g
d
e
et
al.
[
1
7
]
h
as
p
r
esen
ted
an
in
v
o
l
u
n
tar
y
m
ec
h
an
i
s
m
o
f
d
a
il
y
ac
ti
v
it
y
r
ec
o
g
n
itio
n
u
s
i
n
g
s
en
s
o
r
y
d
ata.
Kh
a
n
et
al.
[
1
8
]
h
av
e
p
r
esen
ted
a
co
r
r
elatio
n
al
f
ac
to
r
as a
f
ea
t
u
r
e
f
r
o
m
th
e
ac
t
iv
i
t
y
d
ataset
ca
p
tu
r
ed
u
s
i
n
g
s
e
n
s
o
r
s
u
s
i
n
g
b
o
d
y
ar
ea
n
et
w
o
r
k
.
Kh
ali
f
a
et
a
l.
[
1
9
]
h
av
e
i
n
tr
o
d
u
ce
d
a
u
n
iq
u
e
s
t
u
d
y
w
h
er
e
r
ec
o
g
n
itio
n
is
ca
r
r
ied
o
u
t
f
r
o
m
e
n
er
g
y
h
ar
v
e
s
tin
g
d
ata.
Si
m
ilar
li
n
e
o
f
r
esear
ch
is
al
s
o
ca
r
r
ied
o
u
t
b
y
Hs
u
et
al.
[
2
0
]
w
h
er
e
p
r
in
cip
al
co
m
p
o
n
e
n
t
an
al
y
s
is
i
s
u
s
ed
f
o
r
d
i
m
e
n
s
io
n
al
r
ed
u
ctio
n
Usag
e
o
f
Hid
d
en
Ma
r
k
o
v
Mo
d
el
h
as
b
ee
n
u
s
ed
f
o
r
co
n
s
tr
u
cti
n
g
a
f
r
a
m
e
w
o
r
k
f
o
r
ac
tiv
it
y
r
ec
o
g
n
itio
n
as
s
ee
n
i
n
w
o
r
k
o
f
L
i
et
al.
[
2
1
]
alo
n
g
w
it
h
u
s
a
g
e
o
f
k
-
m
ea
n
s
clu
s
ter
in
g
f
o
r
f
ea
t
u
r
e
e
x
tr
ac
tio
n
.
Hid
d
en
Ma
r
k
o
v
m
o
d
el
an
d
s
u
p
er
v
is
ed
class
i
f
icatio
n
tec
h
n
iq
u
e
ar
e
also
r
ep
o
r
ted
to
b
e
u
s
ed
i
n
t
h
e
ac
ti
v
it
y
r
ec
o
g
n
iti
o
n
s
y
s
te
m
(
So
k
e
t
al.
[
2
2
]
)
.
R
ec
o
g
n
itio
n
s
y
s
te
m
o
v
er
o
n
l
in
e
d
ata
h
a
s
b
ee
n
r
ep
o
r
ted
b
y
Qi
et
al.
[
2
3
]
co
n
s
id
er
in
g
t
h
e
d
ict
io
n
ar
y
lear
n
i
n
g
m
ec
h
an
is
m
.
I
t
w
a
s
al
s
o
r
ep
o
r
ted
in
t
h
e
e
x
i
s
ti
n
g
s
y
s
te
m
th
at
in
-
d
ep
th
lear
n
i
n
g
-
b
ased
tr
ain
i
n
g
ap
p
r
o
ac
h
co
u
ld
b
e
u
s
ed
f
o
r
i
m
a
g
e
-
b
ased
a
ctiv
it
y
r
ec
o
g
n
itio
n
s
y
s
te
m
(
W
an
g
et
al.
[
2
4
]
an
d
T
an
et
al.
[
2
5
]
)
.
Usag
e
o
f
t
h
e
n
et
w
o
r
k
,
e.
g
.
,
W
iFi
s
i
g
n
a
l
a
n
d
r
ad
io
-
f
r
eq
u
e
n
cie
s
w
er
e
also
r
ep
o
r
ted
to
b
e
u
s
ed
in
h
u
m
a
n
ac
ti
v
it
y
r
ec
o
g
n
it
io
n
W
an
g
et
al.
[
2
6
]
,
W
en
y
u
an
et
al.
[
2
7
]
A
ctiv
it
y
r
ec
o
g
n
itio
n
o
n
th
e
b
asi
s
o
f
s
m
ar
t
-
b
ased
d
ata
ar
e
d
is
cu
s
s
ed
b
y
W
an
g
et
al.
[
2
8
]
.
Oth
er
u
n
iq
u
e
r
esear
c
h
i
m
p
le
m
en
ta
tio
n
s
ar
e
also
w
it
n
es
s
ed
in
w
o
r
k
o
f
Yao
et
al
.
[
2
9
]
Yan
g
et
al.
[
3
0
]
an
d
a
u
n
iq
u
e
r
ec
u
r
r
en
t
m
o
d
eli
n
g
is
p
r
esen
ted
u
s
i
n
g
d
ilatio
n
o
p
er
atio
n
f
o
r
ac
tiv
it
y
r
ec
o
g
n
it
io
n
s
y
s
te
m
(
Xi
et
al.
[
3
1
]
)
.
T
h
e
n
ex
t
s
ec
tio
n
d
is
c
u
s
s
es t
h
e
r
esear
ch
p
r
o
b
lem
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
s
imp
lifi
ed
ma
ch
in
e
lea
r
n
in
g
a
p
p
r
o
a
c
h
fo
r
r
ec
o
g
n
iz
in
g
h
u
ma
n
a
ctivity
(
A
b
d
u
l La
teef
Ha
r
o
o
n
P
.
S
)
3467
Af
ter
r
ev
ie
w
in
g
t
h
e
e
x
is
t
in
g
m
ec
h
a
n
i
s
m
ass
o
ciate
d
w
i
t
h
a
n
ac
ti
v
it
y
r
ec
o
g
n
itio
n
s
y
s
te
m
,
it
is
f
o
u
n
d
th
at
th
er
e
is
v
er
y
le
s
s
w
o
r
k
b
ein
g
ca
r
r
ied
o
u
t
to
w
ar
d
s
ad
d
r
ess
in
g
th
e
co
n
v
en
tio
n
al
ch
a
llen
g
es
ass
o
ciate
d
w
it
h
it.
T
h
e
ap
p
r
o
ac
h
es
ar
e
n
o
t
r
ep
o
r
ted
to
m
iti
g
ate
t
h
e
p
r
o
b
le
m
s
o
f
v
ar
iatio
n
o
f
w
i
th
i
n
c
lass
e
s
,
clu
tter
e
x
i
s
ti
n
g
in
th
e
b
ac
k
g
r
o
u
n
d
,
o
cc
lu
s
io
n
,
a
n
d
co
n
d
itio
n
o
f
ill
u
m
i
n
atio
n
a
n
d
p
o
s
es o
f
t
h
e
s
u
b
j
ec
t (
h
u
m
an
)
.
A
clo
s
er
lo
o
k
in
to
th
e
e
x
is
ti
n
g
ap
p
r
o
ac
h
es
w
ill
s
h
o
w
t
h
at
t
h
e
m
aj
o
r
ity
o
f
t
h
e
ex
is
t
in
g
r
esear
c
h
ap
p
r
o
ac
h
es
to
w
ar
d
s
ac
tiv
it
y
r
ec
o
g
n
itio
n
s
y
s
te
m
is
ca
r
r
ie
d
o
u
t o
v
er
s
e
n
s
o
r
y
d
ata
an
d
n
o
t
m
u
ch
o
n
i
m
a
g
es.
A
l
th
o
u
g
h
,
t
h
is
m
ec
h
a
n
i
s
m
o
f
f
er
s
s
i
m
p
li
f
ied
ap
p
r
o
ac
h
es
th
e
y
w
e
r
e
n
ev
er
ac
ce
s
s
ed
f
o
r
th
eir
ac
c
u
r
ac
y
r
ate.
A
p
ar
t
f
r
o
m
t
h
i
s
,
th
e
test
en
v
ir
o
n
m
e
n
t
is
o
n
l
y
r
estricte
d
to
th
e
s
tatic
d
ataset
o
f
ac
ti
v
it
y
r
ec
o
g
n
itio
n
,
an
d
n
o
m
u
c
h
a
n
al
y
s
i
s
h
as
b
ee
n
ca
r
r
ied
o
u
t
f
o
r
o
n
lin
e
d
y
n
a
m
ic
r
ea
l
-
ti
m
e
f
ee
d
s
o
f
ev
e
n
ts
.
Ho
w
e
v
er
,
s
u
c
h
ap
p
r
o
ac
h
es
ar
e
n
ev
er
ab
le
ev
en
to
id
e
n
ti
f
y
t
h
e
p
r
o
b
lem
atic
f
ac
t
t
h
at
a
m
al
g
a
m
atio
n
o
f
v
ar
io
u
s
ac
tio
n
-
b
ased
f
ea
t
u
r
es
i
s
n
e
v
er
s
u
f
f
i
cien
t
to
o
b
tain
t
h
e
v
ar
ia
tio
n
s
ass
o
ciate
d
w
ith
t
h
e
i
m
ag
e
s
as
w
el
l
as
d
iv
er
s
e
attr
ib
u
tes
co
n
n
ec
ted
to
it,
e.
g
.
,
m
o
tio
n
,
s
h
ap
e,
ap
p
ea
r
an
ce
,
etc.
T
h
e
u
s
ag
e
o
f
th
e
n
eu
r
al
n
et
wo
r
k
is
to
o
m
u
c
h
ab
u
n
d
an
t
an
d
n
o
t
m
u
c
h
f
le
x
ib
ilit
y
is
o
f
f
er
e
d
to
w
ar
d
s
class
i
f
icatio
n
p
r
o
b
le
m
s
as
s
o
ci
ated
w
ith
t
h
e
h
u
m
a
n
ac
ti
v
itie
s
.
T
h
er
ef
o
r
e,
th
e
clas
s
i
f
y
in
g
t
h
e
r
ea
l
-
ti
m
e
f
ee
d
i
s
o
n
e
ch
alle
n
g
i
n
g
asp
ec
t
in
ac
ti
v
it
y
r
ec
o
g
n
it
io
n
.
I
n
o
r
d
er
to
in
co
r
p
o
r
ate
a
b
etter
f
o
r
m
o
f
ac
c
u
r
ac
y
,
it
is
r
eq
u
ir
ed
th
at
th
e
f
r
a
m
e
w
o
r
k
o
f
th
e
ac
ti
v
it
y
r
ec
o
g
n
it
io
n
s
y
s
te
m
s
h
o
u
l
d
ca
r
r
y
o
u
t
an
ef
f
ec
ti
v
e
ex
tr
ac
tio
n
o
f
th
e
f
ea
tu
r
e
,
p
r
ec
is
e
r
ep
r
esen
tatio
n
o
f
f
ea
tu
r
e
f
o
llo
w
ed
b
y
clas
s
i
f
icati
o
n
o
f
t
h
e
p
att
er
n
.
T
h
e
p
r
o
p
o
s
ed
w
o
r
k
ca
p
t
u
r
es
th
e
r
ea
l
-
ti
m
e
f
ee
d
o
f
t
h
e
s
u
b
j
ec
t
in
o
r
d
er
to
o
b
tain
t
h
e
d
ep
th
i
n
f
o
r
m
atio
n
.
Ho
w
e
v
er
,
s
u
c
h
f
o
r
m
o
f
r
ea
l
-
ti
m
e
ca
p
t
u
r
es
w
il
l
b
e
as
s
o
ciate
d
w
i
th
n
o
is
es
to
o
th
a
t
ca
n
ad
v
er
s
e
l
y
a
f
f
ec
t
t
h
e
p
r
ec
is
io
n
o
f
r
ec
o
g
n
i
tio
n
.
T
h
er
ef
o
r
e,
th
e
i
n
itia
l
s
tep
in
cl
u
d
es
th
e
e
li
m
i
n
atio
n
o
f
al
l
f
o
r
m
s
o
f
o
u
tlie
r
s
as
w
e
ll
as
m
is
s
in
g
d
ata.
T
h
e
p
r
o
p
o
s
ed
w
o
r
k
is
an
e
x
ten
s
io
n
o
f
o
u
r
p
r
io
r
w
o
r
k
[
3
2
]
to
w
ar
d
s
a
n
ac
ti
v
i
t
y
r
ec
o
g
n
itio
n
s
y
s
te
m
w
h
er
e
th
e
c
u
r
r
en
t
w
o
r
k
co
m
p
lete
l
y
e
m
p
h
asize
s
i
m
p
r
o
v
in
g
th
e
ac
c
u
r
ac
y
o
f
th
e
id
en
t
if
ied
ac
ti
v
it
y
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
id
e
n
ti
f
ies
all
th
e
ac
ti
v
itie
s
o
n
th
e
b
asis
o
f
th
e
li
m
b
m
o
v
e
m
e
n
t
o
f
t
h
e
h
u
m
a
n
b
o
d
y
,
an
d
h
e
n
ce
b
ett
er
a
cc
u
r
ac
y
ca
n
b
e
m
ai
n
tai
n
ed
.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
h
y
p
o
th
e
s
izes
th
at
if
t
h
e
s
i
g
n
i
f
ica
n
t
li
m
b
m
o
v
e
m
e
n
ts
ca
n
b
e
id
en
ti
f
ied
an
d
r
ec
o
g
n
ized
t
h
at
an
y
f
o
r
m
o
f
ap
p
licatio
n
-
o
r
ie
n
ted
h
u
m
an
ac
ti
v
it
y
ca
n
b
e
d
ev
elo
p
ed
co
m
m
er
ciall
y
.
Fig
u
r
e
2
h
i
g
h
lig
h
t
s
th
e
m
ec
h
a
n
i
s
m
o
f
ta
k
i
n
g
th
e
e
v
e
n
t
f
ee
d
as
an
in
p
u
t
w
h
ich
u
n
d
er
g
o
es
a
n
ex
tr
ac
tio
n
p
r
o
ce
s
s
o
f
its
in
d
e
x
p
o
in
ts
o
f
m
o
b
ilit
y
alo
n
g
w
i
th
d
ep
th
m
ap
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
m
a
k
es
u
s
e
o
f
s
eq
u
en
tial
r
elati
v
e
j
o
in
t
an
g
le
ex
is
ti
n
g
b
et
w
ee
n
t
w
o
v
ar
ied
s
k
eleta
l
p
o
in
ts
i
n
o
r
d
er
to
c
o
n
s
tr
u
ct
a
m
atr
ix
f
o
r
r
etain
i
n
g
a
s
p
ec
if
ic
m
o
b
ilit
y
p
atter
n
o
f
t
h
e
s
u
b
j
ec
t.
T
h
is
i
n
f
o
r
m
atio
n
o
f
s
p
ec
i
f
ic
s
u
b
j
ec
t
f
u
r
t
h
er
as
s
is
t
s
i
n
r
ec
o
g
n
itio
n
o
f
t
h
e
ac
ti
v
it
y
o
n
ce
t
h
e
m
atr
i
x
i
s
s
u
b
j
ec
ted
f
o
r
tr
ain
i
n
g
.
A
ll
t
h
e
s
ig
n
i
f
ic
an
t
m
o
b
ilit
y
p
o
in
t
s
ass
o
ciate
d
w
it
h
t
h
e
s
u
b
j
ec
t
is
r
etain
ed
i
n
a
m
atr
ix
f
r
o
m
w
h
er
e
te
m
p
o
r
al
an
d
s
p
atial
in
f
o
r
m
a
tio
n
h
a
s
b
ee
n
u
s
e
d
f
o
r
ex
tr
ac
ti
n
g
f
ea
t
u
r
es.
T
h
e
ex
tr
ac
ted
f
ea
tu
r
e
s
ar
e
th
e
n
s
u
b
j
ec
ted
to
th
e
m
ac
h
i
n
e
lear
n
in
g
m
ec
h
a
n
i
s
m
in
o
r
d
er
to
p
er
f
o
r
m
ac
ti
v
it
y
cla
s
s
i
f
icati
o
n
.
A
d
o
p
tio
n
o
f
m
ac
h
i
n
e
lear
n
in
g
m
ec
h
an
i
s
m
as
s
is
t
s
i
n
th
e
s
elec
tio
n
o
f
m
o
s
t
r
elev
an
t
s
eq
u
en
ce
s
o
f
a
r
elativ
e
j
o
in
t
an
g
le
o
b
tain
ed
f
r
o
m
tr
ain
i
n
g
as
w
e
ll
as
test
i
n
g
d
ata
s
a
m
p
le
f
o
r
class
i
f
icatio
n
o
f
t
h
e
ac
tiv
it
y
.
T
h
e
n
e
x
t sect
io
n
w
ill d
is
c
u
s
s
t
h
e
alg
o
r
ith
m
i
m
p
le
m
e
n
ted
f
o
r
t
h
is
p
u
r
p
o
s
e.
M
o
b
i
l
i
t
y
i
n
d
e
x
p
o
i
n
t
D
e
p
t
h
M
a
p
S
e
l
e
c
t
S
i
g
n
i
f
i
c
a
n
t
M
o
b
i
l
i
t
y
P
o
i
n
t
s
F
e
a
t
u
r
e
E
x
t
r
a
c
t
i
o
n
à
A
p
p
l
y
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
M
e
t
h
o
d
D
e
t
e
r
m
i
n
e
S
p
a
t
i
a
l
V
e
r
i
f
i
c
a
t
i
o
n
D
e
t
e
r
m
i
n
e
T
e
m
p
o
r
a
l
V
e
r
i
f
i
c
a
t
i
o
n
P
e
r
f
o
r
m
A
c
t
i
v
i
t
y
C
l
a
s
s
i
f
i
c
a
t
i
o
n
E
v
e
n
t
F
e
e
d
s
(
O
f
f
l
i
n
e
/
O
n
l
i
n
e
)
Fig
u
r
e
2
.
Sch
e
m
atic
ar
ch
itec
tu
r
e
o
f
p
r
o
p
o
s
ed
s
y
s
te
m
2.
AL
G
O
RI
T
H
M
I
M
P
L
E
M
E
NT
A
T
I
O
N
T
h
e
d
ev
elo
p
m
e
n
t
o
f
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
in
i
tiates
w
i
th
t
h
e
r
ep
r
esen
tatio
n
o
f
th
e
h
u
m
a
n
ac
tiv
it
y
,
an
d
th
er
ef
o
r
e
th
e
f
ir
s
t
s
tep
is
to
c
o
n
s
tr
u
ct
a
m
atr
i
x
f
o
r
e
x
tr
ac
tio
n
p
o
ten
tia
l
f
ea
t
u
r
es.
T
h
is
w
ill
e
n
ab
le
t
h
e
r
eten
tio
n
o
f
m
a
x
i
m
u
m
ac
c
u
r
ac
y
as
w
ell
as
o
p
ti
m
ize
t
h
e
s
p
ac
e
f
o
r
co
m
p
u
tatio
n
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
m
ak
e
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
5
,
Octo
b
er
2
0
1
9
:
3
4
6
5
-
3
4
7
3
3468
u
s
e
o
f
t
w
o
f
o
r
m
s
o
f
f
ea
t
u
r
e
f
o
r
d
ir
ec
tly
r
ep
r
esen
tin
g
t
h
e
s
ig
n
i
f
ican
t
ac
tiv
it
y
v
i
z.
s
p
at
ia
l
-
b
a
s
ed
f
ea
t
u
r
es
ρ
1
a
n
d
te
m
p
o
r
al
-
b
ased
f
ea
t
u
r
es
ρ
2
.
Usi
n
g
t
h
e
f
r
a
m
e
w
o
r
k
o
f
o
u
r
p
r
io
r
w
o
r
k
[
3
2
]
,
th
e
n
o
r
m
a
l
izatio
n
o
f
t
h
e
j
o
in
t
co
o
r
d
in
ates
is
ca
r
r
ied
o
u
t
f
r
o
m
th
e
r
ea
l
-
ti
m
e
f
ee
d
s
o
f
t
h
e
s
u
b
j
ec
ts
(
h
u
m
a
n
)
f
o
r
ca
p
tu
r
in
g
t
h
e
ev
e
n
t
s
.
T
h
e
r
ef
er
en
tial
p
o
in
t
o
f
t
h
e
co
o
r
d
in
ate
s
y
s
te
m
ca
n
b
e
o
b
tain
ed
b
y
a
v
er
ag
in
g
t
h
e
th
r
ee
-
d
i
m
e
n
s
io
n
al
co
o
r
d
in
ates
co
r
r
esp
o
n
d
in
g
to
ce
n
ter
,
le
f
t,
an
d
r
i
g
h
t
s
id
e
o
f
t
h
e
s
u
b
j
ec
t.
T
h
e
f
ir
s
t
al
g
o
r
ith
m
i
s
r
esp
o
n
s
ib
le
f
o
r
r
ec
o
r
d
in
g
th
e
ev
e
n
t a
s
f
o
llo
w
s
:
Alg
o
rit
h
m
f
o
r
Rec
o
rding
t
he
L
iv
e
E
v
en
t
I
np
ut
:
P
na
m
e
(
P
er
s
o
n
Na
m
e)
,
S
ID
(
Sa
m
p
le
I
D)
,
S
db
(
s
tr
u
ctu
r
e)
O
utput
:
E
(
E
v
en
t)
Sta
rt
1
.
in
itP
nam
e
, S
ID
, S
db
,
2
.
F
o
r
i=1
: n
n
r
ep
r
esen
ts
th
e
l
ast f
r
a
m
e
3
.
(
I
col,
I
dep
)
à
g
(
v
id
1
,
v
id
2
)
4
.
(
ix
,
C
o
, C
o2
)
à
m
data
.
(
w
1
,
w
2
,
w
3
)
5
.
S=C
o
(
ix
)
,
S
2
=C
o2
(
ix
)
6
.
If
(
ix
>0
)
7
.
Z
v
al
à
S
2
8
.
If
z
v
al
<r
s
&
&
z
v
al
>r
e
9
.
E
à
ca
p
tu
r
e
(
S
,
s
u
m
(
ix
));
1
0
.
E
nd
1
1
.
E
nd
1
2
.
E
nd
E
nd
T
h
is
alg
o
r
it
h
m
is
r
esp
o
n
s
ib
le
f
o
r
ca
p
tu
r
i
n
g
t
h
e
li
v
e
e
v
en
t
s
t
h
at
h
av
e
a
s
er
ie
s
o
f
h
u
m
a
n
ac
ti
v
it
y
.
I
n
o
r
d
er
to
n
ar
r
o
w
d
o
w
n
t
h
e
an
al
y
s
is
,
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
p
er
f
o
r
m
s
a
s
elec
tio
n
o
f
a
h
u
m
a
n
s
u
b
j
ec
t
an
d
r
ep
r
esen
ts
t
h
e
m
w
it
h
r
esp
ec
t
to
t
w
o
v
ar
iab
les
v
iz.
P
na
m
e
(
P
er
s
o
n
n
a
m
e)
a
n
d
S
ID
(
Sa
m
p
le
I
D)
(
L
in
e
-
1
)
.
T
h
e
r
ea
l
-
ti
m
e
f
ee
d
o
f
t
h
e
ev
en
t
i
s
ca
p
tu
r
ed
w
i
th
r
esp
ec
t
to
th
e
co
lo
r
im
a
g
e
a
n
d
d
ep
th
i
m
a
g
e
th
at
ar
e
r
ep
r
esen
ted
as v
ar
iab
les
v
id
1
a
n
d
v
id
2
r
esp
ec
ti
v
el
y
(
L
in
e
-
3
)
.
A
f
u
n
c
tio
n
g
(
x
)
i
s
cr
ea
ted
to
tak
e
t
h
e
f
ee
d
o
f
b
o
t
h
th
e
r
ea
l
-
ti
m
e
e
v
en
ts
o
f
t
h
e
h
u
m
an
s
u
b
j
ec
t
an
d
s
to
r
e
it
in
t
wo
d
is
cr
ete
m
atr
ice
s
o
f
i
m
a
g
e
co
lo
r
I
col
an
d
i
m
a
g
e
d
ep
th
I
dep
(
L
i
n
e
-
3
)
.
I
n
o
r
d
er
to
o
f
f
er
m
o
r
e
g
r
a
n
u
lar
it
y
in
th
e
ap
p
r
o
ac
h
,
th
e
o
b
j
ec
t a
s
s
o
ciate
d
w
it
h
v
id
1
i
s
s
to
r
ed
in
I
co
l,
b
u
t
th
e
o
b
j
ec
t
ass
o
cia
ted
w
i
th
v
id
2
i
s
s
to
r
ed
in
t
h
r
e
e
d
if
f
er
en
t
m
atr
ice
s
,
i.e
.
,
i
m
a
g
e
d
ep
th
,
m
etad
ata
d
ep
t
h
,
an
d
te
m
p
o
r
al
-
s
p
atial
d
ep
th
.
A
tr
ac
k
er
v
ar
iab
le
ix
is
co
n
s
tr
u
c
ted
th
at
i
s
r
esp
o
n
s
i
b
le
f
o
r
tr
ac
in
g
S
ID
(
L
in
e
-
4
)
w
h
ile
a
m
atr
ic
C
o
a
n
d
C
o2
ar
e
d
ev
elo
p
ed
f
o
r
s
to
r
in
g
t
h
e
t
w
o
-
an
d
th
r
ee
-
d
i
m
e
n
s
io
n
al
co
o
r
d
in
ates
r
esp
ec
tiv
el
y
.
T
h
er
e
f
o
r
e,
th
e
v
ar
iab
le
S
an
d
S
2
is
a
r
ep
r
esen
tat
io
n
o
f
th
e
p
r
o
c
ess
ed
m
atr
i
x
o
f
tr
ac
k
er
ix
(
L
i
n
e
-
5
)
.
I
n
ca
s
e
t
h
er
e
ar
e
p
o
s
itiv
e
n
u
m
b
er
s
o
f
th
e
tr
ac
k
er
/
in
d
ex
er
o
f
t
h
e
ev
e
n
t
s
(
L
i
n
e
-
6
)
,
th
en
a
n
e
w
m
atr
ix
z
v
al
is
co
n
s
tr
u
cted
f
o
r
ca
p
tu
r
i
n
g
all
th
e
ev
e
n
t
r
elate
d
in
f
o
r
m
atio
n
in
th
e
f
o
r
m
o
f
S
an
d
s
u
m
o
f
all
th
e
tr
ac
k
er
v
ar
iab
l
e
ix
(
L
in
e
-
9
)
.
T
h
e
alg
o
r
ith
m
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
d
esi
g
n
ed
f
o
r
p
r
ec
is
e
id
en
tific
atio
n
o
f
th
e
h
u
m
a
n
ac
ti
v
it
y
w
it
h
th
e
a
id
o
f
a
s
i
m
p
le
m
ac
h
in
e
lear
n
i
n
g
m
ec
h
a
n
i
s
m
.
T
h
e
id
ea
o
f
u
s
i
n
g
a
m
ac
h
in
e
lea
r
n
in
g
m
ec
h
an
i
s
m
i
s
tar
g
eted
f
o
r
o
f
f
er
in
g
ac
c
u
r
ac
y
i
n
th
e
id
en
ti
f
icatio
n
p
r
o
ce
s
s
.
I
n
o
r
d
er
to
in
co
r
p
o
r
ate
a
g
r
ea
ter
d
eg
r
ee
o
f
ac
cu
r
ac
y
i
n
th
e
p
r
o
ce
s
s
o
f
t
h
e
ac
tiv
it
y
r
ec
o
g
n
it
io
n
s
y
s
te
m
,
it
is
n
ec
es
s
ar
y
t
h
at
ev
er
y
s
m
aller
p
iece
o
f
in
f
o
r
m
atio
n
as
s
o
ciate
d
w
it
h
t
h
e
e
v
en
t
s
h
o
u
ld
b
e
r
ec
o
g
n
ize
d
.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
m
p
le
m
e
n
t
s
a
m
ec
h
a
n
i
s
m
w
h
er
e
t
h
e
f
ea
tu
r
e
s
ar
e
b
u
ilt
u
p
f
r
o
m
s
p
atia
l
an
d
te
m
p
o
r
al
attr
ib
u
tes
co
n
n
ec
t
ed
to
th
e
r
ea
l
-
ti
m
e
ev
en
t
s
i
n
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
.
T
h
e
alg
o
r
ith
m
tak
e
s
t
h
e
i
n
p
u
t
o
f
r
ea
l
-
ti
m
e
ev
e
n
t
v
id
eo
i
n
t
h
e
f
o
r
m
o
f
I
s
(
in
p
u
t
s
a
m
p
le)
w
h
ic
h
af
ter
p
r
o
ce
s
s
i
n
g
y
ield
s
a
n
o
u
tco
m
e
o
f
s
fe
at
(
s
a
m
p
led
f
ea
t
u
r
e)
.
T
h
e
s
te
p
in
v
o
lv
ed
i
n
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
i
s
as
f
o
llo
w
s
:
Alg
o
rit
h
m
f
o
r
a
ct
iv
it
y
re
co
g
nitio
n us
i
ng
m
a
ch
ine le
a
rnin
g
I
np
ut
: I
s
(
in
p
u
t sa
m
p
le)
O
utput
: s
feat
(
s
a
m
p
led
f
ea
tu
r
e)
Sta
rt
1
.
in
it I
s
,
2
.
F
o
r
i=1
:len
g
th
(
s
db
)
3
.
I
dep
à
s
db
(
i)
//i
m
a
g
e
d
ep
th
4
.
Ob
tain
L
cor
, R
co
r
à
(
x
,
y
,
z
)
5
.
DA
à
√
(
∑(
L
i
-
R
i
)
2
)
,
w
h
e
r
e
i=x
,
y
,
z
6
.
a
à
f
(
P
1
r
,
r
P
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
s
imp
lifi
ed
ma
ch
in
e
lea
r
n
in
g
a
p
p
r
o
a
c
h
fo
r
r
ec
o
g
n
iz
in
g
h
u
ma
n
a
ctivity
(
A
b
d
u
l La
teef
Ha
r
o
o
n
P
.
S
)
3469
7
.
A
à
a.
1
8
0
/p
i
8
.
o
b
tain
s
feat
à
[
A
]
9
.
[
p
op
s
co
r
e]
à
f
2
(s
feat
)
1
0
.
If
s
co
r
e(
p
op
)>
-
th
r
es
1
1
.
R
à
f
lag
p
o
s
iti
v
e
r
ec
o
g
n
itio
n
1
2
.
else
1
3
.
R
à
f
lag
n
eg
a
tiv
e
r
ec
o
g
n
itio
n
1
3
.
E
nd
E
nd
A
lg
o
r
ith
m
S
tep
Dis
cu
s
s
io
n
:
Fo
r
s
i
m
p
ler
p
r
o
ce
s
s
in
g
o
f
r
e
al
-
ti
m
e
f
ee
d
o
f
an
ev
e
n
t,
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
d
i
g
itize
s
t
h
e
f
ee
d
i
n
o
r
d
er
to
o
b
tain
it
as
I
s
(
in
p
u
t
s
a
m
p
le)
w
h
ich
h
as
b
o
t
h
s
p
atial
an
d
te
m
p
o
r
al
in
f
o
r
m
atio
n
(
L
i
n
e
-
1
)
.
T
h
e
n
ex
t
p
ar
t
o
f
th
e
al
g
o
r
ith
m
is
to
o
b
tain
s
i
g
n
if
ican
t
f
ea
t
u
r
es
f
r
o
m
all
th
e
s
p
atia
l
d
ata
(s
db
)
,
w
h
ich
i
s
f
u
r
th
er
u
s
ed
f
o
r
ex
tr
ac
tin
g
th
e
i
m
a
g
e
d
ep
th
I
dep
(
L
in
e
-
3
)
.
I
n
th
is
s
t
ag
e,
b
o
th
t
h
e
co
lo
r
ed
v
er
s
io
n
o
f
th
e
co
r
e
s
k
eleto
n
as
w
ell
as
i
m
a
g
e
d
ep
th
is
o
b
tain
ed
.
T
h
e
co
lo
r
e
d
im
a
g
e
S
is
o
b
tain
ed
f
r
o
m
t
h
e
d
ata
s
tr
u
ct
u
r
e
o
f
s
db
w
h
ile
i
m
a
g
e
d
ep
th
I
dep
is
o
b
tain
ed
f
r
o
m
L
i
n
e
-
3
.
T
h
e
n
ex
t
p
ar
t
o
f
th
e
al
g
o
r
ith
m
is
f
o
cu
s
ed
o
n
o
b
tain
in
g
v
ar
io
u
s
p
o
ten
tial
f
e
atu
r
es
as
s
o
ciate
d
w
it
h
th
e
a
n
k
le
an
d
w
r
is
t
a
s
th
e
y
ar
e
a
p
r
o
m
i
n
en
t
i
n
d
icato
r
o
f
an
y
s
i
g
n
if
ica
n
t
ac
tiv
it
y
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
o
b
tai
n
s
t
h
e
th
r
ee
-
d
i
m
e
n
s
io
n
al
co
o
r
d
in
ate
s
s
y
s
te
m
f
r
o
m
b
o
t
h
th
e
le
f
t
an
d
r
ig
h
t
an
k
le
(
L
i
n
e
-
4
)
.
A
E
u
cl
id
ea
n
d
is
t
a
n
ce
i
s
ap
p
lied
f
o
r
co
m
p
u
ti
n
g
s
p
at
ial
th
e
d
if
f
er
en
ce
s
b
et
w
ee
n
th
e
le
f
t
a
n
d
r
ig
h
t
an
k
le
(
L
i
n
e
-
5
)
co
n
s
id
er
in
g
all
th
e
t
h
r
ee
-
d
i
m
en
s
io
n
al
co
o
r
d
in
ates.
Si
m
ilar
alg
o
r
ith
m
ic
s
tep
s
,
i.e
.
L
in
e
-
4
a
n
d
L
in
e
-
5
i
s
u
s
ed
f
o
r
co
m
p
u
ti
n
g
th
e
E
u
c
lid
ea
n
d
i
s
tan
ce
b
etw
ee
n
t
h
e
le
f
t
an
d
t
h
e
r
ig
h
t
w
r
i
s
t to
o
.
A
lt
h
o
u
g
h
,
th
e
lo
g
ic
f
o
cu
s
e
s
o
n
th
e
id
e
n
ti
f
y
in
g
t
h
e
s
p
atial
a
ttrib
u
te
o
f
t
h
e
d
is
p
lace
m
en
t
c
o
n
s
id
er
in
g
th
e
s
ig
n
i
f
ica
n
t
l
i
m
b
s
,
e.
g
.
,
a
n
k
le
an
d
w
r
i
s
t,
h
o
w
e
v
er
,
t
h
e
te
m
p
o
r
al
attr
ib
u
te
o
f
t
h
e
d
i
s
p
lace
m
en
t
ca
n
b
e
k
n
o
w
n
if
t
h
e
o
r
ie
n
tati
o
n
m
ea
s
u
r
e
i
s
co
n
s
id
er
ed
f
o
r
th
e
ev
e
n
t
ca
p
tu
r
ed
.
T
h
er
ef
o
r
e,
th
e
alg
o
r
ith
m
p
er
f
o
r
m
s
t
h
e
co
m
p
u
tatio
n
o
f
th
e
o
r
ien
tatio
n
m
ea
s
u
r
e
m
e
n
t
o
f
an
o
t
h
er
li
m
b
,
i.e
.
b
o
th
th
e
elb
o
w
.
T
h
e
alg
o
r
ith
m
co
m
p
u
te
s
th
e
ef
f
ec
tiv
e
d
i
s
p
lace
m
e
n
t
o
f
b
o
t
h
th
e
elb
o
w
s
v
iz.
P
1
r
an
d
r
P
2
an
d
ap
p
lies
a
f
u
n
ctio
n
f
(
x
)
o
n
th
is
to
o
b
tain
t
h
e
ac
tu
al
o
r
ien
tat
io
n
f
ac
to
r
ass
o
ci
ated
w
it
h
t
h
e
elb
o
w
(
L
i
n
e
-
)
.
T
h
e
f
u
n
ctio
n
f
(
x
)
co
m
p
u
te
s
i
n
v
e
r
s
e
tan
g
en
t o
f
f
o
u
r
q
u
ad
r
an
ts
o
v
er
t
w
o
v
ar
iab
le
v
i
z.
i)
v
ar
iab
le
-
1
f
o
r
n
o
r
m
alize
d
cr
o
s
s
p
r
o
d
u
ct
o
f
P
1
r
an
d
r
P
2
an
d
ii
)
d
o
t
p
r
o
d
u
ct
o
f
P
1
r
an
d
r
P
2
.
Fin
all
y
,
th
e
o
r
ien
tatio
n
s
co
r
e
is
o
b
tain
ed
A
(
L
i
n
e
-
7
)
.
T
h
is
m
ec
h
a
n
is
m
is
p
er
f
o
r
m
ed
f
o
r
b
o
t
h
elb
o
w
a
n
d
le
g
s
o
r
ien
tatio
n
to
f
i
n
all
y
o
b
tai
n
al
l
t
h
e
f
ea
t
u
r
e
s
s
f
ea
t
f
r
o
m
A
(
L
in
e
-
8
)
.
T
h
e
alg
o
r
it
h
m
ap
p
lies
an
o
th
er
f
u
n
ct
io
n
f
2
(
x
)
o
v
er
t
h
e
o
b
tain
ed
f
ea
t
u
r
es
to
e
x
tr
a
ct
th
e
f
i
n
al
s
et
o
f
f
ea
t
u
r
es
(
L
i
n
e
-
9
)
.
Ho
w
e
v
er
,
th
e
o
b
tain
ed
f
ea
t
u
r
e
is
j
u
s
t
f
o
r
f
ea
tu
r
e
id
e
n
ti
f
icatio
n
t
h
at
d
i
r
ec
tl
y
as
s
is
t
s
i
n
t
h
e
ac
ti
v
it
y
r
ec
o
g
n
itio
n
s
y
s
te
m
.
T
h
e
o
p
e
r
atio
n
ca
r
r
ied
o
u
t
till
th
is
s
ta
g
e
en
s
u
r
e
7
0
%
o
f
ac
cu
r
ac
y
o
w
i
n
g
to
th
e
ad
o
p
tio
n
o
f
s
p
atial
an
d
te
m
p
o
r
al
b
ased
f
ea
tu
r
es;
t
h
er
e
f
o
r
e,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
u
p
g
r
ad
e
th
e
f
u
n
c
tio
n
f
2
(
x
)
u
s
i
n
g
m
ac
h
i
n
e
lear
n
in
g
b
ased
ap
p
r
o
ac
h
.
T
h
er
e
ar
e
v
ar
io
u
s
j
u
s
ti
f
icati
o
n
s
o
f
u
s
i
n
g
m
ac
h
i
n
e
-
b
ased
lear
n
in
g
ap
p
r
o
ac
h
.
A
d
o
p
tio
n
o
f
t
h
i
s
ap
p
r
o
ac
h
allo
w
s
t
h
e
i
m
p
le
m
e
n
tatio
n
o
f
m
u
l
tip
le
f
o
r
m
s
o
f
m
ac
h
in
e
lear
n
i
n
g
ap
p
r
o
ac
h
es
f
o
r
t
h
e
p
u
r
p
o
s
e
o
f
ef
f
icien
t
p
r
ed
ictiv
e
r
ec
o
g
n
itio
n
o
f
h
u
m
a
n
ac
ti
v
it
y
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
p
er
f
o
r
m
s
p
r
ed
ictio
n
o
f
d
ata
w
i
th
r
esp
ec
t
to
th
e
d
ata
h
i
s
to
r
y
,
a
n
d
h
en
ce
all
t
h
e
f
ac
t
o
r
s
(
s
p
atial
as
w
el
l
as
te
m
p
o
r
al
asp
ec
t
s
)
a
r
e
co
n
s
id
er
ed
w
h
i
le
p
er
f
o
r
m
in
g
t
h
e
tr
ain
i
n
g
o
p
er
atio
n
.
W
h
e
n
t
h
i
s
f
u
n
ctio
n
i
s
ap
p
lied
o
n
a
s
et
o
f
f
ea
t
u
r
es,
th
e
tr
ain
i
n
g
y
ield
s
p
r
ed
ictiv
e
o
p
er
ato
r
p
op
an
d
its
r
esp
ec
tiv
e
s
co
r
e
(
L
i
n
e
-
9
)
.
Af
t
er
o
b
tain
in
g
t
h
e
v
al
u
e
o
f
th
e
s
co
r
e,
it
is
co
m
p
ar
ed
w
it
h
t
h
e
cu
t
-
o
f
f
v
al
u
e
th
r
es
w
h
er
e
th
e
p
o
s
iti
v
e
v
al
u
e
will
en
s
u
r
e
p
er
f
ec
t
r
ec
o
g
n
itio
n
R
o
f
th
e
ac
ti
v
it
y
(
L
in
e
-
1
1
)
o
f
t
h
e
e
v
e
n
t
w
h
ile
t
h
e
n
eg
at
iv
e
v
al
u
e
w
i
ll
ca
ll
f
o
r
n
e
g
ati
v
e
r
ec
o
g
n
itio
n
R
(
L
i
n
e
-
1
3
)
.
A
clo
s
er
lo
o
k
in
to
th
i
s
s
tep
o
f
o
p
er
atio
n
w
il
l
s
h
o
w
t
h
at
th
i
s
is
m
ea
n
t
f
o
r
im
p
r
o
v
i
n
g
th
e
ac
cu
r
ac
y
o
f
th
e
r
ec
o
g
n
itio
n
ca
p
ab
ilit
y
.
A
lt
h
o
u
g
h
t
h
e
p
r
o
ce
s
s
i
s
b
it
iter
ati
v
e
i
n
t
h
i
s
r
eg
a
r
d
s
,
in
ter
esti
n
g
l
y
it
o
f
f
er
s
t
h
e
ca
p
ab
ilit
y
to
r
ed
u
ce
d
o
w
n
t
h
e
er
r
o
r
-
p
r
o
n
e
id
en
tif
i
ca
tio
n
s
.
A
cc
o
r
d
in
g
to
th
e
alg
o
r
ith
m
,
i
f
th
e
p
r
o
ce
s
s
d
o
es
f
in
d
a
p
er
f
ec
t
m
atc
h
w
it
h
its
tr
ain
ed
d
atase
t
w
it
h
r
e
s
p
ec
t
to
t
h
e
s
p
atial
an
d
te
m
p
o
r
al
f
ac
to
r
,
it
w
i
ll
m
ea
n
t
h
at
t
h
e
s
u
b
j
ec
t
d
is
p
la
y
s
a
v
er
y
d
i
f
f
er
en
t
m
o
v
e
m
e
n
t
a
n
d
h
en
ce
th
e
r
ec
o
g
n
i
tio
n
s
y
s
te
m
ca
p
tu
r
es
t
h
at
t
h
e
s
u
b
j
ec
t
is
d
i
f
f
er
en
t
an
d
d
is
t
in
ct.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
s
an
e
x
ten
s
i
v
e
g
r
an
u
la
r
it
y
in
it
s
o
u
tco
m
e
f
o
r
ac
tiv
it
y
r
ec
o
g
n
itio
n
s
y
s
te
m
th
at
en
ab
le
s
th
e
s
y
s
te
m
to
p
er
f
o
r
m
a
g
o
o
d
b
alan
ce
b
et
w
ee
n
a
cc
u
r
ac
y
as
w
el
l a
s
id
en
t
if
ica
ti
o
n
p
er
f
o
r
m
an
ce
.
3.
RE
SU
L
T
ANAL
YS
IS
T
h
is
s
ec
tio
n
d
is
c
u
s
s
es
t
h
e
o
u
tco
m
es
o
b
tain
ed
f
r
o
m
t
h
e
i
m
p
le
m
en
ta
tio
n
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
to
w
ar
d
s
t
h
e
id
en
tific
atio
n
o
f
t
h
e
h
u
m
a
n
ac
ti
v
it
y
.
T
h
e
p
r
i
m
e
s
tr
ateg
y
to
a
n
al
y
ze
th
e
o
u
tco
m
e
i
s
to
ass
e
s
s
th
e
m
o
b
il
it
y
o
f
t
h
e
s
u
b
j
ec
t
in
o
r
d
er
to
d
eter
m
i
n
e
t
h
e
ir
p
r
ec
is
e
ac
ti
v
it
y
id
en
tific
atio
n
.
T
h
e
s
t
u
d
y
co
n
s
id
er
s
ap
p
r
o
x
im
a
tel
y
2
0
s
k
eleta
l
j
o
in
ts
.
U
s
in
g
t
h
e
s
i
m
ilar
tes
t
en
v
ir
o
n
m
en
t
o
f
o
u
r
p
r
io
r
ex
p
er
i
m
e
n
t
[
3
2
]
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
h
as
ca
p
t
u
r
ed
a
2
0
x
2
0
m
atr
ix
a
s
s
o
ciat
ed
w
it
h
all
th
e
s
eq
u
e
n
ce
s
o
f
t
h
e
i
n
d
iv
id
u
al
v
id
eo
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
5
,
Octo
b
er
2
0
1
9
:
3
4
6
5
-
3
4
7
3
3470
I
n
th
i
s
s
y
s
te
m
,
all
th
e
ce
ll
s
in
th
e
m
atr
i
x
d
ep
ict
th
e
s
ec
t
o
r
s
th
at
ar
e
o
cc
u
p
ied
b
y
h
i
s
to
g
r
a
m
s
.
Di
f
f
er
en
t
n
u
m
b
er
s
o
f
s
u
b
j
ec
ts
ar
e
co
n
s
i
d
er
ed
f
o
r
th
is
e
x
p
er
i
m
e
n
t
w
h
e
r
e
d
if
f
er
e
n
t
v
id
eo
s
eq
u
e
n
ce
s
h
av
e
b
ee
n
ca
p
t
u
r
ed
an
d
s
to
r
ed
.
T
h
e
s
cr
ip
tin
g
o
f
t
h
e
p
r
o
p
o
s
ed
l
o
g
ic
w
a
s
ca
r
r
ied
o
u
t
in
M
A
T
L
A
B
,
an
d
it
o
f
f
e
r
s
s
u
p
p
o
r
tab
ilit
y
o
f
b
o
th
lif
e
as
w
el
l a
s
o
f
f
li
n
e
an
a
l
y
s
i
s
.
Fig
u
r
e
3
h
i
g
h
l
ig
h
ts
t
h
e
v
is
u
al
o
u
tco
m
e
s
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
w
h
er
e
it
ca
n
b
e
s
ee
n
t
h
a
t
r
ea
l
-
t
i
m
e
f
ee
d
s
ar
e
ca
p
tu
r
ed
f
r
o
m
t
h
e
v
is
u
al
s
e
n
s
o
r
s
i
n
o
r
d
er
to
o
b
tain
t
h
e
co
lo
r
e
d
im
a
g
e
as
w
e
ll
as
d
ep
th
i
m
ag
e.
T
h
is
in
f
o
r
m
a
tio
n
w
ill
a
s
s
i
s
t
in
e
x
tr
ac
tio
n
s
p
atial
an
d
te
m
p
o
r
al
-
b
ased
f
ea
tu
r
e
s
t
h
at
w
il
l
f
i
n
all
y
as
s
is
t
i
n
i
m
p
r
o
v
i
n
g
t
h
e
ac
cu
r
ac
y
o
f
t
h
e
p
r
o
p
o
s
ed
ac
tiv
it
y
r
ec
o
g
n
itio
n
s
y
s
te
m
.
T
h
e
an
al
y
s
is
h
as
b
ee
n
ca
r
r
ied
o
u
t
u
s
i
n
g
3
5
s
u
b
j
ec
ts
(
o
n
l
y
f
o
u
r
d
if
f
er
e
n
t
s
a
m
p
le
te
s
t
s
u
b
j
ec
ts
ar
e
s
h
o
w
n
i
n
Fi
g
u
r
e
2
)
.
T
h
e
n
ex
t
p
ar
t
o
f
t
h
e
an
a
l
y
s
is
is
all
ab
o
u
t
ass
es
s
i
n
g
ac
c
u
r
ac
y
.
Af
ter
th
e
ca
p
tu
r
i
n
g
o
f
t
h
e
ev
en
t
h
as
b
ee
n
ca
r
r
ied
o
u
t,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
co
m
p
u
tes
al
lth
e
e
s
s
e
n
t
ial
m
o
b
ilit
y
asp
ec
ts
as
s
o
ciate
d
w
i
th
th
e
a
n
k
l
e,
elb
o
w
,
w
r
is
t,
leg
,
etc.
Fig
u
r
e
4
h
ig
h
li
g
h
ts
t
h
e
co
m
p
u
tatio
n
o
f
th
e
a
n
k
le
an
d
w
r
is
t
d
is
p
la
ce
m
en
t.
Fig
u
r
e
5
an
d
Fig
u
r
e
6
s
h
o
w
s
th
at
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
ca
p
ab
le
o
f
tr
ac
k
in
g
a
ll
t
h
e
m
i
n
o
r
an
d
in
s
i
g
n
if
ica
n
t
m
o
v
e
m
en
t
o
f
t
h
e
s
u
b
j
ec
t
to
o
.
T
h
e
s
y
s
te
m
also
tr
ac
k
s
i
n
f
o
r
m
atio
n
a
s
s
o
ciate
d
w
it
h
an
k
le
,
w
r
is
t,
elb
o
w
s
,
a
n
d
leg
as
s
h
o
w
n
i
n
Fi
g
u
r
e
5
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
a
ls
o
est
i
m
ate
s
th
e
m
ea
n
m
a
tr
ix
as
well
as
s
tr
ea
m
m
ap
as
e
x
h
ib
ite
d
in
F
ig
u
r
e
7
th
at
o
f
f
er
s
t
h
e
co
m
p
r
eh
e
n
s
iv
e
e
v
id
en
ce
o
f
ac
cu
r
ac
y
o
b
tain
ed
f
o
r
all
th
e
ac
ti
v
it
y
id
en
ti
f
icat
io
n
.
Co
lo
r
I
m
a
g
e
Dept
h I
m
a
g
e
T
est
Sa
mp
le
-
1
T
est
Sa
mp
le
-
2
T
est
Sa
mp
le
-
3
T
est
Sa
mp
le
-
4
Fig
u
r
e
3
.
Vis
u
al
o
u
tco
m
e
s
o
f
p
r
o
p
o
s
ed
ac
tiv
it
y
r
ec
o
g
n
itio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
s
imp
lifi
ed
ma
ch
in
e
lea
r
n
in
g
a
p
p
r
o
a
c
h
fo
r
r
ec
o
g
n
iz
in
g
h
u
ma
n
a
ctivity
(
A
b
d
u
l La
teef
Ha
r
o
o
n
P
.
S
)
3471
Fig
u
r
e
4
.
W
r
is
t a
n
d
a
n
k
le
d
is
p
lace
m
e
n
t c
alcu
latio
n
Fig
u
r
e
5
.
L
eg
a
n
d
elb
o
w
ca
lc
u
latio
n
Fig
u
r
e
6
.
E
v
en
t
A
ttrib
u
te
Dete
ctio
n
u
s
in
g
Hi
s
to
g
r
a
m
Fig
u
r
e
7
.
Ma
tr
ix
r
ep
r
esen
tatio
n
s
f
o
r
d
if
f
er
e
n
t h
i
s
to
g
r
a
m
s
T
h
e
id
ea
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
as
s
ess
ed
w
i
th
r
esp
ec
t
to
th
e
ex
i
s
ti
n
g
ap
p
r
o
ac
h
es
o
f
ac
tiv
i
t
y
r
ec
o
g
n
itio
n
s
y
s
te
m
,
e.
g
.
Z
d
r
av
es
k
i
et
al.
[
3
3
]
,
Nak
ag
a
w
a
e
t
al.
[
3
4
]
,
an
d
He
n
p
r
aser
ttae
et
al.
[
3
5
].
T
h
e
s
u
m
m
ar
ized
o
u
tco
m
e
is
h
ig
h
lig
h
ted
i
n
F
i
g
u
r
e
1.
T
h
e
co
m
p
ar
ativ
e
a
n
al
y
s
i
s
is
s
h
o
w
n
in
F
ig
u
r
e
8
h
ig
h
li
g
h
ts
th
at
th
e
p
r
o
p
o
s
e
d
s
y
s
te
m
o
f
f
er
s
b
etter
ac
cu
r
ac
y
a
s
co
m
p
ar
ed
to
ex
is
t
in
g
ap
p
r
o
ac
h
es
co
n
s
id
er
ed
f
o
r
an
al
y
s
i
s
.
A
lt
h
o
u
g
h
,
t
h
e
ap
p
r
o
ac
h
o
f
Z
d
r
a
v
es
k
i
e
t
al.
[
3
3
]
is
f
o
u
n
d
to
b
e
9
5
%,
s
till
,
its
p
r
ac
tical
ap
p
licab
ili
t
y
,
as
w
ell
as
co
m
p
u
tat
io
n
al
co
m
p
le
x
it
y
,
is
n
o
t
co
m
p
u
ted
.
T
h
e
ap
p
r
o
ac
h
o
f
Nak
a
g
a
w
a
et
al.
[
3
4
]
s
u
f
f
er
s
f
r
o
m
h
i
g
h
er
d
ep
en
d
en
cies
o
f
m
a
s
s
i
v
e
d
ata
f
o
r
id
en
ti
f
icatio
n
.
Si
m
ilar
l
y
,
th
e
w
o
r
k
o
f
Hen
p
r
aser
ttae
et
al.
[
3
5
]
d
o
esn
’
t
co
n
s
id
er
th
e
p
r
o
b
lem
o
f
d
ata
v
ar
iab
ilit
y
,
a
n
d
h
en
ce
t
h
e
y
ar
e
ap
p
licab
le
o
n
ly
f
o
r
s
tatic
d
atasets
w
i
t
h
o
u
t
a
n
y
a
s
s
es
s
m
en
t
o
f
its
co
m
p
u
tatio
n
al
co
m
p
le
x
it
y
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
h
as
e
x
h
ib
ited
1
0
-
1
5
%
o
f
m
e
m
o
r
y
co
n
s
u
m
p
tio
n
w
it
h
0
.
5
3
4
1
s
ec
o
n
d
s
o
f
p
r
o
ce
s
s
in
g
ti
m
e
co
n
s
u
m
p
tio
n
o
v
er
5
3
2
MB
o
f
d
i
g
itized
d
ata
o
f
th
e
r
ea
l
-
ti
m
e
e
v
en
t.
He
n
ce
,
th
e
s
u
p
p
o
r
tab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
q
u
it
e
h
ig
h
er
o
n
p
r
ac
tical
g
r
o
u
n
d
.
I
t
s
h
o
u
ld
b
e
n
o
ted
th
at
all
th
e
ex
is
t
in
g
s
y
s
te
m
ar
e
ex
p
er
i
m
e
n
ted
a
n
d
an
al
y
ze
d
o
n
th
e
b
asis
o
f
th
e
s
ta
n
d
ar
d
d
ataset.
A
lt
h
o
u
g
h
,
it
is
lea
s
t
i
m
p
o
r
tan
t
ab
o
u
t
th
e
f
o
r
m
at
o
f
th
e
d
ata,
h
o
w
e
v
er
,
an
al
y
s
i
s
o
v
er
s
ta
tic
d
atas
et
d
o
esn
’
t
p
r
o
v
e
th
e
p
r
ac
tical
it
y
o
f
th
e
e
x
i
s
ti
n
g
s
o
lu
tio
n
.
Mo
r
eo
v
er
,
th
e
e
x
is
t
i
n
g
co
n
ce
p
ts
to
w
ar
d
s
ac
ti
v
it
y
r
ec
o
g
n
itio
n
ar
e
q
u
ite
h
y
p
o
t
h
e
tical
as
t
h
e
y
w
er
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
5
,
Octo
b
er
2
0
1
9
:
3
4
6
5
-
3
4
7
3
3472
n
ev
er
ass
e
s
s
ed
f
o
r
th
eir
co
m
p
u
tatio
n
al
co
m
p
le
x
it
y
.
Ho
w
e
v
er
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
b
r
i
d
g
es
th
i
s
g
ap
an
d
p
r
o
v
es
th
at
it
m
ai
n
tai
n
s
a
g
o
o
d
b
alan
ce
b
et
w
ee
n
ac
cu
r
ac
y
a
n
d
it
s
o
t
h
er
ass
o
c
iated
p
er
f
o
r
m
an
ce
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
r
esu
l
t
is
th
e
s
a
m
e
f
o
r
b
o
th
r
ea
l
-
t
i
m
e
ca
p
tu
r
es
o
f
s
u
b
j
ec
t
m
o
b
il
it
y
as
w
e
ll
as
s
tatic
f
r
a
m
e
s
to
o
.
Fig
u
r
e
8
.
C
o
m
p
ar
ativ
e
a
n
a
l
y
s
i
s
o
f
ac
cu
r
ac
y
s
co
r
e
(
%)
4.
CO
NCLU
SI
O
N
R
ec
o
g
n
it
io
n
o
f
th
e
s
p
ec
if
ic
ac
tiv
ity
o
f
th
e
h
u
m
a
n
is
q
u
ite
a
d
if
f
icu
lt
task
as
it
s
u
f
f
er
s
f
r
o
m
v
ar
io
u
s
ch
all
en
g
es
ass
o
c
iat
ed
w
ith
th
e
d
y
n
a
m
icity
o
f
m
o
v
e
m
en
t
as
w
ell
as
v
ar
iat
io
n
in
th
e
illu
m
in
atio
n
c
o
n
d
i
ti
o
n
.
T
h
e
o
u
t
co
m
e
ex
h
ib
its
th
a
t
f
ea
tu
r
es
ca
p
tu
r
e
d
o
n
th
e
b
asis
o
f
s
p
at
ial
as
w
ell
as
tem
p
o
r
a
l
f
ac
to
r
s
a
r
e
h
ig
h
ly
s
u
itab
le
f
o
r
ass
ess
in
g
a
ll
th
e
s
ig
n
if
ican
t
m
o
b
il
ity
/d
is
p
la
ce
m
en
t
o
f
th
e
s
u
b
je
cts.
T
h
e
r
e
co
g
n
iti
o
n
o
f
th
e
ac
t
iv
ity
w
as
ca
p
tu
r
ed
in
th
e
f
o
r
m
o
f
d
is
p
l
ac
em
en
t
o
f
v
ar
i
o
u
s
s
ig
n
if
i
ca
n
t
l
im
b
s
o
f
th
e
s
u
b
j
e
ct
as
s
ee
n
f
r
o
m
h
is
to
g
r
am
an
aly
s
is
.
T
h
e
s
tu
d
y
o
u
tc
o
m
e
s
h
o
w
s
th
at
m
ac
h
in
e
-
b
ase
d
le
ar
n
in
g
ap
p
r
o
ac
h
is
h
ig
h
ly
f
r
u
itf
u
l
in
o
b
ta
in
in
g
b
ett
e
r
r
esu
lts
in
th
e
f
o
r
m
o
f
ac
cu
r
a
cy
as
w
ell
as
o
v
e
r
a
ll
s
y
s
tem
p
e
r
f
o
r
m
an
ce
.
T
h
e
r
ef
o
r
e
,
th
e
tech
n
i
ca
l
v
ia
b
il
ity
,
as w
ell
as
th
e
a
p
p
li
ca
b
il
ity
o
f
t
h
e
p
r
o
p
o
s
e
d
s
y
s
tem
,
is
q
u
it
e
h
i
g
h
in
a
p
r
ac
ti
ca
l
en
v
ir
o
n
m
en
t.
RE
F
E
R
E
NC
E
S
[1
]
M
.
H.
Hu
g
o
s,
“
Esse
n
ti
a
ls
o
f
S
u
p
p
ly
Ch
a
in
M
a
n
a
g
e
m
e
n
t,
”
Jo
h
n
W
il
e
y
&
S
o
n
s,
Bu
si
n
e
ss
&
Eco
n
o
m
i
c
s,
p
p
.
3
6
8
,
201
8.
[2
]
F
.
D.
l.
P
ri
e
ta,
e
t
a
l
.
,
“
T
re
n
d
s
in
C
y
b
er
-
P
h
y
sic
a
l
M
u
lt
i
-
A
g
e
n
t
S
y
ste
m
s
,”
T
h
e
PA
AM
S
C
o
ll
e
c
ti
o
n
-
1
5
t
h
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
,
PA
AM
S
2
0
1
7
,
S
p
ri
n
g
e
r
,
p
p
.
3
4
0
,
2
0
1
7
.
[3
]
C.
A
n
to
n
io
u
,
e
t
a
l
.
,
“
M
o
b
i
li
ty
P
a
tt
e
rn
s,
Big
Da
ta
a
n
d
T
ra
n
sp
o
rt
A
n
a
l
y
ti
c
s:
T
o
o
l
s
a
n
d
Ap
p
li
c
a
ti
o
n
s
f
o
r
M
o
d
e
li
n
g
,
”
El
se
v
ier
,
p
p
.
4
5
2
,
2
0
1
8
.
[4
]
W
.
Zh
a
o
,
e
t
a
l
.
,
“
Re
c
e
n
t
De
v
e
lo
p
m
e
n
ts i
n
S
m
a
rt
He
a
lt
h
c
a
re
,
”
Co
mp
u
ter
s
,
p
p
.
3
6
2
,
2
0
1
8
.
[5
]
A
.
E.
Ha
ss
a
n
ien
,
e
t
a
l
.
,
“
A
d
v
a
n
c
e
d
M
a
c
h
in
e
L
e
a
rn
in
g
T
e
c
h
n
o
l
o
g
ies
a
n
d
A
p
p
li
c
a
ti
o
n
s
,”
Fi
rs
t
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
,
AM
L
T
A
2
0
1
2
,
Ca
iro
,
Eg
y
p
t
, D
e
c
e
mb
e
r 8
-
1
0
,
2
0
1
2
,
Pro
c
e
e
d
in
g
s
,
Co
mp
u
ter
s
,
p
p
.
6
0
2
,
2
0
1
2
.
[6
]
M
.
A
.
L
a
b
ra
d
o
r
a
n
d
O.
D.
L
.
Ye
jas
,
“
Hu
m
a
n
A
c
ti
v
it
y
Re
c
o
g
n
it
io
n
:
Us
i
n
g
W
e
a
r
a
b
le
S
e
n
so
rs
a
n
d
S
m
a
rtp
h
o
n
e
s
,
”
CRC P
re
ss
,
p
p
.
2
0
7
,
2
0
1
3
.
[7
]
Y.
M
a
a
n
d
G
.
G
u
a
,
“
S
u
p
p
o
r
t
V
e
c
to
r
M
a
c
h
i
n
e
s A
p
p
li
c
a
ti
o
n
s,
”
S
p
ri
n
g
e
r
S
c
ien
c
e
&
Bu
sin
e
ss
M
e
d
ia,
p
p
.
3
0
2
,
2
0
1
4
.
[8
]
T
.
W
u
e
st,
“
Id
e
n
ti
fy
in
g
P
ro
d
u
c
t
a
n
d
P
ro
c
e
ss
S
tate
Driv
e
rs
in
M
a
n
u
f
a
c
tu
rin
g
S
y
ste
m
s
Us
in
g
S
u
p
e
rv
ise
d
M
a
c
h
in
e
L
e
a
rn
in
g
,
”
S
p
rin
g
e
r
,
p
p
.
2
7
2
,
2
0
1
5
.
[9
]
E
.
Ba
n
g
u
e
ro
,
e
t
a
l
.
,
“
Re
n
e
w
a
b
le
m
icro
g
rid
o
p
e
ra
ti
o
n
a
l
re
su
lt
s
a
n
d
e
c
o
n
om
ic
e
v
a
lu
a
ti
o
n
u
sin
g
RET
S
c
re
e
n
T
M
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
ol
/i
ss
u
e
:
9
(
2
)
,
p
p
.
7
2
3
-
7
3
1
,
2
0
1
9
.
[1
0
]
K.
Dh
in
e
sh
k
u
m
a
r,
e
t
a
l
.
,
“
P
e
rfo
rm
a
n
c
e
a
n
a
l
y
sis
o
f
P
V
p
o
w
e
re
d
m
u
lt
il
e
v
e
l
in
v
e
rter
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
tric
a
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
ol
/i
ss
u
e
:
9
(
2
)
,
p
p
.
7
5
3
-
7
6
0
,
2
0
1
9
.
[1
1
]
A
.
L
.
Ha
ro
o
n
P
.
S
.
a
n
d
U
.
Era
n
n
a
,“
In
sig
h
ts
o
n
Re
se
a
rc
h
-
b
a
se
d
A
p
p
ro
a
c
h
e
s
in
Hu
m
a
n
A
c
ti
v
i
ty
Re
c
o
g
n
it
io
n
S
y
st
e
m
,”
Co
mm
u
n
ica
ti
o
n
s o
n
A
p
p
li
e
d
El
e
c
tro
n
ics
,
v
o
l/
issu
e
:
7
(1
6
)
p
p
.
23
-
3
1
,
M
a
y
2
0
1
8
.
[1
2
]
Z.
Ch
e
n
,
e
t
a
l
.
,
“
Distil
li
n
g
t
h
e
K
n
o
w
led
g
e
f
ro
m
Ha
n
d
c
ra
f
ted
F
e
a
tu
re
s
f
o
r
Hu
m
a
n
A
c
ti
v
it
y
Re
c
o
g
n
it
io
n
,
”
in
I
EE
E
T
ra
n
sa
c
ti
o
n
s
o
n
In
d
u
stri
a
l
I
n
fo
rm
a
ti
c
s
,
v
o
l
/i
ss
u
e
:
14
(
10
)
,
p
p
.
4
3
3
4
-
434
2
,
Oc
t
2
0
1
8
.
[1
3
]
E.
De
-
La
-
Ho
z
-
F
ra
n
c
o
,
e
t
a
l
.
,
“
S
e
n
so
r
-
Ba
se
d
Da
tas
e
ts
f
o
r
Hu
m
a
n
A
c
ti
v
it
y
Re
c
o
g
n
it
io
n
–
A
S
y
ste
m
a
ti
c
Re
v
ie
w
o
f
L
it
e
ra
tu
re
,
”
in
IEE
E
Acc
e
ss
,
v
o
l.
6
,
p
p
.
5
9
1
9
2
-
5
9
2
1
0
,
2
0
1
8
.
[1
4
]
T
.
P
lö
tz
a
n
d
Y.
G
u
a
n
,
“
De
e
p
L
e
a
rn
in
g
f
o
r
Hu
m
a
n
Ac
ti
v
it
y
R
e
c
o
g
n
it
io
n
i
n
M
o
b
il
e
Co
m
p
u
ti
n
g
,
”
in
Co
mp
u
ter
,
v
o
l
/i
ss
u
e
:
51
(
5
)
,
p
p
.
5
0
-
5
9
,
M
a
y
2
0
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
s
imp
lifi
ed
ma
ch
in
e
lea
r
n
in
g
a
p
p
r
o
a
c
h
fo
r
r
ec
o
g
n
iz
in
g
h
u
ma
n
a
ctivity
(
A
b
d
u
l La
teef
Ha
r
o
o
n
P
.
S
)
3473
[1
5
]
Y.
Ch
e
n
,
e
t
a
l
.
,
“
R
o
b
u
st
A
c
ti
v
i
ty
R
e
c
o
g
n
it
io
n
f
o
r
A
g
in
g
S
o
c
iety
,
”
in
IEE
E
J
o
u
rn
a
l
o
f
Bi
o
me
d
i
c
a
l
a
n
d
He
a
lt
h
In
fo
rm
a
t
ics
,
v
o
l
/i
ss
u
e
:
22
(
6
)
,
p
p
.
1
7
5
4
-
1
7
6
4
,
N
o
v
2
0
1
8
.
[1
6
]
M
.
L
.
G
a
v
ril
o
v
a
,
e
t
a
l
.
,
“
Kin
e
c
t
S
e
n
so
r
G
e
stu
re
a
n
d
Ac
ti
v
it
y
Re
c
o
g
n
it
io
n
:
Ne
w
A
p
p
li
c
a
ti
o
n
s
f
o
r
Co
n
su
m
e
r
Co
g
n
it
iv
e
S
y
ste
m
s,
”
in
IEE
E
Co
n
su
me
r E
lec
tro
n
ics
M
a
g
a
zin
e
,
v
o
l
/
issu
e
:
7
(
1
)
,
p
p
.
8
8
-
9
4
,
Ja
n
2
0
1
8
.
[1
7
]
N.
He
g
d
e
,
e
t
a
l
.
,
“
A
u
to
m
a
ti
c
Re
c
o
g
n
it
io
n
o
f
Ac
ti
v
it
ies
o
f
Da
il
y
L
iv
in
g
Util
izin
g
In
so
le
-
Ba
se
d
a
n
d
W
rist
-
W
o
rn
W
e
a
r
a
b
le S
e
n
so
rs,
”
in
I
EE
E
J
o
u
r
n
a
l
o
f
B
io
me
d
ic
a
l
a
n
d
He
a
lt
h
In
f
o
rm
a
ti
c
s
,
v
o
l
/i
ss
u
e
:
22
(
4
)
,
p
p
.
9
7
9
-
9
8
8
,
Ju
l
2
0
1
8
.
[1
8
]
M
.
U.
S
.
K
h
a
n
,
e
t
a
l
.,
“
On
th
e
Co
rre
latio
n
o
f
S
e
n
so
r
L
o
c
a
ti
o
n
a
n
d
Hu
m
a
n
A
c
ti
v
it
y
Re
c
o
g
n
it
io
n
i
n
Bo
d
y
A
r
e
a
Ne
tw
o
rk
s (B
A
Ns
),
”
in
IEE
E
S
y
ste
ms
J
o
u
rn
a
l
,
v
o
l
/
issu
e
:
12
(
1
)
,
p
p
.
8
2
-
9
1
,
M
a
r
2
0
1
8
.
[1
9
]
S
.
Kh
a
li
f
a
,
e
t
a
l
.
,
“
HA
R
KE:
Hu
m
a
n
A
c
ti
v
it
y
R
e
c
o
g
n
it
io
n
f
ro
m
Kin
e
ti
c
En
e
rg
y
Ha
r
v
e
stin
g
D
a
ta
in
W
e
a
ra
b
le
De
v
ice
s,
”
in
IEE
E
T
r
a
n
s
a
c
ti
o
n
s o
n
M
o
b
i
le Co
mp
u
ti
n
g
,
v
o
l
/i
ss
u
e
:
17
(
6
)
,
p
p
.
1
3
5
3
-
1
3
6
8
,
Ju
n
2
0
1
8
.
[2
0
]
Y.
Hs
u
,
e
t
a
l
.
,
“
Hu
m
a
n
Da
il
y
a
n
d
S
p
o
rt
A
c
ti
v
it
y
R
e
c
o
g
n
it
io
n
Us
in
g
a
We
a
ra
b
le
In
e
rti
a
l
S
e
n
so
r
Ne
tw
o
rk
,
”
in
IEE
E
Acc
e
ss
,
v
o
l.
6
,
p
p
.
3
1
7
1
5
-
3
1
7
2
8
,
2
0
1
8
.
[2
1
]
W
.
L
i,
e
t
a
l
.
,
“
L
o
g
-
L
ik
e
li
h
o
o
d
Cl
u
ste
rin
g
-
En
a
b
le
d
P
a
ss
iv
e
RF
S
e
n
sin
g
f
o
r
Re
sid
e
n
ti
a
l
A
c
t
iv
it
y
Re
c
o
g
n
it
io
n
,
”
in
IE
EE
S
e
n
so
rs
J
o
u
rn
a
l
,
v
o
l
/i
ss
u
e
:
18
(
13
)
,
p
p
.
5
4
1
3
-
5
4
2
1
,
Ju
l
20
1
8
.
[2
2
]
P
.
S
o
k
,
e
t
a
l
.
,
“
A
c
ti
v
it
y
Re
c
o
g
n
it
io
n
f
o
r
In
c
o
m
p
lete
S
p
i
n
a
l
Co
rd
I
n
ju
ry
S
u
b
je
c
ts
Us
in
g
H
id
d
e
n
M
a
rk
o
v
M
o
d
e
ls,
”
in
IEE
E
S
e
n
s
o
rs
J
o
u
r
n
a
l
,
v
o
l
/i
ss
u
e
:
18
(
15
)
,
p
p
.
6
3
6
9
-
6
3
7
4
,
A
u
g
2
0
1
8
.
[2
3
]
J.
Qi,
e
t
a
l
.
,
“
L
e
a
rn
in
g
Co
m
p
lex
S
p
a
ti
o
-
T
e
m
p
o
ra
l
Co
n
f
ig
u
r
a
ti
o
n
s
o
f
Bo
d
y
J
o
in
ts
f
o
r
O
n
li
n
e
A
c
ti
v
it
y
Re
c
o
g
n
it
io
n
,
”
in
IE
EE
T
r
a
n
sa
c
ti
o
n
s o
n
Hu
ma
n
-
M
a
c
h
i
n
e
S
y
ste
ms
,
v
o
l
/i
ss
u
e
:
48
(
6
)
,
p
p
.
6
3
7
-
6
4
7
,
De
c
2
0
1
8
.
[2
4
]
J.
W
a
n
g
,
e
t
a
l
.
,
“
De
v
ice
-
F
r
e
e
W
irel
e
ss
L
o
c
a
li
z
a
ti
o
n
a
n
d
A
c
ti
v
it
y
Re
c
o
g
n
i
ti
o
n
:
A
De
e
p
L
e
a
rn
in
g
A
p
p
ro
a
c
h
,
”
in
IE
EE
T
r
a
n
sa
c
ti
o
n
s
o
n
Ve
h
icu
l
a
r T
e
c
h
n
o
l
o
g
y
,
v
o
l
/i
ss
u
e
:
66
(
7
)
,
p
p
.
6
2
5
8
-
6
2
6
7
,
Ju
l
2
0
1
7
.
[2
5
]
T
.
T
a
n
,
e
t
a
l
.
,
“
M
u
lt
i
-
Re
sid
e
n
t
A
c
ti
v
it
y
Re
c
o
g
n
it
io
n
in
a
S
m
a
rt
Ho
m
e
Us
i
n
g
R
G
B
A
c
ti
v
it
y
I
m
a
g
e
a
n
d
DCN
N,
”
in
IEE
E
S
e
n
so
rs
J
o
u
rn
a
l
,
v
o
l
/i
ss
u
e
:
18
(
23
)
,
p
p
.
9
7
1
8
-
9
7
2
7
,
De
c
2
0
1
8
.
[2
6
]
C.
W
a
n
g
,
e
t
a
l
.
,
“
Li
ter
a
tu
re
re
v
ie
w
o
n
w
irele
ss
se
n
sin
g
-
Wi
-
F
i
sig
n
a
l
-
b
a
se
d
r
e
c
o
g
n
it
io
n
o
f
h
u
m
a
n
a
c
ti
v
it
ies
,
”
in
T
sin
g
h
u
a
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
/i
ss
u
e
:
23
(
2
)
,
p
p
.
2
0
3
-
2
2
2
,
A
p
r
2
0
1
8
.
[2
7
]
L
.
W
e
n
y
u
a
n
,
e
t
a
l
.
,
“
F
ro
m
L
e
n
s
t
o
P
rism
:
De
v
ice
-
F
re
e
M
o
d
e
li
n
g
a
n
d
Re
c
o
g
n
it
io
n
o
f
M
u
l
ti
-
P
a
rt
A
c
ti
v
it
ies
,
”
in
IEE
E
Acc
e
ss
,
v
o
l.
6
,
p
p
.
3
6
2
7
1
-
3
6
2
8
2
,
2
0
1
8
.
[2
8
]
L
.
W
e
n
y
u
a
n
,
e
t
a
l
.
,
“
F
ro
m
L
e
n
s
t
o
P
rism
:
De
v
ice
-
F
re
e
M
o
d
e
li
n
g
a
n
d
Re
c
o
g
n
it
io
n
o
f
M
u
l
ti
-
P
a
rt
A
c
ti
v
it
ies
,
”
in
IEE
E
Acc
e
ss
,
v
o
l.
6
,
p
p
.
3
6
2
7
1
-
3
6
2
8
2
,
2
0
1
8
.
[2
9
]
L
.
Ya
o
,
e
t
a
l
.,
“
Co
m
p
re
s
siv
e
R
e
p
re
se
n
tatio
n
f
o
r
De
v
ice
-
F
re
e
A
c
ti
v
it
y
Re
c
o
g
n
it
io
n
w
it
h
P
a
ss
i
v
e
RF
ID
S
ig
n
a
l
S
tren
g
th
,
”
in
IEE
E
T
ra
n
sa
c
ti
o
n
s o
n
M
o
b
i
le Co
mp
u
ti
n
g
,
v
o
l
/i
ss
u
e
:
17
(
2
)
,
p
p
.
2
9
3
-
3
0
6
,
F
e
b
2
0
1
8
.
[3
0
]
Z.
Ya
n
g
,
e
t
a
l
.
,
“
DF
T
e
rNe
t:
T
o
w
a
rd
s
2
-
b
it
D
y
n
a
m
ic
F
u
sio
n
Ne
tw
o
rk
s
f
o
r
A
c
c
u
r
a
te
Hu
m
a
n
Ac
ti
v
it
y
Re
c
o
g
n
it
io
n
,
”
in
IE
EE
Acc
e
ss
,
v
o
l
.
6
,
p
p
.
5
6
7
5
0
-
5
6
7
6
4
,
2
0
1
8
.
[3
1
]
R.
X
i
,
e
t
a
l
.,
“
De
e
p
Dilatio
n
o
n
M
u
lt
im
o
d
a
li
ty
T
i
m
e
S
e
ries
f
o
r
Hu
m
a
n
A
c
ti
v
it
y
Re
c
o
g
n
it
io
n
,
”
in
IEE
E
Acc
e
ss
,
v
o
l.
6
,
p
p
.
5
3
3
8
1
-
5
3
3
9
6
,
2
0
1
8
.
[3
2
]
A
.
L
.
Ha
ro
o
n
P
.
S
.
a
n
d
U.
E
ra
n
n
a
,
“
A
n
Ef
f
ici
e
n
t
A
c
ti
v
it
y
De
tec
ti
o
n
S
y
ste
m
b
a
se
d
o
n
S
k
e
leto
n
Jo
i
n
ts
Id
e
n
ti
f
ica
ti
o
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
ol
/i
ss
u
e
:
8
(
6
)
,
p
p
.
4
9
9
5
-
5
0
0
3
,
2
0
1
8
.
[3
3
]
A
.
H
e
n
p
ra
se
rtt
a
e
,
S
.
T
h
ie
m
jaru
s
a
n
d
S
.
M
a
ru
k
a
tat,
"
Ac
c
u
ra
te
Ac
ti
v
it
y
Re
c
o
g
n
it
io
n
Us
in
g
a
M
o
b
il
e
P
h
o
n
e
Re
g
a
rd
les
s
o
f
De
v
ice
Orie
n
tatio
n
a
n
d
L
o
c
a
ti
o
n
,
"
2
0
1
1
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
B
o
d
y
S
e
n
s
o
r
N
e
two
rk
s
,
Da
ll
a
s,
T
X
,
2
0
1
1
,
p
p
.
4
1
-
46
[3
4
]
E.
Na
k
a
g
a
w
a
,
K.
M
o
ri
y
a
,
H.
S
u
w
a
,
M
.
F
u
ji
m
o
to
,
Y.
A
ra
k
a
w
a
a
n
d
K.
Ya
su
m
o
to
,
"
T
o
wa
rd
re
a
l
-
ti
m
e
in
-
h
o
m
e
a
c
ti
v
it
y
re
c
o
g
n
it
io
n
u
s
in
g
in
d
o
o
r
p
o
siti
o
n
i
n
g
se
n
so
r
a
n
d
p
o
w
e
r
m
e
ters
,
"
2
0
1
7
IEE
E
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Per
v
a
siv
e
Co
mp
u
ti
n
g
a
n
d
C
o
mm
u
n
ica
ti
o
n
s W
o
rk
sh
o
p
s (
Per
Co
m W
o
rk
sh
o
p
s)
,
Ko
n
a
,
HI,
2
0
1
7
,
p
p
.
5
3
9
-
5
4
4
.
[3
5
]
E.
Zd
ra
v
e
v
s
k
i
e
t
a
l
.
,
"
Im
p
ro
v
i
n
g
A
c
ti
v
it
y
Re
c
o
g
n
it
io
n
A
c
c
u
r
a
c
y
in
Am
b
ie
nt
-
A
s
siste
d
L
iv
in
g
S
y
ste
m
s
b
y
A
u
to
m
a
ted
F
e
a
tu
re
En
g
in
e
e
rin
g
,
"
in
IE
EE
Acc
e
ss
,
v
o
l.
5
,
p
p
.
5
2
6
2
-
5
2
8
0
,
2
0
1
7
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Abd
u
l
La
t
e
e
f
H
a
r
o
o
n
P.
S
.
,
c
u
rr
e
n
tl
y
w
o
rk
in
g
a
s
a
n
A
ss
istan
t
P
r
o
f
e
ss
o
r
in
th
e
De
p
a
rtm
e
n
t
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
in
e
e
rin
g
,
Ba
ll
a
ri
In
stit
u
t
e
o
f
T
e
c
h
n
o
lo
g
y
a
n
d
M
a
n
a
g
e
m
e
n
t.
I
h
a
v
e
c
o
m
p
lete
d
B.
E
f
ro
m
RYME
C
Co
ll
e
g
e
,
Ba
ll
a
ri
d
u
rin
g
2
0
0
8
-
2
0
1
2
w
it
h
a
g
g
re
g
a
te
7
2
%
;
I
h
a
v
e
d
o
n
e
M
.
T
e
c
h
f
ro
m
KSS
EM
Co
ll
e
g
e
,
Ba
n
g
a
lo
re
d
u
rin
g
2
0
1
2
-
2
0
1
4
w
it
h
a
g
g
re
g
a
te
8
4
%
.
I
a
m
Cu
rre
n
tl
y
P
u
rsu
i
n
g
P
h
.
D.
f
ro
m
V
T
U
w
it
h
BIT
M
Co
ll
e
g
e
a
s
a
Re
se
a
rc
h
c
e
n
tre.
I
h
a
v
e
p
u
b
li
sh
e
d
7
IEE
E
C
o
n
f
e
re
n
c
e
P
a
p
e
rs
a
n
d
2
0
In
tern
a
ti
o
n
a
l
Jo
u
r
n
a
ls.
M
y
a
re
a
s
o
f
In
tere
st
a
re
Dig
it
a
l
S
ig
n
a
l
P
r
o
c
e
ss
in
g
,
Dig
it
a
l
Im
a
g
e
P
ro
c
e
ss
in
g
,
Co
m
p
u
ter
Visio
n
,
A
RM
M
icro
c
o
n
tro
ll
e
rs,
a
n
d
Ne
u
r
a
l
Ne
tw
o
rk
s
.
U.
Er
a
n
n
a
,
Cu
rre
n
tl
y
w
o
rk
in
g
a
s
P
ro
f
e
ss
o
r
a
n
d
HO
D
in
th
e
D
e
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
,
Ba
ll
a
ri
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
a
n
d
M
a
n
a
g
e
m
e
n
t.
He
h
a
s
p
u
b
li
sh
e
d
8
c
o
n
f
e
re
n
c
e
p
a
p
e
rs
a
n
d
2
0
jo
u
rn
a
l
p
a
p
e
rs.
His
a
re
a
o
f
re
se
a
rc
h
w
a
s
Co
m
m
u
n
ica
ti
o
n
,
Co
n
tr
o
l
S
y
ste
m
Evaluation Warning : The document was created with Spire.PDF for Python.