I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
6
,
Decem
b
er
20
25
,
p
p
.
5
1
6
2
~
5
1
7
2
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
6
.
pp
5
1
6
2
-
5
1
7
2
5162
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Sma
rt
wea
ra
ble
glo
v
e f
o
r enhanced
huma
n
-
ro
bo
t
i
nt
eractio
n
using
multi
-
se
nso
r f
usio
n and
ma
chine learning
No
urdin
e
H
er
ba
z
1
,
H
a
s
s
a
n
E
l Id
r
is
s
i
1
,
H
a
m
za
Sa
bir
2
,
A
bd
elm
a
j
id B
a
dri
1
1
La
b
o
r
a
t
o
r
y
o
f
E
l
e
c
t
r
o
n
i
c
s
,
E
n
e
r
g
y
,
A
u
t
o
ma
t
i
o
n
a
n
d
I
n
f
o
r
ma
t
i
o
n
P
r
o
c
e
ss
i
n
g
(
LE
EA
&
TI
)
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
s a
n
d
Te
c
h
n
i
q
u
e
s
M
o
h
a
mm
e
d
i
a
,
H
a
ssa
n
I
I
U
n
i
v
e
r
si
t
y
o
f
C
a
s
a
b
l
a
n
c
a
,
M
o
h
a
mm
e
d
i
a
,
M
o
r
o
c
c
o
2
La
b
o
r
a
t
o
r
y
o
f
E
n
g
i
n
e
e
r
i
n
g
S
c
i
e
n
c
e
s
& B
i
o
s
c
i
e
n
c
e
s,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
s a
n
d
T
e
c
h
n
i
q
u
e
s
o
f
M
o
h
a
m
me
d
i
a
,
H
a
s
sa
n
I
I
U
n
i
v
e
r
si
t
y
,
C
a
sa
b
l
a
n
c
a
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
1
3
,
2
0
2
5
R
ev
is
ed
J
u
l 1
3
,
2
0
2
5
Acc
ep
ted
Sep
1
4
,
2
0
2
5
Ha
n
d
g
e
stu
re
re
c
o
g
n
it
io
n
(HG
R)
u
sin
g
flex
ib
le
se
n
so
rs
(
f
lex
-
se
n
so
r
)
a
n
d
t
h
e
M
P
U6
0
5
0
se
n
so
r
h
a
s
p
ro
v
e
d
to
b
e
a
k
e
y
a
re
a
o
f
re
se
a
r
c
h
in
h
u
m
a
n
-
m
a
c
h
in
e
in
tera
c
ti
o
n
,
wit
h
m
a
jo
r
a
p
p
l
ica
ti
o
n
s
i
n
b
ias
in
g
,
re
h
a
b
il
it
a
ti
o
n
,
a
n
d
a
ss
isted
ro
b
o
ti
c
s.
T
h
is
p
a
p
e
r
p
r
o
p
o
se
s
a
we
a
ra
b
le
in
telli
g
e
n
t
g
lo
v
e
d
e
sig
n
e
d
to
o
p
e
ra
te
a
r
o
b
o
ti
c
s
a
rm
in
re
a
l
ti
m
e
,
re
ly
in
g
o
n
m
u
lt
i
-
se
n
so
r
f
u
sio
n
a
n
d
m
a
c
h
in
e
lea
rn
in
g
m
e
th
o
d
s
to
e
n
h
a
n
c
e
th
e
s
y
ste
m
'
s
re
sp
o
n
siv
e
n
e
ss
a
n
d
p
re
c
isio
n
.
T
h
e
p
r
o
p
o
se
d
s
y
ste
m
e
n
a
b
les
th
e
in
t
u
it
i
v
e
re
p
r
o
d
u
c
ti
o
n
o
f
h
a
n
d
m
o
v
e
m
e
n
ts
a
n
d
p
re
c
ise
c
o
n
tr
o
l
o
f
th
e
ro
b
o
ti
c
a
rm
.
In
th
e
c
o
n
tex
t
o
f
In
d
u
stry
4
.
0
a
n
d
i
n
tern
e
t
o
f
t
h
in
g
s
(
Io
T
)
,
t
h
e
c
las
sifica
ti
o
n
o
f
g
e
stu
re
s
is
n
e
c
e
ss
a
ry
fo
r
m
a
in
tain
in
g
o
p
e
ra
ti
o
n
a
l
e
fficie
n
c
y
.
To
g
u
a
ra
n
tee
g
e
stu
re
re
c
o
g
n
it
io
n
,
d
a
ta
sig
n
a
ls
fr
o
m
t
h
e
sm
a
rt
g
lo
v
e
a
re
c
o
ll
e
c
ted
a
n
d
trai
n
e
d
b
y
a
re
c
u
rr
e
n
t
n
e
u
ra
l
n
e
two
rk
(RNN
),
w
h
ich
a
c
h
ie
v
e
s 9
8
.
6
7
%
a
c
c
u
ra
c
y
fo
r
re
a
l
-
ti
m
e
c
las
sifica
ti
o
n
o
f
se
v
e
n
g
e
stu
re
s
.
Be
y
o
n
d
i
n
d
u
st
ria
l
a
p
p
l
ica
t
i
o
n
s
,
t
h
e
we
a
ra
b
l
e
s
m
a
rt
g
l
o
v
e
c
a
n
b
e
e
x
p
l
o
i
te
d
i
n
a
re
c
o
g
n
iz
e
d
c
irc
u
it
o
f
a
l
l
s
y
st
e
m
s
,
i
n
c
l
u
d
i
n
g
re
h
a
b
il
it
a
t
i
o
n
e
x
e
rc
i
se
s
t
h
a
t
i
n
v
o
lv
e
re
c
o
r
d
i
n
g
t
h
e
p
r
o
g
r
e
ss
i
o
n
o
f
m
u
sc
u
la
r
a
c
t
i
v
i
ty
f
o
r
t
h
e
a
ss
e
ss
m
e
n
t
o
f
m
o
t
o
r
fu
n
c
t
i
o
n
s
a
n
d
se
r
v
e
a
s
a
t
o
o
l
f
o
r
p
a
ti
e
n
t
re
c
o
v
e
ry
.
K
ey
w
o
r
d
s
:
Flex
s
en
s
o
r
s
Hu
m
an
–
r
o
b
o
t in
te
r
ac
tio
n
I
n
ter
n
et
o
f
t
h
in
g
s
Ma
ch
in
e
lear
n
in
g
alg
o
r
ith
m
s
R
o
b
o
tic
ar
m
s
Sig
n
al
p
r
o
ce
s
s
in
g
W
ea
r
ab
le
d
ev
ice
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
:
No
u
r
d
in
e
Her
b
az
L
ab
o
r
ato
r
y
o
f
E
lectr
o
n
ics,
E
n
er
g
y
,
Au
t
o
m
atio
n
a
n
d
I
n
f
o
r
m
a
tio
n
Pro
ce
s
s
in
g
(
L
E
E
A
&
T
I
)
,
Facu
lty
o
f
Scien
ce
s
an
d
T
ec
h
n
iq
u
es M
o
h
am
m
ed
ia,
Hass
an
I
I
Un
iv
e
r
s
ity
o
f
C
asab
lan
ca
Mo
h
am
m
ed
ia,
2
8
8
0
6
,
M
o
r
o
cc
o
E
m
ail:
h
er
b
az
n
o
u
r
d
i
n
e
@
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
o
d
ay
,
as
co
n
n
ec
tiv
ity
,
au
to
m
atio
n
an
d
em
b
ed
d
ed
in
tell
ig
en
ce
r
ed
e
f
in
e
o
u
r
r
elatio
n
s
h
ip
with
in
ter
ac
tiv
e
s
y
s
tem
s
,
th
e
d
ev
elo
p
m
en
t
o
f
ad
v
a
n
ce
d
h
u
m
an
-
m
ac
h
in
e
i
n
ter
ac
tio
n
(
H
MI
)
s
o
lu
tio
n
s
is
a
f
u
n
d
am
e
n
tal
p
illar
o
f
tech
n
o
lo
g
ical
r
esear
ch
.
Am
o
n
g
t
h
ese
s
o
lu
tio
n
s
,
wea
r
a
b
le
g
estu
r
e
in
t
er
f
ac
es
ar
e
g
ain
in
g
in
p
o
p
u
lar
ity
,
as
th
ey
en
ab
le
in
tu
itiv
e,
co
n
tactless
an
d
ad
ap
t
iv
e
co
m
m
u
n
icatio
n
b
etwe
en
th
e
u
s
er
an
d
d
ig
ital
s
y
s
tem
s
[
1
]
.
T
h
e
in
teg
r
atio
n
o
f
f
le
x
ib
le
s
en
s
o
r
s
an
d
in
e
r
tial
m
ea
s
u
r
em
en
t
u
n
its
(
I
MU
s
)
in
t
o
s
m
ar
t
g
lo
v
es
o
f
f
er
s
a
p
r
o
m
is
in
g
way
to
ac
c
u
r
ately
c
ap
tu
r
e
h
an
d
g
estu
r
es,
wh
ile
r
e
d
u
cin
g
h
ar
d
war
e
c
o
m
p
lex
ity
.
R
ec
en
t
ap
p
r
o
ac
h
es
h
av
e
ex
p
lo
ited
t
h
ese
s
en
s
o
r
s
to
d
r
iv
e
r
o
b
o
tic
a
r
m
s
v
ia
s
en
s
o
r
y
o
b
ject
in
ter
n
et
o
f
th
in
g
s
(
I
o
ST)
p
latf
o
r
m
s
,
with
en
co
u
r
a
g
in
g
r
esu
lts
in
ter
m
s
o
f
c
o
s
t
an
d
ef
f
icien
c
y
[
2
]
.
Ot
h
er
wo
r
k
s
h
a
v
e
p
r
o
p
o
s
ed
co
m
b
in
atio
n
s
o
f
m
icr
o
-
elec
tr
o
-
m
ec
h
an
ical
s
y
s
tem
s
(
ME
MS)
s
en
s
o
r
s
,
co
n
v
o
lu
tio
n
a
l
n
eu
r
al
n
etwo
r
k
s
o
r
B
ay
esian
m
o
d
els
to
im
p
r
o
v
e
th
e
r
o
b
u
s
tn
ess
o
f
th
e
r
ec
o
g
n
i
tio
n
s
y
s
tem
[
3
]
,
[
4
]
.
A
n
u
m
b
er
o
f
lim
itatio
n
s
r
em
ain
d
esp
ite
th
ese
ad
v
an
ce
s
:
So
m
e
f
lex
ib
le
g
lo
v
es
ar
e
ex
p
e
n
s
iv
e
an
d
r
e
q
u
ir
e
f
r
eq
u
e
n
t
ca
li
b
r
atio
n
[
5
]
,
I
MU
s
alo
n
e
ar
e
s
e
n
s
itiv
e
to
tem
p
o
r
al
d
r
if
t
[
6
]
,
elec
tr
o
m
y
o
g
r
ap
h
ic
(
E
MG
)
an
d
p
iezo
r
esis
tiv
e
d
ev
ices
r
eq
u
ir
e
p
r
ec
is
e
wea
r
in
g
co
n
d
itio
n
s
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
S
ma
r
t wea
r
a
b
le
g
lo
ve
fo
r
en
h
a
n
ce
d
h
u
ma
n
-
r
o
b
o
t in
tera
ctio
n
…
(
N
o
u
r
d
in
e
Herb
a
z
)
5163
co
m
p
lex
in
ter
p
r
etatio
n
[
7
]
,
Fin
ally
,
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
o
n
p
o
wer
f
u
l
p
latf
o
r
m
s
(
J
e
ts
o
n
,
GPU)
ar
e
n
o
t
ea
s
ily
em
b
ed
d
ed
[
8
]
,
[
9
]
.
Face
d
with
th
ese
ch
allen
g
es,
th
e
p
r
o
b
lem
o
f
th
is
s
tu
d
y
is
as
f
o
llo
ws:
Ho
w
ca
n
w
e
d
esig
n
a
lig
h
tw
eig
h
t,
lo
w
-
co
s
t,
w
ea
r
a
b
le
g
estu
r
e
in
te
r
fa
ce
c
o
mb
in
in
g
p
a
s
s
ive
a
n
d
in
erti
a
l
s
en
s
o
r
s
w
i
th
r
ea
l
-
time
emb
ed
d
ed
p
r
o
ce
s
s
in
g
to
co
n
tr
o
l a
r
o
b
o
tic
a
r
m
a
cc
u
r
a
t
ely
a
n
d
r
o
b
u
s
tly?
T
h
is
wo
r
k
p
r
o
p
o
s
es
an
a
n
s
wer
th
r
o
u
g
h
th
e
d
ev
elo
p
m
en
t
o
f
a
m
u
ltimo
d
al
s
m
ar
t
g
lo
v
e
co
m
b
in
in
g
r
esis
tiv
e
f
lex
io
n
s
en
s
o
r
s
,
an
MPU6
0
5
0
I
MU
,
an
d
an
E
SP
3
2
b
o
ar
d
f
o
r
o
n
-
b
o
ar
d
p
r
o
ce
s
s
in
g
.
Gestu
r
e
r
ec
o
g
n
itio
n
is
p
r
o
v
id
ed
b
y
o
p
t
im
ized
s
u
p
er
v
is
ed
m
o
d
els,
en
ab
lin
g
d
y
n
am
ic
h
a
n
d
m
o
v
em
e
n
ts
to
b
e
p
r
e
d
icted
an
d
a
r
o
b
o
tic
a
r
m
to
b
e
co
n
tr
o
lled
in
r
ea
l
tim
e.
Ou
r
co
n
t
r
ib
u
tio
n
s
ar
e
as
f
o
llo
ws:
T
h
e
h
ar
d
war
e
d
esig
n
o
f
a
lo
w
-
co
s
t,
en
er
g
y
-
e
f
f
icien
t
s
m
ar
t
g
lo
v
e,
in
teg
r
atin
g
f
lex
s
en
s
o
r
s
an
d
I
MU
.
An
em
b
ed
d
ed
s
o
f
twar
e
ar
ch
itectu
r
e
o
n
E
SP
3
2
,
ca
p
ab
le
o
f
p
r
o
ce
s
s
in
g
s
en
s
o
r
s
ig
n
als
lo
ca
lly
an
d
s
en
d
in
g
g
estu
r
e
co
m
m
a
n
d
s
.
A
m
u
lti
-
s
en
s
o
r
d
ata
f
u
s
io
n
m
eth
o
d
to
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
an
d
s
tab
ilit
y
o
f
g
estu
r
e
class
if
icatio
n
.
I
n
teg
r
atio
n
o
f
th
e
s
y
s
tem
with
a
r
o
b
o
tic
a
r
m
,
v
alid
ated
b
y
e
x
p
er
im
en
ts
r
ep
r
o
d
u
cin
g
c
o
m
p
l
ex
g
estu
r
es
in
an
I
n
d
u
s
tr
i
4
.
0
ty
p
e
e
n
v
ir
o
n
m
en
t.
A
b
en
ch
m
a
r
k
in
g
s
tu
d
y
with
ex
is
tin
g
ap
p
r
o
ac
h
es,
d
em
o
n
s
t
r
atin
g
th
e
r
elev
an
ce
o
f
o
u
r
s
o
lu
tio
n
in
ter
m
s
o
f
laten
cy
,
co
s
t a
n
d
ac
c
u
r
ac
y
.
T
h
e
ex
p
er
im
en
tal
r
esu
lts
o
b
ta
in
ed
s
h
o
w
th
at
o
u
r
s
o
lu
tio
n
p
r
o
v
id
es
r
eliab
le
r
ec
o
g
n
itio
n
a
n
d
s
m
o
o
th
co
n
tr
o
l,
with
an
a
n
g
u
lar
er
r
o
r
o
f
less
th
an
±
0
.
1
5
°
o
n
all
th
r
ee
ax
es
(
r
o
ll,
p
itch
,
y
aw)
.
C
o
m
p
ar
ed
with
m
o
r
e
co
m
p
lex
o
r
co
s
tly
s
y
s
tem
s
,
o
u
r
a
p
p
r
o
ac
h
r
ep
r
esen
ts
a
g
o
o
d
co
m
p
r
o
m
is
e
b
etwe
en
h
a
r
d
war
e
s
im
p
licity
,
g
estu
r
al
p
r
ec
is
io
n
an
d
r
o
b
o
ti
c
in
teg
r
atio
n
[
1
0
]
.
So
m
e
f
lex
ib
le
g
lo
v
es
b
ased
o
n
s
o
f
t
p
ie
zo
r
esis
tiv
e
s
en
s
o
r
s
,
s
u
ch
as
th
o
s
e
b
ased
o
n
p
o
ly
d
i
m
eth
y
ls
ilo
x
an
e
-
ca
r
b
o
n
b
lac
k
(
PDMS
-
C
B
)
,
h
av
e
d
em
o
n
s
tr
at
ed
g
o
o
d
s
en
s
itiv
ity
,
b
u
t
p
o
s
e
ch
allen
g
es
o
f
d
u
r
a
b
ilit
y
an
d
lo
n
g
-
ter
m
r
e
p
r
o
d
u
cib
il
ity
[
1
1
]
.
R
ec
en
t
wo
r
k
h
as
p
r
o
p
o
s
ed
E
MG
m
o
d
els
em
b
ed
d
e
d
o
n
ed
g
e
ar
tific
ial
i
n
tellig
en
ce
(
AI
)
ar
ch
itectu
r
es,
en
ab
lin
g
d
y
n
am
ic
g
estu
r
e
r
ec
o
g
n
itio
n
with
g
o
o
d
p
er
f
o
r
m
an
ce
,
b
u
t sti
ll r
eq
u
ir
in
g
u
s
er
-
s
p
ec
if
ic
tu
n
i
n
g
[
1
2
]
.
T
h
e
r
em
ain
d
e
r
o
f
th
is
ar
tic
le
is
s
tr
u
ctu
r
ed
as
f
o
llo
ws:
Sectio
n
2
p
r
esen
ts
r
elate
d
wo
r
k
an
d
co
m
p
ar
ativ
e
ap
p
r
o
ac
h
es
i
n
th
e
liter
atu
r
e.
Sectio
n
3
d
etails
th
e
s
y
s
tem
ar
ch
itect
u
r
e
an
d
p
r
o
p
o
s
ed
m
eth
o
d
o
l
o
g
y
.
Sectio
n
4
p
r
es
en
ts
th
e
e
x
p
er
im
en
tal
r
esu
lts
an
d
th
eir
co
m
p
ar
is
o
n
with
e
x
is
tin
g
ap
p
r
o
ac
h
es.
Fin
ally
,
s
ec
tio
n
5
co
n
cl
u
d
es th
e
im
p
licatio
n
s
o
f
o
u
r
s
o
lu
tio
n
an
d
p
r
o
p
o
s
es a
v
en
u
es f
o
r
im
p
r
o
v
em
en
t.
2.
RE
L
AT
E
D
WO
RK
2
.
1
.
Wea
ra
ble dev
ice
f
o
r
ma
nip
u
la
t
o
r
co
ntr
o
l:
hu
m
a
n
-
co
m
pu
t
er
inte
ra
ct
io
n
Hu
m
an
-
co
m
p
u
ter
in
te
r
ac
tio
n
s
y
s
tem
s
h
av
e
b
ee
n
r
ev
o
lu
tio
n
ized
b
y
wea
r
ab
le
s
en
s
o
r
s
,
p
r
o
v
id
in
g
a
n
in
tu
itiv
e
an
d
ef
f
icien
t
m
ea
n
s
o
f
co
m
m
u
n
icatio
n
b
etwe
en
h
u
m
an
s
an
d
m
ac
h
in
es.
T
h
e
m
an
y
ap
p
licatio
n
s
o
f
th
ese
s
en
s
o
r
s
h
elp
to
en
h
an
ce
th
e
u
s
er
en
v
ir
o
n
m
en
t
th
r
o
u
g
h
g
estu
r
e
r
ec
o
g
n
itio
n
,
p
h
y
s
io
lo
g
ical
m
o
n
ito
r
i
n
g
,
an
d
h
ap
tic
f
ee
d
b
ac
k
.
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
m
ain
f
ea
tu
r
es
o
f
h
u
m
an
-
m
ac
h
in
e
in
ter
ac
tio
n
s
y
s
tem
s
b
ased
o
n
wea
r
ab
le
s
en
s
o
r
s
an
d
t
h
eir
a
p
p
licatio
n
in
t
h
e
liter
atu
r
e
r
e
v
iew.
R
ec
en
t
in
n
o
v
atio
n
s
in
s
en
s
o
r
tech
n
o
lo
g
ies
h
av
e
s
ig
n
if
ican
tly
im
p
r
o
v
ed
g
estu
r
e
r
ec
o
g
n
itio
n
a
n
d
h
u
m
an
-
m
ac
h
in
e
in
ter
ac
tio
n
w
h
ile
o
p
en
in
g
u
p
n
e
w
p
r
o
s
p
ec
ts
f
o
r
e
r
g
o
n
o
m
ic
a
p
p
li
ca
tio
n
s
.
T
r
ib
o
elec
tr
ic
s
en
s
o
r
s
,
f
lex
s
en
s
o
r
s
,
an
d
d
ielec
tr
ic
elasto
m
er
m
atr
ices:
T
r
ib
o
elec
tr
ic
s
en
s
o
r
s
,
s
u
ch
as
th
e
tr
ib
o
elec
tr
ic
d
r
u
m
n
an
o
g
en
er
ato
r
(
DS
-
T
E
NG)
,
h
av
e
p
r
o
v
e
d
p
a
r
ticu
lar
ly
e
f
f
ec
tiv
e
at
d
etec
tin
g
lig
h
t
p
r
ess
u
r
e
s
ig
n
als,
with
a
d
etec
t
io
n
lim
it
s
et
at
3
.
9
Pa
a
n
d
an
ac
cu
r
ac
y
r
ate
o
f
u
p
to
9
2
%
in
g
estu
r
e
r
ec
o
g
n
itio
n
[
1
3
]
.
At
th
e
s
am
e
tim
e,
th
e
in
teg
r
atio
n
o
f
d
ielec
tr
ic
ela
s
to
m
er
m
atr
ices
in
tex
tiles
en
ab
les
co
n
tin
u
o
u
s
in
ter
ac
tio
n
with
th
e
u
s
er
wh
ile
ac
h
iev
in
g
a
p
r
ed
ictiv
e
ef
f
icien
cy
o
f
at
least
8
0
%,
th
an
k
s
to
h
ig
h
ly
s
o
p
h
is
ticated
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
[
1
4
]
.
T
h
e
r
esear
c
h
f
o
r
th
e
c
o
m
f
o
r
t
an
d
p
er
s
o
n
al
izatio
n
o
f
wea
r
ab
le
d
ev
ices
is
g
r
ea
tly
f
o
cu
s
ed
o
n
th
e
in
teg
r
atio
n
o
f
f
lex
ib
le
s
en
s
o
r
s
,
s
u
ch
as
E
MG
s
ig
n
als
[
1
5
]
,
I
MU
s
en
s
o
r
s
[
1
6
]
,
f
lex
s
en
s
o
r
s
[
2
]
,
o
r
tex
tile
s
en
s
o
r
s
[
5
]
.
Ap
p
licatio
n
s
in
er
g
o
n
o
m
ics
an
d
h
u
m
a
n
-
m
ac
h
i
n
e
in
ter
ac
tio
n
:
I
n
th
e
f
ield
o
f
in
tellig
en
t
wea
r
ab
les,
ar
tific
ial
in
tellig
en
ce
-
ass
is
ted
ex
o
-
s
k
eleto
n
s
m
a
k
e
in
d
u
s
tr
ial
task
s
ea
s
ier
b
y
r
ed
u
cin
g
m
u
s
cu
lar
f
atig
u
e
an
d
m
ax
im
izin
g
p
o
s
tu
r
e.
Su
ch
d
e
v
ices
in
teg
r
ate
m
ac
h
in
e
-
lear
n
i
n
g
m
o
d
els
to
o
f
f
er
r
ea
l
-
tim
e
p
er
s
o
n
alize
d
s
u
p
p
o
r
t
[
3
]
,
[
9
]
.
I
n
ad
d
itio
n
,
en
a
b
lin
g
s
y
s
tem
s
co
m
b
in
in
g
tr
ib
o
elec
t
r
ic
s
en
s
in
g
an
d
p
n
e
u
m
atic
f
ee
d
b
ac
k
e
n
h
an
ce
th
e
u
s
er
ex
p
e
r
ien
ce
b
y
p
r
o
v
id
in
g
r
ea
lis
tic
to
u
ch
s
en
s
atio
n
s
,
with
ap
p
licatio
n
s
in
v
ir
tu
al
r
ea
lity
(
VR
)
a
n
d
r
eh
ab
ilit
atio
n
[
1
3
]
.
Desp
ite
th
ese
ad
v
an
ce
s
,
ch
allen
g
es
r
e
m
ain
,
p
ar
ticu
lar
ly
in
te
r
m
s
o
f
s
en
s
o
r
ac
cu
r
ac
y
,
co
m
f
o
r
t,
an
d
en
e
r
g
y
ef
f
icien
c
y
.
Fu
r
th
e
r
m
in
iatu
r
izatio
n
a
n
d
u
s
er
ad
a
p
tab
ilit
y
ar
e
cr
u
cial
ar
ea
s
o
f
r
esear
ch
to
en
s
u
r
e
o
p
tim
al
in
teg
r
atio
n
in
a
v
ar
iety
o
f
ap
p
licatio
n
co
n
te
x
ts
[
1
]
.
I
n
ad
d
itio
n
,
th
e
wid
e
s
p
r
ea
d
ad
o
p
tio
n
o
f
wea
r
ab
le
s
en
s
o
r
s
m
ay
b
e
h
a
m
p
er
ed
b
y
c
o
n
ce
r
n
s
a
b
o
u
t
d
ata
p
r
iv
ac
y
,
cy
b
e
r
s
ec
u
r
ity
,
a
n
d
o
v
er
-
r
elian
ce
o
n
d
ig
ital te
ch
n
o
lo
g
ies.
2
.
2
.
H
a
nd
m
o
v
em
ent
re
c
o
g
n
it
io
n
ba
s
ed
o
n si
g
na
l
Sig
n
al
-
b
ased
r
ec
o
g
n
itio
n
o
f
h
an
d
g
estu
r
es,
i
n
p
a
r
ticu
lar
s
ig
n
als
f
r
o
m
f
lex
io
n
o
r
E
MG
s
en
s
o
r
s
,
h
as
attr
ac
ted
g
r
o
win
g
in
ter
est
in
a
v
ar
iety
o
f
ap
p
licatio
n
s
,
esp
ec
i
ally
p
r
o
s
th
etics,
r
o
b
o
tic
ar
m
c
o
n
tr
o
l,
an
d
h
u
m
an
-
co
m
p
u
ter
in
ter
f
ac
e.
T
h
e
im
p
l
em
en
tatio
n
o
f
m
ac
h
in
e
lear
n
i
n
g
tech
n
o
l
o
g
y
h
el
p
ed
in
cr
ea
s
e
th
e
ac
cu
r
ac
y
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
6
,
Decem
b
e
r
20
25
:
5
1
6
2
-
5
1
7
2
5164
ef
f
icien
cy
o
f
r
ec
o
g
n
izin
g
h
a
n
d
g
estu
r
es
f
r
o
m
s
ig
n
al
-
b
ased
d
ata.
T
h
is
tech
n
o
lo
g
y
n
o
t
o
n
l
y
en
h
a
n
ce
s
h
u
m
a
n
-
co
m
p
u
ter
i
n
ter
ac
tio
n
b
u
t a
ls
o
s
er
v
es a
s
a
v
ital to
o
l f
o
r
i
n
d
iv
i
d
u
als with
h
ea
r
in
g
im
p
air
m
en
t
s
.
Flex
s
en
s
o
r
tech
n
o
lo
g
y
:
Flex
s
en
s
o
r
s
h
av
e
an
im
p
o
r
tan
t
r
o
le
to
p
lay
in
g
estu
r
e
r
ec
o
g
n
itio
n
,
m
ea
s
u
r
in
g
th
e
d
eg
r
ee
o
f
f
in
g
er
f
lex
io
n
an
d
p
r
o
v
id
in
g
r
ea
l
-
tim
e
d
ata
o
n
h
an
d
m
o
v
em
e
n
t
s
.
T
h
eir
in
teg
r
atio
n
with
o
th
er
s
en
s
in
g
s
y
s
tem
s
,
s
u
ch
as
I
MU
s
,
s
ig
n
if
ican
tly
en
h
an
ce
s
th
e
ac
c
u
r
ac
y
o
f
g
estu
r
e
r
ec
o
g
n
itio
n
[
1
7
]
.
Ma
ch
in
e
lear
n
i
n
g
h
as
o
p
tim
ized
g
estu
r
e
class
if
icatio
n
b
y
ex
p
lo
itin
g
v
ar
io
u
s
alg
o
r
ith
m
s
,
in
clu
d
in
g
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NN)
,
Gau
s
s
ian
n
aiv
e
B
ay
es
,
r
an
d
o
m
f
o
r
est,
k
-
n
ea
r
est n
ei
g
h
b
o
r
s
(
KNN)
,
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SV
M)
[
1
8
]
.
M
u
ltimo
d
al
d
ata
an
a
ly
s
is
,
wh
ich
co
m
b
in
es
f
lex
io
n
s
en
s
o
r
s
ig
n
als
with
o
th
er
d
ata
s
o
u
r
ce
s
,
h
as
p
r
o
v
e
d
a
m
ajo
r
en
h
a
n
ce
m
en
t
to
th
e
ef
f
ec
tiv
en
ess
o
f
class
if
icatio
n
m
o
d
els.
T
h
ese
ad
v
an
ce
s
f
ac
ilit
ate
in
ter
ac
tio
n
with
th
e
en
v
ir
o
n
m
en
t
an
d
h
elp
to
o
v
er
co
m
e
p
h
y
s
ical
lim
itatio
n
s
.
Ho
wev
er
,
d
esp
ite
th
e
p
r
o
g
r
ess
m
ad
e
in
th
e
d
esig
n
o
f
f
lex
ib
le
s
en
s
o
r
s
an
d
th
eir
c
o
m
b
in
atio
n
with
ad
v
an
ce
d
m
ac
h
i
n
e
lear
n
in
g
tech
n
iq
u
es,
g
estu
r
e
r
ec
o
g
n
itio
n
s
till
s
u
f
f
er
s
f
r
o
m
a
ce
r
tain
lack
o
f
v
ar
iety
i
n
tr
ain
in
g
d
atasets
.
W
id
er
d
ata
co
llectio
n
o
n
d
iv
e
r
s
e
s
en
s
o
r
s
r
em
ain
s
ess
en
tial to
im
p
r
o
v
e
m
o
d
el
r
o
b
u
s
tn
ess
an
d
g
en
e
r
aliza
tio
n
.
E
MG
s
ig
n
al
ac
q
u
is
itio
n
an
d
p
r
o
ce
s
s
in
g
:
T
h
e
ac
q
u
is
itio
n
an
d
an
aly
s
is
o
f
E
MG
s
ig
n
als
is
an
im
p
o
r
tan
t
s
tep
in
th
e
r
ec
o
g
n
iti
o
n
o
f
h
an
d
m
o
v
e
m
en
ts
.
T
h
e
s
ig
n
als
ar
e
ca
p
tu
r
ed
v
ia
elec
tr
o
d
es
attac
h
ed
to
th
e
s
k
in
,
allo
win
g
d
etec
tio
n
o
f
th
e
elec
tr
ical
ac
tiv
ity
g
en
er
ated
b
y
m
u
s
cle
co
n
tr
ac
tio
n
s
[
1
9
]
.
T
o
im
p
r
o
v
e
s
ig
n
al
p
r
o
ce
s
s
in
g
an
d
r
ec
o
g
n
itio
n
a
cc
u
r
ac
y
,
v
a
r
io
u
s
p
r
e
-
p
r
o
ce
s
s
in
g
s
tep
s
ar
e
im
p
lem
en
ted
,
n
o
tab
ly
,
in
ter
f
e
r
en
ce
f
ilter
in
g
,
ex
tr
ac
tio
n
o
f
r
elev
an
t
s
eg
m
en
ts
,
an
d
f
ea
tu
r
e
n
o
r
m
a
lizatio
n
.
I
n
r
ea
l
-
tim
e,
h
an
d
g
e
s
tu
r
es
ar
e
id
en
tifie
d
b
y
ac
ce
ler
atio
n
s
en
s
o
r
s
an
d
g
y
r
o
s
co
p
es,
w
h
ich
s
en
d
th
e
in
f
o
r
m
atio
n
to
co
n
tr
o
l
a
p
p
lic
atio
n
s
v
ia
ad
-
h
o
c
wir
eless
co
m
m
u
n
icatio
n
[
2
0
]
.
Featu
r
e
ex
tr
ac
tio
n
co
n
s
titu
tes
a
k
ey
p
h
ase
in
s
ig
n
al
in
ter
p
r
etatio
n
in
g
en
er
al.
Var
io
u
s
tech
n
iq
u
es
h
a
v
e
b
e
en
ad
o
p
te
d
,
s
u
ch
as
tim
e
-
s
y
n
ch
r
o
n
o
u
s
av
er
ag
in
g
[
2
1
]
–
[
2
3
]
,
tim
e
-
d
o
m
ai
n
d
escr
ip
to
r
s
,
an
d
wa
v
elet
tr
an
s
f
o
r
m
atio
n
s
,
to
b
etter
d
is
tin
g
u
is
h
th
e
v
alu
e
o
f
ea
c
h
s
ig
n
al.
T
ab
le
1
.
Ov
e
r
v
iew
o
f
s
tu
d
ies
o
n
m
o
d
el
-
b
ased
a
p
p
r
o
ac
h
es a
n
d
s
en
s
o
r
tech
n
o
lo
g
ies f
o
r
g
es
tu
r
e
r
ec
o
g
n
itio
n
Y
e
a
r
Ref
.
M
o
d
e
l
/
C
l
a
ssi
f
i
e
r
P
e
r
f
o
r
ma
n
c
e
me
t
r
i
c
s
G
e
st
u
r
e
/
P
u
r
p
o
se
S
e
n
s
o
r
s
C
o
n
t
r
o
l
l
e
d
r
o
b
o
t
i
c
s
2
0
1
9
[
5
]
N
e
u
r
a
l
n
e
t
w
o
r
k
(NN)
/
D
y
n
a
mi
c
t
i
me
w
a
r
p
i
n
g
(
D
TW)
a
l
g
o
r
i
t
h
m
D
a
t
a
f
r
o
m
4
m
a
l
e
s a
g
e
d
2
4
v
o
l
u
n
t
e
e
r
s,
R
e
c
o
g
n
i
t
i
o
n
a
c
c
u
r
a
c
y
:
9
8
.
5
%
f
o
r
2
0
0
0
st
a
t
i
c
d
i
g
i
t
s
g
e
s
t
u
r
e
s,
9
8
.
3
%
f
o
r
1
8
0
C
S
L
w
o
r
d
samp
l
e
s
.
C
h
i
n
e
se
C
S
L
;
d
a
t
a
h
a
v
e
b
e
e
n
c
o
l
l
e
c
t
e
d
w
i
t
h
2
0
0
0
s
t
a
t
i
c
d
i
g
i
t
a
n
d
9
C
S
L
w
o
r
d
s
a
m
p
l
e
s.
R
G
O
-
c
o
a
t
e
d
t
e
x
t
i
l
e
d
a
t
a
-
g
l
o
v
e
.
2
0
2
0
[
1
1
]
F
i
n
i
t
e
e
l
e
m
e
n
t
met
h
o
d
(
F
E
M
)
S
t
r
e
t
c
h
a
b
l
e
P
D
M
S
-
C
B
st
r
a
i
n
s
e
n
s
o
r
s
a
r
e
v
a
l
i
d
a
t
e
d
t
o
a
c
c
o
mm
o
d
a
t
e
l
a
r
g
e
r
d
e
f
o
r
mat
i
o
n
s
(
>
3
0
%)
C
o
n
t
r
o
l
s
t
h
e
mo
t
i
o
n
o
f
r
o
b
o
t
f
i
n
g
e
r
s
r
e
mo
t
e
l
y
P
D
M
S
-
C
B
st
r
a
i
n
sen
s
o
r
s
✓
2
0
2
1
[
1
5
]
Te
a
g
e
r
-
K
a
i
ser
e
n
e
r
g
y
o
p
e
r
a
t
o
r
(
TK
EO
)
/
(
me
a
n
a
b
s
o
l
u
t
e
v
a
l
u
e
,
z
e
r
o
c
r
o
ssi
n
g
s)
3
E
M
G
s
i
g
n
a
l
s fr
o
m
4
h
e
a
l
t
h
y
s
u
b
j
e
c
t
s
.
A
c
c
u
r
a
c
i
e
s:
7
4
–
9
8
%
.
Th
e
b
e
st
mo
d
e
l
h
a
d
9
6
.
6
7
%
a
c
c
u
r
a
c
y
,
9
9
.
6
6
%
r
e
c
a
l
l
,
a
n
d
9
6
.
9
9
%
p
r
e
c
i
si
o
n
.
C
l
a
s
si
f
y
i
n
g
u
p
p
e
r
a
r
m mo
v
e
me
n
t
s
u
s
i
n
g
EM
G
s
i
g
n
a
l
s.
C
o
n
t
r
o
l
l
i
n
g
a
2
-
D
o
F
r
o
b
o
t
i
c
a
r
m
e
f
f
e
c
t
i
v
e
l
y
.
Th
r
e
e
E
M
G
sen
s
o
r
s
✓
2
0
2
2
[
2
4
]
B
a
y
e
s
i
a
n
F
C
-
D
e
n
seN
e
t
s
4
.
7
%
i
n
c
r
e
a
se
i
n
mI
o
U
c
o
m
p
a
r
e
d
w
i
t
h
Eg
o
h
a
n
d
s
H
u
ma
n
-
r
o
b
o
t
c
o
l
l
a
b
o
r
a
t
i
o
n
(
H
R
C
)
d
a
t
a
se
t
f
r
o
m
3
h
u
m
a
n
a
g
e
n
t
s/
r
e
c
o
r
d
e
d
t
h
e
H
R
C
i
ma
g
e
d
a
t
a
u
si
n
g
a
c
a
mera
--
✓
2
0
2
3
[
1
6
]
G
a
u
ss
i
a
n
N
a
i
v
e
B
a
y
e
s
a
n
d
r
a
n
d
o
m
f
o
r
e
st
3
3
0
0
sa
mp
l
e
s
f
r
o
m
1
0
su
b
j
e
c
t
s
p
e
r
f
o
r
mi
n
g
h
a
n
d
g
e
st
u
r
e
s
.
c
a
sc
a
d
e
d
c
l
a
ss
i
f
i
e
r
w
i
t
h
h
i
g
h
a
c
c
u
r
a
c
y
(
9
2
%)
a
n
d
l
o
w
l
a
t
e
n
c
y
(
7
.
5
ms r
e
c
o
g
.
t
i
m
e
)
A
sy
n
c
h
r
o
n
o
u
s
h
a
n
d
g
e
s
t
u
r
e
d
e
t
e
c
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
me
t
h
o
d
6
D
o
F
I
M
U
s,
d
a
t
a
g
l
o
v
e
✓
2
0
2
3
[
1
7
]
D
y
n
a
mi
c
t
i
me
w
a
r
p
i
n
g
(
D
TW)
f
u
si
o
n
a
l
g
o
r
i
t
h
m
r
e
c
o
g
n
i
t
i
o
n
a
c
c
u
r
a
c
y
w
a
s 8
5
.
2
1
%
A
meric
a
n
A
S
L;
d
a
t
a
h
a
v
e
b
e
e
n
c
o
l
l
e
c
t
e
d
w
i
t
h
2
0
A
S
L
w
o
r
d
s
I
n
e
r
t
i
a
l
a
n
d
b
e
n
d
i
n
g
se
n
so
r
s
2
0
2
4
[
2
5
]
M
O
A
/
S
C
o
n
v
/
B
i
-
LSTM
/
G
R
U
m
o
d
e
l
A
c
c
u
r
a
c
y
,
P
r
e
c
i
s
i
o
n
,
R
e
c
a
l
l
,
F
1
-
S
c
o
r
e
(
≈
0
.
9
8
6
6
)
1
6
,
0
0
0
S
a
m
p
l
e
s,
4
I
n
d
i
v
i
d
u
a
l
s,
2
0
G
e
st
u
r
e
s
--
✓
2
0
2
5
[
2
6
]
I
n
t
e
g
r
a
t
i
o
n
o
f
S
W
C
N
Ts
w
i
t
h
i
n
P
D
M
S
ma
t
r
i
x
.
A
c
h
i
e
v
i
n
g
a
7
0
%
st
r
a
i
n
r
a
n
g
e
a
n
d
a
g
a
u
g
e
f
a
c
t
o
r
o
f
7
3
M
o
v
e
me
n
t
s
o
f
d
i
f
f
.
F
i
n
g
e
r
s
S
W
C
N
Ts/
P
D
M
S
c
o
m
p
o
si
t
e
s
t
r
a
i
n
sen
s
o
r
s
✓
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
S
ma
r
t wea
r
a
b
le
g
lo
ve
fo
r
en
h
a
n
ce
d
h
u
ma
n
-
r
o
b
o
t in
tera
ctio
n
…
(
N
o
u
r
d
in
e
Herb
a
z
)
5165
2
.
3
.
Rea
l
-
t
im
e
r
o
bo
t
ic
a
r
m
c
o
ntr
o
llin
g
R
ea
l
-
tim
e
co
n
tr
o
l
o
f
r
o
b
o
tic
a
r
m
s
v
ia
s
m
ar
t
g
lo
v
es
o
r
wea
r
a
b
le
d
ev
ices
u
s
es
th
e
p
o
wer
o
f
ad
v
an
ce
d
s
en
s
o
r
tech
n
o
lo
g
ies
in
s
y
n
er
g
y
with
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
f
o
r
n
at
u
r
al,
in
tu
itiv
e
h
u
m
an
-
m
ac
h
in
e
in
ter
ac
tio
n
.
T
h
ese
s
y
s
tem
s
d
etec
t
h
an
d
g
estu
r
es,
wh
ich
a
r
e
in
ter
p
r
ete
d
an
d
co
n
v
er
ted
in
to
co
m
m
a
n
d
s
f
o
r
r
o
b
o
tic
ar
m
s
in
a
v
a
r
iety
o
f
ap
p
licatio
n
s
,
f
r
o
m
r
e
h
ab
ilit
atio
n
an
d
g
am
i
n
g
to
i
n
d
u
s
tr
ial
au
to
m
atio
n
.
Sm
a
r
t
g
lo
v
e
s
y
s
tem
s
in
teg
r
ate
v
ar
io
u
s
tech
n
o
lo
g
ies
to
en
h
an
ce
r
o
b
o
t
co
m
m
a
n
d
.
T
h
e
in
teg
r
atio
n
o
f
m
u
ltimo
d
al
tactile
p
er
ce
p
tio
n
en
ab
les
s
m
ar
t
g
lo
v
es
t
o
an
al
y
ze
tactile
i
n
f
o
r
m
atio
n
an
d
b
u
ild
m
o
d
els
o
f
th
e
wo
r
ld
in
th
e
s
en
s
e
o
f
o
b
ject
s
h
ap
es
an
d
g
r
ip
s
tates,
u
s
in
g
p
r
ess
u
r
e,
b
en
d
in
g
,
an
d
also
h
ea
t
s
en
s
o
r
s
[
2
7
]
.
B
y
in
teg
r
atin
g
d
ee
p
lear
n
in
g
i
n
to
f
le
x
ib
le
s
m
ar
t
g
lo
v
es,
it
is
p
o
s
s
ib
le
to
d
eter
m
in
e
f
in
g
er
m
o
v
em
e
n
t
in
ten
tio
n
s
ea
r
ly
o
n
,
t
h
u
s
r
ed
u
cin
g
c
o
m
m
u
n
icatio
n
laten
cy
an
d
en
h
an
cin
g
r
o
b
o
t
co
n
t
r
o
l
[
2
8
]
.
On
t
h
e
o
th
er
h
an
d
,
b
y
u
s
in
g
s
u
r
f
ac
e
E
MG
(
E
lectr
o
m
y
o
g
r
am
)
s
ig
n
als,
it
is
p
o
s
s
ib
le
to
ex
ce
ed
ce
r
tain
ef
f
icien
cy
th
r
esh
o
ld
s
in
g
estu
r
e
r
ec
o
g
n
itio
n
,
th
u
s
en
ab
lin
g
a
m
in
im
al
m
o
d
e
o
f
o
p
er
atio
n
to
b
etter
co
n
t
r
o
l r
o
b
o
tic
ar
m
s
[
1
5
]
.
Gestu
r
e
-
co
n
tr
o
lled
r
o
b
o
tic
ar
m
s
ar
e
in
cr
ea
s
in
g
ly
ap
p
lied
in
m
an
u
f
ac
tu
r
in
g
an
d
teac
h
in
g
,
s
tr
ea
m
lin
in
g
o
p
er
atio
n
s
a
n
d
e
n
h
an
cin
g
lear
n
i
n
g
ex
p
er
ien
ce
s
.
T
h
is
en
a
b
les f
in
e
-
g
r
ain
ed
r
ec
o
g
n
itio
n
to
c
o
n
tr
o
l r
o
b
o
tic
d
ev
ices
[
2
9
]
.
3.
M
AT
E
R
I
AL
S AN
D
M
E
T
H
O
D
Han
d
g
estu
r
es
h
av
e
two
m
ain
f
u
n
ctio
n
s
:
to
c
o
n
v
e
y
in
f
o
r
m
ati
o
n
an
d
to
en
a
b
le
f
u
n
ctio
n
al
in
ter
ac
tio
n
.
W
ea
r
ab
le
in
ter
f
ac
es
ca
n
f
ac
ilit
ate
g
estu
r
e
r
ec
o
g
n
itio
n
in
b
o
t
h
th
ese
ar
ea
s
,
en
ab
lin
g
s
ea
m
less
co
m
m
u
n
icatio
n
b
etwe
en
h
u
m
a
n
s
an
d
m
ac
h
i
n
e
s
an
d
ev
en
b
etwe
en
i
n
d
iv
id
u
a
ls
.
T
h
is
im
p
r
o
v
es
th
e
q
u
ality
o
f
life
an
d
c
r
ea
tes
m
o
r
e
in
tu
itiv
e
i
n
ter
ac
tio
n
s
.
H
u
m
an
s
g
en
e
r
ally
u
s
e
th
eir
h
an
d
s
an
d
f
in
g
er
s
to
p
e
r
f
o
r
m
s
p
ec
if
ic
task
s
o
r
ex
p
r
ess
id
ea
s
.
Ho
wev
er
,
k
e
y
b
o
a
r
d
s
c
an
lim
it
th
is
ex
p
r
ess
io
n
,
r
estr
ictin
g
d
ir
ec
t
an
d
in
tu
itiv
e
co
m
m
u
n
icatio
n
d
u
e
to
h
ar
d
war
e
co
n
s
tr
ain
ts
.
Han
d
g
estu
r
es
o
f
ten
in
v
o
lv
e
co
o
r
d
in
ated
m
o
v
em
e
n
ts
o
f
all
f
iv
e
f
in
g
er
s
an
d
ca
n
b
e
co
m
p
lex
,
in
v
o
lv
in
g
ac
tio
n
s
s
u
ch
as
f
in
g
er
f
lex
io
n
/e
x
ten
s
io
n
,
ab
d
u
ctio
n
/ad
d
u
ctio
n
,
wr
is
t
r
o
tatio
n
,
d
e
v
iatio
n
,
an
d
h
a
n
d
p
o
s
itio
n
in
g
.
I
n
m
an
y
ap
p
licatio
n
s
,
it
is
n
o
t
n
ec
ess
ar
y
to
c
ap
tu
r
e
ev
er
y
p
o
s
s
ib
le
h
an
d
p
o
s
e;
in
s
tead
,
d
ef
in
in
g
a
s
p
ec
if
ic
s
et
o
f
g
estu
r
es c
an
p
r
o
v
id
e
ad
e
q
u
ate
p
e
r
f
o
r
m
an
ce
f
o
r
th
e
in
te
n
d
ed
p
u
r
p
o
s
e.
Fig
u
r
e
1
s
h
o
ws
th
e
o
v
er
all
a
r
c
h
it
ec
t
u
r
e
o
f
t
h
e
p
r
o
p
o
s
e
d
s
y
s
te
m
,
d
i
v
i
d
e
d
i
n
t
o
f
o
u
r
m
ai
n
m
o
d
u
les:
d
ata
co
l
le
cti
o
n
,
p
r
e
-
p
r
o
ce
s
s
in
g
,
g
e
s
tu
r
e
r
ec
o
g
n
iti
o
n
a
n
d
r
o
b
o
t
ic
ar
m
c
o
n
tr
o
l
.
T
h
e
s
m
a
r
t
g
lo
v
e
c
ap
tu
r
es
r
e
al
-
ti
m
e
d
at
a
f
r
o
m
t
h
e
f
l
ex
io
n
s
e
n
s
o
r
s
an
d
I
MU
(
ac
ce
l
er
o
m
et
e
r
an
d
g
y
r
o
s
c
o
p
e
)
,
tr
an
s
m
it
te
d
wi
r
e
le
s
s
ly
f
o
r
p
r
o
c
ess
i
n
g
.
T
h
e
d
ata
is
t
h
e
n
n
o
r
m
ali
ze
d
,
f
ilt
er
e
d
a
n
d
s
e
g
m
en
te
d
t
o
e
x
t
r
a
ct
f
ea
tu
r
es
u
s
e
f
u
l
f
o
r
t
r
a
i
n
i
n
g
a
R
NN
m
o
d
el.
Fin
all
y
,
r
ec
o
g
n
iz
ed
g
est
u
r
es
a
r
e
t
r
a
n
s
l
ate
d
i
n
t
o
p
r
ec
is
e
c
o
m
m
an
d
s
f
o
r
r
o
b
o
ti
c
ar
m
c
o
n
tr
o
l
,
d
em
o
n
s
tr
ati
n
g
f
l
u
i
d
,
r
e
al
-
ti
m
e
i
n
te
r
a
cti
o
n
.
T
h
e
E
S
P3
2
is
a
p
o
r
ta
b
l
e
ca
r
d
u
s
i
n
g
an
A
T
m
eg
a
3
2
8
C
PU
wit
h
a
s
in
g
le
8
-
b
it
c
h
i
p
,
a
n
o
p
e
r
at
in
g
v
o
l
ta
g
e
o
f
5
V
,
a
n
d
a
p
r
o
ce
s
s
i
n
g
cl
o
c
k
o
f
1
6
MH
z
.
T
h
e
b
o
a
r
d
h
as
8
an
al
o
g
p
i
n
s
f
o
r
c
o
n
n
ec
t
in
g
t
h
e
v
a
r
i
o
u
s
ty
p
es
o
f
s
en
s
o
r
y
in
p
u
t
u
s
e
d
in
t
h
is
w
o
r
k
.
T
h
e
s
e
c
o
n
d
p
ar
t
in
v
o
l
v
es
r
ec
ei
v
i
n
g
an
d
p
r
e
-
p
r
o
c
ess
in
g
i
n
p
u
t
d
at
a
f
r
o
m
t
h
e
f
le
x
s
e
n
s
o
r
s
,
wh
i
ch
a
r
e
p
r
o
c
ess
e
d
an
d
d
i
g
itiz
ed
i
n
t
h
e
MCU
,
w
h
er
e
t
h
e
m
o
v
e
m
e
n
ts
ar
e
r
e
co
g
n
iz
e
d
an
d
t
r
a
n
s
m
itt
ed
t
o
a
l
ap
to
p
v
ia
t
h
e
E
SP
3
2
'
s
b
u
ilt
-
i
n
W
i
-
Fi
m
o
d
u
le
t
o
c
o
n
tr
o
l
t
h
e
r
o
b
o
ti
c
a
r
m
.
Fig
u
r
e
2
illu
s
tr
ates
th
e
o
p
e
r
at
io
n
al
p
r
o
ce
s
s
o
f
t
h
e
co
n
tin
u
o
u
s
lo
o
p
s
y
s
tem
.
Af
ter
i
n
itializatio
n
,
d
ata
f
r
o
m
th
e
f
lex
io
n
s
en
s
o
r
s
a
n
d
MPU6
0
5
0
ar
e
ac
q
u
ir
ed
an
d
p
r
e
-
p
r
o
ce
s
s
ed
(
f
ilter
ed
an
d
n
o
r
m
alize
d
)
.
E
ac
h
d
etec
ted
g
estu
r
e
is
class
if
ied
in
r
ea
l
tim
e,
th
en
co
n
v
er
ted
i
n
to
a
s
p
ec
if
ic
co
m
m
an
d
tr
an
s
m
itted
v
ia
W
i
-
Fi
to
th
e
E
SP
3
2
t
o
c
o
n
tr
o
l
th
e
r
o
b
o
tic
ar
m
.
T
h
e
s
y
s
tem
r
em
ain
s
o
n
s
tan
d
b
y
f
o
r
co
n
tin
u
o
u
s
g
estu
r
e
a
n
aly
s
is
u
n
til
a
s
to
p
co
n
d
itio
n
is
tr
ig
g
er
ed
.
Fig
u
r
e
1
.
A
p
r
o
p
o
s
ed
ar
ch
itect
u
r
e
f
o
r
th
e
g
estu
r
e
r
ec
o
g
n
itio
n
an
d
in
tellig
en
t
g
lo
v
e
c
o
n
tr
o
l s
y
s
tem
f
o
r
th
e
r
o
b
o
tic
ar
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
6
,
Decem
b
e
r
20
25
:
5
1
6
2
-
5
1
7
2
5166
Fig
u
r
e
2
.
Flo
wch
ar
t
o
f
th
e
g
estu
r
e
r
ec
o
g
n
itio
n
a
n
d
r
o
b
o
tic
ar
m
co
n
tr
o
l
p
r
o
ce
s
s
3
.
1
.
S
m
a
rt
g
lo
v
e
c
a
pturing
dev
ice
T
h
e
wea
r
ab
le
tech
n
o
lo
g
y
o
f
t
h
e
in
tellig
en
t
g
lo
v
e
,
in
wh
ich
th
e
g
estu
r
e
ca
p
tu
r
e
d
e
v
ice
r
e
p
r
esen
ts
an
ess
en
tial
ad
v
an
ce
,
is
c
o
n
f
r
o
n
t
ed
with
g
estu
r
e
r
ec
o
g
n
itio
n
,
en
ab
lin
g
in
tu
itiv
e
i
n
ter
ac
tio
n
b
etwe
en
m
an
an
d
m
ac
h
in
e.
Usi
n
g
s
en
s
o
r
s
o
f
all
k
in
d
s
,
th
is
d
ev
ice
ca
p
t
u
r
es
u
p
p
er
lim
b
m
o
v
em
en
ts
an
d
tr
a
n
s
f
o
r
m
s
th
em
in
to
co
m
m
an
d
s
th
at
ca
n
b
e
u
s
ed
f
o
r
a
v
ar
iety
o
f
a
p
p
licatio
n
s
,
f
r
o
m
g
am
es
to
m
e
d
ical
r
eh
ab
ilit
a
tio
n
.
Han
d
g
estu
r
e
d
ata
to
co
n
tr
o
l
th
e
r
o
b
o
tic
ar
m
is
ca
p
tu
r
ed
u
s
in
g
a
s
m
ar
t
wea
r
ab
le
g
lo
v
e
.
T
h
e
Sm
ar
t
-
G
lo
v
e
ass
em
b
les
h
an
d
g
estu
r
e
d
ata
f
r
o
m
5
b
en
d
in
g
s
en
s
o
r
s
an
d
an
MPU
6
0
5
0
,
wh
i
ch
ar
e
m
o
u
n
ted
to
th
e
t
o
p
o
f
o
u
r
p
r
o
to
t
y
p
e
g
lo
v
e
as
s
h
o
wn
in
Fig
u
r
e
3
(
a
)
s
h
o
ws
th
e
tem
p
o
r
al
e
v
o
lu
tio
n
o
f
s
i
g
n
als
f
r
o
m
th
e
f
i
v
e
f
le
x
io
n
s
en
s
o
r
s
(
th
u
m
b
,
in
d
e
x
f
in
g
er
,
m
i
d
d
le
f
in
g
er
,
r
i
n
g
f
in
g
er
an
d
litt
le
f
in
g
e
r
)
,
as
well
as
th
e
in
er
tial
ax
es
(
X,
Y,
Z
)
,
f
o
r
d
if
f
e
r
en
t
g
estu
r
e
s
eq
u
en
ce
s
.
C
o
lo
r
ed
ar
ea
s
id
en
tify
s
eg
m
en
ts
co
r
r
esp
o
n
d
in
g
to
d
is
tin
ct
r
ec
o
g
n
ized
g
estu
r
es.
Fig
u
r
e
3
(
b
)
s
h
o
ws
th
e
s
m
ar
t
g
lo
v
e
in
ac
tu
al
o
p
er
atio
n
,
with
s
en
s
o
r
wir
in
g
v
is
ib
le
an
d
th
e
s
ig
n
al
v
is
u
aliza
tio
n
in
ter
f
ac
e
d
is
p
lay
e
d
o
n
s
cr
ee
n
.
T
h
is
ex
p
er
im
en
t
al
co
n
f
ig
u
r
atio
n
v
alid
ates
th
e
g
lo
v
e'
s
ab
ilit
y
to
ca
p
tu
r
e
f
in
e
v
ar
iatio
n
s
in
m
o
v
em
en
t i
n
r
ea
l tim
e.
(
a)
(
b
)
Fig
u
r
e
3
.
Sm
ar
t
-
g
lo
v
e
ca
p
tu
r
i
n
g
d
ev
ice:
(
a)
v
is
u
aliza
tio
n
o
f
m
u
ltis
en
s
o
r
y
d
ata
co
llected
,
a
n
d
(
b
)
th
e
s
m
ar
t
g
lo
v
e
d
u
r
in
g
g
estu
r
e
ex
ec
u
tio
n
3
.
2
.
Ro
bo
t
ic
a
r
m
s
y
s
t
em
As
th
e
s
m
ar
t
g
l
o
v
e
p
er
f
o
r
m
s
m
o
v
em
en
ts
,
it
d
eliv
er
s
s
ig
n
als
r
elate
d
t
o
th
e
an
g
le
o
f
th
e
f
le
x
s
en
s
o
r
s
as
well
as
ac
ce
ler
atio
n
v
ia
MPU
6
0
5
0
.
T
o
ch
ar
ac
te
r
ize
th
is
r
el
atio
n
s
h
ip
,
a
wea
r
ab
le
s
en
s
o
r
g
lo
v
e
was
d
esig
n
ed
b
y
in
te
g
r
atin
g
f
lex
ib
le
s
en
s
o
r
s
an
d
a
n
MPU6
0
5
0
t
o
tr
ac
k
h
an
d
m
o
v
e
m
en
ts
.
Af
ter
ca
lib
r
atio
n
,
f
iv
e
a
n
alo
g
v
alu
es
f
r
o
m
th
e
f
lex
i
b
le
s
en
s
o
r
s
an
d
th
r
ee
an
alo
g
in
p
u
t
v
alu
es
f
r
o
m
th
e
ac
ce
ler
o
m
eter
wer
e
co
llected
s
im
u
ltan
eo
u
s
ly
.
T
h
ese
v
alu
es
wer
e
co
n
v
e
r
ted
to
d
ig
ital d
ata
(
1
0
b
its
)
v
ia
t
h
e
E
SP
3
2
'
s
ADC
u
s
in
g
(
1
)
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
S
ma
r
t wea
r
a
b
le
g
lo
ve
fo
r
en
h
a
n
ce
d
h
u
ma
n
-
r
o
b
o
t in
tera
ctio
n
…
(
N
o
u
r
d
in
e
Herb
a
z
)
5167
=
2
×
(
1
)
H
e
r
e
,
r
e
p
r
e
s
e
n
ts
t
h
e
i
n
p
u
t
v
o
l
t
a
g
e
,
c
o
r
r
e
s
p
o
n
d
s
t
o
t
h
e
d
i
g
i
t
al
v
o
l
t
a
g
e
r
e
a
d
i
n
g
f
r
o
m
t
h
e
E
SP
3
2
’
s
,
d
e
n
o
t
e
s
t
h
e
s
u
p
p
l
y
v
o
l
t
a
g
e
,
a
n
d
is
t
h
e
AD
C
r
es
o
l
u
t
i
o
n
.
T
h
e
r
e
s
is
ta
n
c
e
o
f
e
a
c
h
f
le
x
s
e
n
s
o
r
w
a
s
t
h
e
n
d
e
te
r
m
i
n
e
d
u
s
i
n
g
t
h
e
v
o
l
ta
g
e
d
i
v
i
d
e
r
f
o
r
m
u
l
a
(
2
)
,
w
h
i
c
h
is
u
s
e
d
t
o
es
tim
a
t
e
t
h
e
r
es
is
t
a
n
ce
o
f
t
h
e
f
le
x
i
b
l
e
s
e
n
s
o
r
R
f
le
x
as
a
f
u
n
c
t
i
o
n
o
f
t
h
e
m
e
a
s
u
r
e
d
v
o
l
t
ag
e
,
t
h
e
r
e
f
e
r
e
n
c
e
r
es
is
t
a
n
ce
R
,
a
n
d
t
h
e
s
u
p
p
l
y
v
o
l
t
a
g
e
cc
,
a
c
c
o
r
d
i
n
g
t
o
(
2
)
:
=
−
1
×
(
2
)
T
h
e
o
u
tp
u
t
v
o
ltag
e
V
out
is
in
ef
f
ec
t
f
ix
e
d
b
y
th
e
cir
cu
it
c
o
n
f
ig
u
r
atio
n
,
wh
er
e
R
2
c
o
r
r
esp
o
n
d
s
to
th
e
v
ar
ia
b
le
r
esis
tan
ce
o
f
th
e
f
lex
s
en
s
o
r
(
R
flex
)
,
R
1
r
ep
r
esen
tin
g
a
k
n
o
w
n
r
ef
er
e
n
ce
r
esis
tan
ce
b
etwe
en
3
3
-
4
5
k
o
h
m
,
an
d
V
in
th
e
in
p
u
t
v
o
ltag
e
o
f
5
V.
V
out
is
r
ec
o
r
d
ed
u
s
in
g
th
e
E
SP
3
2
'
s
1
0
-
b
it
ADC
(
an
alo
g
-
to
-
d
i
g
ital
co
n
v
er
ter
)
,
s
o
th
e
r
esis
tan
ce
o
f
th
e
b
en
d
in
g
tr
an
s
d
u
ce
r
s
ca
n
b
e
d
ir
ec
tly
d
ed
u
ce
d
f
r
o
m
th
e
d
ig
ital
v
al
u
es
s
u
p
p
lied
b
y
th
e
ADC,
b
y
ap
p
ly
in
g
(
3
)
p
r
e
v
io
u
s
ly
co
n
s
id
er
ed
u
n
d
er
th
e
ass
u
m
p
tio
n
t
h
at
th
e
v
a
r
iatio
n
s
m
ea
s
u
r
ed
co
r
r
esp
o
n
d
t
o
v
ar
iatio
n
s
Flex
io
n
d
e
g
r
ee
:
=
(
1
1
+
2
)
(
3
)
T
h
e
wea
r
ab
le
s
en
s
o
r
g
lo
v
e
also
in
teg
r
ates
an
ac
ce
ler
o
m
eter
,
wh
ich
co
n
v
er
ts
its
An
alo
g
in
p
u
t
v
alu
es
(
Ax
e
x
,
Ax
e
y,
a
n
d
Ax
e
z
)
in
to
d
ig
ital
v
alu
es
u
s
in
g
th
e
es
p
3
2
'
s
in
ter
n
al
1
0
-
b
it
ADC.
T
h
ese
d
ata
wer
e
u
s
ed
d
ir
ec
tly
in
th
e
s
tu
d
y
.
T
ab
le
2
s
h
o
ws
th
e
av
e
r
ag
es
o
f
th
e
v
al
u
es
m
ea
s
u
r
ed
(
in
m
illi
v
o
lts
)
b
y
th
e
f
iv
e
f
lex
ib
l
e
s
en
s
o
r
s
an
d
th
e
r
aw
ac
ce
ler
o
m
eter
v
alu
es
(
X,
Y,
Z
ax
es)
f
o
r
ea
ch
co
n
tr
o
l
g
estu
r
e.
T
h
ese
d
a
ta
p
r
o
v
id
e
a
u
s
ef
u
l
b
aselin
e
f
o
r
s
eg
m
en
tatio
n
an
d
lab
elin
g
d
u
r
in
g
class
if
icatio
n
m
o
d
el
tr
ain
in
g
.
T
h
ey
h
ig
h
lig
h
t
th
e
d
is
tin
ctio
n
b
etwe
en
g
estu
r
es th
r
o
u
g
h
s
p
ec
if
ic
s
ig
n
al
v
ar
iatio
n
s
,
en
a
b
lin
g
r
eliab
le
r
ec
o
g
n
itio
n
v
ia
m
ac
h
i
n
e
lear
n
in
g
.
Fig
u
r
e
4
illu
s
tr
ates
th
e
c
o
m
p
lete
ar
ch
itectu
r
e
o
f
th
e
g
estu
r
e
r
ec
o
g
n
itio
n
m
o
d
el
b
ased
o
n
a
R
NN,
ap
p
lied
to
th
e
tem
p
o
r
al
d
ata
a
cq
u
ir
ed
b
y
th
e
s
m
ar
t
g
lo
v
e.
Fl
ex
ib
le
s
en
s
o
r
s
m
ea
s
u
r
e
f
in
g
e
r
cu
r
v
atu
r
e
,
wh
ile
th
e
MPU6
0
5
0
s
en
s
o
r
p
r
o
v
id
es
th
r
ee
-
ax
is
ac
ce
ler
atio
n
an
d
r
o
tatio
n
d
ata.
T
h
ese
d
ata
ar
e
co
ll
ec
ted
co
n
tin
u
o
u
s
ly
an
d
o
r
g
an
ized
i
n
tim
e
s
eq
u
en
c
es.
T
ab
le
2
.
Sen
s
o
r
v
alu
e
r
a
n
g
es c
o
r
r
esp
o
n
d
in
g
t
o
ea
ch
ac
tio
n
#
S
a
m
p
l
e
s
F
l
e
x
i
b
l
e
se
n
s
o
r
s
d
a
t
a
(
mV
o
l
t
a
g
e
)
A
c
c
e
l
e
r
o
met
e
r
d
a
t
a
F
l
e
x
1
F
l
e
x
2
F
l
e
x
3
F
l
e
x
4
F
l
e
x
5
A
x
e
X
A
x
e
Y
A
x
e
Z
G
r
i
p
P
i
n
c
e
6
3
9
7
0
9
7
0
2
9
5
9
9
5
8
16
,
208
-
8
2
4
3
,
9
4
4
O
p
e
n
P
i
n
c
e
6
5
2
8
0
1
7
7
0
9
8
1
9
7
6
15
,
292
1
,
2
0
4
5
,
9
1
6
Up
6
5
7
7
8
4
7
4
8
9
2
6
9
3
0
12
,
348
-
7
,
512
7
,
9
7
2
D
o
w
n
6
6
1
8
0
7
7
5
0
9
7
5
9
7
6
10
,
560
2
,
6
8
4
11
,
336
M
o
v
e
l
e
f
t
6
4
4
8
4
9
7
9
1
9
5
3
9
5
5
15
,
980
-
1
,
780
4
,
1
2
8
M
o
v
e
r
i
g
h
t
6
5
6
7
8
6
7
4
1
9
7
4
9
7
1
8
,
9
0
8
11
,
924
-
7
,
828
N
o
t
h
i
n
g
6
6
5
7
3
2
7
0
1
9
6
5
9
6
8
15
,
536
-
1
,
216
6
,
4
3
6
Fig
u
r
e
4
.
Vis
u
aliza
tio
n
o
f
m
u
l
tis
en
s
o
r
y
d
ata
co
llected
b
y
th
e
s
m
ar
t g
lo
v
e
d
u
r
in
g
g
estu
r
e
e
x
ec
u
tio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
6
,
Decem
b
e
r
20
25
:
5
1
6
2
-
5
1
7
2
5168
E
ac
h
s
eq
u
en
ce
co
r
r
esp
o
n
d
s
to
a
ca
n
d
id
ate
g
estu
r
e
,
r
e
p
r
esen
t
ed
b
y
a
m
u
ltiv
ar
iate
v
ec
to
r
e
n
ter
in
g
th
e
R
NN
b
lo
ck
,
wh
ich
m
o
d
els
tem
p
o
r
al
d
ep
e
n
d
en
cies
v
ia
r
ec
u
r
r
en
t
ce
lls
.
T
h
e
R
NN
o
u
tp
u
ts
ar
e
th
en
ag
g
r
e
g
ated
an
d
p
r
o
ce
s
s
ed
b
y
a
class
if
ier
an
d
a
So
f
tMa
x
ac
tiv
atio
n
f
u
n
ctio
n
to
id
en
tif
y
th
e
m
o
s
t
lik
ely
g
estu
r
e
am
o
n
g
th
e
p
r
ed
ef
in
e
d
g
estu
r
es.
T
h
is
p
i
p
elin
e
en
ab
les
ef
f
icien
t,
r
ea
l
-
tim
e
r
ec
o
g
n
itio
n
o
f
d
y
n
am
ic
g
estu
r
es,
with
th
e
ac
cu
r
ac
y
d
em
o
n
s
tr
ated
in
o
u
r
ex
p
e
r
im
en
tal
r
esu
lts
as
s
h
o
w
n
in
Fig
u
r
es
5
a
n
d
6
.
I
ts
lig
h
t
weig
h
t,
s
eq
u
e
n
tial
s
tr
u
ctu
r
e
is
p
ar
ticu
lar
ly
well
s
u
ited
to
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
em
b
ed
d
e
d
s
y
s
tem
s
s
u
ch
as th
e
E
SP
3
2
.
Fig
u
r
e
5
.
C
lass
if
ier
p
er
f
o
r
m
an
ce
ev
alu
atio
n
f
o
r
r
o
b
o
tic
m
o
v
e
m
en
ts
Fig
u
r
e
6
.
E
v
o
lu
tio
n
o
f
l
o
s
s
f
u
n
ctio
n
an
d
ac
c
u
r
ac
y
d
u
r
i
n
g
tr
ai
n
in
g
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Gestu
r
e
co
n
tr
o
l
h
as
b
ec
o
m
e
a
v
er
y
p
r
o
m
is
in
g
a
p
p
r
o
ac
h
in
th
e
f
ield
o
f
h
u
m
an
-
m
ac
h
in
e
in
ter
f
ac
es,
p
ar
ticu
lar
ly
f
o
r
r
eh
ab
ilit
atio
n
,
teleo
p
er
atio
n
,
a
n
d
r
o
b
o
tic
ass
is
tan
ce
ap
p
licatio
n
s
[
4
]
–
[
7
]
,
[
1
0
]
.
Ho
wev
e
r
,
r
ea
l
-
tim
e
g
estu
r
e
r
ec
o
g
n
itio
n
s
till
p
o
s
es
ch
allen
g
es
d
u
e
to
en
v
ir
o
n
m
en
tal
in
ter
f
er
e
n
ce
,
th
e
v
a
r
iab
ilit
y
o
f
h
u
m
an
m
o
v
em
en
ts
,
an
d
th
e
h
a
r
d
war
e
lim
itatio
n
s
o
f
o
n
-
b
o
ar
d
s
e
n
s
o
r
s
.
I
n
th
is
r
esear
ch
,
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
s
u
g
g
ested
an
d
d
ev
el
o
p
ed
s
o
lu
tio
n
is
ass
e
s
s
ed
b
y
co
m
p
ar
in
g
it
with
wo
r
k
s
in
th
e
liter
atu
r
e
[
1
0
]
,
[
1
5
]
,
[
1
6
]
,
as
s
h
o
wn
in
T
ab
le
3
.
T
h
e
s
elec
tio
n
o
f
th
e
o
p
er
atin
g
m
o
d
e
f
o
r
r
o
b
o
tic
ar
m
co
n
t
r
o
l
is
b
ased
o
n
th
e
u
s
e
o
f
m
o
v
em
en
t
d
ictio
n
ar
ies
d
etec
tab
le
b
y
f
lex
ib
le
s
en
s
o
r
s
an
d
an
ac
ce
le
r
o
m
eter
MPU6
0
5
0
.
Ma
c
h
in
e
lear
n
in
g
ap
p
lied
to
th
is
class
if
icatio
n
r
eq
u
ir
es
a
tr
ain
i
n
g
p
h
ase
u
s
in
g
d
atasets
g
en
er
ated
f
r
o
m
r
elev
a
n
t
f
ea
tu
r
es
in
s
m
ar
t
g
lo
v
e
s
ig
n
als
ex
tr
ac
ted
f
o
r
ea
ch
g
estu
r
e.
I
n
th
is
s
tu
d
y
,
we
p
r
o
p
o
s
e
m
o
tio
n
d
ictio
n
ar
ies b
ased
o
n
th
e
an
aly
s
is
o
f
s
ig
n
als f
r
o
m
an
MPU6
0
5
0
ac
ce
ler
o
m
eter
as
well
as
f
r
o
m
f
iv
e
f
lex
io
n
s
en
s
o
r
s
in
teg
r
ated
in
to
t
h
e
s
m
ar
t
g
lo
v
e.
B
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
S
ma
r
t wea
r
a
b
le
g
lo
ve
fo
r
en
h
a
n
ce
d
h
u
ma
n
-
r
o
b
o
t in
tera
ctio
n
…
(
N
o
u
r
d
in
e
Herb
a
z
)
5169
ex
er
cisi
n
g
m
o
v
em
e
n
ts
th
r
o
u
g
h
o
u
r
s
m
ar
t
g
lo
v
e,
we
h
av
e
d
ef
in
ed
r
e
p
er
to
ir
es
o
f
u
s
ab
le
g
estu
r
es.
Fig
u
r
e
7
s
h
o
ws
th
e
s
ix
h
an
d
g
estu
r
e
s
d
etec
tab
le
b
y
th
e
s
m
ar
t
g
lo
v
e
an
d
th
eir
d
ir
ec
t
co
r
r
es
p
o
n
d
e
n
ce
with
th
e
m
o
v
em
en
ts
o
f
th
e
r
o
b
o
tic
ar
m
.
E
ac
h
g
estu
r
e
-
s
u
ch
as
p
in
ch
in
g
,
h
an
d
o
p
e
n
in
g
,
u
p
/
d
o
wn
an
d
lef
t/rig
h
t
m
o
v
em
en
ts
-
is
ca
p
tu
r
e
d
b
y
t
h
e
f
lex
ib
le
s
en
s
o
r
s
an
d
in
e
r
tial
u
n
it
(
MPU6
0
5
0
)
,
th
en
in
ter
p
r
eted
in
to
s
p
ec
if
i
c
co
m
m
an
d
s
.
T
h
is
g
estu
r
e
d
ictio
n
ar
y
g
u
ar
an
tees
in
tu
itiv
e,
n
atu
r
al
co
n
tr
o
l
o
f
th
e
r
o
b
o
tic
ar
m
v
ia
wir
eless
g
estu
r
e
in
ter
ac
tio
n
.
T
ab
le
3
.
A
p
e
r
f
o
r
m
an
ce
c
o
m
p
ar
is
o
n
with
o
th
er
s
tu
d
ies
P
u
b
l
i
c
a
t
i
o
n
s
,
Y
e
a
r
Ty
p
e
o
f
s
e
n
s
o
r
Le
a
r
n
i
n
g
mo
d
e
l
C
o
n
t
r
o
l
l
e
d
r
o
b
o
t
i
c
s
R
a
w
D
a
t
a
#
G
e
s
t
u
r
e
s
A
c
c
u
r
a
c
y
Lu
e
t
a
l
.
[
1
6
]
,
2
0
2
3
I
M
U
s
Bi
-
LST
M
✓
5
(
I
M
U
s)
10
9
2
%
La
k
s
o
n
o
e
t
a
l
.
[
1
5
]
,
2
0
2
1
EM
G
s
K
N
N
✓
3
(
E
M
G
)
4
9
6
.
6
7
%
a
c
c
u
r
a
c
y
,
9
9
.
6
6
%
r
e
c
a
l
l
,
9
6
.
9
9
%
p
r
e
c
i
s
i
o
n
.
C
r
u
z
e
t
a
l
.
[
1
0
]
,
2
0
2
3
EM
G
+
I
M
U
DQN
✓
EM
G
-
I
M
U
sen
so
r
6
9
7
.
4
5
±
1
.
0
2
%
a
n
d
8
8
.
0
5
±
3
.
1
0
%
P
r
o
p
o
se
d
a
p
p
r
o
a
c
h
M
P
U
6
0
5
0
+
F
l
e
x
R
N
N
✓
5
(
f
l
e
x
)
+
1
(
I
M
U
)
7
9
8
.
6
7
%
Fig
u
r
e
7
.
Dictio
n
a
r
y
o
f
g
estu
r
es r
ec
o
g
n
ized
f
o
r
r
o
b
o
tic
ar
m
co
n
tr
o
l u
s
in
g
f
lex
io
n
an
d
in
er
t
ial
s
en
s
o
r
s
Han
d
g
estu
r
e
r
ec
o
g
n
itio
n
alg
o
r
ith
m
s
ca
n
b
e
ca
teg
o
r
ized
i
n
to
two
m
ain
ty
p
es:
i)
clas
s
i
f
icatio
n
o
f
h
an
d
p
o
s
es
an
d
tr
ajec
to
r
ies,
aim
ed
at
i
d
en
tify
in
g
s
p
ec
if
ic
g
estu
r
es
(
f
o
r
ex
am
p
le,
r
ec
o
g
n
itio
n
o
f
th
e
Gr
i
p
Pen
ce
g
estu
r
e
o
r
cy
clic
h
an
d
m
o
v
em
en
t)
,
an
d
ii)
co
n
tin
u
o
u
s
p
ar
am
eter
r
eg
r
ess
io
n
,
en
ab
li
n
g
v
ar
iab
les
s
u
ch
as
f
in
g
er
f
le
x
io
n
a
n
g
le
o
r
h
an
d
tr
ajec
to
r
y
o
r
wr
is
t d
ev
iatio
n
to
b
e
esti
m
ated
in
r
ea
l tim
e.
Fig
u
r
e
8
illu
s
tr
ates
th
e
en
tire
p
r
o
ce
s
s
in
g
p
i
p
elin
e,
f
r
o
m
th
e
ac
q
u
is
itio
n
o
f
s
en
s
o
r
y
d
ata
b
y
th
e
s
m
ar
t
g
lo
v
e
(
f
lex
io
n
s
+
I
MU
)
to
th
e
f
in
al
d
ec
is
io
n
b
y
a
class
if
ie
r
b
ased
o
n
a
d
ee
p
n
eu
r
al
n
et
wo
r
k
.
Af
ter
s
ig
n
al
v
is
u
aliza
tio
n
,
n
o
r
m
aliza
tio
n
a
n
d
f
ilter
in
g
,
th
e
ex
tr
ac
te
d
f
ea
t
u
r
es
ar
e
tr
an
s
m
itted
to
th
e
d
ee
p
lear
n
in
g
m
o
d
u
le,
wh
er
e
a
n
eu
r
al
n
etwo
r
k
an
d
a
So
f
tMa
x
class
if
ier
en
ab
le
r
ea
l
-
tim
e
g
estu
r
e
p
r
ed
ictio
n
.
T
h
e
ex
am
p
le
p
r
esen
ted
s
h
o
ws r
ec
o
g
n
itio
n
o
f
a
clo
s
ed
g
r
ip
with
9
9
% a
cc
u
r
ac
y
.
Fig
u
r
e
8
.
Sig
n
al
p
r
o
ce
s
s
in
g
ch
ain
an
d
g
estu
r
e
class
if
icatio
n
v
ia
d
ee
p
lear
n
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
6
,
Decem
b
e
r
20
25
:
5
1
6
2
-
5
1
7
2
5170
Fig
u
r
e
5
s
h
o
ws
two
co
n
f
u
s
io
n
m
atr
ices
illu
s
tr
atin
g
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
class
if
icatio
n
m
o
d
el
f
o
r
s
ev
en
g
estu
r
es:
“M
o
v
e
L
ef
t”,
“M
o
v
e
R
ig
h
t”,
“Gr
ip
Pin
ce
”,
“Op
en
Pin
ce
”,
“Up
”,
‘
D
o
wn
’
an
d
“No
th
in
g
”.
O
n
th
e
lef
t,
t
h
e
a
b
s
o
lu
te
v
al
u
e
m
atr
ix
s
h
o
ws
th
e
n
u
m
b
er
o
f
co
r
r
ec
t
p
r
ed
ictio
n
s
p
er
class
,
wh
ile
o
n
th
e
r
ig
h
t,
th
e
n
o
r
m
alize
d
p
er
ce
n
tag
e
m
atr
ix
s
h
o
ws
th
at
th
e
av
er
ag
e
ac
cu
r
ac
y
o
f
t
h
e
m
o
d
el
r
ea
ch
es
9
8
.
6
7
%,
with
p
er
f
ec
t
r
ec
o
g
n
itio
n
f
o
r
t
h
e
“No
th
in
g
”
g
estu
r
es
an
d
r
ates
ab
o
v
e
9
7
% f
o
r
th
e
m
aj
o
r
ity
o
f
class
es.
T
h
ese
r
esu
lts
v
alid
ate
th
e
r
o
b
u
s
tn
ess
o
f
o
u
r
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
f
o
r
r
ea
l
-
tim
e
co
n
tr
o
l o
f
th
e
r
o
b
o
tic
ar
m
.
Fig
u
r
e
6
illu
s
tr
ates
th
e
co
n
v
er
g
en
ce
o
f
th
e
m
o
d
el
d
u
r
in
g
tr
ain
in
g
o
v
e
r
5
0
e
p
o
ch
s
.
T
h
e
lef
t
-
h
an
d
cu
r
v
e
s
h
o
ws
a
r
ap
id
d
ec
r
ea
s
e
in
lo
s
s
f
r
o
m
th
e
v
er
y
f
ir
s
t
iter
atio
n
s
,
r
ea
ch
in
g
s
tab
ilit
y
at
a
lo
w
lev
el
f
o
r
b
o
th
th
e
tr
ain
in
g
an
d
test
s
ets.
T
h
e
r
ig
h
t
-
h
a
n
d
cu
r
v
e
r
ev
ea
ls
ac
c
u
r
ac
y
ab
o
v
e
9
0
%
as
ea
r
ly
as
th
e
1
0
ᵉ
ep
o
c
h
,
an
d
r
ea
ch
in
g
alm
o
s
t
9
8
.
6
7
%
f
o
r
t
r
ain
in
g
,
attesti
n
g
to
th
e
n
etwo
r
k
'
s
lear
n
in
g
ef
f
icien
c
y
.
T
h
is
s
tab
ilit
y
in
d
icate
s
a
g
o
o
d
b
ias
-
v
ar
ian
ce
c
o
m
p
r
o
m
i
s
e,
with
litt
le
o
v
er
lear
n
in
g
.
T
ab
le
3
co
m
p
ar
is
o
n
h
ig
h
lig
h
ts
th
at
o
u
r
ap
p
r
o
ac
h
u
s
in
g
o
n
ly
lo
w
-
co
s
t
s
en
s
o
r
s
(
MPU6
0
5
0
+
f
lex
ib
l
e
s
en
s
o
r
s
)
ac
h
iev
es
ac
cu
r
ac
y
s
u
p
er
io
r
o
r
eq
u
iv
alen
t
to
o
th
e
r
m
o
r
e
co
m
p
lex
s
y
s
tem
s
b
ase
d
o
n
E
MG
o
r
d
ee
p
Q
-
lear
n
in
g
(
DQN
)
.
I
t
co
m
b
in
es
ef
f
icien
cy
,
lo
w
co
s
t
an
d
r
o
b
u
s
tn
ess
f
o
r
r
ea
l
-
tim
e
r
o
b
o
tic
co
n
tr
o
l.
T
h
is
s
tu
d
y
p
r
esen
ts
s
ev
er
al
lim
itatio
n
s
th
at
m
er
it
f
u
r
th
er
in
v
esti
g
atio
n
.
Firstl
y
,
th
e
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
wa
s
tr
ain
ed
an
d
v
alid
ated
with
d
ata
f
r
o
m
a
s
in
g
le
p
ar
ticip
an
t,
r
eq
u
ir
in
g
a
r
ec
alib
r
atio
n
an
d
r
e
-
tr
ain
in
g
p
h
ase
f
o
r
ea
ch
n
ew
u
s
er
,
wh
ich
m
a
y
af
f
ec
t
t
h
e
g
en
er
aliza
b
ilit
y
an
d
s
ca
lab
ilit
y
o
f
th
e
m
o
d
el.
I
n
ad
d
itio
n
,
th
e
cu
r
r
en
t
im
p
lem
en
tatio
n
h
as
n
o
t
y
et
b
ee
n
test
ed
in
an
em
b
ed
d
ed
s
y
s
tem
f
o
r
r
em
o
te
class
if
icatio
n
,
a
k
e
y
s
tep
in
ass
es
s
in
g
its
p
r
ac
tical
in
teg
r
at
io
n
as
well
as
n
o
n
-
c
u
ttin
g
-
o
f
f
d
u
r
i
n
g
l
o
n
g
-
d
is
tan
ce
co
n
tr
o
l.
Fin
ally
,
th
e
s
tu
d
y
was
lim
ited
to
a
r
estricte
d
s
et
o
f
g
estu
r
es
an
d
a
s
in
g
le
u
s
er
;
f
u
tu
r
e
wo
r
k
will
n
ee
d
to
ex
p
a
n
d
th
e
d
atab
ase
b
y
in
teg
r
atin
g
a
g
r
ea
ter
d
i
v
er
s
ity
o
f
g
estu
r
es
an
d
p
a
r
ticip
an
ts
in
v
o
lv
ed
in
e
v
alu
atin
g
t
h
e
ad
ap
tab
ilit
y
an
d
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el
in
d
if
f
er
en
t p
o
p
u
latio
n
s
.
5.
CO
NCLU
SI
O
N
I
n
th
is
s
tu
d
y
,
we
d
esig
n
e
d
a
n
d
im
p
lem
e
n
ted
a
wea
r
ab
le
s
m
ar
t
g
lo
v
e
in
te
g
r
atin
g
f
lex
io
n
s
en
s
o
r
s
an
d
an
MPU6
0
5
0
in
er
tial
s
en
s
o
r
,
co
m
b
in
e
d
with
an
R
NN
-
b
a
s
ed
d
ee
p
lear
n
in
g
m
o
d
el
f
o
r
r
ea
l
-
tim
e
g
estu
r
e
r
ec
o
g
n
itio
n
.
T
h
e
p
r
o
p
o
s
ed
h
a
r
d
war
e
a
n
d
s
o
f
twar
e
ar
c
h
itectu
r
e
e
n
ab
les
f
lu
i
d
an
d
i
n
tu
itiv
e
in
ter
ac
tio
n
with
a
r
o
b
o
tic
ar
m
,
ac
h
ie
v
in
g
a
class
if
icatio
n
ac
cu
r
ac
y
o
f
9
8
.
6
7
%
o
n
s
ev
en
d
is
tin
ct
g
estu
r
es.
E
x
p
er
im
en
tal
r
esu
lts
d
em
o
n
s
tr
ate
th
e
r
o
b
u
s
tn
ess
an
d
r
eliab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
.
Mu
lti
-
s
en
s
o
r
f
u
s
io
n
,
ac
co
m
p
an
ie
d
b
y
a
p
r
e
-
p
r
o
ce
s
s
in
g
p
r
o
ce
s
s
in
clu
d
in
g
d
ata
b
o
u
n
d
ar
y
d
etec
tio
n
,
n
o
r
m
aliza
tio
n
an
d
lear
n
in
g
b
ased
o
n
r
ec
u
r
r
en
t
n
etwo
r
k
s
,
en
ab
les
ac
cu
r
ate
in
ter
p
r
etatio
n
o
f
d
y
n
am
ic
g
estu
r
es.
A
co
m
p
ar
is
o
n
with
o
th
er
r
ec
en
t
ap
p
r
o
ac
h
es
h
ig
h
lig
h
ts
th
e
h
i
g
h
p
e
r
f
o
r
m
an
ce
o
f
o
u
r
s
y
s
tem
,
d
esp
ite
its
lig
h
ter
ar
c
h
itectu
r
e
an
d
lo
w
-
co
s
t h
ar
d
war
e.
T
h
is
wo
r
k
th
u
s
co
n
tr
i
b
u
tes
to
th
e
ad
v
a
n
ce
m
en
t
o
f
wea
r
ab
le
h
u
m
an
-
m
ac
h
in
e
in
ter
f
a
ce
s
,
with
p
o
ten
tial
ap
p
licatio
n
s
in
th
e
f
ield
s
o
f
ass
is
ted
r
o
b
o
tics
,
m
ed
ical
r
eh
ab
ilit
atio
n
an
d
I
n
d
u
s
tr
y
4
.
0
.
T
h
an
k
s
to
its
ab
ilit
y
to
in
ter
p
r
et
g
estu
r
es
i
n
r
ea
l
tim
e,
wh
ile
e
n
s
u
r
in
g
p
r
ec
is
e
co
n
tr
o
l
o
f
th
e
r
o
b
o
ti
c
ar
m
,
o
u
r
s
o
lu
tio
n
ef
f
ec
tiv
ely
m
ee
ts
th
e
r
e
q
u
ir
em
en
ts
o
f
in
ter
ac
tiv
e
em
b
ed
d
e
d
s
y
s
tem
s
.
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
.
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
Auth
o
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
No
u
rd
in
e
He
rb
a
z
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ha
ss
a
n
El
Id
rissi
✓
✓
✓
✓
✓
✓
✓
Ha
m
z
a
S
a
b
ir
✓
✓
✓
✓
✓
✓
✓
Ab
d
e
lma
ji
d
Ba
d
ri
✓
✓
✓
✓
✓
✓
✓
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
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
S
ma
r
t wea
r
a
b
le
g
lo
ve
fo
r
en
h
a
n
ce
d
h
u
ma
n
-
r
o
b
o
t in
tera
ctio
n
…
(
N
o
u
r
d
in
e
Herb
a
z
)
5171
CO
NFLIC
T
O
F
IN
TERE
S
T
S
TATEMENT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DA
TA AV
AI
LABI
L
ITY
Der
iv
ed
d
ata
s
u
p
p
o
r
tin
g
th
e
f
i
n
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
i
n
g
au
th
o
r
N.
H.
o
n
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
Y
.
R
u
i
y
a
n
g
,
W
.
D
e
p
e
n
g
,
Z.
S
h
u
f
a
n
g
,
a
n
d
o
t
h
e
r
s,
“
W
e
a
r
a
b
l
e
s
e
n
s
o
r
s‐
e
n
a
b
l
e
d
h
u
m
a
n
–
m
a
c
h
i
n
e
i
n
t
e
r
a
c
t
i
o
n
s
y
st
e
m
s:
f
r
o
m
d
e
si
g
n
t
o
a
p
p
l
i
c
a
t
i
o
n
,
”
A
d
v
a
n
c
e
d
Fu
n
c
t
i
o
n
a
l
M
a
t
e
ri
a
l
s
,
v
o
l
.
3
1
,
n
o
.
1
1
,
p
.
2
0
0
8
9
3
6
,
2
0
2
1
.
[
2
]
T.
M
.
N
.
U
.
A
k
h
u
n
d
a
n
d
o
t
h
e
r
s,
“
I
o
S
T
-
e
n
a
b
l
e
d
r
o
b
o
t
i
c
a
r
m
c
o
n
t
r
o
l
a
n
d
a
b
n
o
r
m
a
l
i
t
y
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
mi
n
i
m
a
l
f
l
e
x
se
n
s
o
r
s
a
n
d
G
a
u
ss
i
a
n
M
i
x
t
u
r
e
mo
d
e
l
s,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
4
5
2
6
5
–
4
5
2
7
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
8
0
3
6
0
.
[
3
]
H
.
S
ü
m
b
ü
l
,
“
A
n
o
v
e
l
M
EM
S
a
n
d
f
l
e
x
sen
s
o
r
-
b
a
se
d
h
a
n
d
g
e
st
u
r
e
r
e
c
o
g
n
i
t
i
o
n
a
n
d
r
e
g
e
n
e
r
a
t
i
n
g
sy
s
t
e
m
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
1
3
3
6
8
5
–
1
3
3
6
9
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
4
4
8
2
3
2
.
[
4
]
V
.
B
e
r
e
z
h
n
o
y
,
D
.
P
o
p
o
v
,
I
.
A
f
a
n
a
s
y
e
v
,
a
n
d
N
.
M
a
v
r
i
d
i
s,
“
T
h
e
h
a
n
d
-
g
e
st
u
r
e
-
b
a
s
e
d
c
o
n
t
r
o
l
i
n
t
e
r
f
a
c
e
w
i
t
h
w
e
a
r
a
b
l
e
g
l
o
v
e
s
y
s
t
e
m
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
1
5
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
c
s
i
n
C
o
n
t
r
o
l
,
A
u
t
o
m
a
t
i
o
n
a
n
d
Ro
b
o
t
i
c
s
-
Vo
l
u
m
e
2
:
I
C
I
N
C
O
,
2
0
1
8
,
p
p
.
4
4
8
–
4
5
5
,
d
o
i
:
1
0
.
5
2
2
0
/
0
0
0
6
9
0
9
3
0
4
4
8
0
4
5
5
.
[
5
]
X
.
H
u
a
n
g
a
n
d
o
t
h
e
r
s,
“
Tr
a
c
i
n
g
t
h
e
mo
t
i
o
n
o
f
f
i
n
g
e
r
j
o
i
n
t
s
f
o
r
g
e
st
u
r
e
r
e
c
o
g
n
i
t
i
o
n
v
i
a
sewi
n
g
R
G
O
-
c
o
a
t
e
d
f
i
b
e
r
s
o
n
t
o
a
t
e
x
t
i
l
e
g
l
o
v
e
,
”
I
EE
E
S
e
n
so
rs
J
o
u
rn
a
l
,
v
o
l
.
1
9
,
n
o
.
2
0
,
p
p
.
9
5
0
4
–
9
5
1
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
1
9
.
2
9
2
4
7
9
7
.
[
6
]
S
.
Li
u
a
n
d
C
.
S
u
n
,
“
M
a
st
e
r
-
sl
a
v
e
c
o
n
t
r
o
l
sy
s
t
e
m
f
o
r
v
i
r
t
u
a
l
–
p
h
y
si
c
a
l
i
n
t
e
r
a
c
t
i
o
n
s
u
si
n
g
h
a
n
d
s
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
3
,
n
o
.
7
1
0
7
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
1
6
7
1
0
7
.
[
7
]
J.
C
h
e
n
,
C
.
W
a
n
g
,
J.
C
h
e
n
,
a
n
d
B
.
Y
i
n
,
“
M
a
n
i
p
u
l
a
t
o
r
c
o
n
t
r
o
l
sy
s
t
e
m
b
a
se
d
o
n
f
l
e
x
i
b
l
e
se
n
so
r
t
e
c
h
n
o
l
o
g
y
,
”
Mi
c
ro
m
a
c
h
i
n
e
s
,
v
o
l
.
1
4
,
n
o
.
1
6
9
7
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
mi
1
4
0
9
1
6
9
7
.
[
8
]
L.
Y
u
e
,
L
.
Z
o
n
g
x
i
n
g
,
D
.
H
u
i
,
J.
C
h
a
o
,
L
.
Z
i
q
i
a
n
g
,
a
n
d
L.
Zh
o
u
j
i
e
,
“
H
o
w
t
o
a
c
h
i
e
v
e
h
u
m
a
n
–
ma
c
h
i
n
e
i
n
t
e
r
a
c
t
i
o
n
b
y
f
o
o
t
g
e
st
u
r
e
r
e
c
o
g
n
i
t
i
o
n
:
a
r
e
v
i
e
w
,
”
I
EEE
S
e
n
s
o
rs
J
o
u
rn
a
l
,
v
o
l
.
2
3
,
n
o
.
1
5
,
p
p
.
1
6
5
1
5
–
1
6
5
2
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
3
.
3
2
8
5
2
1
4
.
[
9
]
A
.
F
i
l
i
p
o
w
s
k
a
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
g
e
s
t
u
r
e
r
e
c
o
g
n
i
t
i
o
n
g
l
o
v
e
:
d
e
si
g
n
a
n
d
i
m
p
l
e
me
n
t
a
t
i
o
n
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
4
,
n
o
.
6
1
5
7
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
4
1
8
6
1
5
7
.
[
1
0
]
P
.
J.
C
r
u
z
,
J.
P
.
V
á
sc
o
n
e
z
,
R
.
R
o
m
e
r
o
,
a
n
d
o
t
h
e
r
s,
“
A
d
e
e
p
q
-
n
e
t
w
o
r
k
b
a
s
e
d
h
a
n
d
g
e
st
u
r
e
r
e
c
o
g
n
i
t
i
o
n
sy
s
t
e
m
f
o
r
c
o
n
t
r
o
l
o
f
r
o
b
o
t
i
c
p
l
a
t
f
o
r
ms,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
3
,
n
o
.
7
9
5
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
023
-
3
4
5
4
0
-
x.
[
1
1
]
W
.
D
o
n
g
,
L
.
Y
a
n
g
,
a
n
d
G
.
F
o
r
t
i
n
o
,
“
S
t
r
e
t
c
h
a
b
l
e
h
u
m
a
n
m
a
c
h
i
n
e
i
n
t
e
r
f
a
c
e
b
a
s
e
d
o
n
sm
a
r
t
g
l
o
v
e
e
mb
e
d
d
e
d
w
i
t
h
P
D
M
S
-
C
B
st
r
a
i
n
sen
s
o
r
s,”
I
EEE
S
e
n
so
rs
J
o
u
r
n
a
l
,
v
o
l
.
2
0
,
n
o
.
1
4
,
p
p
.
8
0
7
3
–
8
0
8
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
0
.
2
9
8
2
0
7
0
.
[
1
2
]
E.
K
i
m
,
J.
S
h
i
n
,
Y
.
K
w
o
n
,
a
n
d
B
.
P
a
r
k
,
“
E
M
G
-
b
a
se
d
d
y
n
a
mi
c
h
a
n
d
g
e
s
t
u
r
e
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
e
d
g
e
A
I
f
o
r
h
u
m
a
n
–
r
o
b
o
t
i
n
t
e
r
a
c
t
i
o
n
,
”
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
2
,
n
o
.
1
5
4
1
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
2
0
7
1
5
4
1
.
[
1
3
]
M
.
G
u
o
,
Y
.
X
i
a
,
J.
L
i
u
,
Y
.
Z
h
a
n
g
,
M
.
Li
,
a
n
d
X
.
W
a
n
g
,
“
W
e
a
r
a
b
l
e
p
r
e
ssu
r
e
se
n
so
r
b
a
se
d
o
n
t
r
i
b
o
e
l
e
c
t
r
i
c
n
a
n
o
g
e
n
e
r
a
t
o
r
f
o
r
i
n
f
o
r
mat
i
o
n
e
n
c
o
d
i
n
g
,
g
e
s
t
u
r
e
r
e
c
o
g
n
i
t
i
o
n
,
a
n
d
w
i
r
e
l
e
ss
r
e
a
l
-
t
i
m
e
r
o
b
o
t
c
o
n
t
r
o
l
,
”
Ad
v
a
n
c
e
d
F
u
n
c
t
i
o
n
a
l
M
a
t
e
ri
a
l
s
,
p
.
2
4
1
9
2
0
9
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
2
/
a
d
f
m.
2
0
2
4
1
9
2
0
9
.
[
1
4
]
S
.
G
r
a
t
z
-
K
e
l
l
y
e
t
a
l
.
,
“
M
u
l
t
i
f
u
n
c
t
i
o
n
a
l
s
e
n
s
o
r
a
r
r
a
y
f
o
r
u
s
e
r
i
n
t
e
r
a
c
t
i
o
n
b
a
se
d
o
n
d
i
e
l
e
c
t
r
i
c
e
l
a
s
t
o
m
e
r
s
w
i
t
h
sp
u
t
t
e
r
e
d
me
t
a
l
e
l
e
c
t
r
o
d
e
s,
”
M
a
t
e
ri
a
l
s
,
v
o
l
.
1
7
,
n
o
.
2
3
,
p
.
5
9
9
3
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
m
a
1
7
2
3
5
9
9
3
.
[
1
5
]
P
.
W
.
La
k
s
o
n
o
,
T
.
K
i
t
a
m
u
r
a
,
J.
M
u
g
u
r
o
,
K
.
M
a
t
s
u
sh
i
t
a
,
M
.
S
a
s
a
k
i
,
a
n
d
M
.
S
.
A
.
b
i
n
S
u
h
a
i
m
i
,
“
M
i
n
i
mu
m
m
a
p
p
i
n
g
f
r
o
m
E
M
G
si
g
n
a
l
s
a
t
h
u
m
a
n
E
l
b
o
w
a
n
d
sh
o
u
l
d
e
r
m
o
v
e
me
n
t
s
i
n
t
o
t
w
o
D
o
F
u
p
p
e
r
-
l
i
mb
r
o
b
o
t
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Ma
c
h
i
n
e
s
,
v
o
l
.
9
,
n
o
.
5
6
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
ma
c
h
i
n
e
s
9
0
3
0
0
5
6
.
[
1
6
]
C
.
L
u
e
t
a
l
.
,
“
O
n
l
i
n
e
h
a
n
d
g
e
s
t
u
r
e
d
e
t
e
c
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
f
o
r
U
A
V
m
o
t
i
o
n
p
l
a
n
n
i
n
g
,
”
M
a
c
h
i
n
e
s
,
v
o
l
.
1
1
,
n
o
.
2
1
0
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
ma
c
h
i
n
e
s
1
1
0
2
0
2
1
0
.
[
1
7
]
C
.
L
u
,
S
.
A
mi
n
o
,
a
n
d
L.
J
i
n
g
,
“
D
a
t
a
g
l
o
v
e
w
i
t
h
b
e
n
d
i
n
g
se
n
s
o
r
a
n
d
i
n
e
r
t
i
a
l
se
n
s
o
r
b
a
se
d
o
n
w
e
i
g
h
t
e
d
D
T
W
f
u
si
o
n
f
o
r
s
i
g
n
l
a
n
g
u
a
g
e
r
e
c
o
g
n
i
t
i
o
n
,
”
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
2
,
n
o
.
6
1
3
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
2
0
3
0
6
1
3
.
[
1
8
]
N
.
H
e
r
b
a
z
,
H
.
E
l
I
d
r
i
ssi
,
a
n
d
A
.
B
a
d
r
i
,
“
A
M
o
r
o
c
c
a
n
si
g
n
l
a
n
g
u
a
g
e
r
e
c
o
g
n
i
t
i
o
n
a
l
g
o
r
i
t
h
m
u
si
n
g
a
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
J
o
u
rn
a
l
o
f
I
C
T
S
t
a
n
d
a
rd
i
z
a
t
i
o
n
,
v
o
l
.
1
0
,
n
o
.
0
3
,
p
p
.
4
1
1
–
4
2
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
3
0
5
2
/
j
i
c
t
s
2
2
4
5
-
8
0
0
X
.
1
0
3
3
.
[
1
9
]
M
.
K
a
r
r
e
n
b
a
c
h
,
P
.
P
r
e
e
c
h
a
y
a
so
m
b
o
o
n
,
P
.
S
a
u
e
r
,
D
.
B
o
e
,
a
n
d
E.
R
o
mb
o
k
a
s
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
n
d
sess
i
o
n
-
s
p
e
c
i
f
i
c
r
a
p
i
d
r
e
c
a
l
i
b
r
a
t
i
o
n
f
o
r
d
y
n
a
m
i
c
h
a
n
d
g
e
st
u
r
e
r
e
c
o
g
n
i
t
i
o
n
f
r
o
m
E
M
G
,
”
Fr
o
n
t
i
e
rs
i
n
B
i
o
e
n
g
i
n
e
e
ri
n
g
a
n
d
B
i
o
t
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
,
n
o
.
1
0
3
4
6
7
2
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
8
9
/
f
b
i
o
e
.
2
0
2
2
.
1
0
3
4
6
7
2
.
[
2
0
]
A
.
R
e
y
e
s
-
M
u
ñ
o
z
,
M
.
D
o
m
i
n
g
o
,
M
.
L
ó
p
e
z
-
Tr
i
n
i
d
a
d
,
a
n
d
J.
D
e
l
g
a
d
o
,
“
I
n
t
e
g
r
a
t
i
o
n
o
f
b
o
d
y
s
e
n
so
r
n
e
t
w
o
r
k
s
a
n
d
v
e
h
i
c
u
l
a
r
a
d
-
h
o
c
n
e
t
w
o
r
k
s fo
r
t
r
a
f
f
i
c
saf
e
t
y
,
”
S
e
n
so
rs
,
v
o
l
.
1
6
,
n
o
.
1
,
Ja
n
.
2
0
1
6
,
d
o
i
:
1
0
.
3
3
9
0
/
s1
6
0
1
0
1
0
7
.
[
2
1
]
H
.
S
a
b
i
r
,
M
.
O
u
ss
a
i
d
,
a
n
d
N
.
N
g
o
t
e
,
“
A
n
e
x
p
e
r
i
m
e
n
t
a
l
m
e
t
h
o
d
f
o
r
d
i
a
g
n
o
s
t
i
c
o
f
i
n
c
i
p
i
e
n
t
b
r
o
k
e
n
r
o
t
o
r
b
a
r
f
a
u
l
t
i
n
i
n
d
u
c
t
i
o
n
mac
h
i
n
e
s
,
”
H
e
l
i
y
o
n
,
v
o
l
.
8
,
n
o
.
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
2
.
e
0
9
1
3
6
.
[
2
2
]
N
.
A
.
A
l
m
u
j
a
l
l
y
e
t
a
l
.
,
“
W
e
a
r
a
b
l
e
s
e
n
so
r
s
-
b
a
s
e
d
a
ss
i
st
i
v
e
t
e
c
h
n
o
l
o
g
i
e
s fo
r
p
a
t
i
e
n
t
h
e
a
l
t
h
m
o
n
i
t
o
r
i
n
g
,
”
Fr
o
n
t
i
e
rs i
n
B
i
o
e
n
g
i
n
e
e
ri
n
g
a
n
d
Bi
o
t
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
3
,
p
.
1
4
3
7
8
7
7
,
2
0
2
5
.
[
2
3
]
Z.
La
i
,
H
.
L
i
,
D
.
Zh
a
n
g
,
Y
.
Zh
a
o
,
W
.
Q
i
a
n
,
a
n
d
C
.
S
.
Je
n
se
n
,
“
E
2
u
s
d
:
Ef
f
i
c
i
e
n
t
-
y
e
t
-
e
f
f
e
c
t
i
v
e
u
n
s
u
p
e
r
v
i
se
d
s
t
a
t
e
d
e
t
e
c
t
i
o
n
f
o
r
mu
l
t
i
v
a
r
i
a
t
e
t
i
m
e
ser
i
e
s
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
A
C
M
W
e
b
C
o
n
f
e
r
e
n
c
e
2
0
2
4
,
M
a
y
2
0
2
4
,
p
p
.
3
0
1
0
–
3
0
2
1
.
[
2
4
]
S
.
S
a
j
e
d
i
,
W
.
Li
u
,
K
.
El
t
o
u
n
y
,
S
.
B
e
h
d
a
d
,
M
.
Z
h
e
n
g
,
a
n
d
X
.
L
i
a
n
g
,
“
U
n
c
e
r
t
a
i
n
t
y
-
a
ssi
st
e
d
i
ma
g
e
-
p
r
o
c
e
ssi
n
g
f
o
r
h
u
ma
n
-
r
o
b
o
t
c
l
o
s
e
c
o
l
l
a
b
o
r
a
t
i
o
n
,
”
I
E
EE
Ro
b
o
t
i
c
s
a
n
d
A
u
t
o
m
a
t
i
o
n
L
e
t
t
e
rs
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
4
2
3
6
–
4
2
4
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
L
R
A
.
2
0
2
2
.
3
1
5
0
4
8
7
.
[
2
5
]
M
.
H
.
Z
a
f
a
r
,
S
.
K
.
R
.
M
o
o
s
a
v
i
,
a
n
d
F
.
S
a
n
f
i
l
i
p
p
o
,
“
E
n
h
a
n
c
i
n
g
u
n
ma
n
n
e
d
g
r
o
u
n
d
v
e
h
i
c
l
e
p
e
r
f
o
r
ma
n
c
e
i
n
S
A
R
o
p
e
r
a
t
i
o
n
s:
i
n
t
e
g
r
a
t
e
d
g
e
st
u
r
e
-
c
o
n
t
r
o
l
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
f
o
r
o
p
t
i
m
i
se
d
v
i
c
t
i
m
d
e
t
e
c
t
i
o
n
,
”
Fro
n
t
i
e
rs
i
n
Ro
b
o
t
i
c
s
a
n
d
AI
,
v
o
l
.
1
1
,
n
o
.
1
3
5
6
3
4
5
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
8
9
/
f
r
o
b
t
.
2
0
2
4
.
1
3
5
6
3
4
5
.
[
2
6
]
S
.
B
a
l
o
d
a
,
S
.
K
.
S
r
i
r
a
m
,
P
.
S
h
a
r
m
a
,
S
.
S
i
n
g
h
,
a
n
d
N
.
G
u
p
t
a
,
“
D
e
v
e
l
o
p
m
e
n
t
o
f
S
W
C
N
Ts/
P
D
M
S
c
o
m
p
o
s
i
t
e
s
t
r
a
i
n
s
e
n
s
o
r
s
i
n
t
e
g
r
a
t
e
d
s
mart
g
l
o
v
e
f
o
r
h
u
ma
n
-
ma
c
h
i
n
e
i
n
t
e
r
f
a
c
e
a
p
p
l
i
c
a
t
i
o
n
s
,
”
I
EE
E
S
e
n
s
o
rs
J
o
u
rn
a
l
,
v
o
l
.
2
5
,
n
o
.
2
,
p
p
.
2
4
0
0
–
2
4
0
7
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
[
2
7
]
Y
.
Ji
a
n
g
e
t
a
l
.
,
“
A
m
u
l
t
i
f
u
n
c
t
i
o
n
a
l
t
a
c
t
i
l
e
se
n
so
r
y
sy
s
t
e
m
f
o
r
r
o
b
o
t
i
c
i
n
t
e
l
l
i
g
e
n
t
i
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
ma
n
i
p
u
l
a
t
i
o
n
p
e
r
c
e
p
t
i
o
n
,
”
Ad
v
a
n
c
e
d
S
c
i
e
n
c
e
,
v
o
l
.
1
1
,
p
.
2
4
0
2
7
0
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
2
/
a
d
v
s.
2
0
2
4
0
2
7
0
5
.
[
2
8
]
G
.
Y
a
n
g
a
n
d
o
t
h
e
r
s,
“
A
n
I
o
T
-
e
n
a
b
l
e
d
st
r
o
k
e
r
e
h
a
b
i
l
i
t
a
t
i
o
n
s
y
st
e
m b
a
se
d
o
n
smar
t
w
e
a
r
a
b
l
e
a
r
m
b
a
n
d
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
EE
E
J
o
u
rn
a
l
o
f
T
r
a
n
sl
a
t
i
o
n
a
l
E
n
g
i
n
e
e
r
i
n
g
i
n
H
e
a
l
t
h
a
n
d
M
e
d
i
c
i
n
e
,
v
o
l
.
6
,
p
.
2
1
0
0
5
1
0
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
JT
EH
M
.
2
0
1
8
.
2
8
2
2
6
8
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.