T
E
L
K
O
M
N
I
K
A
T
elec
o
m
m
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
,
p
p
.
1
3
4
~
1
4
5
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Kem
en
r
is
tek
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A.
v
1
9
i1
.
1
6
5
6
6
134
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Im
pro
v
ed my
o
elect
ric pa
tt
er
n reco
g
nition o
f
fi
ng
er
mo
v
ement
using
rej
ec
tion
-
b
a
sed ex
treme
lea
r
ning
ma
chine
K
ha
irul Ana
m
1
,
Adel
Al
-
J
um
a
ily
2
1
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
E
n
g
i
n
e
e
rin
g
,
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
U
n
iv
e
rsity
o
f
Je
m
b
e
r,
In
d
o
n
e
sia
2
S
c
h
o
o
l
o
f
El
e
c
tri
c
a
l,
M
e
c
h
a
n
ica
l
a
n
d
M
e
c
h
a
tro
n
ic
S
y
ste
m
s,
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
a
n
d
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
,
Un
iv
e
rsity
o
f
Tec
h
n
o
lo
g
y
S
y
d
n
e
y
,
Au
stra
li
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
1
,
2
0
2
0
R
ev
is
ed
Au
g
1
0
,
2
0
2
0
Acc
ep
ted
Sep
1
5
,
2
0
2
0
M
y
o
e
lec
tri
c
c
o
n
tro
l
s
y
ste
m
(M
CS
)
h
a
d
b
e
e
n
a
p
p
li
e
d
t
o
h
a
n
d
e
x
o
sk
e
leto
n
t
o
imp
ro
v
e
th
e
h
u
m
a
n
-
m
a
c
h
i
n
e
i
n
tera
c
ti
o
n
.
Th
e
c
u
rre
n
t
M
CS
e
n
a
b
les
th
e
e
x
o
sk
e
leto
n
to
m
o
v
e
a
ll
fin
g
e
rs
c
o
n
c
u
rre
n
tl
y
fo
r
o
p
e
n
i
n
g
a
n
d
c
lo
sin
g
h
a
n
d
a
n
d
d
o
e
s
n
o
t
c
o
n
sid
e
r
ro
b
u
st
n
e
ss
issu
e
c
a
u
se
d
b
y
th
e
c
o
n
d
i
ti
o
n
n
o
t
c
o
n
sid
e
re
d
in
th
e
train
i
n
g
sta
g
e
.
Th
is
stu
d
y
a
d
d
re
ss
e
d
a
n
e
w
M
CS
e
m
p
l
o
y
in
g
n
o
v
e
l
m
y
o
e
lec
tri
c
p
a
tt
e
rn
re
c
o
g
n
it
io
n
(M
-
P
R)
t
o
h
a
n
d
le
m
o
re
m
o
v
e
m
e
n
ts.
F
u
rth
e
rm
o
re
,
a
re
jec
ti
o
n
-
b
a
se
d
ra
d
ial
-
b
a
sis
fu
n
c
ti
o
n
e
x
trem
e
lea
rn
in
g
m
a
c
h
i
n
e
(RBF
-
EL
M
)
wa
s
p
r
o
p
o
s
e
d
to
tac
k
le
th
e
m
o
v
e
m
e
n
ts
th
a
t
a
re
n
o
t
i
n
c
lu
d
e
d
in
th
e
train
in
g
sta
g
e
.
T
h
e
re
su
lt
s
o
f
th
e
o
ffli
n
e
e
x
p
e
rime
n
ts
sh
o
we
d
th
e
RBF
-
E
LM
with
re
jec
ti
o
n
m
e
c
h
a
n
ism
(RBF
-
ELM
-
R)
o
u
tp
e
rfo
rm
e
d
RBF
-
EL
M
wit
h
o
u
t
re
jec
ti
o
n
m
e
c
h
a
n
ism
a
n
d
o
th
e
r
we
ll
-
k
n
o
wn
c
las
sifiers
.
In
t
h
e
o
n
l
in
e
e
x
p
e
rime
n
ts,
u
sin
g
1
0
-
train
e
d
c
las
se
s,
th
e
M
-
P
R
a
c
h
iev
e
d
a
n
a
c
c
u
ra
c
y
o
f
8
9
.
7
3
%
a
n
d
8
9
.
2
2
%
u
si
n
g
RBF
-
ELM
-
R
a
n
d
RB
F
-
EL
M
,
re
sp
e
c
ti
v
e
ly
.
In
th
e
e
x
p
e
rime
n
t
wit
h
5
-
t
ra
in
e
d
c
las
se
s
a
n
d
5
-
u
n
train
e
d
c
las
se
s,
th
e
M
-
P
R
a
c
c
u
ra
c
y
wa
s 8
0
.
2
2
%
a
n
d
5
9
.
6
4
%
u
si
n
g
R
BF
-
ELM
-
R
a
n
d
RBF
-
EL
M
,
re
sp
e
c
ti
v
e
ly
K
ey
w
o
r
d
s
:
E
x
tr
em
e
lear
n
in
g
m
ac
h
in
e
Fin
g
er
m
o
v
e
m
en
t
Han
d
ex
o
s
k
eleto
n
My
o
elec
tr
ic
p
atter
n
r
ec
g
n
itio
n
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
lic
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Kh
air
u
l A
n
am
Dep
ar
tm
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
Un
iv
er
s
ity
o
f
J
em
b
er
Kalim
an
tan
3
7
St,
J
em
b
er
,
E
a
s
t Jav
a,
I
n
d
o
n
esia
E
m
ail: k
h
air
u
l@
u
n
ej.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Ma
n
y
co
u
n
tr
ies
h
av
e
a
s
ig
n
if
ican
t
n
u
m
b
er
o
f
p
eo
p
le
with
d
is
ab
ili
ty
.
T
h
e
r
esu
lts
o
f
th
e
Su
r
v
ey
o
f
Dis
ab
ilit
y
,
Ag
ein
g
an
d
C
ar
er
s
(
SDAC
)
in
2
0
0
9
s
h
o
we
d
th
at
f
o
u
r
m
illi
o
n
p
eo
p
le
in
Au
s
tr
a
lia
(
1
8
.
5
%)
s
u
f
f
er
f
r
o
m
d
is
ab
ilit
y
.
Stro
k
e
is
o
n
e
o
f
th
e
m
ajo
r
f
ac
to
r
s
ca
u
s
in
g
d
i
s
ab
ilit
y
in
Au
s
tr
alia.
I
n
2
0
0
9
,
i
t
was
esti
m
ated
th
at
1.
8
%
o
f
A
u
s
tr
alian
s
h
av
e
s
u
f
f
er
ed
f
r
o
m
a
s
tr
o
k
e.
Of
th
e
p
eo
p
le
wh
o
ar
e
im
p
air
ed
d
u
e
t
o
s
tr
o
k
e,
6
2
%
r
ep
o
r
te
d
th
at
s
tr
o
k
e
is
th
e
p
r
im
ar
y
ca
u
s
e
o
f
d
is
ab
ilit
y
.
Ab
o
u
t
4
0
%
o
f
th
em
h
av
e
d
if
f
icu
lties
u
s
in
g
th
eir
ar
m
s
o
r
f
in
g
e
r
s
o
r
d
if
f
ic
u
lties
in
g
r
ip
p
in
g
[
1
]
.
I
n
e
v
itab
ly
,
h
a
n
d
d
is
ab
ilit
y
ca
u
s
ed
b
y
s
tr
o
k
e
h
as
d
ec
r
ea
s
ed
t
h
e
q
u
ality
o
f
life
f
o
r
in
d
i
v
id
u
als
an
d
ca
r
er
s
.
T
h
er
ef
o
r
e,
m
a
n
y
attem
p
ts
h
a
v
e
b
ee
n
m
ad
e
to
tack
le
th
is
p
r
o
b
lem
th
r
o
u
g
h
tr
ad
itio
n
al
th
er
a
p
y
o
r
ev
e
n
ad
v
an
ce
d
tech
n
o
lo
g
y
s
u
ch
as
r
o
b
o
t
tech
n
o
lo
g
y
[2
-
5]
.
T
h
e
h
an
d
ex
o
s
k
eleto
n
,
as
a
p
ar
t
o
f
r
o
b
o
tic
d
e
v
ices,
b
ec
o
m
es
th
e
b
est
s
o
lu
tio
n
to
r
ec
o
v
er
i
n
g
th
e
q
u
ality
o
f
life
f
o
r
th
e
f
o
llo
wi
n
g
r
ea
s
o
n
s
.
I
t
is
p
o
r
tab
le
an
d
wo
r
n
b
y
th
e
s
u
b
ject
s
o
th
at
th
e
th
er
a
p
y
ca
n
b
e
d
o
n
e
an
y
wh
e
r
e
a
n
d
an
y
tim
e.
B
esid
es,
it
is
ea
s
y
t
o
b
e
eq
u
ip
p
e
d
with
an
i
n
ter
ac
tiv
e
in
ter
f
ac
e
s
u
ch
as a
g
a
m
e
tech
n
o
lo
g
y
t
o
en
h
a
n
ce
th
e
ef
f
ec
tiv
e
n
ess
o
f
th
e
th
er
a
p
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
I
mp
r
o
ve
d
myo
elec
tr
ic
p
a
tter
n
r
ec
o
g
n
itio
n
o
f fin
g
er mo
ve
men
t u
s
in
g
r
ejec
tio
n
.
.
.
(
K
h
a
ir
u
l A
n
a
m
)
135
T
h
e
h
an
d
e
x
o
s
k
eleto
n
is
ex
p
e
cted
to
h
elp
th
e
wea
r
er
co
m
f
o
r
tab
ly
.
T
h
e
r
ef
o
r
e,
a
u
s
er
d
o
e
s
n
o
t
f
ee
l
u
n
co
m
f
o
r
tab
le
an
d
h
av
e
t
r
o
u
b
le
wh
en
d
o
i
n
g
a
m
o
ti
o
n
task
wh
ile
wea
r
in
g
it.
I
n
o
th
er
wo
r
d
s
,
th
e
ass
is
tan
ce
s
h
o
u
ld
b
e
p
r
o
v
i
d
ed
as
n
ee
d
e
d
[
6
,
7
]
.
T
o
attain
s
u
ch
a
s
m
o
o
th
i
n
ter
ac
tio
n
,
th
e
c
o
n
tr
o
l
s
y
s
tem
o
f
th
e
r
o
b
o
t
s
h
o
u
ld
co
n
s
id
er
th
e
h
u
m
a
n
in
ten
tio
n
.
Ho
wev
er
,
d
ev
elo
p
in
g
s
u
ch
a
co
n
tr
o
l
m
eth
o
d
is
n
o
t
an
ea
s
y
task
.
Dif
f
er
en
t
b
io
lo
g
ical
s
ig
n
als
h
av
e
b
ee
n
co
n
s
id
er
ed
to
d
etec
t
th
e
u
s
er
’
s
in
ten
tio
n
.
My
o
elec
tr
ic
s
ig
n
al
(
ME
S)
o
r
elec
tr
o
m
y
o
g
r
ap
h
y
(
E
MG
)
s
ig
n
al
th
at
co
n
tain
s
s
u
f
f
icien
t
in
f
o
r
m
atio
n
o
f
th
e
u
s
er
’
s
in
ten
tio
n
h
as
b
ee
n
u
s
ed
t
o
co
n
tr
o
l
r
eh
ab
ilit
atio
n
d
ev
ices
o
r
ass
is
tiv
e
r
o
b
o
ts
f
o
r
y
ea
r
s
.
My
o
elec
tr
ic
co
n
tr
o
l
h
as
b
ee
n
im
p
lem
en
ted
in
two
way
s
:
n
o
n
-
p
atter
n
r
ec
o
g
n
itio
n
an
d
p
atter
n
r
ec
o
g
n
itio
n
[
8
]
.
I
n
th
e
f
ir
s
t
ap
p
licatio
n
,
th
e
E
MG
s
ig
n
al
h
as
b
ee
n
u
tili
ze
d
to
d
etec
t
f
o
r
ce
o
r
a
n
y
p
h
y
s
ical
in
f
o
r
m
atio
n
s
u
ch
as
a
n
g
le
to
co
n
tr
o
l
th
e
e
x
o
s
k
eleto
n
d
e
v
ices
[
9
-
1
1
]
.
T
h
e
s
ec
o
n
d
ty
p
e
o
f
E
MG
im
p
lem
e
n
tatio
n
is
th
e
E
MG
-
b
ased
p
att
er
n
r
ec
o
g
n
itio
n
.
I
t h
as
b
ee
n
d
o
n
e
b
y
an
al
y
zin
g
th
e
E
MG
s
ig
n
als
an
d
class
if
y
in
g
t
h
e
co
r
r
ec
t
m
o
v
em
e
n
t
f
r
o
m
p
r
ed
ef
in
ed
s
ets
o
f
lim
b
m
o
v
em
e
n
ts
.
Dif
f
er
en
t
ty
p
e
s
o
f
m
o
v
em
en
ts
h
av
e
b
ee
n
s
tu
d
i
ed
s
o
f
ar
s
u
ch
as h
an
d
[
1
2
-
1
9
]
an
d
leg
[
2
0
,
21]
m
o
v
em
en
ts
.
So
m
e
h
an
d
e
x
o
s
k
eleto
n
s
h
av
e
em
p
lo
y
ed
s
u
r
f
ac
e
E
MG
to
co
m
e
u
p
with
a
s
m
o
o
th
h
u
m
an
-
ma
ch
in
e
in
ter
ac
tio
n
.
Mu
las
et
a
l.
[
2
2
]
h
av
e
d
e
v
elo
p
e
d
a
h
an
d
e
x
o
s
k
el
eto
n
co
n
tr
o
lled
b
y
E
MG
s
ig
n
al.
T
h
e
E
MG
s
ig
n
al
co
llected
f
r
o
m
th
e
s
u
b
ject’
s
f
o
r
ea
r
m
is
u
s
ed
to
p
r
ed
ict
t
h
e
u
s
er
’
s
in
ten
tio
n
to
m
o
v
e
o
r
n
o
t
to
m
o
v
e.
T
h
is
in
f
o
r
m
atio
n
was
em
p
lo
y
ed
to
d
r
iv
e
f
in
g
er
s
o
f
th
e
h
an
d
ex
o
s
k
eleto
n
o
r
k
ee
p
th
em
in
a
r
e
s
t
s
tate.
All
f
in
g
er
s
ex
clu
d
in
g
th
e
th
u
m
b
a
r
e
co
n
tr
o
lled
s
im
u
ltan
eo
u
s
ly
.
Fu
r
th
e
r
m
o
r
e,
W
eg
e
an
d
Z
im
m
e
r
m
an
n
[
2
3
]
h
av
e
d
ev
elo
p
ed
m
y
o
elec
tr
ic
c
o
n
tr
o
l
s
y
s
tem
(
MCS
)
f
o
r
a
h
a
n
d
ex
o
s
k
eleto
n
th
at
co
u
l
d
m
o
v
e
an
in
d
iv
i
d
u
al
f
in
g
e
r
b
ased
o
n
th
e
u
s
er
'
s
in
ten
tio
n
.
T
h
e
MCS
u
tili
ze
s
E
MG
elec
tr
o
d
es to
ac
q
u
ir
e
elec
tr
ical
ac
tiv
ities
f
r
o
m
1
6
m
u
s
cles.
Mo
r
eo
v
er
,
th
e
co
n
tr
o
l
s
y
s
tem
em
p
lo
y
s
a
b
lin
d
s
o
u
r
ce
s
ep
ar
atio
n
t
o
s
ep
ar
ate
th
e
in
f
o
r
m
atio
n
co
n
tain
e
d
in
th
e
h
ig
h
-
d
en
s
ity
s
u
r
f
ac
e
E
MG
s
ig
n
als
at
th
e
f
o
r
ea
r
m
in
to
s
ev
er
al
s
ig
n
als
r
ela
ted
to
a
s
p
ec
if
ic
f
in
g
e
r
m
o
v
e
m
en
t.
Ho
wev
er
,
th
e
ex
p
er
im
en
tal
r
esu
lt is
n
o
t satis
f
y
in
g
.
T
h
e
latest
MC
S
f
o
r
th
e
h
an
d
ex
o
s
k
eleto
n
is
th
e
o
n
e
d
ev
e
l
o
p
ed
b
y
Ho
et
a
l.
[
2
4
]
.
T
h
e
ex
o
s
k
eleto
n
’
s
s
tr
u
ctu
r
e
f
its
d
if
f
er
en
t
f
in
g
e
r
len
g
th
s
an
d
alig
n
s
with
th
e
v
ir
t
u
al
c
en
ter
o
f
r
o
tatio
n
o
f
th
e
m
etata
r
s
o
p
h
alan
g
ea
l
(
MCP
)
an
d
th
e
p
r
o
x
im
al
in
ter
p
h
alan
g
ea
l
(
PIP)
.
T
h
is
d
ev
ice
is
ab
le
t
o
d
etec
t
th
e
u
s
er
’
s
in
ten
t
io
n
f
r
o
m
th
e
u
s
er
’
s
mus
cle
f
o
r
h
a
n
d
o
p
en
in
g
an
d
c
lo
s
in
g
.
T
h
u
s
,
th
is
d
ev
ice
is
ab
l
e
to
d
r
iv
e
all
th
e
f
in
g
er
m
o
v
em
en
ts
s
im
u
ltan
eo
u
s
ly
to
o
p
en
an
d
clo
s
e
th
e
h
an
d
.
T
h
e
af
o
r
em
e
n
tio
n
ed
f
ac
ts
s
h
o
w
th
at
th
e
wo
r
k
ab
le
m
y
o
elec
tr
ic
co
n
tr
o
ller
o
n
t
h
e
cu
r
r
en
t
h
an
d
ex
o
s
k
eleto
n
d
ea
l
s
with
s
im
p
l
e
f
in
g
er
m
o
v
em
e
n
ts
,
i.e
.
s
im
u
ltan
eo
u
s
f
i
n
g
er
m
o
v
em
en
ts
s
u
ch
as
o
p
en
in
g
an
d
clo
s
in
g
th
e
h
an
d
.
Mo
r
e
o
v
er
,
th
e
p
r
esen
t
E
MG
-
b
ased
co
n
tr
o
ller
is
d
esig
n
e
d
to
r
ec
o
g
n
ize
th
e
m
o
v
em
en
ts
th
at
a
r
e
in
v
o
lv
ed
i
n
th
e
tr
ain
in
g
.
Ho
we
v
er
,
it
f
ail
s
to
r
ec
o
g
n
ize
th
e
m
o
v
em
en
ts
t
h
at
ar
e
n
o
t
in
clu
d
e
d
in
th
e
tr
ain
i
n
g
s
tag
e
[
2
5
]
.
I
n
r
ea
l
-
tim
e
ap
p
licatio
n
,
th
e
tr
ain
ed
m
o
v
em
en
ts
ar
e
lim
ited
,
y
et
th
e
u
n
tr
ai
n
ed
m
o
v
em
en
ts
ar
e
m
an
y
.
As
a
r
esu
lt,
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
M
C
S
d
ec
r
ea
s
es
wh
en
it
wo
r
k
s
i
n
r
ea
l
-
tim
e
o
r
clin
ical
ap
p
licatio
n.
I
n
s
u
m
m
ar
y
,
two
m
ain
p
r
o
b
le
m
s
ap
p
ea
r
in
th
e
cu
r
r
en
t
MCS
f
o
r
th
e
h
an
d
ex
o
s
k
eleto
n
.
T
h
e
f
ir
s
t
is
r
elate
d
to
th
e
lim
ited
n
u
m
b
er
o
f
f
in
g
e
r
m
o
v
em
en
ts
th
at
ca
n
b
e
d
ea
lt
with
.
T
h
e
s
ec
o
n
d
is
r
elat
ed
to
th
e
ca
p
ab
ilit
y
o
f
th
e
MCS
to
r
ejec
t
th
e
u
n
tr
ain
ed
m
o
v
e
m
en
ts
th
at
p
o
s
s
ib
ly
ap
p
ea
r
i
n
th
e
r
ea
l
-
tim
e
ap
p
l
icatio
n
.
T
h
is
p
ap
er
p
r
o
p
o
s
es
a
n
ew
M
C
S
f
o
r
th
e
h
an
d
ex
o
s
k
eleto
n
th
at
o
v
er
co
m
es
th
ese
two
is
s
u
es.
T
h
e
im
p
r
o
v
e
d
MCS
th
at
i
s
p
r
o
p
o
s
ed
em
p
lo
y
s
th
e
E
MG
-
b
ased
p
atter
n
r
ec
o
g
n
itio
n
(
E
MG
-
PR
)
to
en
ab
le
co
m
p
lex
f
in
g
er
m
o
v
em
e
n
ts
,
in
s
tead
o
f
h
an
d
o
p
e
n
in
g
a
n
d
clo
s
in
g
.
Fu
r
th
er
m
o
r
e,
to
c
o
p
e
with
th
e
u
n
tr
ain
ed
m
o
v
e
m
en
t
is
s
u
e,
th
is
p
ap
er
p
r
o
p
o
s
es
a
class
if
ier
ca
lled
r
ad
ial
b
asis
f
u
n
ctio
n
e
x
tr
em
e
lear
n
in
g
m
ac
h
in
e
[
2
6
]
with
r
ejec
tio
n
m
ec
h
an
is
m
(
R
B
F
-
ELM
-
R
)
.
R
B
F
-
ELM
-
R
d
etec
ts
th
e
u
n
tr
ain
ed
m
o
v
e
m
e
n
ts
an
d
r
ejec
ts
th
em
.
I
n
o
th
er
wo
r
d
s
,
th
e
s
y
s
tem
will
co
n
s
id
er
th
e
r
ejec
ted
m
o
v
em
en
ts
as
a
n
o
-
ac
tio
n
o
r
a
r
est
s
tate.
T
h
e
p
ap
e
r
is
o
r
g
an
ized
as
f
o
llo
ws
;
s
ec
tio
n
2
p
r
o
v
id
es
a
d
escr
ip
tio
n
o
f
th
e
b
asic
co
n
ce
p
t
o
f
R
B
F
-
E
L
M
with
r
ejec
tio
n
m
ec
h
an
i
s
m
(
R
B
F
-
ELM
-
R
)
.
Sectio
n
3
p
r
esen
ts
th
e
p
r
o
p
o
s
ed
MCS
.
Sectio
n
4
p
r
o
v
id
es
th
e
ex
p
er
im
e
n
tal
r
esu
lt
an
d
s
tatis
tical
an
aly
s
i
s
f
o
r
th
e
o
f
f
lin
e
a
n
d
o
n
lin
e
class
if
icatio
n
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
tem
o
n
th
e
h
an
d
ex
o
s
k
eleto
n
.
Sec
tio
n
5
p
r
esen
ts
th
e
co
n
clu
s
io
n
.
2.
RE
J
E
C
T
I
O
N
-
B
AS
E
D
E
X
T
RE
M
E
L
E
AR
NING
M
ACH
I
NE
2
.
1
.
E
x
t
re
m
e
lea
rning
m
a
c
hin
e
E
x
t
r
e
m
e
l
e
a
r
n
i
n
g
m
a
c
h
i
n
e
(
ELM
)
i
s
a
n
e
x
c
e
p
t
i
o
n
a
l
i
n
n
o
v
at
i
o
n
o
f
s
i
n
g
l
e
-
l
a
y
e
r
f
e
e
d
-
f
o
r
wa
r
d
n
e
u
r
a
l
n
e
t
w
o
r
k
(
S
L
FN
)
,
w
h
i
c
h
o
v
e
r
c
o
m
e
s
s
h
o
r
t
c
o
m
i
n
g
s
o
f
t
h
e
n
e
u
r
a
l
n
e
t
w
o
r
k
,
e
s
p
e
c
ia
l
l
y
i
n
t
h
e
p
r
o
c
es
s
i
n
g
t
i
m
e
.
I
t
o
m
it
s
a
n
i
t
e
r
a
t
i
v
e
l
e
a
r
n
i
n
g
p
r
o
c
e
s
s
b
y
s
e
t
t
i
n
g
t
h
e
h
i
d
d
e
n
n
o
d
e
we
i
g
h
t
r
a
n
d
o
m
l
y
a
n
d
c
a
l
c
u
l
a
t
i
n
g
t
h
e
o
u
t
p
u
t
w
e
i
g
h
t
a
n
a
l
y
t
i
c
al
l
y
.
T
h
e
r
e
f
o
r
e
,
t
h
e
t
r
a
in
i
n
g
t
i
m
e
i
s
e
x
t
r
e
m
e
l
y
f
a
s
t
w
h
e
n
c
o
m
p
a
r
e
d
w
i
t
h
t
h
e
t
r
a
d
i
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
.
I
n
t
e
r
e
s
ti
n
g
l
y
,
t
h
e
h
i
d
d
e
n
n
o
d
e
p
a
r
t
c
a
n
b
e
c
o
n
s
t
r
u
c
te
d
u
s
i
n
g
ei
t
h
e
r
o
r
i
g
i
n
a
l
n
o
d
e
s
o
r
a
k
e
r
n
e
l
f
u
n
c
t
i
o
n
[
2
6
]
.
T
h
e
o
u
tp
u
t f
u
n
ctio
n
o
f
E
L
M
f
o
r
a
g
e
n
er
alize
d
SLFN
(
f
o
r
o
n
e
o
u
tp
u
t
n
o
d
e
ca
s
e)
is
:
(
)
=
∑
ℎ
(
)
=
1
=
ℎ
(
)
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
13
4
-
1
4
5
136
wh
er
e
β
=
[
1
,
.
.
.
,
]
is
th
e
v
ec
to
r
o
f
th
e
o
u
t
p
u
t
weig
h
t
b
etwe
en
th
e
h
i
d
d
e
n
lay
er
o
f
L
n
o
d
es
a
n
d
th
e
o
u
t
p
u
t
n
o
d
e,
h
(
x
)
=
[
ℎ
1
(
)
,
.
.
.
,
ℎ
(
)
]
is
th
e
o
u
tp
u
t
v
ec
to
r
o
f
t
h
e
h
id
d
e
n
lay
er
.
T
h
e
o
b
jectiv
e
o
f
E
L
M
is
to
m
in
im
ize
th
e
er
r
o
r
an
d
t
h
e
n
o
r
m
o
f
weig
h
t:
:
‖
−
‖
2
‖
‖
(
2
)
wh
er
e
T
is
th
e
tar
g
et.
Fo
r
th
e
c
lass
if
icatio
n
p
u
r
p
o
s
e,
th
e
o
u
tp
u
t o
f
E
L
M
as sh
o
wn
in
(
1
)
co
u
ld
b
e
m
o
d
if
ied
as:
(
)
=
ℎ
(
)
=
ℎ
(
)
(
1
+
)
−
1
(
3
)
wh
er
e
=
[
ℎ
(
1
)
⋮
ℎ
(
)
]
=
[
ℎ
1
(
1
)
⋯
ℎ
(
1
)
⋮
⋮
⋮
ℎ
1
(
)
⋯
ℎ
(
)
]
(
4
)
an
d
C
is
a
u
s
er
-
s
p
ec
if
ie
d
p
a
r
a
m
eter
,
L
is
th
e
n
u
m
b
er
o
f
th
e
h
id
d
e
n
u
n
it,
an
d
N
is
th
e
n
u
m
b
er
o
f
th
e
tr
ain
in
g
d
ata.
T
h
e
p
ar
a
m
eter
s
C
an
d
L
s
h
o
u
ld
b
e
ch
o
s
en
p
r
o
p
e
r
ly
to
ac
h
iev
e
g
o
o
d
g
e
n
er
aliza
tio
n
p
e
r
f
o
r
m
an
ce
.
Ho
we
v
er
,
th
er
e
is
n
o
s
p
ec
if
ic
m
eth
o
d
to
d
eter
m
in
e
b
o
th
p
ar
am
eter
s
ex
ce
p
t
tr
ial
an
d
er
r
o
r
.
Fo
r
tu
n
atel
y
,
Hu
an
g
et
a
l.
[
2
6
]
p
r
o
v
e
d
th
at
th
e
b
ig
n
u
m
b
er
o
f
L
g
iv
es
a
g
o
o
d
p
er
f
o
r
m
a
n
ce
s
o
th
at
th
e
u
s
er
s
ju
s
t
n
ee
d
to
d
ete
r
m
in
e
th
e
p
ar
am
eter
o
f
C
.
Fu
r
th
er
m
o
r
e,
in
(
4
)
,
h
(
x
)
is
a
f
ea
tu
r
e
m
ap
p
in
g
(
h
id
d
e
n
l
ay
er
o
u
t
p
u
t v
ec
to
r
)
.
2
.
2
.
Ra
dia
l
ba
s
is
ELM
I
f
th
e
f
ea
tu
r
e
m
a
p
p
in
g
h
(
x
)
is
u
n
k
n
o
wn
to
th
e
u
s
er
,
a
k
er
n
e
l
f
u
n
ctio
n
ca
n
b
e
u
s
ed
to
r
e
p
r
esen
t
h
(
x
)
.
T
h
en
,
as sh
o
wn
i
n
(
3
)
wo
u
ld
b
e:
1
1
1
1
()
(
,
)
1
(
,
)
TT
E
L
M
N
fx
C
K
x
x
C
K
x
x
−
−
=+
=
+
h(
x
)
H
H
H
T
T
(
5
)
wh
er
e
=
:
,
=
ℎ
(
)
.
(
)
=
(
,
)
(
6
)
an
d
K
is
a
k
er
n
el
f
u
n
ctio
n
.
F
o
llo
win
g
o
u
r
wo
r
k
r
esu
lts
[
2
7
,
2
8
]
,
th
is
p
ap
er
em
p
lo
y
e
d
a
r
ad
ial
b
asis
f
u
n
ctio
n
(
R
B
F)
k
er
n
el
an
d
it
i
s
ca
lled
r
ad
ial
b
asis
f
u
n
ctio
n
ex
tr
em
e
lear
n
in
g
m
ac
h
in
e
(
R
B
F
-
E
L
M)
.
T
h
e
R
B
F
k
er
n
el
i
s
d
ef
in
ed
as
(
,
)
=
(
−
‖
−
‖
2
)
(
7
)
2
.
3
.
R
BF
-
ELM
-
R
T
o
r
ejec
t
t
h
e
m
o
v
em
en
ts
th
at
a
r
e
n
o
t
tr
ain
ed
o
r
in
v
o
lv
ed
in
t
h
e
tr
ain
in
g
s
ec
tio
n
o
r
e
v
en
t
h
e
m
o
v
em
en
ts
th
at
m
ay
b
e
o
u
t
o
f
p
h
y
s
ical
lim
itati
o
n
,
a
r
ejec
tio
n
m
ec
h
a
n
is
m
is
ad
d
ed
to
th
e
R
B
F
-
E
L
M.
T
h
e
r
ejec
tio
n
m
ec
h
an
is
m
is
co
n
d
u
cte
d
b
ase
d
o
n
th
e
co
n
f
i
d
e
n
ce
lev
el
o
f
t
h
e
o
u
tp
u
t
o
f
R
B
F
-
E
L
M.
T
h
e
o
u
tp
u
t
is
ac
ce
p
ted
if
th
e
co
n
f
id
e
n
ce
lev
el
is
h
ig
h
e
r
t
h
an
th
e
p
r
ed
ef
in
e
d
th
r
esh
o
ld
v
alu
e.
T
h
is
v
alu
e
is
d
er
i
v
e
d
f
r
o
m
th
e
ex
p
e
r
im
en
tal
p
r
o
ce
d
u
r
es
th
at
d
if
f
er
en
tiate
t
h
e
r
est
s
tate
an
d
t
h
e
f
in
g
er
m
o
v
em
en
ts
.
Oth
er
wis
e,
th
e
o
u
tp
u
t
will
b
e
r
ejec
ted
if
th
e
co
n
f
id
en
ce
lev
el
is
lo
wer
th
an
th
e
p
r
e
d
ef
in
ed
th
r
esh
o
l
d
v
alu
e.
T
h
e
c
o
n
f
i
d
en
ce
le
v
el
is
ca
lcu
lated
u
s
in
g
en
tr
o
p
y
[
2
9
]
an
d
d
ef
i
n
ed
b
y
;
(
)
=
∑
(
)
∑
(
(
)
)
(
8
)
wh
er
e
N
is
th
e
n
u
m
b
er
o
f
th
e
o
u
tp
u
t
u
n
it,
n
is
th
e
iter
atio
n
o
f
d
ata,
an
d
Oj
is
th
e
jth
o
u
tp
u
t
o
f
th
e
o
u
tp
u
t
lay
er
o
f
E
L
M
.
T
h
e
lo
w
en
tr
o
p
y
in
d
i
ca
tes
th
at
th
e
p
r
o
b
ab
ilit
y
o
f
a
s
p
ec
if
ic
o
u
tp
u
t
ca
n
clea
r
ly
b
e
d
if
f
er
en
tiated
f
r
o
m
o
th
er
s
.
On
th
e
o
th
er
h
an
d
,
h
ig
h
en
tr
o
p
y
im
p
lies
th
at
th
e
p
r
o
b
ab
ilit
ies
o
f
th
e
o
u
tp
u
ts
ar
e
s
im
ilar
o
r
v
er
y
clo
s
e
to
ea
ch
o
th
er
s
o
th
at
th
er
e
is
am
b
ig
u
ity
in
d
eter
m
in
in
g
t
h
e
co
r
r
e
ct
o
u
tp
u
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
I
mp
r
o
ve
d
myo
elec
tr
ic
p
a
tter
n
r
ec
o
g
n
itio
n
o
f fin
g
er mo
ve
men
t u
s
in
g
r
ejec
tio
n
.
.
.
(
K
h
a
ir
u
l A
n
a
m
)
137
3.
T
H
E
P
RO
P
O
SE
D
M
YO
E
L
E
CT
RIC CO
N
T
RO
L
F
O
R
T
H
E
H
AND
E
XO
SK
E
L
E
T
O
N
T
h
is
p
ap
er
p
r
o
p
o
s
es
a
n
o
v
el
M
C
S
f
o
r
th
e
h
an
d
ex
o
s
k
eleto
n
w
ith
m
in
im
u
m
c
h
an
n
el
r
ea
d
in
g
.
T
h
e
MCS
co
n
s
is
ts
o
f
two
m
ain
p
ar
ts
,
th
e
m
y
o
elec
tr
ic
p
atter
n
r
ec
o
g
n
itio
n
(
MPR
)
an
d
n
o
n
-
p
atter
n
r
ec
o
g
n
itio
n
b
lo
c
k
s
(M
-
non
-
PR
)
,
as
d
ep
icted
in
Fig
u
r
e
1
.
Usi
n
g
ju
s
t
two
E
MG
ch
an
n
els,
th
e
MPR
p
r
o
d
u
ce
s
t
h
e
in
ten
d
ed
f
in
g
er
m
o
tio
n
t
h
at
th
e
r
o
b
o
t
s
h
o
u
ld
p
er
f
o
r
m
an
d
th
e
M
-
n
o
n
-
PR
e
s
tim
ates
th
e
s
tr
en
g
th
o
f
t
h
e
i
n
ten
d
ed
m
o
v
em
en
t.
Ho
wev
er
,
in
th
is
p
ap
er
,
all
e
x
p
er
im
en
ts
in
v
o
lv
e
d
o
n
ly
o
n
e
lev
el
o
f
s
tr
en
g
th
,
wh
ich
is
m
ax
im
u
m
v
o
lu
n
tar
y
co
n
tr
ac
tio
n
(
MV
C
)
.
Fig
u
r
e
1
.
My
o
elec
tr
ic
co
n
t
r
o
l
s
y
s
tem
d
ev
elo
p
ed
t
o
co
n
tr
o
l th
e
h
an
d
e
x
o
s
k
eleto
n
3
.
1
.
Da
t
a
a
qu
is
it
io
n
T
h
e
Flex
C
o
m
p
I
n
f
in
iti™
Sy
s
t
em
f
r
o
m
T
h
o
u
g
h
t
T
ec
h
n
o
lo
g
y
was
u
s
ed
to
ac
q
u
ir
e
th
e
s
ig
n
als
f
r
o
m
two
E
MG
s
en
s
o
r
s
,
My
o
Scan
™
T
9
5
0
3
M,
th
at
wer
e
p
u
t
o
n
th
e
s
u
b
ject’
s
f
o
r
ea
r
m
as
s
ee
n
in
Fig
u
r
e
2
.
T
h
e
ac
q
u
ir
e
d
E
MG
s
ig
n
als
wer
e
am
p
lifie
d
with
a
to
tal
g
ain
o
f
1
0
0
0
an
d
s
am
p
led
at
2
0
0
0
Hz.
A
b
an
d
-
p
ass
f
ilter
b
etwe
en
2
0
Hz
an
d
5
0
0
Hz
f
ilter
s
th
e
co
llected
E
MG
s
ig
n
als.
B
esid
es
,
a
n
o
tch
f
ilter
was
em
p
lo
y
ed
to
r
em
o
v
e
th
e
5
0
Hz
lin
e
in
ter
f
er
en
ce
.
B
ef
o
r
e
b
ein
g
ap
p
lied
to
th
e
h
a
n
d
e
x
o
s
k
elet
o
n
,
th
e
MCS
was
test
ed
in
th
e
o
f
f
lin
e
e
xpe
r
im
e
n
t
to
ex
am
in
e
a
n
d
v
er
if
y
t
h
e
ef
f
ic
ac
y
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
tem
.
E
i
g
h
t
s
u
b
jects
wer
e
in
v
o
lv
ed
c
o
n
s
is
tin
g
o
f
2
f
em
ales
an
d
6
m
ales
ag
e
d
2
4
-
6
0
y
ea
r
s
.
All
s
u
b
jects
wer
e
n
o
r
m
ally
li
m
b
ed
with
n
o
m
u
s
cle
d
is
o
r
d
er
.
T
h
e
s
u
b
jects
wer
e
ask
ed
to
p
er
f
o
r
m
a
p
ar
ticu
l
ar
p
o
s
tu
r
e
o
f
f
in
g
er
m
o
v
em
e
n
t
f
o
r
5
s
an
d
th
e
n
tak
e
r
est
f
o
r
5
s
.
E
ac
h
ac
tio
n
was
r
ep
ea
ted
s
ix
tim
es.
Fig
u
r
e
2
.
Placem
en
t
o
f
th
e
ele
ctr
o
d
e
A
(
f
le
x
o
r
p
o
licis
lo
n
g
u
s
)
an
d
elec
tr
o
d
e
B
(
f
lex
o
r
d
ig
itar
iu
m
s
u
p
er
f
icialis
)
3
.
2
.
M
y
o
elec
t
ric
pa
t
er
n
re
co
g
nitio
n
F
ig
u
r
e
3
d
escr
ib
es
th
e
m
y
o
e
lectr
ic
p
atter
n
r
ec
o
g
n
itio
n
(
MPR
)
u
s
in
g
r
ejec
tio
n
-
b
ased
E
L
M.
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
ev
alu
ates
th
e
am
p
litu
d
e
o
f
th
e
E
MG
s
ig
n
al
s
to
d
etec
t
th
e
m
o
ti
o
n
i
n
ten
tio
n
o
f
th
e
u
s
er
.
T
o
d
o
s
o
,
th
e
av
er
ag
e
o
f
r
o
o
t
m
ea
n
s
q
u
ar
e
(
R
MS)
f
r
o
m
two
ch
an
n
els
is
co
m
p
ar
ed
with
th
e
th
r
esh
o
ld
v
alu
e.
I
f
th
e
m
ea
n
is
lo
wer
th
an
th
e
th
r
esh
o
ld
v
alu
e,
th
is
p
r
o
d
u
ce
s
“n
o
m
o
tio
n
”.
Oth
er
wis
e,
th
e
MPR
will
b
e
ac
tiv
ated
an
d
g
en
er
ates
th
e
in
ten
d
ed
m
o
v
e
m
en
t.
I
n
m
o
r
e
d
etail
ex
p
lan
atio
n
f
r
o
m
f
e
atu
r
e
e
x
tr
ac
tio
n
t
o
p
o
s
t
-
p
r
o
ce
s
s
in
g
,
t
h
e
f
o
llo
win
g
will illu
s
tr
ate
it.
As
s
tated
in
T
k
ac
h
et
a
l.
[
3
0
]
th
at
t
h
e
c
o
ef
f
icien
ts
o
f
a
u
to
r
eg
r
ess
iv
e
(
AR
)
m
o
d
el
a
n
d
tim
e
-
d
o
m
ain
(
T
D)
f
ea
tu
r
es
we
r
e
s
tab
le
an
d
r
o
b
u
s
t
to
th
e
elec
tr
o
d
e
lo
ca
tio
n
s
h
if
t
a
n
d
th
e
ch
a
n
g
e
o
f
s
ig
n
al
lev
el,
th
is
p
a
p
er
ex
tr
ac
ted
f
ea
tu
r
es
f
r
o
m
th
e
T
D
f
ea
tu
r
e
a
n
d
co
e
f
f
icien
ts
o
f
t
h
e
au
to
r
eg
r
ess
iv
e
m
o
d
el.
T
h
e
T
D
f
ea
tu
r
es
co
n
s
is
ted
o
f
m
ea
n
a
b
s
o
lu
te
v
al
u
e
(
MA
V)
,
s
lo
p
e
s
ig
n
ch
a
n
g
es
(
SS
C
)
,
wav
ef
o
r
m
le
n
g
th
(
W
L
)
,
a
n
d
ze
r
o
cr
o
s
s
in
g
s
(
Z
C
)
.
I
n
ad
d
itio
n
,
th
e
p
a
r
am
eter
s
o
f
Hjo
r
th
tim
e
d
o
m
ain
p
ar
am
eter
s
wer
e
ad
d
ed
to
im
p
r
o
v
e
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
s
y
s
tem
[
3
1
]
. T
h
e
f
ea
t
u
r
es we
r
e
ex
tr
ac
ted
with
d
u
r
atio
n
o
f
1
0
0
m
s
ev
er
y
1
0
0
m
s
.
Af
ter
f
ea
tu
r
es we
r
e
ex
tr
ac
te
d
f
r
o
m
all
E
MG
c
h
an
n
els,
th
ey
wer
e
th
en
co
n
ca
ten
ated
to
f
o
r
m
a
la
r
g
e
f
ea
tu
r
e
s
et.
As
a
r
es
u
lt,
th
e
d
im
en
s
io
n
o
f
th
e
f
ea
tu
r
e
s
et
is
lar
g
e.
T
h
e
r
ef
o
r
e,
th
e
d
im
e
n
s
io
n
was
r
e
d
u
ce
d
an
d
at
t
h
e
s
am
e
tim
e
p
r
o
jecte
d
to
n
ew
f
ea
tu
r
es
th
at
ar
e
m
o
r
e
s
ep
ar
ab
le.
T
h
is
p
ap
er
u
tili
ze
d
s
p
ec
tr
al
r
eg
r
ess
io
n
d
is
cr
im
in
an
t
an
aly
s
is
(
SR
DA)
,
f
o
llo
win
g
th
e
r
ec
o
m
m
en
d
atio
n
o
f
p
r
ev
io
u
s
wo
r
k
[
28]
.
SR
DA
i
s
an
ex
ten
s
io
n
o
f
li
n
ea
r
d
is
cr
im
in
a
n
t
an
al
y
s
is
(
L
DA
)
th
at
ca
n
im
p
r
o
v
e
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
L
DA
in
ter
m
s
o
f
s
p
ee
d
a
n
d
ab
ili
ty
to
wo
r
k
o
n
a
lar
g
e
d
ataset
[
3
2
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
13
4
-
1
4
5
138
T
o
en
h
an
ce
th
e
class
if
icatio
n
p
er
f
o
r
m
an
ce
,
th
e
p
r
o
p
o
s
ed
MCS
in
tr
o
d
u
ce
s
a
r
ejec
tio
n
m
ec
h
an
is
m
in
t
o
r
ad
ial
b
asis
f
u
n
cti
o
n
e
x
tr
em
e
lear
n
in
g
m
ac
h
in
e
o
r
as
it
is
c
alled
R
B
F
-
ELM
-
R
.
T
o
in
v
esti
g
ate
an
d
v
er
i
f
y
th
e
p
er
f
o
r
m
an
ce
o
f
R
B
F
-
ELM
-
R
,
o
f
f
lin
e
class
if
icatio
n
wa
s
co
n
d
u
cted
.
I
n
th
e
o
f
f
lin
e
class
if
icatio
n
,
th
e
p
er
f
o
r
m
an
ce
o
f
R
B
F
-
ELM
-
R
was
co
m
p
ar
ed
with
th
e
o
r
ig
in
a
l
R
B
F
-
E
L
M
an
d
o
th
er
well
-
k
n
o
wn
class
if
ier
s
s
u
ch
as
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
,
least
-
s
q
u
ar
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
L
S
-
SVM)
,
lin
ea
r
d
i
s
cr
im
in
an
t
an
aly
s
is
(
L
DA)
,
an
d
k
-
n
ea
r
est
n
ei
g
h
b
o
r
(
k
NN)
.
T
h
e
r
e
wer
e
1
0
class
es
in
v
o
lv
ed
in
th
e
e
x
p
er
im
en
t
s
.
T
h
ese
1
0
class
es
co
n
s
is
t
o
f
5
in
d
iv
id
u
al
f
in
g
e
r
m
o
v
em
en
ts
,
4
co
m
b
in
ed
f
in
g
e
r
m
o
v
e
m
en
ts
,
an
d
h
an
d
-
clo
s
e
(
HC
)
m
o
v
em
en
t.
T
h
e
in
d
iv
id
u
al
f
in
g
e
r
m
o
v
em
e
n
ts
in
v
o
lv
e
th
u
m
b
(
T
)
,
in
d
e
x
(
I
)
,
m
id
d
le
(
M)
,
r
i
n
g
(
R
)
,
an
d
litt
le
(
L
)
f
in
g
er
s
.
T
h
e
f
o
u
r
co
m
b
in
ed
m
o
v
em
en
ts
wer
e
t
h
e
p
in
ch
in
g
o
f
th
u
m
b
an
d
i
n
d
e
x
(
T
-
I
)
,
t
h
u
m
b
an
d
m
id
d
le
(
T
-
M)
,
th
u
m
b
an
d
r
i
ng
(T
-
R
)
,
an
d
th
u
m
b
an
d
litt
le
(
T
-
L
)
.
T
h
e
class
if
ier
s
o
m
etim
es
m
is
clas
s
if
ies
th
e
m
o
v
em
en
t
in
to
wr
o
n
g
m
o
v
em
en
ts
.
T
h
e
p
o
s
t
-
p
r
o
ce
s
s
in
g
t
h
at
is
co
n
d
u
cted
af
ter
th
e
class
if
icatio
n
ca
n
o
v
e
r
co
m
e
th
is
is
s
u
e.
A
m
ajo
r
ity
v
o
te
[
3
3
]
is
o
n
e
o
f
th
e
p
o
s
t
-
p
r
o
ce
s
s
in
g
m
et
h
o
d
s
th
at
ca
n
b
e
u
s
ed
to
s
m
o
o
t
h
en
th
e
class
if
icatio
n
r
esu
lts
.
I
t
em
p
lo
y
s
th
e
o
u
tp
u
t
f
r
o
m
th
e
p
r
esen
t
s
tate
an
d
p
r
ev
io
u
s
s
tates
an
d
p
r
o
d
u
ce
s
a
n
ew
class
if
icatio
n
r
esu
lt
b
ase
d
o
n
th
e
class
th
at
ap
p
ea
r
s
m
o
s
t
f
r
eq
u
en
tl
y
.
T
h
is
p
r
o
ce
d
u
r
e
p
r
o
d
u
ce
s
th
e
f
in
g
er
m
o
v
e
m
en
t
class
th
at
r
em
o
v
es
f
ak
e
m
is
class
if
icatio
n
s
.
Fig
u
r
e
3
.
T
h
e
p
r
o
p
o
s
ed
m
y
o
el
ec
tr
ic
p
atter
n
r
ec
o
g
n
itio
n
3
.
3
.
M
y
o
elec
t
ric
no
n
-
pa
t
er
n r
ec
o
g
nitio
n
T
h
e
m
ain
co
m
p
o
n
e
n
t
o
f
MCS
is
th
e
m
y
o
elec
tr
ic
p
atter
n
r
ec
o
g
n
itio
n
(
M
-
PR
)
.
Nev
er
th
eless
,
t
h
e
MCS
also
co
n
s
is
ts
o
f
th
e
m
y
o
elec
t
r
ic
n
o
n
-
p
atter
n
r
ec
o
g
n
itio
n
(
M
-
non
-
PR
)
to
d
etec
t
th
e
s
tr
e
n
g
th
o
f
th
e
in
te
n
d
ed
m
o
v
em
en
t.
Ho
wev
e
r
,
th
e
M
-
n
o
n
-
PR
is
n
o
t
d
is
cu
s
s
ed
in
th
is
p
ap
er
.
All
ex
p
er
im
en
ts
co
n
s
id
er
th
e
MV
C
.
T
h
e
M
-
non
-
PR
s
y
s
tem
h
as
s
im
ilar
s
tep
s
as
th
e
M
-
P
R
ex
ce
p
t
in
th
e
class
if
icatio
n
s
tag
e.
As
s
e
en
in
Fig
u
r
e
1
,
t
h
e
M
-
non
-
PR
esti
m
ates
th
e
s
tr
en
g
th
o
f
th
e
s
ig
n
al
b
y
g
ettin
g
th
e
r
o
o
t
m
ea
n
s
q
u
a
r
e
(
R
MS)
v
al
u
es
o
f
all
th
e
E
MG
ch
an
n
els.
T
h
e
n
,
th
e
a
v
er
ag
e
o
f
R
MS
v
alu
es is
ca
lcu
lated
an
d
s
en
t to
th
e
p
r
o
p
o
r
tio
n
al
co
n
tr
o
ller
.
3
.
4
.
P
r
o
po
rt
io
na
l
co
ntr
o
ller
I
n
th
is
p
r
o
p
o
r
tio
n
al
c
o
n
tr
o
lle
r
,
th
e
c
o
n
tr
o
l
s
ig
n
al
f
o
r
th
e
h
an
d
e
x
o
s
k
eleto
n
is
p
r
o
p
o
r
ti
o
n
al
to
t
h
e
co
n
tr
ac
tio
n
lev
el
o
f
th
e
E
MG
s
ig
n
al.
I
f
th
e
in
ten
d
ed
m
o
tio
n
is
d
etec
ted
,
th
en
th
e
m
o
to
r
co
m
m
an
d
is
s
en
t
to
th
e
r
o
b
o
t.
T
h
e
am
p
litu
d
e
o
f
th
e
r
o
b
o
t
m
o
tio
n
is
p
r
o
p
o
r
tio
n
al
t
o
th
e
c
o
n
tr
ac
tio
n
lev
el
o
f
t
h
e
E
MG
s
ig
n
al.
I
f
th
e
co
n
tr
ac
tio
n
lev
el
ex
ce
ed
s
th
e
MV
C
,
th
en
th
e
MV
C
will b
e
u
s
ed
as th
e
m
o
to
r
c
o
m
m
an
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
I
mp
r
o
ve
d
myo
elec
tr
ic
p
a
tter
n
r
ec
o
g
n
itio
n
o
f fin
g
er mo
ve
men
t u
s
in
g
r
ejec
tio
n
.
.
.
(
K
h
a
ir
u
l A
n
a
m
)
139
3
.
5
.
T
he
ha
nd
ex
o
s
k
elet
o
n
T
h
e
p
r
o
p
o
s
ed
MCS
was
ap
p
lied
to
t
h
e
h
a
n
d
ex
o
s
k
eleto
n
d
e
v
elo
p
ed
in
o
u
r
p
r
e
v
io
u
s
wo
r
k
[
3
4
]
.
T
h
e
h
an
d
ex
o
s
k
eleto
n
is
ab
le
to
f
lex
f
in
g
er
s
ac
tiv
ely
at
th
e
m
etac
ar
p
o
p
h
alan
g
ea
l
(
MCP
)
jo
in
t
an
d
p
ass
iv
ely
at
th
e
p
r
o
x
im
al
i
n
ter
p
h
ala
n
g
ea
l (
PIP
)
an
d
d
is
tal
in
ter
p
h
alan
g
ea
l (
D
I
P)
jo
in
t.
T
h
e
Ar
d
u
in
o
m
icr
o
c
o
n
tr
o
ller
b
o
ar
d
was
u
s
ed
to
d
r
iv
e
th
e
f
iv
e
lin
ea
r
DC
m
o
to
r
s
f
o
r
ac
t
u
atin
g
th
e
h
an
d
e
x
o
s
k
eleto
n
as
d
escr
ib
e
d
in
Fig
u
r
e
1
a
n
d
Fig
u
r
e
4
.
T
h
e
h
a
n
d
e
x
o
s
k
eleto
n
d
id
n
o
t
h
a
v
e
an
y
s
en
s
o
r
s
,
n
ei
th
er
f
o
r
ce
n
o
r
an
g
le
s
en
s
o
r
s
.
T
h
e
h
an
d
ex
o
s
k
eleto
n
m
er
ely
r
elied
o
n
th
e
E
MG
s
en
s
o
r
s
.
Fig
u
r
e
4
.
T
h
e
h
a
n
d
ex
o
s
k
eleto
n
u
s
ed
in
th
e
ex
p
e
r
im
en
t
4.
RE
SU
L
T
A
ND
ANA
L
YS
I
S
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
r
esu
lt
s
o
f
o
f
f
lin
e
an
d
o
n
lin
e
ex
p
er
im
en
ts
.
Of
f
lin
e
ex
p
er
im
en
t
was
co
n
d
u
cte
d
to
in
v
esti
g
ate
t
h
e
p
er
f
o
r
m
an
c
e
o
f
th
e
p
r
o
p
o
s
ed
MCS
,
in
p
a
r
ticu
lar
th
e
m
y
o
elec
tr
ic
p
atter
n
r
ec
o
g
n
itio
n
u
s
in
g
R
B
F
-
ELM
-
R
.
Me
an
wh
ile,
o
n
lin
e
ex
p
e
r
im
en
t
was
aim
ed
at
ap
p
ly
i
n
g
th
e
p
r
o
p
o
s
ed
MCS
to
t
h
e
h
an
d
ex
o
s
k
eleto
n
.
T
o
test
th
e
p
r
o
p
o
s
ed
m
eth
o
d
,
c
o
m
p
a
r
is
o
n
with
o
th
er
well
-
k
n
o
wn
class
if
ier
s
was a
ls
o
ca
r
r
ied
o
u
t.
4
.
1
.
O
f
f
lin
e
e
x
perim
ent
4
.
1
.
1
.
T
he
perf
rm
a
nce
o
f
RB
F
-
ELM
-
R
I
n
th
e
o
f
f
lin
e
ex
p
er
im
en
t,
th
e
p
ap
er
in
v
esti
g
ates
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
r
ejec
tio
n
m
ec
h
an
is
m
in
R
B
F
-
ELM
-
R
an
d
its
im
p
licati
o
n
o
n
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
y
o
elec
tr
ic
p
atter
n
r
ec
o
g
n
itio
n
s
y
s
tem
.
As
s
ee
n
in
T
ab
le
s
1
an
d
2
,
all
ex
p
er
im
e
n
ts
u
s
ed
s
ix
ca
teg
o
r
i
es
f
r
o
m
1
0
class
es.
E
ac
h
o
f
th
em
co
n
s
is
t
s
o
f
tr
ain
ed
an
d
u
n
tr
ain
ed
class
es
r
an
g
in
g
f
r
o
m
5
an
d
5
to
1
0
an
d
0
,
r
esp
ec
t
iv
ely
.
W
h
en
th
e
M
-
PR
was
tr
a
in
ed
u
s
in
g
5
tr
ain
e
d
class
es
f
o
r
test
in
g
d
ata,
th
e
r
e
m
ain
in
g
5
class
es
wer
e
u
s
ed
f
o
r
tr
ain
in
g
d
ata.
T
h
is
will
co
n
tin
u
e
f
r
o
m
th
e
f
ir
s
t
ca
teg
o
r
y
to
th
e
s
ix
th
.
I
n
ad
d
itio
n
,
th
r
esh
o
ld
v
al
u
e
v
a
r
ied
f
r
o
m
0
.
1
t
o
1
.
0
with
in
cr
em
e
n
t 0
.
1
.
Fu
r
th
er
m
o
r
e
,
th
is
p
ap
er
in
v
e
s
tig
ates
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
s
y
s
tem
th
at
u
tili
ze
s
th
e
r
ejec
tio
n
m
ec
h
an
is
m
an
d
co
m
p
ar
es
it
w
ith
th
e
s
y
s
tem
w
ith
o
u
t
t
h
e
r
eje
ctio
n
m
ec
h
a
n
is
m
.
Sin
ce
th
is
s
tu
d
y
c
o
n
d
u
cted
1
0
class
es
in
wh
i
ch
ea
ch
h
as
tr
ai
n
ed
an
d
u
n
tr
ai
n
ed
class
es,
th
r
ee
-
f
o
ld
cr
o
s
s
v
alid
atio
n
was
u
s
ed
.
T
h
is
m
ea
n
s
th
at
wh
en
ab
o
u
t
3
0
%
o
f
th
e
d
ata
is
u
s
ed
f
o
r
test
in
g
,
th
e
r
em
ai
n
in
g
is
f
o
r
tr
ain
in
g
.
Fig
u
r
e
5
an
d
T
ab
le
1
p
r
esen
t
t
h
e
ex
p
er
im
en
tal
r
esu
lts
.
Fig
u
r
e
5
a
n
d
T
a
b
le
1
i
n
d
icat
e
th
at
M
-
PR
with
s
m
all
th
r
esh
o
ld
v
al
u
es
ac
h
iev
ed
h
ig
h
ac
cu
r
ac
y
.
I
n
ad
d
itio
n
,
th
e
s
y
s
tem
th
at
is
tr
ain
ed
u
s
in
g
5
class
es
an
d
th
e
n
test
ed
u
s
in
g
5
u
n
tr
ain
e
d
cla
s
s
es
ac
h
iev
ed
p
o
o
r
ac
cu
r
ac
y
.
An
o
t
h
er
in
ter
esti
n
g
f
ac
t
p
r
o
v
id
ed
in
T
a
b
le
1
is
th
at
th
e
s
y
s
tem
w
i
th
o
u
t
r
ejec
tio
n
m
ec
h
an
is
m
(
R
B
F
-
E
L
M)
an
d
with
r
ejec
tio
n
m
ec
h
an
is
m
(
R
B
F
-
ELM
-
R
)
e
x
p
er
ien
ce
d
p
o
o
r
p
er
f
o
r
m
an
ce
wh
en
th
e
u
n
tr
ain
e
d
class
es
wer
e
im
p
o
s
ed
in
to
th
e
s
y
s
tem
.
T
h
e
ac
cu
r
ac
y
o
f
R
B
F
-
E
L
M
o
n
1
0
tr
ain
ed
class
es
was
8
7
%.
Ho
wev
er
,
th
e
ac
cu
r
ac
y
d
r
o
p
p
ed
t
o
6
5
.
9
%
wh
en
o
n
e
u
n
tr
ain
ed
class
was
in
tr
o
d
u
ce
d
to
th
e
s
y
s
tem
(
as
ca
n
b
e
n
o
ticed
in
th
e
d
ar
k
-
g
r
a
y
b
ac
k
g
r
o
u
n
d
in
T
ab
le
1
.
Fo
r
t
u
n
ately
,
t
h
e
s
y
s
tem
with
r
ejec
tio
n
m
ec
h
an
is
m
(
R
B
F
-
ELM
-
R
)
co
u
l
d
im
p
r
o
v
e
th
e
d
r
o
p
p
ed
ac
c
u
r
ac
y
o
f
R
B
F
-
E
L
M
d
u
e
to
th
e
ex
is
ten
ce
o
f
th
e
u
n
tr
ai
n
ed
class
es
in
th
e
test
in
g
s
tag
e
b
y
ar
o
u
n
d
1
0
%,
wh
e
n
u
s
in
g
t
h
r
esh
o
ld
1
.
0
.
Similar
im
p
r
o
v
em
en
t
also
o
cc
u
r
r
e
d
in
all
ca
s
es,
b
u
t
th
e
en
h
a
n
ce
m
en
t
b
ec
am
e
less
b
y
in
cr
ea
s
in
g
t
h
e
n
u
m
b
er
o
f
u
n
tr
ain
e
d
class
es in
th
e
test
in
g
.
I
n
ad
d
itio
n
to
T
ab
le
1
,
T
ab
le
2
d
escr
ib
e
s
th
e
ac
cu
r
ac
y
wh
en
th
e
r
ejec
tio
n
m
ec
h
an
is
m
is
co
m
b
in
ed
with
th
e
m
ajo
r
ity
v
o
te.
I
t
s
ee
m
s
th
at
th
e
m
ajo
r
ity
v
o
te
d
ec
r
ea
s
es
th
e
ac
cu
r
ac
y
o
f
th
e
s
y
s
te
m
with
th
e
r
ejec
tio
n
m
ec
h
an
is
m
,
esp
ec
ially
f
o
r
lo
w
th
r
esh
o
ld
v
alu
es.
T
h
e
r
ejec
t
io
n
r
ate
o
f
th
e
lo
w
th
r
esh
o
ld
v
alu
e
is
h
ig
h
s
o
th
at
th
e
m
ajo
r
ity
v
o
te
d
o
es
n
o
t
h
a
v
e
en
o
u
g
h
d
ata
to
v
o
te
th
e
co
r
r
ec
t
o
u
tp
u
ts
.
T
h
e
r
ef
o
r
e,
th
e
m
ajo
r
ity
v
o
te
is
n
o
t
ap
p
r
o
p
r
iate
to
b
e
im
p
lem
en
ted
o
n
th
e
r
ejec
tio
n
-
b
ased
class
if
ier
,
esp
ec
ially
f
o
r
th
e
lo
w
th
r
es
h
o
ld
v
al
u
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
13
4
-
1
4
5
140
T
ab
le
1
.
T
h
e
ac
cu
r
ac
y
ac
h
iev
e
d
ac
r
o
s
s
eig
h
t su
b
jects u
s
in
g
s
ix
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
with
o
u
t u
s
in
g
th
e
m
ajo
r
ity
v
o
te
#
c
l
a
sse
s
R
e
j
e
c
t
i
o
n
w
i
t
h
t
h
r
e
s
h
o
l
d
(
a
c
c
u
r
a
c
y
%
)
N
o
R
e
j
e
c
t
i
o
n
Tr
a
i
n
-
ed
Un
-
t
r
a
i
n
e
d
0
.
1
0
.
2
0
.
3
0
.
4
0
.
5
0
.
6
0
.
7
0
.
8
0
.
9
1
.
0
5
5
7
1
.
0
6
0
.
1
4
9
.
3
4
3
.
8
3
8
.
1
34
.1
3
1
.
2
2
8
.
4
2
6
.
5
2
5
.
4
2
3
.
8
6
4
7
4
.
5
7
4
.
6
6
1
.
2
5
6
.
2
5
1
.
6
4
7
.
4
4
3
.
7
4
0
.
1
3
6
.
6
3
4
.
6
3
0
.
8
7
3
NA
8
7
.
7
7
5
.
4
6
8
.
5
6
3
.
7
5
8
.
6
5
5
.
0
5
1
.
2
4
7
.
6
4
4
.
7
3
9
.
5
8
2
NA
9
4
.
1
8
8
.
5
7
9
.
0
7
5
.
0
7
0
.
8
6
7
.
8
6
4
.
6
6
1
.
7
5
8
.
7
5
1
.
1
9
1
NA
9
7
.
8
9
5
.
4
8
9
.
1
8
5
.
9
8
4
.
8
8
3
.
4
8
1
.
2
7
8
.
5
7
5
.
9
6
5
.
9
10
0
NA
NA
9
9
.
6
9
9
.
0
9
8
.
6
9
8
.
4
9
8
.
1
9
7
.
4
9
6
.
2
9
4
.
6
8
7
.
0
T
ab
le
2
.
T
h
e
ac
cu
r
ac
y
ac
h
iev
e
d
ac
r
o
s
s
eig
h
t su
b
jects u
s
in
g
s
ix
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
u
s
in
g
th
e
m
ajo
r
ity
v
o
te
#
C
l
a
ss
e
s
R
e
j
e
c
t
i
o
n
w
i
t
h
t
h
r
e
s
h
o
l
d
(
a
c
c
u
r
a
c
y
%
)
No
R
e
j
e
c
t
i
o
n
Tr
a
i
n
e
d
Un
-
t
r
a
i
n
e
d
0
.1
0
.
2
0
.
3
0
.
4
0
.
5
0
.
6
0
.
7
0
.
8
0
.
9
1
.
0
5
5
4
3
.
1
5
5
.
7
4
6
.
8
4
2
.
0
3
6
.
7
3
3
.
1
3
0
.
4
2
8
.
0
2
6
.
3
2
5
.
2
2
3
.
6
6
4
4
6
.
6
6
4
.
2
5
6
.
7
5
3
.
2
4
9
.
2
4
5
.
5
4
2
.
4
3
9
.
3
3
6
.
2
3
4
.
4
3
0
.
8
7
3
NA
6
2
.
0
6
7
.
2
6
3
.
5
6
0
.
1
5
6
.
0
5
3
.
1
5
0
.
1
4
7
.
2
4
4
.
7
4
0
.
1
8
2
NA
5
0
.
2
7
4
.
0
7
1
.
4
6
9
.
6
6
6
.
9
6
4
.
9
6
2
.
5
6
0
.
6
5
8
.
4
5
2
.
3
9
1
NA
5
9
.
1
7
0
.
7
7
7
.
7
7
8
.
4
7
9
.
3
7
9
.
2
7
8
.
1
7
6
.
5
7
5
.
2
6
8
.
1
10
0
NA
NA
6
3
.
2
8
1
.
6
8
7
.
6
9
0
.
5
9
2
.
1
9
2
.
7
9
3
.
0
9
2
.
9
9
0
.
5
Fig
u
r
e
5
.
Var
iatio
n
o
f
r
ejec
tio
n
th
r
esh
o
ld
o
n
th
e
s
y
s
tem
p
er
f
o
r
m
an
ce
with
o
u
t m
ajo
r
ity
v
o
t
e
Fu
r
th
er
m
o
r
e
,
Fig
u
r
e
5
i
n
d
icat
es
th
at
th
e
s
m
aller
th
e
th
r
esh
o
ld
v
alu
e
is
,
th
e
m
o
r
e
ac
cu
r
ate
th
e
s
y
s
tem
is
.
Ho
wev
er
,
th
e
r
ejec
tio
n
r
ate
o
f
t
h
e
s
y
s
tem
s
h
o
u
l
d
b
e
co
n
s
i
d
er
ed
p
r
o
p
er
ly
t
o
d
eter
m
in
e
th
e
o
p
tim
al
th
r
esh
o
ld
v
alu
e
an
d
av
o
id
wr
o
n
g
r
ejec
ti
o
n
.
T
ab
le
3
ca
n
b
e
u
s
ed
to
f
in
d
th
e
o
p
tim
al
th
r
esh
o
l
d
v
alu
e
f
o
r
ea
ch
ca
s
e.
I
n
t
h
e
ex
p
er
im
en
t
th
at
u
s
ed
5
tr
ain
e
d
class
es,
th
e
p
er
ce
n
tag
e
o
f
th
e
u
n
tr
ain
ed
d
ata
is
7
5
%.
I
t
im
p
lies
th
at
th
e
s
y
s
tem
with
r
ejec
tio
n
m
ec
h
an
is
m
co
u
ld
r
ejec
t
t
h
e
o
u
tp
u
t
b
y
a
r
ejec
t
io
n
r
ate
ar
o
u
n
d
o
r
less
th
an
th
i
s
v
alu
e.
T
h
er
ef
o
r
e,
th
r
esh
o
ld
r
a
n
g
in
g
0
.
2
-
0
.
4
ca
n
b
e
th
e
o
p
tim
al
s
o
lu
tio
n
f
o
r
th
i
s
ca
s
e.
Similar
ly
,
if
th
e
s
am
e
p
r
o
ce
d
u
r
e
is
ap
p
lied
,
th
e
g
r
ay
b
ac
k
g
r
o
u
n
d
in
T
ab
le
3
p
r
esen
ts
th
e
p
o
s
s
ib
le
th
r
esh
o
ld
v
alu
es f
o
r
d
if
f
e
r
en
t c
ases
.
L
o
o
k
in
g
at
T
ab
les
1
an
d
2
,
th
e
d
ata
p
r
esen
ted
p
r
o
v
e
th
at
th
e
m
o
tio
n
r
ejec
tio
n
in
th
e
m
y
o
elec
t
r
ic
co
n
tr
o
l
im
p
r
o
v
es
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
s
y
s
tem
.
Fig
u
r
e
6
s
h
o
ws
a
d
etailed
co
m
p
ar
is
o
n
b
etwe
e
n
th
e
two
s
y
s
tem
s
,
R
B
F
-
E
L
M
an
d
R
B
F
-
ELM
-
R
,
o
n
th
e
1
0
-
class
es
ex
p
er
im
en
t.
T
h
e
f
ig
u
r
e
clea
r
ly
in
d
icate
s
th
a
t
R
B
F
-
ELM
-
R
o
u
tp
er
f
o
r
m
s
R
B
F
-
E
L
M
o
n
all
s
u
b
jects
wit
h
o
u
t
ex
ce
p
tio
n
.
R
B
F
-
E
L
M
attain
ed
ac
cu
r
ac
y
o
f
ar
o
u
n
d
9
0
%
wh
ile
R
B
F
-
ELM
-
R
is
ar
o
u
n
d
9
2
%.
T
h
e
s
u
p
e
r
io
r
ity
o
f
R
B
F
-
ELM
-
R
o
v
er
R
B
F
-
E
L
M
is
m
o
r
e
o
b
v
io
u
s
wh
en
o
n
e
-
way
ANOV
A
tes
t
is
co
n
d
u
cted
.
B
y
s
ettin
g
p
at
0
.
0
5
,
th
e
p
-
v
alu
e
was
0
.
0
3
4
,
wh
ic
h
was
less
t
h
an
0
.
0
5
.
T
h
er
ef
o
r
e,
th
e
en
h
an
ce
m
en
t m
ad
e
b
y
R
B
F
-
ELM
-
R
is
s
tat
is
tical
ly
s
ig
n
if
ican
t.
T
ab
le
3
.
T
h
e
r
ejec
tio
n
r
ate
o
f
t
h
r
esh
o
ld
ex
p
er
im
en
ts
o
n
eig
h
t
s
u
b
jects u
s
in
g
th
r
ee
f
o
l
d
cr
o
s
s
-
v
alid
atio
n
#
Tr
a
i
n
e
d
c
l
a
ss
e
s
U
n
t
r
a
i
n
e
d
c
l
a
ss
e
s (%)
Th
r
e
s
h
o
l
d
(
r
e
j
e
c
t
i
o
n
r
a
t
e
%)
0
.
1
0
.
2
0
.
3
0
.
4
0
.
5
0
.
6
0
.
7
0
.
8
0
.
9
1
.
0
5
75
8
9
.
6
8
0
.
1
6
4
.
7
5
6
.
0
4
7
.
4
3
8
.
8
3
2
.
0
2
4
.
2
1
5
.
6
1
0
.
7
6
60
9
9
.
5
8
8
.
9
7
1
.
9
6
2
.
1
5
2
.
6
4
3
.
1
3
5
.
5
2
6
.
9
1
7
.
4
1
1
.
9
7
45
1
0
0
9
5
.
3
8
0
.
9
7
0
.
1
6
0
.
2
4
9
.
0
4
0
.
5
3
2
.
4
2
3
.
2
1
5
.
8
8
30
1
0
0
9
8
.
1
8
6
.
5
7
3
.
4
6
3
.
2
5
2
.
7
4
3
.
5
3
6
.
0
2
7
.
9
2
0
.
4
9
15
1
0
0
9
9
.
3
9
1
.
3
7
7
.
6
6
6
.
6
5
6
.
4
4
6
.
3
3
8
.
5
3
0
.
7
2
3
.
4
10
0
.
0
1
0
0
1
0
0
9
4
.
2
8
1
.
0
6
9
.
6
5
8
.
4
4
7
.
5
3
8
.
8
3
1
.
6
2
3
.
9
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
I
mp
r
o
ve
d
myo
elec
tr
ic
p
a
tter
n
r
ec
o
g
n
itio
n
o
f fin
g
er mo
ve
men
t u
s
in
g
r
ejec
tio
n
.
.
.
(
K
h
a
ir
u
l A
n
a
m
)
141
Fig
u
r
e
6
.
Acc
u
r
ac
y
ac
h
iev
ed
b
y
R
B
F
-
E
L
M
an
d
R
B
F
-
ELM
-
R
(
th
r
esh
o
ld
=
1
.
0
)
ac
r
o
s
s
eig
h
t s
u
b
jects u
s
in
g
th
r
ee
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
u
s
in
g
m
ajo
r
ity
v
o
te
4
.
1
.
2
.
RB
F
-
E
L
M
-
R
a
nd
o
t
her
cla
s
s
if
iers
T
h
is
ex
p
er
im
en
t
ex
am
in
es
th
e
p
er
f
o
r
m
an
ce
o
f
R
B
F
-
ELM
-
R
in
co
m
p
ar
is
o
n
with
ce
r
tain
w
ell
-
k
n
o
wn
class
if
ier
s
s
u
ch
as
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
,
least
-
s
q
u
ar
e
SVM
(
L
S
-
SVM)
,
lin
ea
r
d
i
s
cr
im
in
an
t
an
aly
s
is
(
L
DA)
,
an
d
k
-
n
ea
r
est
n
eig
h
b
o
r
(
k
NN)
.
T
h
e
ex
p
e
r
im
en
tal
r
esu
lts
ar
e
d
escr
ib
ed
in
Fig
u
r
e
7
an
d
T
ab
le
4
.
Fig
u
r
e
7
s
h
o
ws
th
at
R
B
F
-
ELM
-
R
with
th
e
r
ejec
tio
n
th
r
esh
o
ld
1
.
0
attain
ed
th
e
b
est
ac
cu
r
ac
y
o
f
all
class
if
ier
s
a
cr
o
s
s
d
if
f
er
en
t
class
n
u
m
b
er
s
.
T
h
e
ac
cu
r
ac
y
o
f
all
class
if
ier
s
d
ec
r
ea
s
ed
as
th
e
n
u
m
b
er
o
f
tr
ain
ed
class
es
d
ec
r
ea
s
ed
wh
ile
th
e
n
u
m
b
e
r
o
f
u
n
tr
ain
e
d
class
es
in
cr
ea
s
ed
.
No
class
if
ier
s
co
u
ld
co
p
e
with
th
is
s
itu
atio
n
,
in
p
ar
ticu
lar
in
th
e
5
-
tr
ain
e
d
class
ex
p
er
im
en
t.
Fig
u
r
e
7
.
Acc
u
r
ac
y
o
f
R
B
F
-
ELM
-
R
(
with
r
ejec
tio
n
th
r
esh
o
l
d
1
.
0
)
co
m
p
ar
ed
with
o
th
er
well
-
k
n
o
wn
class
if
ier
s
T
ab
le
4
.
Acc
u
r
ac
y
o
f
th
e
r
ea
l
-
t
im
e
ex
p
er
im
en
t
u
s
in
g
1
0
tr
ain
ed
class
es u
s
in
g
m
ajo
r
ity
v
o
te
#
Tr
a
i
n
e
d
C
l
a
s
ses
A
c
c
u
r
a
c
y
(
%)
S
V
M
LS
-
S
V
M
L
DA
k
N
N
RBF
-
EL
M
RBF
-
EL
M
-
R
5
2
3
.
3
6
2
3
.
4
3
2
3
.
5
3
2
3
.
5
9
2
3
.
6
4
2
5
.
2
0
6
3
0
.
4
2
3
0
.
3
1
3
0
.
7
7
3
0
.
9
0
3
0
.
8
4
3
4
.
4
0
7
3
9
.
2
6
3
9
.
0
6
3
9
.
8
2
3
9
.
9
5
4
0
.
0
7
4
4
.
7
0
8
5
1
.
3
5
5
1
.
5
4
5
1
.
7
1
5
2
.
1
6
5
2
.
2
6
5
8
.
4
0
9
6
6
.
8
5
6
7
.
0
6
6
7
.
2
0
6
7
.
8
4
6
8
.
0
7
7
5
.
2
0
10
8
8
.
2
6
8
8
.
5
2
8
8
.
9
9
9
0
.
0
3
9
0
.
4
6
92
.
9
0
T
h
is
is
th
e
f
ac
t
o
f
th
e
r
ea
l
-
ti
m
e
ap
p
licatio
n
;
th
e
n
u
m
b
er
o
f
m
o
v
em
en
ts
th
at
ar
e
n
o
t
in
v
o
lv
ed
in
th
e
tr
ain
in
g
s
ec
tio
n
is
m
u
ch
lar
g
er
th
an
th
o
s
e
th
at
ar
e
p
ar
tici
p
atin
g
in
th
e
tr
ain
in
g
s
ec
tio
n
.
T
h
e
ad
v
a
n
tag
e
o
f
R
B
F
-
ELM
-
R
is
h
ig
h
lig
h
ted
in
th
is
s
itu
ati
o
n
.
B
y
v
ar
y
in
g
th
e
r
ejec
tio
n
th
r
esh
o
ld
,
t
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
M
-
PR
ca
n
b
e
im
p
r
o
v
ed
.
L
o
o
k
in
g
at
T
ab
le
1
in
t
h
e
ca
s
e
o
f
th
e
5
-
tr
ain
ed
class
es
(
f
ir
s
t
r
o
w)
,
if
th
e
r
ejec
tio
n
th
r
esh
o
ld
is
d
ec
r
ea
s
ed
f
r
o
m
1
.
0
t
o
0
.
2
,
t
h
e
ac
cu
r
ac
y
o
f
R
B
F
-
E
L
M
ca
n
b
e
en
h
a
n
ce
d
f
r
o
m
2
5
.
4
% t
o
6
0
.
1
%.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
13
4
-
1
4
5
142
4
.
2
.
O
nli
ne
ex
perim
ent
T
h
e
r
esu
lt
o
f
th
e
o
f
f
lin
e
ex
p
er
im
en
ts
co
n
clu
d
es
th
at
th
e
s
y
s
tem
with
r
ejec
tio
n
m
ec
h
an
is
m
co
u
ld
en
h
an
ce
th
e
class
if
icatio
n
p
er
f
o
r
m
an
ce
,
esp
ec
ially
wh
en
th
e
u
n
tr
ain
ed
m
o
v
e
m
en
ts
ar
e
in
tr
o
d
u
ce
d
in
th
e
test
in
g
s
tag
e.
I
n
th
is
e
x
p
e
r
im
en
t,
th
e
r
esu
lt
o
f
th
e
o
f
f
lin
e
class
if
icatio
n
was
ap
p
lied
to
th
e
r
ea
l
-
tim
e
ap
p
licatio
n
to
co
n
tr
o
l
t
h
e
h
an
d
ex
o
s
k
eleto
n
.
I
n
th
e
o
n
li
n
e
ex
p
er
im
en
t,
an
a
b
le
-
b
o
d
ie
d
u
s
er
wo
r
e
th
e
h
an
d
ex
o
s
k
eleto
n
o
n
th
e
lef
t
h
an
d
.
O
n
th
e
r
ig
h
t
h
an
d
,
th
er
e
wer
e
two
E
MG
s
e
n
s
o
r
s
p
la
ce
d
o
n
th
e
f
o
r
ea
r
m
,
as
s
h
o
wn
i
n
Fig
u
r
e
8.
T
h
is
is
d
o
n
e
s
in
ce
m
a
n
y
p
e
o
p
le
m
a
y
s
u
f
f
er
f
r
o
m
o
n
e
s
id
e
m
o
to
r
f
u
n
ctio
n
d
ef
icien
cy
o
f
t
h
e
b
o
d
y
(
h
em
ip
ar
esis
)
.
Fig
u
r
e
8
e
x
h
ib
its
th
e
ex
am
p
le
o
f
th
e
r
ea
l
-
tim
e
ex
p
e
r
im
en
ts
o
n
th
e
h
a
n
d
e
x
o
s
k
eleto
n
o
n
th
e
ab
le
-
b
o
d
ie
d
s
u
b
ject.
T
h
e
f
ig
u
r
e
o
n
ly
p
r
o
v
i
d
es
6
m
o
v
e
m
en
ts
.
I
n
th
e
ex
p
e
r
im
en
t,
1
0
m
o
v
e
m
en
ts
wer
e
te
s
ted
as
well.
I
n
th
is
ex
p
er
im
en
t,
th
e
s
u
b
ject
p
er
f
o
r
m
ed
1
0
s
u
b
s
eq
u
en
t
m
o
v
em
en
t
s
f
r
o
m
t
h
e
th
u
m
b
,
in
d
ex
f
in
g
er
u
n
til
th
e
h
an
d
-
cl
o
s
e
m
o
v
em
en
t.
T
h
e
d
u
r
atio
n
o
f
ea
ch
m
o
v
e
m
en
t is 5
s
with
a
r
est
s
tate
in
b
etwe
en
last
in
g
2
.
5
s
.
Fig
u
r
e
8
.
An
ex
am
p
le
o
f
th
e
o
n
lin
e
ex
p
er
im
e
n
t o
f
m
y
o
elec
tr
ic
p
atter
n
r
ec
o
g
n
itio
n
with
m
o
tio
n
r
ejec
tio
n
o
n
th
e
ex
o
s
k
eleto
n
h
an
d
T
h
er
e
ar
e
two
s
ce
n
ar
io
s
in
v
o
l
v
ed
.
T
h
e
f
ir
s
t
s
ce
n
ar
io
is
w
h
en
all
1
0
m
o
v
em
e
n
ts
ar
e
in
clu
d
ed
in
th
e
tr
ain
in
g
a
n
d
test
in
g
s
ess
io
n
s
.
As
f
o
r
th
e
s
ec
o
n
d
s
ce
n
ar
io
,
5
i
n
d
iv
id
u
al
m
o
v
e
m
en
ts
ar
e
i
n
v
o
lv
ed
in
th
e
tr
ain
i
n
g
s
ess
io
n
.
Ho
wev
er
,
in
th
e
test
in
g
s
ess
io
n
,
th
e
tr
ain
ed
s
y
s
tem
is
test
ed
with
1
0
f
i
n
g
er
m
o
v
e
m
en
ts
:
5
in
d
iv
id
u
a
l
f
in
g
er
s
an
d
5
c
o
m
b
in
e
d
f
i
n
g
er
s
.
I
n
a
d
d
itio
n
,
th
e
s
u
b
ject
r
ep
e
ated
th
e
ex
p
er
im
e
n
t
f
o
u
r
tim
e
s
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
s
y
s
tem
is
p
r
esen
ted
in
T
ab
le
5
.
T
h
e
ex
p
er
im
en
t
r
esu
lts
in
T
ab
le
5
s
h
o
w
th
at
th
e
av
er
a
g
e
ac
c
u
r
ac
y
o
f
th
e
r
ea
l
-
tim
e
ap
p
licat
io
n
ac
r
o
s
s
t
h
e
f
o
u
r
tr
ials
is
8
9
.
2
2
%
an
d
8
9
.
7
2
%
u
s
in
g
R
B
F
-
E
L
M
an
d
R
B
F
-
ELM
-
R
,
r
esp
ec
tiv
ely
.
I
n
o
n
lin
e
ex
p
er
im
en
t,
th
e
ex
p
e
r
im
en
t
o
n
5
tr
ain
ed
c
lass
es
an
d
u
n
tr
ain
e
d
class
es
was
also
co
n
d
u
cted
.
T
h
e
r
esu
lts
ar
e
p
r
esen
ted
in
T
ab
le
5
(
o
n
th
e
r
ig
h
t
-
h
an
d
s
id
e)
.
T
ab
le
5
s
h
o
ws
th
at
t
h
e
r
eje
ctio
n
m
ec
h
a
n
is
m
co
u
ld
m
i
n
im
ize
th
e
p
e
r
f
o
r
m
an
ce
d
eg
r
ad
atio
n
o
f
th
e
r
ea
l
-
tim
e
m
y
o
elec
tr
ic
p
atter
n
r
ec
o
g
n
iti
o
n
(
M
-
PR
)
.
T
h
e
M
-
PR
u
s
in
g
R
B
F
-
ELM
-
R
co
u
ld
ac
h
iev
e
th
e
ac
cu
r
ac
y
o
f
ab
o
u
t
8
0
% wh
ile
th
e
o
n
e
u
s
in
g
R
B
F
-
E
L
M
attain
ed
th
e
ac
c
u
r
ac
y
o
f
ab
o
u
t
5
9
%
.
T
ab
le
5
.
Acc
u
r
ac
y
o
f
th
e
r
ea
l
-
t
im
e
ex
p
er
im
en
t
Tr
i
a
l
s
1
0
Tr
a
i
n
e
d
c
l
a
sse
s
5
Tr
a
i
n
e
d
c
l
a
ss
e
s
a
n
d
5
u
n
t
r
a
i
n
e
d
c
l
a
s
ses
RBF
-
EL
M
RBF
-
EL
M
-
R
RBF
-
EL
M
RBF
-
EL
M
-
R
1
8
9
.
0
6
9
0
.
4
6
5
9
.
3
8
8
2
.
0
1
2
8
9
.
4
5
8
9
.
7
5
6
0
.
5
5
7
9
.
0
7
3
9
0
.
2
3
9
0
.
0
6
6
0
.
2
9
8
1
.
4
5
4
8
8
.
1
5
8
8
.
6
4
5
8
.
33
7
8
.
3
5
M
e
a
n
8
9
.
2
2
8
9
.
7
3
5
9
.
6
4
8
0
.
2
2
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
I
mp
r
o
ve
d
myo
elec
tr
ic
p
a
tter
n
r
ec
o
g
n
itio
n
o
f fin
g
er mo
ve
men
t u
s
in
g
r
ejec
tio
n
.
.
.
(
K
h
a
ir
u
l A
n
a
m
)
143
T
h
e
tim
in
g
d
ia
g
r
am
o
f
th
e
o
n
l
in
e
ex
p
er
im
e
n
t
o
n
5
tr
ain
ed
class
es
an
d
u
n
tr
ain
ed
class
es
is
p
r
esen
ted
in
Fig
u
r
e
9
.
T
h
e
f
ig
u
r
e
p
r
esen
ts
th
e
o
u
tp
u
ts
o
f
m
y
o
elec
tr
ic
p
atter
n
r
ec
o
g
n
itio
n
u
s
in
g
th
r
ee
d
if
f
er
en
t
s
ce
n
ar
io
s
.
T
h
e
f
ir
s
t
s
ce
n
ar
io
is
th
e
o
u
tp
u
t
o
f
R
B
F
-
E
L
M,
i.e
.
th
e
s
y
s
tem
th
at
d
o
es
n
o
t
u
s
e
th
e
r
ejec
tio
n
m
ec
h
an
is
m
.
I
t
is
s
h
o
wn
in
th
e
f
ig
u
r
e
b
y
th
e
letter
A.
T
h
e
s
ec
o
n
d
s
ce
n
a
r
io
is
t
h
e
o
u
tp
u
t
o
f
R
B
F
-
ELM
-
R
wit
h
r
ejec
tio
n
th
r
esh
o
ld
0
.
3
,
wh
ich
is
s
h
o
wn
b
y
th
e
letter
B
in
t
h
e
f
ig
u
r
e.
T
h
e
last
s
ce
n
ar
io
,
wh
ich
is
s
h
o
wn
b
y
th
e
l
etter
C
,
is
th
e
o
u
tp
u
t
o
f
R
B
F
-
ELM
-
R
with
r
ejec
tio
n
th
r
esh
o
ld
0
.
3
,
b
u
t
it
em
p
lo
y
ed
d
if
f
er
e
n
t
co
n
ce
p
ts
o
f
“n
o
m
o
tio
n
”
f
r
o
m
th
e
p
r
ev
io
u
s
R
B
F
-
ELM
-
R.
T
h
e
r
e
jectio
n
m
o
tio
n
in
R
B
F
-
ELM
-
R
co
u
ld
b
e
a
p
p
lied
in
two
wa
y
s
d
ep
en
d
in
g
o
n
th
e
im
p
lem
en
tatio
n
o
f
“
n
o
m
o
tio
n
.
”
First,
“n
o
m
o
tio
n
”
m
ea
n
s
th
at
th
e
o
u
tp
u
t
o
f
th
e
s
y
s
tem
was
a
r
est
s
tate.
T
h
er
ef
o
r
e,
wh
en
ev
er
th
e
s
y
s
tem
r
ejec
ts
a
m
o
tio
n
,
th
e
s
y
s
te
m
f
o
r
ce
d
th
e
o
u
t
p
u
t
to
th
e
r
est
s
tate
b
y
n
eg
lectin
g
th
e
cu
r
r
e
n
t
m
o
v
em
en
t
.
As
a
r
e
s
u
lt,
th
e
o
u
t
p
u
t
ch
a
n
g
ed
f
r
o
m
o
n
e
s
tate
to
a
r
est
s
tate
b
ac
k
a
n
d
f
o
r
th
f
r
eq
u
en
tly
,
as
s
h
o
wn
in
Fig
u
r
e
9
,
p
ar
t
B
.
Un
f
o
r
tu
n
ately
,
th
is
ac
tio
n
will
b
e
in
c
o
n
v
e
n
ien
t
f
o
r
t
h
e
u
s
er
s
.
T
h
e
s
ec
o
n
d
im
p
lem
en
tatio
n
o
f
“
n
o
m
o
tio
n
”
was
th
at,
in
s
tea
d
o
f
th
e
r
est
s
tate,
th
e
o
u
tp
u
t
was
th
e
last
m
o
v
em
en
t
p
r
o
d
u
ce
d
b
ef
o
r
e
th
e
im
p
lem
en
tatio
n
o
f
t
h
e
r
ejec
tio
n
m
ec
h
a
n
is
m
.
T
h
is
s
ce
n
ar
io
p
r
o
d
u
ce
d
s
m
o
o
th
er
o
u
tp
u
t
th
an
th
e
f
ir
s
t
s
ce
n
ar
io
,
as
s
h
o
w
n
in
Fig
u
r
e
9
,
p
ar
t
C
.
Fo
r
th
is
r
ea
s
o
n
,
th
e
s
ec
o
n
d
s
ce
n
ar
io
was
a
g
o
o
d
ch
o
ice
f
o
r
co
n
tr
o
llin
g
th
e
h
an
d
e
x
o
s
k
eleto
n
.
Ho
wev
er
,
th
er
e
is
a
d
r
awb
ac
k
wh
en
u
s
in
g
th
e
p
r
ev
i
o
u
s
s
tate
as
“n
o
m
o
tio
n
.
”
W
h
en
th
e
p
r
ev
io
u
s
s
tate
is
th
e
wr
o
n
g
m
o
v
em
en
t,
th
en
t
h
e
“n
o
m
o
ti
o
n
”
p
r
o
d
u
ce
s
th
e
wr
o
n
g
m
o
v
em
en
t
as
well.
Fo
r
ex
am
p
le,
s
ee
Fig
u
r
e
9
,
p
a
r
t
C
,
th
e
th
u
mb
-
in
d
ex
f
in
g
e
r
m
o
v
e
m
en
t
(
T
I
)
is
a
m
o
tio
n
th
at
was
n
o
t
in
clu
d
ed
in
t
h
e
tr
ain
in
g
s
tag
e.
W
h
en
it
is
im
p
o
s
ed
o
n
th
e
s
y
s
tem
,
th
e
s
y
s
tem
o
u
tp
u
ts
th
e
L
m
o
v
e
m
en
t.
I
n
f
a
ct,
th
e
co
r
r
ec
t
o
u
tp
u
t
s
h
o
u
ld
b
e
n
o
m
o
v
em
e
n
t.
Fig
u
r
e
9
.
R
ea
l
-
tim
e
ex
p
e
r
i
m
en
t r
esu
lts
o
v
er
tim
e
u
s
in
g
th
r
esh
o
ld
0
.
3
u
s
in
g
5
tr
ain
e
d
class
es
an
d
5
u
n
tr
ain
e
d
class
es
4
.
3
.
L
im
it
a
t
io
n o
f
t
he
w
o
rk
T
h
e
wo
r
k
in
th
is
p
ap
er
h
as
s
o
m
e
lim
itatio
n
s
.
First,
th
e
ex
p
er
im
en
ts
co
n
d
u
cted
in
th
is
p
ap
e
r
wo
r
k
ed
o
n
th
e
m
o
v
em
e
n
t
at
MV
C
.
Actu
ally
,
th
e
n
o
n
-
p
atter
n
r
ec
o
g
n
it
io
n
m
eth
o
d
h
as
b
ee
n
d
e
v
elo
p
ed
to
m
ea
s
u
r
e
th
e
co
n
tr
ac
tio
n
lev
el
o
f
th
e
E
MG
s
ig
n
al.
Ho
wev
er
,
it
was
n
o
t
d
i
s
cu
s
s
ed
in
d
etail.
I
n
f
u
tu
r
e
ex
p
er
im
en
ts
,
d
if
f
e
r
en
t
lev
els
o
f
co
n
tr
ac
tio
n
o
f
th
e
m
o
v
em
en
ts
s
h
o
u
ld
b
e
co
n
s
id
er
e
d
to
test
th
e
r
eliab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
in
th
e
r
ea
l
ap
p
licatio
n
.
T
h
e
s
ec
o
n
d
lim
itatio
n
o
f
th
is
wo
r
k
is
th
e
f
ac
t
th
at
th
e
ex
o
s
k
eleto
n
u
s
e
d
in
th
e
ex
p
e
r
im
en
t
s
im
p
ly
r
elies
o
n
th
e
E
MG
s
en
s
o
r
with
o
u
t
an
y
p
h
y
s
ical
s
en
s
o
r
s
.
T
h
is
s
itu
atio
n
is
n
o
t g
o
o
d
f
o
r
th
e
u
s
er
’
s
s
af
ety
b
ec
au
s
e
th
e
E
MG
s
ig
n
al
i
s
d
y
n
am
ic
an
d
ea
s
y
to
ch
an
g
e
d
u
e
to
s
m
all
m
o
v
em
en
ts
.
T
h
er
ef
o
r
e,
p
h
y
s
ical
s
en
s
o
r
s
Evaluation Warning : The document was created with Spire.PDF for Python.