T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n Co
m
pu
t
i
ng
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
2
3
,
No
.
2
,
A
p
r
il 2
0
2
5
,
p
p
.
4
8
4
~
4
9
4
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
:
1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
2
3
i2
.
2
5
8
7
6
484
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//telko
mn
ika
.
u
a
d
.
a
c.
i
d
I
m
po
sing
neu
ra
l
netw
o
rk
s
a
nd P
S
O
o
pti
m
i
z
a
tion in
t
he
quest
for o
pti
m
a
l an
k
le
-
foo
t
o
rthos
is dy
n
a
m
ic
m
o
del
ling
Anni
s
a
J
a
m
a
li
1
,
Aida
Su
r
ia
n
a
Abdu
l R
a
za
k
1
,
Sh
a
hro
l M
o
ha
m
a
dd
a
n
2
1
D
e
p
a
r
t
me
n
t
o
f
M
e
c
h
a
n
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
i
M
a
l
a
y
si
a
S
a
r
a
w
a
k
,
S
a
r
a
w
a
k
,
M
a
l
a
y
si
a
2
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
S
h
i
b
a
u
r
a
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
To
k
y
o
,
Jap
a
n
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
2
1
,
2023
R
ev
i
s
ed
No
v
2
8
,
2
0
2
4
A
cc
ep
ted
Dec
2
6
,
2
0
2
4
In
d
iv
id
u
a
ls
w
it
h
a
b
n
o
rm
a
l
wa
lk
i
n
g
p
a
tt
e
rn
s
d
u
e
t
o
v
a
rio
u
s
c
o
n
d
i
ti
o
n
s
f
a
c
e
sig
n
if
ica
n
t
c
h
a
ll
e
n
g
e
s
in
d
a
il
y
a
c
ti
v
it
ies
,
e
sp
e
c
iall
y
w
a
l
k
in
g
.
A
n
k
le
-
f
o
o
t
o
rth
o
sis
(A
F
O)
d
e
v
ice
s
a
re
c
ru
c
ial
in
p
r
o
v
id
i
n
g
e
ss
e
n
ti
a
l
su
p
p
o
rt
to
t
h
e
ir
l
o
w
e
r
li
m
b
s.
Ac
c
u
ra
tel
y
m
o
d
e
li
n
g
th
e
d
y
n
a
m
ic
b
e
h
a
v
io
r
o
f
A
F
O
sy
ste
m
s,
p
a
rti
c
u
larly
in
p
re
d
ictin
g
g
ro
u
n
d
r
e
a
c
ti
o
n
f
o
rc
e
s,
is
a
c
o
m
p
lex
y
e
t
v
it
a
l
tas
k
to
e
n
su
re
th
e
ir
e
f
fe
c
ti
v
e
n
e
s
s.
T
h
is
r
e
se
a
rc
h
d
e
v
e
lo
p
s
d
y
n
a
m
i
c
m
o
d
e
ls
f
o
r
A
F
O
s
y
ste
m
s
u
sin
g
a
d
v
a
n
c
e
d
m
o
d
e
li
n
g
tec
h
n
iq
u
e
s,
e
m
p
lo
y
in
g
b
o
th
p
a
r
a
m
e
tri
c
a
n
d
non
-
p
a
ra
m
e
tri
c
a
p
p
ro
a
c
h
e
s.
P
a
r
a
m
e
tri
c
m
e
th
o
d
s,
su
c
h
a
s
p
a
rti
c
le
s
w
a
r
m
o
p
ti
m
iza
ti
o
n
(
P
S
O),
a
n
d
n
o
n
-
p
a
ra
m
e
tri
c
m
e
th
o
d
s,
li
k
e
m
u
lt
i
-
la
y
e
r
p
e
rc
e
p
tro
n
(M
L
P
)
n
e
u
ra
l
n
e
tw
o
rk
s,
a
re
u
ti
li
z
e
d
th
ro
u
g
h
sy
ste
m
id
e
n
ti
f
ica
ti
o
n
m
e
th
o
d
s
.
A
c
c
o
rd
in
g
to
th
e
f
in
d
i
n
g
s,
th
e
M
L
P
n
e
u
ra
l
n
e
tw
o
rk
c
o
n
ti
n
u
o
u
sly
g
e
n
e
ra
tes
o
b
jec
ti
v
e
re
su
lt
s
a
n
d
p
e
rf
o
rm
s
e
x
c
e
p
ti
o
n
a
ll
y
w
e
ll
in
c
o
rre
c
tl
y
d
e
tec
ti
n
g
th
e
A
F
O
s
y
ste
m
,
a
tt
a
in
in
g
a
n
o
ti
c
e
a
b
ly
lo
w
e
r
m
e
a
n
sq
u
a
re
d
p
re
d
icti
o
n
e
rro
r
o
f
0
.
0
0
0
0
1
1
.
T
h
is
re
se
a
rc
h
h
ig
h
li
g
h
ts
th
e
p
o
ten
ti
a
l
o
f
a
d
v
a
n
c
e
d
m
o
d
e
li
n
g
tec
h
n
iq
u
e
s,
p
a
rti
c
u
larly
M
L
P
n
e
u
ra
l
n
e
tw
o
rk
s,
in
e
n
h
a
n
c
in
g
A
F
O
s
y
ste
m
m
o
d
e
li
n
g
a
c
c
u
ra
c
y
.
A
lt
h
o
u
g
h
p
a
r
a
m
e
tri
c
tec
h
n
iq
u
e
s
li
k
e
P
S
O
a
re
u
se
f
u
l,
th
e
M
L
P
a
p
p
ro
a
c
h
p
e
rf
o
rm
s
b
e
tt
e
r,
o
f
f
e
rin
g
in
sig
h
tf
u
l
i
n
f
o
r
m
a
ti
o
n
a
b
o
u
t
m
o
d
e
ll
in
g
A
F
O
s
y
ste
m
s
a
n
d
in
d
i
c
a
ti
n
g
th
a
t
n
o
n
-
p
a
ra
m
e
tri
c
tec
h
n
iq
u
e
s
li
k
e
M
L
P
n
e
u
ra
l
n
e
tw
o
rk
s h
a
v
e
p
o
ten
t
ial
to
f
u
rth
e
r
A
F
O cre
a
ti
o
n
a
n
d
c
o
n
tro
l
.
K
ey
w
o
r
d
s
:
An
k
le
-
f
o
o
t o
r
th
o
s
is
Mo
d
elin
g
Neu
r
al
n
et
w
o
r
k
P
ar
ticle
s
w
ar
m
o
p
ti
m
izatio
n
S
y
s
te
m
id
e
n
ti
f
icatio
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
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
An
n
is
a
J
a
m
ali
Dep
ar
t
m
en
t o
f
Me
ch
a
n
ical
E
n
g
in
ee
r
i
n
g
,
Facu
lt
y
o
f
E
n
g
i
n
ee
r
in
g
,
U
n
i
v
er
s
iti Ma
la
y
s
ia
Sar
a
w
a
k
Sar
a
w
a
k
,
Ma
la
y
s
ia
E
m
ail: j
an
n
is
a
@
u
n
i
m
a
s
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
m
ed
ical
co
n
d
itio
n
k
n
o
wn
as
a
s
tr
o
k
e
h
ap
p
en
s
w
h
en
th
e
b
r
ain
’
s
b
lo
o
d
s
u
p
p
l
y
i
s
i
n
ter
r
u
p
ted
,
h
ar
m
i
n
g
b
r
ain
n
er
v
e
s
an
d
i
n
te
r
f
er
in
g
w
it
h
i
n
f
o
r
m
atio
n
tr
an
s
m
is
s
io
n
b
et
w
ee
n
t
h
e
b
r
ain
a
n
d
th
e
li
m
b
s
[
1
]
.
On
e
co
n
s
eq
u
e
n
ce
o
f
s
tr
o
k
e
ca
n
b
e
f
o
o
t
d
r
o
p
,
a
n
eu
r
o
m
u
s
c
u
lar
d
is
o
r
d
er
[
2
]
.
W
h
en
w
al
k
i
n
g
i
n
th
e
s
w
i
n
g
p
h
ase,
p
atien
ts
w
i
th
f
o
o
t d
r
o
p
s
d
r
ag
t
h
eir
to
es b
ec
au
s
e
t
h
e
y
h
a
v
e
d
if
f
icu
l
t
y
d
o
r
s
i
f
lex
in
g
t
h
eir
f
ee
t
[
3
]
-
[
6
]
.
As
s
ee
n
in
Fi
g
u
r
e
1
,
th
ese
p
atien
ts
co
n
s
eq
u
en
tl
y
e
x
h
ib
it
v
ar
ia
t
io
n
s
f
r
o
m
t
h
e
t
y
p
ical
g
ait
p
atte
r
n
.
An
k
le
-
f
o
o
t
o
r
th
o
s
es
(
AFOs
)
ar
e
f
r
eq
u
en
tl
y
u
tili
s
ed
f
o
r
r
eh
ab
ilit
a
tio
n
tr
ain
i
n
g
in
th
is
s
it
u
atio
n
s
i
n
ce
th
e
y
o
f
f
er
s
tab
ili
t
y
an
d
p
r
eser
v
e
r
an
g
e
o
f
m
o
tio
n
.
A
FOs
h
a
v
e
b
ee
n
s
h
o
w
n
to
i
n
cr
ea
s
e
g
ait
s
p
ee
d
w
h
en
co
m
p
ar
ed
to
n
o
n
-
A
FO
s
ce
n
ar
io
s
[
7
]
-
[
9
]
.
T
h
is
i
m
p
r
o
v
e
m
en
t
in
g
a
it
v
elo
cit
y
is
i
m
p
o
r
tan
t
b
ec
au
s
e
it
d
ir
ec
tl
y
a
f
f
ec
t
s
th
e
q
u
a
lit
y
o
f
li
f
e
f
o
r
s
tr
o
k
e
s
u
r
v
i
v
o
r
s
,
allo
w
i
n
g
th
e
m
to
m
o
v
e
m
o
r
e
ef
f
icie
n
tl
y
an
d
r
ed
u
ce
th
e
r
is
k
.
T
o
en
s
u
r
e
th
at
p
atien
t
s
r
ec
eiv
e
th
e
m
o
s
t
ad
v
a
n
ta
g
es,
cli
n
icia
n
s
m
u
s
t
th
u
s
u
n
d
er
s
tan
d
t
h
e
m
e
ch
an
ica
l
p
r
o
p
er
ties
o
f
AFOs
,
s
u
ch
a
s
r
ig
id
it
y
a
n
d
th
eir
e
f
f
ec
t
s
o
n
g
ai
t
[
1
0
]
-
[
1
3
]
.
I
t is o
f
t
h
e
u
t
m
o
s
t i
m
p
o
r
tan
ce
,
in
cli
n
ical
p
r
ac
tice,
to
m
o
d
if
y
th
e
to
r
q
u
e
o
f
A
FO
in
ac
co
r
d
an
ce
w
it
h
th
e
u
n
iq
u
e
b
o
d
y
f
u
n
ctio
n
an
d
g
ai
t
ca
p
ab
ilit
ies
o
f
ea
ch
p
atien
t
[
1
4
]
,
[
1
5
]
.
Nev
er
th
eless
,
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
mp
o
s
in
g
n
e
u
r
a
l n
etw
o
r
ks a
n
d
P
S
O
o
p
timiz
a
tio
n
in
t
h
e
q
u
est
fo
r
o
p
tima
l a
n
kle
-
f
o
o
t
…
(
A
n
n
is
a
Ja
ma
li
)
485
co
n
v
e
n
tio
n
al
t
h
er
ap
eu
tic
ap
p
r
o
ac
h
es
th
at
r
el
y
o
n
m
an
u
al
s
u
p
p
o
r
t
ar
e
lab
o
r
io
u
s
f
o
r
p
r
ac
titi
o
n
er
s
an
d
co
u
ld
n
o
t
o
f
f
er
co
n
ti
n
u
o
u
s
ass
i
s
ta
n
ce
f
o
r
p
r
o
lo
n
g
ed
d
u
r
atio
n
s
[
1
6
]
,
[
1
7
]
.
Fig
u
r
e
1
.
W
alk
in
g
g
ai
t p
h
ase
;
i
n
itial
co
n
tact
(
I
C
)
,
f
o
o
t f
lat
(
F
F),
h
ee
l
-
o
f
f
(
HO)
,
an
d
to
e
-
o
f
f
(
T
O)
[
1
2
]
Mo
d
elin
g
A
FO
i
s
ch
a
lle
n
g
i
n
g
,
p
ar
ticu
lar
l
y
w
h
e
n
co
n
s
id
er
in
g
g
r
o
u
n
d
r
ea
ctio
n
f
o
r
ce
s
in
co
m
p
le
x
s
y
s
te
m
s
w
ith
m
u
l
tip
le
p
o
in
ts
o
f
g
r
o
u
n
d
co
n
tact
[
1
8
]
.
A
FO
m
o
d
els
h
a
v
e
b
ee
n
cr
ea
ted
u
s
in
g
a
v
ar
iet
y
o
f
tech
n
iq
u
es,
s
u
ch
as
m
u
s
cu
lo
s
k
eleta
l
s
i
m
u
latio
n
s
,
d
ir
ec
t
m
u
lt
i
p
le
s
h
o
o
tin
g
tec
h
n
iq
u
es,
Mo
n
t
e
C
ar
lo
s
im
u
lat
io
n
s
,
co
m
p
u
tatio
n
al
m
o
d
elli
n
g
a
n
d
f
u
n
ct
io
n
al
elec
tr
ical
s
ti
m
u
latio
n
s
[
1
9
]
,
[
2
0
]
.
I
n
r
ec
en
t
y
ea
r
s
,
s
y
s
te
m
id
en
ti
f
ica
tio
n
h
as
g
ai
n
ed
atten
tio
n
f
o
r
ac
cu
r
atel
y
m
o
d
elin
g
d
y
n
a
m
ic
s
y
s
te
m
s
.
P
ar
a
m
etr
ic
id
e
n
ti
f
icatio
n
i
n
v
o
l
v
es t
w
o
p
h
ase
s
:
q
u
a
litati
v
e
o
p
er
atio
n
,
w
h
ich
es
tab
lis
h
e
s
th
e
s
y
s
te
m
’
s
s
tr
u
ct
u
r
e,
an
d
id
en
tif
icatio
n
,
w
h
ic
h
d
eter
m
i
n
es
n
u
m
er
ical
v
alu
e
s
f
o
r
s
tr
u
ct
u
r
al
p
ar
am
ete
r
s
.
T
r
ad
itio
n
al
m
et
h
o
d
s
lik
e
th
e
least
s
q
u
ar
es
m
eth
o
d
an
d
Z
a
ts
io
r
s
k
y
r
e
g
r
ess
io
n
eq
u
atio
n
s
h
av
e
b
ee
n
u
s
ed
f
o
r
p
ar
am
etr
ic
id
en
ti
f
icatio
n
[
2
1
]
.
T
h
e
g
o
al
is
to
ap
p
ly
th
i
s
co
n
tr
o
l m
e
th
o
d
’
s
in
v
er
s
e
d
y
n
a
m
ic
m
o
d
el
to
h
u
m
an
g
ait
s
y
s
te
m
s
.
W
h
ile
g
e
n
etic
al
g
o
r
ith
m
s
ar
e
w
ell
-
k
n
o
w
n
as
a
s
to
ch
a
s
ti
ca
ll
y
o
p
ti
m
al
ap
p
r
o
ac
h
,
p
ar
ticle
s
w
ar
m
o
p
tim
izatio
n
(
P
SO)
,
an
o
th
er
g
lo
b
al
o
p
tim
izatio
n
a
lg
o
r
it
h
m
,
h
as
g
ai
n
ed
p
r
o
m
i
n
en
ce
[
2
2
]
.
P
SO
r
elies
o
n
s
o
cial
in
f
o
r
m
atio
n
e
x
c
h
an
g
e
a
m
o
n
g
m
e
m
b
er
s
o
f
a
g
r
o
u
p
to
f
in
d
s
p
ec
if
ic
p
ar
a
m
eter
s
et
s
th
a
t
o
p
ti
m
ize
a
n
o
b
j
ec
tiv
e
f
u
n
ctio
n
.
I
t is s
u
itab
le
f
o
r
n
o
n
l
in
ea
r
d
esig
n
s
p
ac
es
w
i
th
d
is
co
n
ti
n
u
i
ties
a
n
d
d
iv
er
s
e
co
n
s
tr
ai
n
ts
.
No
n
-
p
ar
a
m
e
tr
ic
m
o
d
el
s
o
f
t
en
in
co
r
p
o
r
ate
co
m
p
o
n
en
t
s
o
f
s
o
f
t
co
m
p
u
ti
n
g
m
eth
o
d
s
,
s
u
c
h
as
n
eu
r
a
l
n
et
w
o
r
k
s
(
NNs)
a
n
d
f
u
zz
y
lo
g
ic.
Dee
p
n
e
u
r
al
n
et
w
o
r
k
s
c
o
n
s
is
t
o
f
la
y
er
s
o
f
ar
ti
f
icial
n
eu
r
o
n
s
t
h
at
m
i
m
ic
b
io
lo
g
ical
n
eu
r
o
n
s
’
f
u
n
ctio
n
i
n
g
,
m
a
k
i
n
g
th
e
m
e
f
f
ec
t
iv
e
f
o
r
v
ar
io
u
s
m
ac
h
i
n
e
lear
n
i
n
g
ta
s
k
s
.
Dec
is
io
n
tr
ee
s
,
u
tili
ze
d
in
r
an
d
o
m
f
o
r
ests
,
c
o
n
tr
ib
u
te
to
th
e
f
i
n
al
clas
s
i
f
i
ca
tio
n
b
y
ag
g
r
e
g
ati
n
g
j
u
d
g
m
en
ts
b
ased
o
n
in
p
u
t
v
ar
iab
les.
R
e
s
ea
r
ch
in
d
icate
s
t
h
at
d
ee
p
n
e
u
r
al
n
et
w
o
r
k
m
o
d
el
s
p
er
f
o
r
m
w
ell,
p
ar
ticu
lar
l
y
i
n
p
r
ed
ictin
g
t
h
e
n
ee
d
f
o
r
AFOs
[
2
3
]
.
T
h
e
aim
o
f
th
i
s
r
esear
ch
is
to
e
x
p
lo
r
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
d
y
n
a
m
ic
m
o
d
el
f
o
r
A
F
O
u
s
i
n
g
p
ar
am
etr
i
c
an
d
n
o
n
-
p
ar
a
m
e
tr
ic
m
o
d
elli
n
g
m
et
h
o
d
o
lo
g
ies.
T
h
e
p
ar
a
m
etr
i
c
ap
p
r
o
ac
h
in
v
o
l
v
es
t
h
e
u
tili
za
tio
n
o
f
P
SO
,
w
h
ile
th
e
n
o
n
-
p
ar
a
m
etr
ic
ap
p
r
o
ac
h
e
m
p
lo
y
s
m
u
lti
-
la
y
er
p
er
ce
p
tr
o
n
(
ML
P
)
n
eu
r
al
n
et
w
o
r
k
s
.
T
h
ese
m
o
d
els
ar
e
cr
ea
ted
u
s
i
n
g
in
f
o
r
m
at
io
n
o
b
tain
ed
f
r
o
m
a
n
e
x
p
er
i
m
e
n
tal
s
et
u
p
an
d
th
e
s
y
s
te
m
id
en
ti
f
icat
io
n
a
p
p
r
o
ac
h
.
Fo
llo
w
i
n
g
m
o
d
el
d
e
v
elo
p
m
e
n
t,
a
t
h
o
r
o
u
g
h
v
alid
atio
n
p
r
o
ce
s
s
en
s
u
es,
w
i
th
t
h
e
ac
q
u
ir
ed
r
esu
lt
s
s
u
b
j
ec
t
to
m
etic
u
lo
u
s
co
m
p
ar
is
o
n
an
d
an
al
y
s
i
s
.
T
h
e
f
in
d
i
n
g
s
p
r
o
v
id
e
to
im
p
r
o
v
i
n
g
th
e
d
ev
elo
p
m
e
n
t
an
d
co
n
tr
o
l
o
f
A
FO
s
y
s
te
m
s
,
b
en
ef
it
in
g
in
d
i
v
id
u
al
s
w
ith
m
o
b
il
it
y
i
m
p
air
m
e
n
t
s
ca
u
s
ed
b
y
co
n
d
itio
n
s
lik
e
f
o
o
t
d
r
o
p
,
s
tr
o
k
e,
an
d
o
th
er
d
is
ab
ilit
ies.
2.
M
E
T
H
O
D
T
h
is
s
tu
d
y
p
r
esen
t
s
a
co
m
p
r
e
h
en
s
i
v
e
ap
p
r
o
ac
h
to
m
o
d
elin
g
an
A
FO,
a
s
ill
u
s
tr
ated
i
n
Fi
g
u
r
e
2
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
d
esi
g
n
e
d
to
ac
cu
r
ately
r
ep
licate
th
e
d
y
n
a
m
ic
b
eh
a
v
io
r
o
f
th
e
an
k
le.
B
y
in
co
r
p
o
r
atin
g
b
o
th
p
ar
a
m
etr
ic
a
n
d
n
o
n
-
p
ar
a
m
etr
ic
tec
h
n
iq
u
e
s
,
th
e
s
t
u
d
y
e
x
p
lo
r
es
v
ar
io
u
s
m
o
d
elin
g
o
p
ti
o
n
s
to
id
e
n
ti
f
y
t
h
e
m
o
s
t
ef
f
ec
t
iv
e
ap
p
r
o
ac
h
.
Ultim
atel
y
,
th
i
s
m
o
d
elin
g
f
r
a
m
e
wo
r
k
ai
m
s
to
en
h
an
ce
t
h
e
d
ev
el
o
p
m
e
n
t
an
d
co
n
tr
o
l
o
f
AFOs
,
e
n
s
u
r
in
g
t
h
e
y
clo
s
e
l
y
m
i
m
ic
t
h
e
n
atu
r
al
d
y
n
a
m
ic
s
o
f
th
e
a
n
k
le
.
2
.
1
.
E
x
peri
m
ent
a
t
io
n
s
et
up
a
nd
da
t
a
a
cquis
it
io
n
I
n
itiall
y
,
an
AFO
r
ig
w
i
th
o
n
e
d
eg
r
ee
o
f
f
r
ee
d
o
m
(
DOF)
w
a
s
d
esig
n
ed
an
d
f
ab
r
icate
d
.
T
h
e
s
tr
u
ct
u
r
e
s
p
ec
if
icall
y
d
e
s
ig
n
ed
f
o
r
ch
i
ld
r
en
u
tili
ze
d
3
D
p
r
in
tin
g
m
ater
ials
,
b
o
asti
n
g
ap
p
r
o
x
i
m
ate
d
im
e
n
s
io
n
s
o
f
0
.
1
5
m
×
0
.
0
5
m
×
0
.
0
3
m
.
T
a
b
le
1
o
u
tlin
es t
h
e
s
p
ec
i
f
icatio
n
s
o
f
th
e
i
n
s
tr
u
m
en
tatio
n
e
m
p
lo
y
ed
in
t
h
is
s
tu
d
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
2
,
A
p
r
il
20
25
:
4
8
4
-
494
486
Fig
u
r
e
2
.
T
h
e
ex
p
er
im
e
n
tal
s
e
t
u
p
o
f
A
FO
T
ab
le
1
.
T
h
e
A
FO
i
n
s
tr
u
m
e
n
t
atio
n
I
t
e
m
S
p
e
c
i
f
i
c
a
t
i
o
n
M
o
d
e
l
s
i
z
e
(
L
×
W
×
H)
0
:
1
5
m
0
:
0
5
m
0
:
0
3
m
M
o
t
o
r
L
i
n
e
a
r
a
c
t
u
a
t
o
r
:
1
2
V
,
5
1
m
m st
r
o
k
e
a
n
d
9
0
0
N
l
o
a
d
r
a
t
i
n
g
M
o
t
o
r
d
r
i
v
e
r
L
2
9
8
N
:
2
A
,
5
-
35
V
P
o
w
e
r
su
p
p
l
y
12
V
S
e
n
so
r
I
M
U
se
n
so
r
:
M
P
U
6
0
5
0
M
i
c
r
o
c
o
n
t
r
o
l
l
e
r
A
r
d
u
i
n
o
M
e
g
a
T
h
e
p
r
im
ar
y
o
b
j
ec
tiv
e
o
f
t
h
i
s
s
et
u
p
w
as
to
ca
p
t
u
r
e
t
h
e
i
n
p
u
t
-
o
u
tp
u
t
d
y
n
a
m
ics
o
f
t
h
e
AFO
d
u
r
i
n
g
r
eh
ab
ilit
atio
n
s
es
s
io
n
s
,
s
p
ec
if
icall
y
f
o
cu
s
in
g
o
n
d
o
r
s
i
f
le
x
i
o
n
an
d
p
lan
tar
f
le
x
io
n
m
o
v
e
m
en
ts
.
T
o
f
ac
ilit
ate
m
o
b
il
it
y
,
a
lin
ea
r
ac
tu
ato
r
ex
er
ted
f
o
r
ce
o
n
to
th
e
A
FO
at
th
e
r
ea
r
o
f
th
e
f
o
o
t
b
r
ac
e,
th
er
eb
y
t
r
an
s
f
er
r
in
g
k
in
e
tic
en
er
g
y
,
as
d
ep
icted
in
Fig
u
r
e
2
.
A
lin
ea
r
ac
tu
ato
r
w
as
s
p
ec
if
icall
y
c
h
o
s
e
n
b
ec
au
s
e
o
f
its
lo
n
g
-
ter
m
d
ep
en
d
ab
ilit
y
,
h
i
g
h
to
r
q
u
e
ca
p
ac
it
y
,
an
d
ac
cu
r
ate
s
tr
o
k
e
co
n
t
r
o
l.
T
h
e
lin
ea
r
ac
tu
ato
r
w
a
s
in
ter
f
ac
ed
w
ith
a
m
o
to
r
d
r
iv
er
(
L
2
9
8
N)
,
w
h
ic
h
in
tu
r
n
w
a
s
co
n
tr
o
lled
b
y
th
e
A
r
d
u
i
n
o
Me
g
a
m
icr
o
co
n
tr
o
lle
r
.
T
h
is
m
icr
o
co
n
tr
o
ller
w
a
s
co
n
n
ec
ted
to
a
co
m
p
u
ter
v
ia
US
B
co
n
n
ec
tio
n
.
T
h
e
co
n
f
i
g
u
r
atio
n
o
f
t
h
e
r
i
g
allo
w
ed
f
o
r
a
d
o
r
s
if
lex
io
n
an
g
le
o
f
+2
0
d
eg
r
ee
s
an
d
a
p
la
n
t
ar
f
lex
io
n
an
g
le
o
f
-
2
0
d
eg
r
ee
s
.
I
MU
s
e
n
s
o
r
was
u
t
ilized
to
d
etec
t
t
h
e
an
g
u
lar
m
o
v
e
m
e
n
t
d
u
r
in
g
e
x
e
r
cises
,
s
p
ec
i
f
icall
y
r
ep
r
esen
tin
g
f
ee
t
d
o
r
s
if
lex
io
n
an
d
p
lan
tar
f
le
x
io
n
,
as
d
ep
icted
in
th
e
s
ch
e
m
at
ic
d
iag
r
a
m
o
f
Fi
g
u
r
e
3
.
T
h
is
s
en
s
o
r
w
a
s
d
ir
ec
tl
y
lin
k
ed
to
th
e
d
ata
ac
q
u
is
itio
n
s
y
s
te
m
,
co
m
p
r
is
in
g
t
h
e
A
r
d
u
i
n
o
Me
g
a
m
icr
o
c
o
n
tr
o
ller
,
w
h
ic
h
,
i
n
tu
r
n
,
co
n
n
ec
ted
to
a
co
m
p
u
ter
v
ia
USB
.
Fig
u
r
e
3
.
S
ch
e
m
atic
d
iag
r
a
m
o
f
AFO
12V
Ba
tter
y
A
F
O
Rig
La
ptop
Moto
r D
rive
r
Ar
du
i
no
Me
ga
S
topwa
tch
I
MU Senso
r
I
MU Senso
r
Line
a
r
A
c
tuator
Moto
r
d
rive
r
P
owe
r supply
C
omput
e
r
MA
TL
A
B/
Si
mulink
Ar
duino M
e
ga
S
topwa
tch
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
mp
o
s
in
g
n
e
u
r
a
l n
etw
o
r
ks a
n
d
P
S
O
o
p
timiz
a
tio
n
in
t
h
e
q
u
est
fo
r
o
p
tima
l a
n
kle
-
f
o
o
t
…
(
A
n
n
is
a
Ja
ma
li
)
487
A
p
er
s
o
n
a
l
n
o
teb
o
o
k
w
it
h
a
p
o
w
er
f
u
l
p
r
o
ce
s
s
o
r
,
4
.
0
0
G
B
o
f
R
A
M,
an
d
M
A
T
L
A
B
s
o
f
t
w
ar
e
w
a
s
u
s
ed
to
an
al
y
s
e
th
e
g
e
n
er
ated
s
ig
n
al
s
.
T
h
e
Si
m
u
li
n
k
p
r
o
g
r
a
m
w
as u
s
ed
to
cr
ea
te
th
e
i
n
ter
f
ac
e
f
o
r
d
ata
g
ath
er
i
n
g
.
An
o
th
er
tech
n
iq
u
e
w
a
s
to
ap
p
ly
a
b
an
g
-
b
an
g
to
r
q
u
e
s
ig
n
a
l
to
th
e
AFO
in
o
r
d
er
t
o
s
im
u
lta
n
eo
u
s
l
y
ac
ti
v
ate
th
e
ac
tu
ato
r
w
ith
t
h
e
r
eq
u
ir
ed
to
r
q
u
e.
2
.
2
.
Sy
s
t
em
i
dentif
ica
t
io
n
T
h
e
d
y
n
a
m
ic
s
y
s
te
m
o
f
th
e
A
F
O
w
as
m
o
d
elled
in
th
i
s
w
o
r
k
u
s
in
g
th
e
s
y
s
te
m
id
en
ti
f
icat
io
n
t
ec
h
n
iq
u
e.
I
n
th
i
s
tech
n
iq
u
e,
f
o
u
r
m
ai
n
s
tag
es
w
er
e
i
n
v
o
l
v
ed
th
at
is
d
ata
ac
q
u
i
s
itio
n
,
m
o
d
el
s
tr
u
ct
u
r
e
s
elec
tio
n
,
m
o
d
el
esti
m
atio
n
,
an
d
m
o
d
el
v
alid
at
io
n
.
T
o
ex
p
lo
r
e
th
e
ef
f
ec
ts
o
f
p
ar
am
etr
ic
an
d
n
o
n
-
p
ar
a
m
etr
ic
ap
p
r
o
ac
h
es,
t
h
e
m
o
d
e
l
e
s
t
im
at
i
o
n
i
n
th
is
s
t
u
d
y
w
as
c
o
n
d
u
c
t
e
d
u
s
in
g
PS
O
a
n
d
ML
PN
N
,
r
e
s
p
e
ct
iv
e
ly
.
Su
b
s
e
q
u
en
tly
,
s
y
s
t
em
i
d
e
n
tif
i
c
at
i
o
n
s
w
e
r
e
f
o
r
m
u
l
at
e
d
u
t
il
i
z
in
g
an
au
t
o
-
r
eg
r
e
s
s
iv
e
w
ith
ex
o
g
en
o
u
s
(
A
R
X
)
a
n
d
n
o
n
l
in
e
a
r
a
u
t
o
-
r
eg
r
es
s
i
v
e
w
ith
ex
o
g
e
n
o
u
s
(
NA
R
X
)
m
o
d
el
s
t
r
u
c
tu
r
e
,
c
o
r
r
e
s
p
o
n
d
i
n
g
ly
.
T
h
e
A
R
X
m
o
d
el
s
t
r
u
ctu
r
e
is
d
e
s
c
r
i
b
e
in
(
1
)
:
(
)
=
(
−
1
)
(
−
1
)
(
)
+
(
)
(
−
1
)
(
1
)
w
h
er
e
th
e
e
x
p
r
ess
io
n
s
o
f
A
(
z
−
1
)
an
d
B
(
z
−
1
)
ar
e;
(
−
1
)
=
1
+
1
−
1
+
…
.
+
−
(
−
1
)
=
0
+
1
−
1
+
…
.
+
−
(
−
1
)
(
2
)
W
h
ite
n
o
i
s
e,
(
)
=0
,
n
is
th
e
m
o
d
el
’
s
o
r
d
er
s
,
an
d
[
1
,
…
,
,
1
,
…
,
]
ar
e
th
e
m
o
d
el
p
ar
a
m
eter
s
t
h
at
n
ee
d
to
b
e
esti
m
ated
to
d
eter
m
i
n
e
−
1
.
T
h
e
s
y
s
te
m
’
s
o
u
tp
u
t
v
ec
to
r
is
d
e
n
o
ted
b
y
(
)
an
d
its
in
p
u
t
v
ec
to
r
b
y
(
)
.
I
n
(
3
)
y
ield
s
th
e
n
e
u
r
al
n
et
w
o
r
k
au
to
r
eg
r
ess
i
v
e
m
o
d
el
w
it
h
eXo
g
en
o
u
s
i
n
p
u
t
s
(
NNAR
X)
m
o
d
el
s
tr
u
c
tu
r
e
r
eg
r
ess
io
n
v
ec
to
r
.
T
h
r
o
u
g
h
t
h
e
in
te
g
r
atio
n
o
f
n
e
u
r
al
n
et
w
o
r
k
s
i
n
to
t
h
e
m
o
d
el
f
r
a
m
e
w
o
r
k
,
NN
A
R
X
o
v
er
co
m
es
th
e
d
r
a
w
b
ac
k
s
o
f
N
AR
X.
(
)
=
[
(
−
1
)
,
…
.
,
(
−
,
)
,
(
−
)
,
…
.
,
(
−
−
+
1
)
]
(
3
)
w
h
er
e
(
)
d
en
o
tes
th
e
r
eg
r
ess
io
n
v
ec
to
r
at
tim
e
s
tep
,
t.
P
ast
v
alu
es
o
f
th
e
s
y
s
te
m
’
s
i
n
p
u
t
an
d
o
u
tp
u
t
ar
e
u
s
ed
to
g
en
er
ate
t
h
e
r
eg
r
ess
io
n
v
ec
t
o
r
.
In
(
4
)
g
iv
es t
h
e
o
n
e
s
tep
ah
ea
d
(
OSA
)
f
o
r
ec
ast o
f
th
e
NN
AR
X
m
o
d
el:
̂
(
)
=
(
−
1
,
)
=
g
(
(
)
,
)
(
4
)
w
h
er
e
g
i
s
th
e
f
u
n
ctio
n
th
a
t th
e
n
eu
r
al
n
et
w
o
r
k
ap
p
r
o
ac
h
h
as
ac
h
iev
ed
.
2
.
2
.
1
.
P
a
ra
m
et
ric
esti
m
a
t
io
n
v
ia
pa
rt
icle
s
w
a
r
m
o
pti
m
iza
t
io
n
P
ar
am
etr
ic
s
y
s
te
m
id
e
n
ti
f
icati
o
n
in
v
o
lv
e
s
u
ti
lizi
n
g
m
ea
s
u
r
a
b
le
d
ata
to
d
ev
elo
p
m
ath
e
m
ati
ca
l
m
o
d
els
th
at
r
ep
r
esen
t a
d
y
n
a
m
ic
s
y
s
te
m
[
2
4
]
.
Go
o
d
m
o
d
els ar
e
n
ec
ess
ar
y
f
o
r
m
o
s
t
m
o
d
el
-
b
ased
co
n
tr
o
l
m
et
h
o
d
s
.
T
h
e
k
e
y
tas
k
a
f
ter
d
ef
i
n
i
n
g
th
e
m
o
d
el
s
tr
u
ctu
r
e
i
s
to
est
i
m
a
te
it
s
p
ar
a
m
eter
s
,
t
y
p
icall
y
d
eter
m
in
ed
b
y
ap
p
l
y
i
n
g
a
g
lo
b
al
m
i
n
i
m
u
m
cr
ite
r
io
n
f
u
n
c
tio
n
.
P
SO w
as
i
n
s
p
ir
ed
b
y
th
e
s
tu
d
y
o
f
n
at
u
r
al
s
o
cial
b
eh
a
v
io
r
s
in
an
i
m
al
s
,
s
u
c
h
as
s
c
h
o
o
ls
o
f
f
is
h
,
s
w
ar
m
s
o
f
b
ee
s
,
an
d
b
ir
d
f
lo
ck
s
,
an
d
o
p
er
ates
b
ased
o
n
a
p
o
p
u
latio
n
m
o
d
el
[
2
5
]
.
P
SO
is
ea
s
y
to
ap
p
ly
to
a
v
ar
iet
y
o
f
o
p
ti
m
is
atio
n
is
s
u
e
s
a
n
d
h
as
a
s
tr
ai
g
h
t
f
o
r
w
ar
d
ap
p
r
o
ac
h
.
A
lt
h
o
u
g
h
i
t c
an
b
e
ch
alle
n
g
i
n
g
to
in
itiali
s
e
its
p
ar
a
m
eter
s
.
D
esp
ite
th
e
f
ac
t
th
at
i
n
itial
is
i
n
g
its
p
ar
am
e
ter
s
ca
n
b
e
d
if
f
icu
lt,
P
SO
h
as
a
h
ig
h
ch
an
ce
a
n
d
e
f
f
icien
c
y
o
f
f
in
d
in
g
th
e
g
lo
b
al
o
p
ti
m
a
an
d
r
e
q
u
ir
es
f
e
w
m
o
d
i
f
icatio
n
s
.
PS
O
ca
n
co
n
v
er
g
e
to
o
q
u
ick
l
y
an
d
g
et
s
t
u
c
k
in
lo
ca
l
o
p
tim
a,
d
esp
ite
it
s
q
u
ic
k
er
r
o
r
co
n
v
er
g
e
n
ce
.
I
n
th
e
p
r
o
ce
s
s
o
f
id
en
tify
in
g
th
e
o
p
tim
al
s
o
l
u
tio
n
i
n
m
u
lt
id
i
m
en
s
io
n
a
l
s
p
ac
e,
th
e
P
SO
alg
o
r
ith
m
m
i
m
ics
b
ir
d
s
u
s
i
n
g
N
p
ar
ticles
[
2
6
]
.
P
o
s
itio
n
(
)
an
d
v
elo
cit
y
(
)
,
w
h
er
e
i
is
t
h
e
p
ar
ticle
la
b
el,
ar
e
th
e
t
w
o
ch
ar
ac
ter
is
tic
s
o
f
ev
er
y
p
ar
tic
le.
T
h
e
p
ar
ticle
’
s
m
o
v
e
m
e
n
t
i
s
r
ep
r
esen
ted
b
y
(
),
as
s
ee
n
i
n
(
5
)
.
(
)
is
th
e
o
u
tco
m
e
o
f
t
h
e
p
ar
ticle
’
s
m
o
t
i
o
n
an
d
a
p
o
ten
tial so
l
u
tio
n
to
t
h
e
ass
o
ciate
d
o
p
ti
m
i
s
atio
n
p
r
o
b
le
m
,
as ill
u
s
tr
ated
in
(
6
)
.
E
ac
h
p
ar
ticle
’
s
f
it
n
es
s
v
alu
e
,
w
h
ich
i
s
ca
lcu
lated
u
s
in
g
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
,
q
u
an
tif
ie
s
th
e
d
if
f
er
e
n
ce
b
et
w
ee
n
th
e
c
u
r
r
en
t
ca
n
d
id
ate
s
o
l
u
tio
n
a
n
d
t
h
e
b
est
s
o
l
u
tio
n
.
T
h
e
i
n
d
iv
id
u
al
e
x
tr
e
m
u
m
is
t
h
e
o
p
tim
a
l so
lu
tio
n
f
o
r
in
d
iv
id
u
al
p
ar
ticle
s
ea
r
ch
,
in
co
n
tr
as
t to
its
h
i
s
to
r
ical
an
d
p
r
esen
t
s
o
lu
t
i
o
n
s
.
Fo
r
th
e
w
h
o
le
p
ar
ticle
s
w
ar
m
,
t
h
e
p
o
p
u
latio
n
ex
tr
e
m
u
m
Z
is
t
h
e
b
est
s
o
lu
tio
n
r
elat
iv
e
to
it
s
h
i
s
to
r
ica
l
s
o
lu
tio
n
an
d
all
in
d
iv
id
u
al
ex
tr
e
m
u
m
o
f
th
e
cu
r
r
en
t
g
en
er
atio
n
.
T
h
e
p
ar
ticle
p
o
p
u
latio
n
co
n
tin
u
o
u
s
l
y
u
p
d
at
es
th
e
p
o
s
itio
n
an
d
v
elo
cit
y
o
f
p
ar
ticles
b
y
m
o
n
ito
r
in
g
b
o
th
i
n
d
iv
id
u
al
an
d
g
r
o
u
p
ex
tr
e
m
u
m
s
d
u
r
i
n
g
th
e
s
ea
r
c
h
a
n
d
iter
atio
n
p
r
o
ce
s
s
in
o
r
d
er
to
id
en
tify
t
h
e
o
p
ti
m
a
l
s
o
lu
tio
n
t
h
at
s
ati
s
f
ies
th
e
r
eq
u
ir
e
m
e
n
t
s
.
T
h
e
o
p
tim
is
at
io
n
o
u
tco
m
e
ca
n
b
e
s
ee
n
in
th
e
f
i
n
al
g
r
o
u
p
ex
tr
e
m
u
m
Z
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
2
,
A
p
r
il
20
25
:
4
8
4
-
494
488
−
=
+
1
(
)
(
−
)
+
2
(
)
(
−
)
(
5
)
−
=
+
(
6
)
w
h
er
e
t
h
e
le
f
t
p
ar
t
o
f
th
e
eq
u
atio
n
r
ep
r
esen
ts
th
e
n
e
w
v
e
l
o
cit
y
a
n
d
p
o
s
itio
n
o
f
t
h
e
p
ar
t
icle
in
th
e
cu
r
r
en
t
g
en
er
atio
n
,
an
d
th
e
r
i
g
h
t
p
ar
t
r
ep
r
esen
ts
t
h
e
p
ar
ticle
p
r
o
p
er
tie
s
f
r
o
m
t
h
e
p
r
ev
io
u
s
g
e
n
er
atio
n
.
T
h
e
in
er
tia
f
ac
to
r
is
eq
u
al
to
0
.
5
.
1
an
d
2
ar
e
lear
n
in
g
f
ac
to
r
s
w
ith
v
alu
e
s
o
f
2
.
I
n
ad
d
itio
n
,
th
e
p
o
p
u
latio
n
s
ize
N
(
1
,
5
9
9
)
w
a
s
ad
j
u
s
ted
to
N/2
,
r
esu
ltin
g
in
7
9
9
.
5
an
d
th
e
m
a
x
i
m
u
m
n
u
m
b
e
r
o
f
iter
atio
n
s
M
w
as
s
et
to
1
,
0
0
0
.
2
.
2
.
2
.
No
n
-
pa
ra
m
et
ric
e
s
t
i
ma
t
io
n by
us
ing
m
ulti
-
la
y
er
perc
ept
ro
n neura
l
net
w
o
rk
T
h
e
A
FO
w
a
s
m
o
d
elled
u
s
i
n
g
an
ML
P
n
eu
r
al
n
et
w
o
r
k
f
o
r
n
o
n
-
p
ar
a
m
etr
ic
esti
m
atio
n
.
T
h
e
ML
P
n
eu
r
al
n
et
w
o
r
k
f
a
m
il
y
is
th
e
m
o
s
t
co
m
m
o
n
l
y
u
tili
s
ed
b
ec
au
s
e
it
ca
n
esti
m
ate
a
v
er
y
co
m
p
le
x
f
o
r
m
u
la
ass
o
ciatio
n
w
h
ile
p
r
o
d
u
cin
g
a
s
i
m
p
le
m
o
d
el
[
2
7
]
.
I
n
th
e
ML
P
,
th
e
in
p
u
t
lay
er
is
f
o
r
m
ed
b
y
a
s
i
n
g
le
s
et
o
f
n
o
d
es,
an
d
th
e
o
u
tp
u
t is g
e
n
er
ated
b
y
a
s
ec
o
n
d
lay
er
,
w
ith
s
e
v
er
al
h
id
d
en
la
y
er
s
p
o
s
itio
n
ed
b
et
w
ee
n
th
e
m
.
T
h
e
in
p
u
t la
y
er
,
o
u
tp
u
t
la
y
er
,
an
d
h
id
d
en
lay
er
w
it
h
d
if
f
er
en
t
s
tr
en
g
t
h
w
e
ig
h
ts
m
ak
e
u
p
th
e
n
et
w
o
r
k
la
y
er
.
T
h
e
q
u
alities
o
f
t
h
e
f
u
n
ctio
n
(
.
)
in
cl
u
d
e
r
ad
ial
b
asis
,
h
y
p
er
b
o
lic
ta
n
g
e
n
t,
s
i
g
m
o
id
,
th
r
es
h
o
ld
,
an
d
lin
ea
r
.
T
h
e
n
et
w
o
r
k
ca
n
fo
r
ec
ast th
e
o
u
tp
u
t,
̂
,
as p
r
ec
is
el
y
as
f
ea
s
ib
le
t
h
an
k
s
to
t
h
e
m
ap
p
in
g
.
I
n
(
7
)
,
th
e
ML
P
o
u
tp
u
t is d
is
p
la
y
ed
:
̂
(
,
)
=
(
∑
∙
=
1
(
∑
+
=
1
0
)
+
0
)
(
7
)
L
e
v
en
b
er
g
-
Ma
r
q
u
ar
d
t
(
L
M)
is
ch
o
s
en
f
o
r
tr
ain
i
n
g
n
et
w
o
r
k
s
b
ec
au
s
e
o
f
its
f
ast
co
n
v
er
g
e
n
ce
,
ev
e
n
th
o
u
g
h
it
d
em
a
n
d
s
h
i
g
h
er
m
e
m
o
r
y
u
s
ag
e
co
m
p
ar
ed
to
alter
n
ati
v
e
alg
o
r
ith
m
s
.
T
h
e
L
M
m
i
n
i
m
is
e
s
th
e
r
esid
u
al,
(
,
)
=
(
)
−
̂
(
,
)
,
in
o
r
d
er
to
m
ax
i
m
i
s
e
th
e
er
r
o
r
b
ased
o
n
th
e
cr
iter
io
n
in
(
8
)
:
(
)
=
(
1
2
)
∑
−
2
(
,
)
≈
=
1
(
,
)
(
8
)
w
h
er
e
r
ep
r
esen
ts
t
h
e
tr
ain
i
n
g
d
ata
s
et.
2
.
2
.
3
.
M
o
del v
a
lid
a
t
io
n
T
o
en
s
u
r
e
th
e
ad
eq
u
ac
y
o
f
th
e
m
o
d
el
u
n
d
er
d
ev
elo
p
m
en
t,
t
h
e
v
alid
atio
n
p
h
ase
i
s
ess
e
n
tial
[
1
5
]
.
T
h
is
v
alid
atio
n
p
r
o
ce
s
s
e
m
p
lo
y
s
th
r
ee
m
eth
o
d
s
:
O
S
A
p
r
ed
ictio
n
,
MSE
,
an
d
co
r
r
elatio
n
t
est.
T
h
e
s
t
u
d
y
e
x
a
m
i
n
es
f
i
v
e
co
r
r
elatio
n
f
u
n
ct
io
n
s
:
(
)
=
[
(
−
)
(
)
]
=
(
)
,
(
)
=
[
(
−
)
(
)
]
=
0
,
∀
,
2
(
)
=
[
2
(
−
)
−
̅
2
(
)
(
)
]
=
0
,
∀
,
(
9
)
2
2
(
)
=
[
2
(
−
)
−
̅
2
(
)
2
(
)
]
=
0
,
∀
,
(
)
(
)
=
[
(
)
(
−
1
−
)
(
−
1
−
)
]
=
0
,
≥
0
,
(
)
=
(
+
1
)
(
+
1
)
,
(
)
is
an
i
m
p
u
ls
e
f
u
n
ctio
n
,
a
n
d
(
)
is
th
e
cr
o
s
s
-
co
r
r
elatio
n
f
u
n
ctio
n
b
et
w
ee
n
(
)
an
d
(
)
.
A
ll f
i
v
e
r
eq
u
ir
em
en
ts
n
ee
d
to
b
e
m
et
b
ec
au
s
e
th
e
M
L
P
m
o
d
el
is
b
u
ilt
u
s
i
n
g
t
h
e
N
A
R
X
s
tr
u
ct
u
r
e,
w
h
ic
h
m
a
k
es
it
a
n
o
n
lin
ea
r
s
y
s
te
m
.
C
o
n
v
er
s
e
l
y
,
an
o
th
er
P
SO
m
o
d
el
e
m
p
lo
y
i
n
g
a
li
n
ea
r
s
y
s
te
m
n
ec
es
s
itates t
h
e
f
u
l
f
i
ll
m
e
n
t o
f
o
n
l
y
t
h
r
ee
co
n
d
itio
n
s
.
T
h
e
s
tu
d
y
e
m
p
lo
y
s
1
,
5
9
9
d
ata
p
o
in
ts
f
o
r
P
SO
an
d
2
,
1
8
9
d
ata
p
o
in
ts
f
o
r
M
L
P
in
test
i
n
g
.
T
h
e
s
elec
tio
n
o
f
1
,
5
9
9
d
ata
p
o
in
ts
f
o
r
P
SO
ai
m
s
f
o
r
in
cr
ea
s
ed
s
tab
ilit
y
i
n
r
esu
lt
s
,
w
h
ile
2
,
1
8
9
d
ata
p
o
in
ts
f
o
r
ML
P
co
r
r
esp
o
n
d
to
th
e
e
n
tire
t
y
o
f
f
i
v
e
w
al
k
i
n
g
c
y
cles
d
u
r
in
g
t
h
e
e
x
p
er
i
m
e
n
t
.
T
h
e
9
5
%
co
n
f
id
en
ce
b
an
d
s
ar
e
u
s
ed
,
w
h
ich
ar
e
ar
o
u
n
d
±
1
.
9
6
/
√
N
(
N
d
ata)
,
w
it
h
o
n
e
o
r
m
o
r
e
f
u
n
c
tio
n
p
o
in
ts
f
a
lli
n
g
o
u
t
s
id
e
o
f
th
ese
li
m
its
i
n
d
icati
n
g
a
s
u
b
s
ta
n
tial
li
n
k
[
2
8
]
.
T
h
e
m
o
d
el
is
d
ee
m
ed
ad
eq
u
ate
if
th
e
c
o
r
r
elatio
n
f
u
n
ctio
n
s
r
e
m
ai
n
w
i
th
i
n
t
h
e
co
n
f
id
en
c
e
in
ter
v
a
ls
.
3.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
I
n
th
is
r
esear
c
h
,
th
e
co
llected
d
atasets
w
er
e
s
p
lit
i
n
to
t
w
o
p
ar
ts
:
o
n
e
f
o
r
tr
ain
in
g
th
e
m
o
d
el
an
d
th
e
o
th
er
f
o
r
ev
al
u
ati
n
g
it
s
p
er
f
o
r
m
an
ce
.
T
h
e
v
a
lid
atio
n
o
f
t
h
e
d
ev
elo
p
ed
s
y
s
te
m
i
n
v
o
lv
ed
m
u
ltip
le
m
etr
ics,
in
cl
u
d
in
g
MSE
,
OS
A
p
r
ed
icti
o
n
,
co
r
r
elatio
n
test
s
,
an
d
ex
a
m
in
atio
n
o
f
th
e
p
o
le
-
ze
r
o
d
iag
r
a
m
f
o
r
s
tab
ili
t
y
.
T
h
e
m
o
s
t
ap
p
r
o
p
r
iate
m
o
d
el
w
a
s
ch
o
s
en
p
r
i
m
ar
il
y
b
ased
o
n
r
o
b
u
s
tn
e
s
s
s
t
u
d
ies,
w
i
th
an
e
m
p
h
a
s
is
o
n
ac
h
iev
in
g
a
lo
w
MSE
,
h
i
g
h
s
ta
b
ilit
y
,
a
n
d
u
n
b
iased
o
u
tco
m
e
s
i
n
co
r
r
elatio
n
te
s
ts
.
T
h
ese
ev
al
u
atio
n
s
w
er
e
cr
i
tical
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
mp
o
s
in
g
n
e
u
r
a
l n
etw
o
r
ks a
n
d
P
S
O
o
p
timiz
a
tio
n
in
t
h
e
q
u
est
fo
r
o
p
tima
l a
n
kle
-
f
o
o
t
…
(
A
n
n
is
a
Ja
ma
li
)
489
to
en
s
u
r
i
n
g
t
h
at
th
e
d
ev
elo
p
ed
m
o
d
el
p
er
f
o
r
m
ed
v
er
y
w
ell
.
Sin
ce
th
er
e
w
as
n
o
p
r
io
r
u
n
d
er
s
tan
d
in
g
o
f
th
e
o
p
tim
a
l
m
o
d
el
f
o
r
an
AFO,
th
e
s
tr
u
ct
u
r
e
r
ea
lizatio
n
p
r
o
ce
s
s
e
m
p
lo
y
ed
a
h
e
u
r
is
tic
m
et
h
o
d
.
3
.
1
.
M
o
dellin
g
us
ing
pa
rt
icl
e
s
w
a
r
m
o
pti
m
iza
t
io
n
T
h
e
d
ataset
u
til
ized
f
o
r
p
ar
am
etr
ic
m
o
d
elin
g
w
it
h
P
SO
c
o
m
p
r
i
s
ed
1
,
5
9
9
d
ata
p
o
in
ts
,
w
h
ic
h
w
er
e
d
iv
id
ed
in
to
t
w
o
eq
u
al
s
et
s
o
f
7
9
9
.
5
d
ata
p
o
in
ts
ea
ch
.
T
h
e
s
ec
o
n
d
s
et
s
er
v
ed
as
th
e
v
alid
ati
o
n
test
s
et,
an
d
th
e
f
ir
s
t
s
et
s
er
v
ed
as
th
e
m
o
d
elli
n
g
est
i
m
a
tio
n
s
et.
MSE
,
s
tab
il
it
y
cr
iter
ia
an
d
t
w
o
co
r
r
elatio
n
test
s
w
er
e
u
s
ed
to
ev
alu
a
te
th
e
tr
an
s
f
er
f
u
n
ctio
n
i
n
th
e
P
SO
m
o
d
elli
n
g
p
r
o
ce
s
s
i
n
o
r
d
er
to
v
alid
ate
th
e
f
in
d
i
n
g
s
.
I
t
w
as
d
eter
m
in
ed
th
at
a
m
o
d
el
o
r
d
er
o
f
f
o
u
r
y
ie
ld
ed
th
e
m
o
s
t
f
av
o
r
ab
le
o
u
tco
m
es.
T
h
e
P
SO
al
g
o
r
ith
m
w
a
s
co
n
f
i
g
u
r
ed
w
ith
a
m
ax
i
m
u
m
o
f
1
0
0
0
iter
atio
n
s
a
n
d
a
s
w
ar
m
s
ize
o
f
4
0
0
.
Fig
u
r
e
4
illu
s
tr
ates
t
h
e
P
SO
p
r
ed
ictio
n
s
o
f
th
e
r
o
ll
a
x
is
a
n
g
le.
T
h
e
g
r
ap
h
d
e
m
o
n
s
tr
ates
th
at
P
SO
m
an
a
g
ed
to
ap
p
r
o
x
i
m
ate
ce
r
ta
in
asp
ec
ts
o
f
th
e
a
ct
u
al
d
ata.
Ho
w
e
v
er
,
n
o
ticea
b
le
d
is
p
ar
iti
es
ex
i
s
t
b
et
w
ee
n
t
h
e
ac
tu
al
a
n
d
p
r
ed
icted
P
SO
o
u
tp
u
ts
.
F
u
r
th
er
i
n
v
esti
g
atio
n
o
n
Fig
u
r
e
5
ab
o
u
t
co
r
r
elatio
n
test
s
f
o
r
ea
ch
r
o
ll
a
x
i
s
an
g
le
s
h
o
w
t
h
at
all
f
all
o
u
t
s
id
e
o
f
its
9
5
% c
o
n
f
id
en
ce
in
ter
v
a
l.
T
h
is
s
ig
n
i
f
y
t
h
at
t
h
er
e
is
b
ia
s
in
t
h
e
m
o
d
el.
Fig
u
r
e
4
.
T
h
e
o
u
tp
u
t a
n
d
esti
m
ated
o
u
tp
u
t o
f
r
o
ll a
x
is
a
n
g
le
Fig
u
r
e
5
.
T
h
e
co
r
r
elatio
n
test
f
o
r
r
o
ll a
x
is
an
g
le
(
P
SO
)
Fig
u
r
e
6
s
h
o
w
s
t
h
e
s
tab
ilit
y
te
s
t
r
esu
l
t,
w
h
ic
h
s
h
o
w
s
t
h
at
t
h
e
p
o
les
ar
e
v
is
ib
le
in
s
id
e
th
e
u
n
it
y
cir
cle
an
d
th
e
ze
r
o
s
ar
e
at
t
h
e
o
r
i
g
i
n
.
Fo
r
“
×,
”
t
h
e
p
o
les
r
ep
r
esen
t
th
e
s
y
m
b
o
l,
w
h
ile
f
o
r
“
○.
”
t
h
e
ze
r
o
.
Du
e
to
th
e
p
o
les
’
p
lace
m
e
n
t i
n
s
id
e
t
h
e
u
n
it c
ir
cle,
th
e
s
y
s
te
m
is
s
tab
le.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
2
,
A
p
r
il
20
25
:
4
8
4
-
494
490
Fig
u
r
e
6
.
T
h
e
s
tab
ilit
y
test
f
o
r
r
o
ll a
x
is
an
g
le
(
P
SO)
T
ab
le
2
p
r
esen
ts
t
h
e
n
u
m
er
ica
l
o
u
tco
m
es
o
f
t
h
e
o
p
ti
m
al
m
o
d
el
o
r
d
er
.
I
t
is
n
o
te
w
o
r
th
y
t
h
at
ea
ch
m
o
d
el
d
em
o
n
s
tr
ate
s
b
ias,
p
r
o
m
p
ti
n
g
th
e
u
tili
za
t
io
n
o
f
MSE
v
al
u
es
as
in
d
icato
r
s
f
o
r
d
eter
m
i
n
i
n
g
t
h
e
s
u
p
er
io
r
m
o
d
el.
Am
o
n
g
t
h
e
v
ar
io
u
s
m
o
d
el
o
r
d
er
s
ev
al
u
ated
,
it
w
as
f
o
u
n
d
th
a
t
m
o
d
el
o
r
d
er
4
y
ield
ed
th
e
lo
w
e
s
t
MSE
v
alu
e
s
f
o
r
b
o
th
th
e
tr
ain
in
g
an
d
te
s
ti
n
g
d
atasets
,
w
h
ic
h
w
er
e
1
.
8
0
7
5
×
10
-
4
an
d
1
.
7
7
4
3
×
10
-
5
,
r
esp
ec
tiv
el
y
,
t
h
u
s
es
tab
lis
h
in
g
it a
s
th
e
o
p
ti
m
a
l
m
o
d
el
f
o
r
P
SO o
p
tim
izatio
n
m
et
h
o
d
.
T
ab
le
2
.
C
o
m
p
ar
is
o
n
o
f
P
SO
o
p
tim
izatio
n
p
er
f
o
r
m
a
n
ce
i
n
d
if
f
er
en
t
n
u
m
b
er
o
f
m
o
d
el
o
r
d
er
M
o
d
e
l
o
r
d
e
r
M
S
E
i
n
t
r
a
i
n
i
n
g
d
a
t
a
M
S
E
i
n
t
e
st
i
n
g
d
a
t
a
S
t
a
b
i
l
i
t
y
C
o
r
r
e
l
a
t
i
o
n
t
e
st
2
1
.
3
6
1
2
×
10
-
4
6
.
1
7
9
3
×
10
-
5
U
n
st
a
b
l
e
B
i
a
se
d
4
1
.
8
0
7
5
×
10
-
4
1
.
7
7
4
3
×
10
-
5
S
t
a
b
l
e
B
i
a
se
d
6
2
.
6
7
5
8
×
10
-
4
1
.
2
6
2
1
×
10
-
5
S
t
a
b
l
e
B
i
a
se
d
8
4
.
4
3
0
9
×
10
-
4
8
.
9
2
3
6
×
10
-
5
U
n
st
a
b
l
e
B
i
a
se
d
10
9
.
7
8
2
6
×
10
-
4
5
.
2
7
1
8
×
10
-
4
U
n
st
a
b
l
e
B
i
a
se
d
3
.
2
.
M
o
dellin
g
us
ing
m
ulti
-
l
a
y
er
perc
ept
ro
n
T
h
e
d
ataset
co
m
p
r
is
in
g
2
,
1
8
9
d
ata
p
o
in
ts
f
o
r
n
o
n
-
p
ar
a
m
etr
ic
m
o
d
eli
n
g
w
it
h
n
e
u
r
al
n
et
wo
r
k
m
u
lt
i
-
la
y
er
p
er
ce
p
tr
o
n
(
NN
ML
P
)
w
as
s
p
lit
in
to
t
w
o
s
et
s
:
o
n
e
co
n
t
ain
i
n
g
1
,
5
3
2
p
o
in
ts
f
o
r
m
o
d
elin
g
(
t
h
e
esti
m
atio
n
s
et)
an
d
t
h
e
o
th
er
co
n
tai
n
in
g
6
5
7
p
o
in
ts
f
o
r
v
alid
atio
n
(
th
e
test
s
e
t
)
.
T
o
v
alid
ate
th
e
r
es
u
lts
,
th
e
NN
M
L
P
m
o
d
eli
n
g
w
a
s
co
m
p
ar
ed
u
s
in
g
MSE
an
d
f
iv
e
co
r
r
elatio
n
test
s
.
Giv
e
n
th
e
lack
o
f
p
r
io
r
k
n
o
w
led
g
e
r
eg
ar
d
in
g
ap
p
r
o
p
r
iate
d
elay
n
u
m
b
er
s
an
d
m
o
d
el
s
tr
u
ct
u
r
es
f
o
r
NN
ML
P
,
a
h
eu
r
is
tic
m
e
th
o
d
w
a
s
em
p
lo
y
ed
to
d
eter
m
i
n
e
th
e
s
tr
u
ctu
r
e.
Du
r
in
g
t
h
is
tec
h
n
iq
u
e,
th
r
ee
cr
u
cial
f
ac
to
r
s
w
er
e
co
n
s
id
er
ed
:
th
e
er
r
o
r
,
th
e
s
ize
o
f
th
e
NN
s
tr
u
ctu
r
e
(
o
r
th
e
n
u
m
b
er
o
f
n
eu
r
o
n
es),
an
d
t
h
e
n
u
m
b
er
o
f
d
ela
y
s
i
g
n
al
s
D
u
e
to
th
e
r
an
d
o
m
n
e
s
s
i
n
v
o
l
v
ed
in
s
elec
ti
n
g
th
e
b
est
m
o
d
el,
a
s
s
e
s
s
i
n
g
t
h
e
f
in
a
l
co
m
p
o
n
en
t
w
a
s
cr
u
cial
i
n
d
eter
m
i
n
in
g
th
e
id
ea
l
n
u
m
b
er
o
f
d
ela
y
s
ig
n
al
s
an
d
th
e
co
n
f
i
g
u
r
atio
n
f
o
r
ea
ch
m
o
d
el.
Valid
atio
n
MSE
,
m
o
d
elli
n
g
MSE
,
an
d
co
r
r
elatio
n
test
s
w
e
r
e
u
s
ed
to
d
eter
m
i
n
e
th
e
s
elec
t
io
n
cr
iter
ia.
T
h
e
s
tu
d
y
s
tar
ted
w
it
h
a
m
o
d
el
s
tr
u
ct
u
r
e
o
f
[
2
2
1
]
,
w
h
ic
h
in
clu
d
ed
o
n
e
n
eu
r
o
n
e
i
n
t
h
e
o
u
t
p
u
t
la
y
er
,
t
w
o
n
eu
r
o
n
es i
n
t
h
e
s
ec
o
n
d
h
i
d
d
en
la
y
er
,
an
d
t
w
o
n
e
u
r
o
n
es
in
t
h
e
f
ir
s
t
h
id
d
en
la
y
er
.
T
h
e
d
ela
y
n
u
m
b
er
s
er
v
e
d
as a
r
ep
r
esen
tatio
n
o
f
t
h
e
in
p
u
t la
y
er
.
E
ig
h
t d
ela
y
s
i
g
n
a
ls
,
ei
g
h
t
n
e
u
r
o
n
es i
n
th
e
f
ir
s
t a
n
d
s
ec
o
n
d
h
id
d
en
la
y
er
s
,
an
d
o
n
e
n
eu
r
o
n
e
i
n
th
e
o
u
tp
u
t
la
y
er
w
er
e
th
e
n
u
s
ed
to
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
,
r
esu
lti
n
g
in
a
m
o
d
el
s
tr
u
ct
u
r
e
o
f
[
8
8
1
]
.
Fig
u
r
e
7
s
h
o
w
s
th
e
M
L
P
p
r
e
d
ictio
n
s
f
o
r
th
e
r
o
ll
ax
is
an
g
le,
w
i
th
t
h
e
ac
tu
al
d
ata
s
h
o
w
n
b
y
a
v
er
tical
lin
e
at
p
o
in
t
1
,
5
3
2
.
W
ith
a
n
ea
r
l
y
ze
r
o
d
if
f
er
en
ce
b
et
w
ee
n
th
e
r
ea
l
an
d
an
ticip
ated
ML
P
o
u
tp
u
t,
th
e
g
r
ap
h
s
h
o
w
s
h
o
w
w
e
ll th
e
M
L
P
tr
ac
k
s
th
e
ac
tu
a
l d
ata.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
mp
o
s
in
g
n
e
u
r
a
l n
etw
o
r
ks a
n
d
P
S
O
o
p
timiz
a
tio
n
in
t
h
e
q
u
est
fo
r
o
p
tima
l a
n
kle
-
f
o
o
t
…
(
A
n
n
is
a
Ja
ma
li
)
491
Fig
u
r
e
8
s
h
o
w
s
t
h
e
co
r
r
elatio
n
test
r
esu
lt
s
f
o
r
all
r
o
ll
ax
is
an
g
le
s
.
T
h
e
ac
cu
r
aten
ess
o
f
th
e
m
o
d
el
is
d
em
o
n
s
tr
ated
b
y
t
h
e
M
L
P
r
esu
lt
s
,
w
h
ic
h
clea
r
l
y
lie
in
s
id
e
th
e
9
5
%
co
n
f
id
en
ce
le
v
el.
T
h
is
u
n
d
er
s
co
r
es
t
h
e
u
n
b
ia
s
ed
n
atu
r
e
o
f
th
e
m
o
d
el’
s
p
r
ed
ictio
n
s
.
T
ab
le
3
d
is
p
lay
s
th
e
n
u
m
er
ical
r
esu
lts
p
er
tain
in
g
to
th
e
o
p
tim
a
l
m
o
d
el
s
tr
u
ctu
r
e
a
n
d
d
ela
y
o
f
NN
M
L
P
.
Am
o
n
g
th
e
lis
ted
c
o
n
f
i
g
u
r
atio
n
s
,
th
e
m
o
d
el
s
tr
u
c
tu
r
e
[
8
8
1
]
w
i
th
8
d
elay
s
s
ta
n
d
s
o
u
t,
s
h
o
w
ca
s
in
g
th
e
lo
w
est
M
SE
o
f
1
.
1
0
3
4
×
1
0
-
5
,
th
u
s
co
n
f
ir
m
in
g
its
s
tat
u
s
as
t
h
e
b
est
-
p
er
f
o
r
m
i
n
g
m
o
d
el.
Fig
u
r
e
7
.
T
h
e
o
u
tp
u
t a
n
d
esti
m
ated
o
u
tp
u
t o
f
r
o
ll a
x
is
a
n
g
le
(
ML
P
)
Fig
u
r
e
8
.
T
h
e
co
r
r
elatio
n
test
f
o
r
r
o
ll a
x
is
an
g
le
(
M
L
P
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
2
,
A
p
r
il
20
25
:
4
8
4
-
494
492
T
ab
le
3
.
C
o
m
p
ar
is
o
n
o
f
NN
ML
P
p
er
f
o
r
m
an
ce
M
o
d
e
l
s
t
r
u
c
t
u
r
e
D
e
l
a
y
M
S
E
C
o
r
r
e
l
a
t
i
o
n
t
e
st
[
2
2
1]
2
2
.
3
8
2
9
×
10
-
4
U
n
b
i
a
se
d
[
4
4
1
]
2
3
.
5
6
7
1
×
10
-
4
U
n
b
i
a
se
d
[
6
6
1
]
6
2
.
7
1
4
9
×
10
-
4
U
n
b
i
a
se
d
[
8
8
1
]
7
1
.
8
6
2
5
×
10
-
4
U
n
b
i
a
se
d
[
8
8
1
]
8
1
.
1
0
3
4
×
10
-
5
U
n
b
i
a
se
d
3
.
3
.
Co
m
pa
ra
t
iv
e
a
s
s
ess
m
en
t
a
nd
dis
cu
s
s
io
n
T
h
o
r
o
u
g
h
tr
ain
i
n
g
an
d
test
i
n
g
p
r
o
to
c
o
ls
,
to
g
eth
er
w
i
th
ex
te
n
s
i
v
e
co
r
r
elatio
n
s
tu
d
ie
s
,
h
av
e
b
ee
n
u
s
ed
to
v
alid
ate
P
SO
an
d
NN
ML
P
-
b
ased
m
o
d
els.
T
h
e
o
u
tco
m
e
s
o
f
th
ese
ass
e
s
s
m
en
ts
co
n
s
i
s
t
en
tl
y
s
h
o
w
th
at
t
h
e
d
if
f
er
e
n
t m
o
d
elli
n
g
ap
p
r
o
ac
h
es
tak
en
i
n
to
co
n
s
id
er
atio
n
in
th
is
s
tu
d
y
f
u
n
ctio
n
s
atis
f
ac
to
r
il
y
.
W
ith
an
em
p
h
asi
s
o
n
m
ea
n
-
s
q
u
ar
ed
er
r
o
r
an
d
co
r
r
elatio
n
test
r
esu
lts
,
T
ab
le
3
p
r
o
v
id
es
a
s
u
cc
in
c
t
o
v
er
v
i
e
w
o
f
th
e
r
elati
v
e
ef
f
ec
tiv
e
n
e
s
s
o
f
p
ar
a
m
etr
ic
a
n
d
n
o
n
-
p
ar
a
m
e
tr
ic
m
o
d
elli
n
g
te
ch
n
iq
u
es.
W
h
en
co
m
p
ar
in
g
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
t
w
o
m
o
d
elli
n
g
m
et
h
o
d
o
lo
g
ie
s
,
T
ab
le
4
d
em
o
n
s
tr
at
es
th
at
th
e
NN
ML
P
-
b
ased
n
o
n
-
p
ar
a
m
etr
i
c
ap
p
r
o
ac
h
o
f
f
er
s
a
b
etter
ap
p
r
o
x
i
m
at
io
n
to
th
e
s
y
s
te
m
r
esp
o
n
s
e
t
h
an
P
SO.
T
h
is
co
n
clu
s
io
n
i
s
co
n
s
is
te
n
t
w
it
h
ea
r
lier
s
tu
d
ies
s
h
o
w
i
n
g
th
a
t
p
ar
a
m
etr
ic
m
o
d
elli
n
g
tech
n
iq
u
es
lik
e
G
A
t
y
p
ical
l
y
p
r
o
d
u
ce
i
n
f
er
io
r
r
es
u
lts
v
er
s
u
s
n
o
n
-
p
ar
a
m
etr
ic
tech
n
iq
u
e
s
li
k
e
NN
M
L
P
[
1
3
]
.
A
d
d
itio
n
all
y
,
t
h
e
r
es
u
lts
o
f
t
h
e
co
r
r
elatio
n
test
s
h
o
w
t
h
at
NN
ML
P
p
er
f
o
r
m
s
b
etter
th
a
n
P
SO,
s
h
o
w
i
n
g
a
s
m
al
ler
m
ea
n
-
s
q
u
ar
ed
er
r
o
r
.
T
ab
le
4
.
P
er
f
o
r
m
a
n
ce
o
f
p
ar
am
etr
ic
a
n
d
n
o
n
-
p
ar
a
m
etr
ic
m
o
d
ellin
g
ap
p
r
o
ac
h
es
A
l
g
o
r
i
t
h
m
M
S
E
C
o
r
r
e
l
a
t
i
o
n
t
e
st
N
N
M
L
P
0
.
0
0
0
0
1
1
0
3
4
U
n
b
i
a
se
d
PSO
0
.
0
0
0
1
8
0
7
5
B
i
a
se
d
Ho
w
e
v
er
,
a
n
o
tab
le
ad
v
a
n
ta
g
e
o
f
P
SO
lies
in
its
f
e
w
er
p
ar
a
m
eter
s
r
eq
u
ir
i
n
g
tu
n
i
n
g
.
Desp
ite
its
ca
p
ab
ilit
y
to
f
i
n
d
th
e
b
es
t
s
o
l
u
tio
n
t
h
r
o
u
g
h
p
ar
ticle
in
ter
ac
t
io
n
,
as
d
ictated
b
y
(
5
)
,
P
SO
p
r
o
g
r
ess
es
r
elati
v
el
y
s
lo
w
l
y
to
w
ar
d
th
e
g
lo
b
al
o
p
ti
m
u
m
d
u
e
to
th
e
h
i
g
h
-
d
i
m
en
s
io
n
a
l
s
ea
r
ch
s
p
ac
e
[
2
9
]
.
Mo
r
eo
v
er
,
it
ten
d
s
to
g
en
er
at
e
s
u
b
o
p
ti
m
al
o
u
tco
m
e
s
w
h
e
n
co
n
f
r
o
n
ted
w
ith
co
m
p
le
x
a
n
d
ex
t
en
s
i
v
e
d
ataset
s
.
T
h
es
e
r
esu
lts
h
i
g
h
li
g
h
t
th
e
ef
f
ec
tiv
e
n
ess
o
f
u
s
i
n
g
NN
ML
P
to
ad
d
r
ess
d
if
f
ic
u
lt
n
o
n
li
n
ea
r
p
r
o
b
lem
s
w
h
ile
m
a
n
a
g
i
n
g
s
u
b
s
ta
n
tial
a
m
o
u
n
ts
o
f
i
n
p
u
t
d
ata.
NN
ML
P
is
a
p
r
ac
tical
t
o
o
l
f
o
r
b
o
t
h
r
esear
ch
er
s
an
d
p
r
ac
titi
o
n
er
s
ac
r
o
s
s
a
r
an
g
e
o
f
f
ield
s
b
ec
a
u
s
e
it
g
en
er
ate
s
p
r
ed
ictio
n
s
q
u
ick
l
y
a
f
ter
tr
ai
n
i
n
g
.
R
e
m
ar
k
ab
l
y
,
ev
e
n
w
it
h
s
m
aller
s
a
m
p
le
s
izes,
N
N
ML
P
m
ain
tain
s
a
co
m
p
ar
a
b
le
ac
cu
r
ac
y
r
atio
,
h
ig
h
li
g
h
ti
n
g
it
s
r
o
b
u
s
t
n
es
s
an
d
v
er
s
atili
t
y
.
4.
CO
NCLU
SI
O
N
T
h
e
m
o
d
ellin
g
o
f
an
A
F
O
u
s
i
n
g
b
o
th
P
SO
an
d
N
N
M
L
P
h
a
s
b
ee
n
d
etailed
,
en
c
o
m
p
a
s
s
i
n
g
p
ar
a
m
etr
ic
an
d
n
o
n
-
p
ar
a
m
e
tr
ic
tech
n
iq
u
e
s
.
T
h
e
AFO
m
o
v
e
s
alo
n
g
t
h
e
x
-
a
x
i
s
t
h
r
o
u
g
h
b
a
n
g
-
b
an
g
to
r
q
u
e
ap
p
licatio
n
,
w
i
th
m
o
tio
n
d
ata
co
llected
v
ia
Si
m
u
li
n
k
a
n
d
a
n
k
le
an
g
le
m
ea
s
u
r
e
d
u
s
i
n
g
an
I
MU
s
e
n
s
o
r
,
p
r
o
ce
s
s
ed
b
y
a
n
A
r
d
u
i
n
o
Me
g
a.
T
h
e
m
o
d
ellin
g
o
cc
u
r
s
w
it
h
i
n
th
e
M
A
T
L
A
B
/Si
m
u
li
n
k
en
v
ir
o
n
m
e
n
t
an
d
is
v
alid
ate
d
th
r
o
u
g
h
tr
ain
in
g
,
test
v
alid
atio
n
,
m
ea
n
-
s
q
u
ar
ed
er
r
o
r
an
aly
s
is
,
an
d
co
r
r
elatio
n
test
s
.
Fi
n
d
in
g
s
in
d
icate
t
h
at
N
N
ML
P
o
u
tp
er
f
o
r
m
s
P
SO
in
m
o
d
ellin
g
AFO
.
T
h
e
m
o
s
t
ef
f
ec
ti
v
e
NN
ML
P
m
o
d
el
w
ill
b
e
ap
p
lied
in
d
ev
elo
p
in
g
co
n
tr
o
l
s
tr
ateg
ies
to
r
eg
u
late
t
h
e
AFO
an
k
le
an
g
le,
ex
a
m
in
i
n
g
co
n
tr
o
l
s
ch
e
m
es
to
ad
d
r
ess
v
ar
y
in
g
co
n
s
tr
ai
n
ts
o
r
d
is
tu
r
b
an
ce
s
b
ef
o
r
e
th
e
ex
p
er
i
m
en
tal
p
h
a
s
e.
Fu
tu
r
e
s
tu
d
ies
co
u
ld
co
n
ce
n
tr
ate
o
n
en
h
a
n
ci
n
g
th
e
s
e
m
o
d
els
’
p
r
ec
is
io
n
a
n
d
r
esil
ie
n
ce
to
v
ar
io
u
s
e
n
v
ir
o
n
m
e
n
tal
f
ac
to
r
s
an
d
d
is
tu
r
b
an
ce
s
.
T
h
e
r
esp
o
n
s
i
v
e
n
ess
a
n
d
p
er
f
o
r
m
a
n
ce
o
f
AFO
s
y
s
te
m
s
m
a
y
also
b
e
im
p
r
o
v
ed
b
y
lo
o
k
i
n
g
at
th
e
in
te
g
r
atio
n
o
f
r
ea
l
-
ti
m
e
ad
ap
tiv
e
co
n
tr
o
l
m
et
h
o
d
s
w
i
th
NN
ML
P
m
o
d
els.
I
n
v
e
s
tig
a
tin
g
o
th
er
ad
v
a
n
ce
d
m
ac
h
i
n
e
lear
n
i
n
g
tech
n
iq
u
e
s
an
d
h
y
b
r
id
ap
p
r
o
ac
h
es
m
a
y
p
r
o
v
id
e
v
al
u
ab
le
in
s
i
g
h
ts
a
n
d
i
m
p
r
o
v
e
m
e
n
ts
.
Fin
all
y
,
co
n
d
u
cti
n
g
ex
te
n
s
i
v
e
clin
ical
tr
ials
w
ill
b
e
ess
en
t
i
al
to
v
alid
ate
th
ese
m
o
d
el
s
an
d
co
n
tr
o
l stra
te
g
ies i
n
r
ea
l
-
w
o
r
ld
s
ce
n
ar
io
s
,
e
n
s
u
r
i
n
g
t
h
eir
p
r
ac
tical
ef
f
icac
y
an
d
r
eliab
ilit
y
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
s
w
o
u
ld
lik
e
to
e
x
p
r
ess
th
eir
g
r
ati
tu
d
e
to
th
e
Min
i
s
ter
o
f
Hig
h
er
E
d
u
ca
tio
n
Ma
la
y
s
ia
(
MO
HE
)
an
d
U
n
iv
er
s
iti
Ma
la
y
s
ia
Sar
a
w
ak
(
UNI
M
A
S)
f
o
r
f
u
n
d
i
n
g
a
n
d
p
r
o
v
id
in
g
f
ac
ilit
ies
to
co
n
d
u
ct
t
h
i
s
s
tu
d
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
mp
o
s
in
g
n
e
u
r
a
l n
etw
o
r
ks a
n
d
P
S
O
o
p
timiz
a
tio
n
in
t
h
e
q
u
est
fo
r
o
p
tima
l a
n
kle
-
f
o
o
t
…
(
A
n
n
is
a
Ja
ma
li
)
493
RE
F
E
R
E
NC
E
S
[
1
]
A
.
M
.
Jo
sh
u
a
,
Z
.
M
i
sr
i
,
S
.
R
a
i
,
a
n
d
V
.
H
.
N
a
m
p
o
o
t
h
i
r
i
,
“
S
t
r
o
k
e
,
”
i
n
P
h
y
s
i
o
t
h
e
ra
p
y
f
o
r
A
d
u
l
t
N
e
u
r
o
l
o
g
i
c
a
l
C
o
n
d
i
t
i
o
n
s
,
S
i
n
g
a
p
o
r
e
:
S
p
r
i
n
g
e
r
N
a
t
u
r
e
S
i
n
g
a
p
o
r
e
,
2
0
2
2
,
p
p
.
1
8
5
–
307
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
19
-
0
2
0
9
-
3
_
3
.
[
2
]
M
.
V
a
l
i
,
V
.
P
e
t
r
o
v
i
ć
,
S
.
B
o
e
r
sma,
J.
W
.
v
a
n
W
i
n
g
e
r
d
e
n
,
L
.
Y
.
P
a
o
,
a
n
d
M
.
K
ü
h
n
,
“
A
d
j
o
i
n
t
-
b
a
se
d
mo
d
e
l
p
r
e
d
i
c
t
i
v
e
c
o
n
t
r
o
l
f
o
r
o
p
t
i
m
a
l
e
n
e
r
g
y
e
x
t
r
a
c
t
i
o
n
i
n
w
a
k
e
d
w
i
n
d
f
a
r
ms,
”
C
o
n
t
r
o
l
E
n
g
i
n
e
e
ri
n
g
Pr
a
c
t
i
c
e
,
v
o
l
.
8
4
,
p
p
.
4
8
–
6
2
,
M
a
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
n
e
n
g
p
r
a
c
.
2
0
1
8
.
1
1
.
0
0
5
.
[
3
]
S
.
P
r
e
n
t
o
n
,
K
.
L
.
H
o
l
l
a
n
d
s,
a
n
d
L
.
P
.
J.
K
e
n
n
e
y
,
“
F
u
n
c
t
i
o
n
a
l
e
l
e
c
t
r
i
c
a
l
st
i
m
u
l
a
t
i
o
n
v
e
r
su
s
a
n
k
l
e
f
o
o
t
o
r
t
h
o
se
s
f
o
r
f
o
o
t
-
d
r
o
p
:
A
m
e
t
a
-
a
n
a
l
y
si
s o
f
o
r
t
h
o
t
i
c
e
f
f
e
c
t
s,
”
J
o
u
rn
a
l
o
f
Re
h
a
b
i
l
i
t
a
t
i
o
n
Me
d
i
c
i
n
e
,
v
o
l
.
4
8
,
n
o
.
8
,
p
p
.
6
4
6
–
6
5
6
,
2
0
1
6
,
d
o
i
:
1
0
.
2
3
4
0
/
1
6
5
0
1
9
7
7
-
2
1
3
6
.
[
4
]
C
.
P
e
i
sh
u
n
,
Z
.
H
a
i
w
a
n
g
,
L
.
T
a
o
t
a
o
,
G
.
H
o
n
g
l
i
,
M
.
Y
u
,
a
n
d
Z
.
W
a
n
r
o
n
g
,
“
C
h
a
n
g
e
s
i
n
G
a
i
t
C
h
a
r
a
c
t
e
r
i
st
i
c
s
o
f
S
t
r
o
k
e
P
a
t
i
e
n
t
s
w
i
t
h
F
o
o
t
D
r
o
p
a
f
t
e
r
t
h
e
C
o
m
b
i
n
a
t
i
o
n
T
r
e
a
t
me
n
t
o
f
F
o
o
t
D
r
o
p
S
t
i
m
u
l
a
t
o
r
a
n
d
M
o
v
i
n
g
T
r
e
a
d
mi
l
l
T
r
a
i
n
i
n
g
,
”
Ne
u
ra
l
P
l
a
st
i
c
i
t
y
,
p
p
.
1
–
5
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
9
4
8
0
9
5
7
.
[
5
]
N
.
S
h
a
h
a
n
d
K
.
V
e
mu
l
a
p
a
l
l
i
,
“
F
o
o
t
D
r
o
p
S
e
c
o
n
d
a
r
y
t
o
A
n
k
l
e
S
p
r
a
i
n
i
n
T
w
o
P
a
e
d
i
a
t
r
i
c
P
a
t
i
e
n
t
s:
A
C
a
se
S
e
r
i
e
s,
”
C
u
re
u
s
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
7
7
5
9
/
c
u
r
e
u
s
.
2
6
3
9
8
.
[
6
]
O
.
El
d
i
r
d
i
r
y
,
R
.
Z
a
i
e
r
,
A
.
A
l
-
Y
a
h
me
d
i
,
I
.
B
a
h
a
d
u
r
,
a
n
d
F
.
A
l
n
a
j
j
a
r
,
“
M
o
d
e
l
i
n
g
o
f
a
b
i
p
e
d
r
o
b
o
t
f
o
r
i
n
v
e
st
i
g
a
t
i
n
g
f
o
o
t
d
r
o
p
u
si
n
g
M
A
TL
A
B
/
S
i
mu
l
i
n
k
,
”
S
i
m
u
l
a
t
i
o
n
M
o
d
e
l
l
i
n
g
Pr
a
c
t
i
c
e
a
n
d
T
h
e
o
ry
,
O
c
t
.
2
0
2
0
,
d
o
i
:
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
i
mp
a
t
.
2
0
2
0
.
1
0
2
0
7
2
.
[
7
]
H
.
M
.
N
a
z
h
a
,
S
.
S
z
á
v
a
i
,
M
.
A
.
D
a
r
w
i
c
h
,
a
n
d
D
.
J
u
h
r
e
,
“
P
a
ss
i
v
e
A
r
t
i
c
u
l
a
t
e
d
a
n
d
N
o
n
-
A
r
t
i
c
u
l
a
t
e
d
A
n
k
l
e
–
F
o
o
t
O
r
t
h
o
se
s
f
o
r
G
a
i
t
R
e
h
a
b
i
l
i
t
a
t
i
o
n
:
A
N
a
r
r
a
t
i
v
e
R
e
v
i
e
w
,
”
H
e
a
l
t
h
c
a
r
e
(
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
1
,
n
o
.
7
,
p
p
.
1
–
1
8
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
h
e
a
l
t
h
c
a
r
e
1
1
0
7
0
9
4
7
.
[
8
]
J.
L
a
i
d
l
e
r
,
“
T
h
e
i
mp
a
c
t
o
f
a
n
k
l
e
-
f
o
o
t
o
r
t
h
o
se
s
o
n
b
a
l
a
n
c
e
i
n
o
l
d
e
r
a
d
u
l
t
s:
A
sco
p
i
n
g
r
e
v
i
e
w
,
”
C
a
n
a
d
i
a
n
Pro
s
t
h
e
t
i
c
s
a
n
d
O
rt
h
o
t
i
c
s
J
o
u
rn
a
l
,
v
o
l
.
4
,
n
o
.
1
,
J
a
n
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
1
3
7
/
c
p
o
j
.
v
4
i
1
.
3
5
1
3
2
.
[
9
]
P
.
F
o
n
se
c
a
e
t
a
l
.
,
“
D
o
e
s
g
a
i
t
w
i
t
h
a
n
a
n
k
l
e
f
o
o
t
o
r
t
h
o
si
s
i
mp
r
o
v
e
o
r
c
o
mp
r
o
mi
se
mi
n
i
m
u
m
f
o
o
t
c
l
e
a
r
a
n
c
e
?
,
”
S
e
n
so
rs
,
v
o
l
.
2
1
,
n
o
.
2
3
,
p
p
.
1
–
9
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
1
2
3
8
0
8
9
.
[
1
0
]
T
.
K
o
b
a
y
a
sh
i
,
F
.
G
a
o
,
N
.
L
e
c
u
r
si
,
K
.
B
.
F
o
r
e
man
,
a
n
d
M
.
S
.
O
r
e
n
d
u
r
f
f
,
“
Ef
f
e
c
t
o
f
sh
o
e
s
o
n
s
t
i
f
f
n
e
ss
a
n
d
e
n
e
r
g
y
e
f
f
i
c
i
e
n
c
y
o
f
a
n
k
l
e
-
f
o
o
t
o
r
t
h
o
si
s:
B
e
n
c
h
t
e
st
i
n
g
a
n
a
l
y
si
s,
”
J
o
u
r
n
a
l
o
f
A
p
p
l
i
e
d
B
i
o
m
e
c
h
a
n
i
c
s
,
v
o
l
.
3
3
,
n
o
.
6
,
p
p
.
4
6
0
–
4
6
3
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
2
3
/
j
a
b
.
2
0
1
6
-
0
3
0
9
.
[
1
1
]
M
.
Y
a
mamo
t
o
,
K
.
S
h
i
m
a
t
a
n
i
,
H
.
O
k
a
n
o
,
a
n
d
H
.
T
a
k
e
mu
r
a
,
“
Ef
f
e
c
t
o
f
A
n
k
l
e
-
F
o
o
t
O
r
t
h
o
si
s
S
t
i
f
f
n
e
ss
o
n
M
u
scl
e
F
o
r
c
e
d
u
r
i
n
g
G
a
i
t
t
h
r
o
u
g
h
M
e
c
h
a
n
i
c
a
l
T
e
st
i
n
g
a
n
d
G
a
i
t
S
i
m
u
l
a
t
i
o
n
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
9
8
0
3
9
–
9
8
0
4
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
9
5
5
3
0
.
[
1
2
]
S
.
R
a
me
z
a
n
i
,
B
.
B
r
a
d
y
,
H
.
K
i
m,
M
.
K
.
C
a
r
r
o
l
l
,
a
n
d
H
.
C
h
o
i
,
“
A
M
e
t
h
o
d
f
o
r
Q
u
a
n
t
i
f
y
i
n
g
S
t
i
f
f
n
e
ss
o
f
A
n
k
l
e
-
F
o
o
t
O
r
t
h
o
se
s
T
h
r
o
u
g
h
M
o
t
i
o
n
C
a
p
t
u
r
e
a
n
d
O
p
t
i
mi
z
a
t
i
o
n
A
l
g
o
r
i
t
h
m,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
5
8
9
3
0
–
5
8
9
3
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
7
8
7
0
1
.
[
1
3
]
A
.
C
o
c
c
i
a
e
t
a
l
.
,
“
B
i
o
me
c
h
a
n
i
c
a
l
mo
d
e
l
l
i
n
g
f
o
r
q
u
a
n
t
i
t
a
t
i
v
e
a
sse
ssm
e
n
t
o
f
g
a
i
t
k
i
n
e
ma
t
i
c
s
i
n
d
r
o
p
f
o
o
t
p
a
t
i
e
n
t
s
w
i
t
h
a
n
k
l
e
f
o
o
t
o
r
t
h
o
si
s,
”
i
n
2
0
2
2
I
EE
E
I
n
t
e
rn
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
Me
d
i
c
a
l
Me
a
s
u
re
m
e
n
t
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
Me
Me
A
2
0
2
2
-
C
o
n
f
e
re
n
c
e
Pro
c
e
e
d
i
n
g
s
,
I
EEE,
Ju
n
.
2
0
2
2
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
M
e
M
e
A
5
4
9
9
4
.
2
0
2
2
.
9
8
5
6
5
4
9
.
[
1
4
]
C
.
Z
h
o
u
,
Z
.
Y
a
n
g
,
K
.
L
i
,
a
n
d
X
.
Y
e
,
“
R
e
se
a
r
c
h
a
n
d
D
e
v
e
l
o
p
me
n
t
o
f
A
n
k
l
e
–
F
o
o
t
O
r
t
h
o
s
e
s:
A
R
e
v
i
e
w
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
1
7
,
p
p
.
1
–
1
5
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
2
1
7
6
5
9
6
.
[
1
5
]
W
.
W
u
,
H
.
Z
h
o
u
,
Y
.
G
u
o
,
Y
.
W
u
,
a
n
d
J.
G
u
o
,
“
P
e
g
-
in
-
h
o
l
e
a
sse
mb
l
y
i
n
l
i
v
e
-
l
i
n
e
mai
n
t
e
n
a
n
c
e
b
a
se
d
o
n
g
e
n
e
r
a
t
i
v
e
map
p
i
n
g
a
n
d
se
a
r
c
h
i
n
g
n
e
t
w
o
r
k
,
”
Ro
b
o
t
i
c
s
a
n
d
A
u
t
o
n
o
m
o
u
s
S
y
st
e
m
s
,
v
o
l
.
1
4
3
,
p
p
.
1
–
1
1
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
o
b
o
t
.
2
0
2
1
.
1
0
3
7
9
7
.
[
1
6
]
M
.
H
a
me
d
a
n
i
,
V
.
P
r
a
d
a
,
P
.
T
o
g
n
e
t
t
i
,
V
.
L
e
o
n
i
,
a
n
d
A
.
S
c
h
e
n
o
n
e
,
“
R
o
b
o
t
-
a
ssi
st
e
d
a
n
d
t
r
a
d
i
t
i
o
n
a
l
i
n
t
e
n
s
i
v
e
r
e
h
a
b
i
l
i
t
a
t
i
o
n
t
h
e
r
a
p
y
i
n
t
h
e
t
r
e
a
t
me
n
t
o
f
p
o
st
-
a
c
u
t
e
st
r
o
k
e
p
a
t
i
e
n
t
:
t
h
e
e
x
p
e
r
i
e
n
c
e
o
f
a
st
a
n
d
a
r
d
r
e
h
a
b
i
l
i
t
a
t
i
o
n
w
a
r
d
,
”
N
e
u
r
o
l
o
g
i
c
a
l
S
c
i
e
n
c
e
s
,
v
o
l
.
4
3
,
n
o
.
6
,
p
p
.
3
9
9
9
–
4
0
0
1
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
0
7
2
-
0
2
2
-
0
6
0
4
1
-
8.
[
1
7
]
S
.
F
a
t
o
n
e
,
W
.
B
.
Jo
h
n
so
n
,
a
n
d
K
.
T
u
c
k
e
r
.,
“
A
t
h
r
e
e
-
d
i
me
n
s
i
o
n
a
l
mo
d
e
l
t
o
a
sse
ss
t
h
e
e
f
f
e
c
t
o
f
a
n
k
l
e
j
o
i
n
t
a
x
i
s
mi
sal
i
g
n
me
n
t
s
i
n
a
n
k
l
e
-
f
o
o
t
o
r
t
h
o
se
s,
”
Pr
o
st
h
e
t
i
c
s
a
n
d
O
rt
h
o
t
i
c
s
I
n
t
e
r
n
a
t
i
o
n
a
l
,
v
o
l
.
4
0
,
n
o
.
2
,
p
p
.
2
4
0
–
2
4
6
,
2
0
1
6
,
d
o
i
:
1
0
.
1
1
7
7
/
0
3
0
9
3
6
4
6
1
3
5
1
6
4
8
8
.
[
1
8
]
M
.
S
r
e
e
n
i
v
a
sa
,
M
.
M
i
l
l
a
r
d
,
M
.
F
e
l
i
s,
K
.
M
o
mb
a
u
r
,
a
n
d
S
.
I
.
W
o
l
f
,
“
O
p
t
i
m
a
l
c
o
n
t
r
o
l
b
a
se
d
s
t
i
f
f
n
e
ss
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
a
n
a
n
k
l
e
-
f
o
o
t
o
r
t
h
o
si
s
u
s
i
n
g
a
p
r
e
d
i
c
t
i
v
e
w
a
l
k
i
n
g
mo
d
e
l
,
”
Fr
o
n
t
i
e
rs
i
n
C
o
m
p
u
t
a
t
i
o
n
a
l
N
e
u
r
o
sc
i
e
n
c
e
,
v
o
l
.
1
1
,
A
p
r
.
2
0
1
7
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
c
o
m.2
0
1
7
.
0
0
0
2
3
.
[
1
9
]
M
.
R
o
se
n
b
e
r
g
a
n
d
K
.
M
.
S
t
e
e
l
e
,
“
S
i
mu
l
a
t
e
d
i
mp
a
c
t
s
o
f
a
n
k
l
e
f
o
o
t
o
r
t
h
o
se
s
o
n
mu
s
c
l
e
d
e
man
d
a
n
d
r
e
c
r
u
i
t
me
n
t
i
n
t
y
p
i
c
a
l
l
y
d
e
v
e
l
o
p
i
n
g
c
h
i
l
d
r
e
n
a
n
d
c
h
i
l
d
r
e
n
w
i
t
h
c
e
r
e
b
r
a
l
p
a
l
sy
a
n
d
c
r
o
u
c
h
g
a
i
t
,
”
PL
o
S
O
N
E
,
v
o
l
.
1
2
,
n
o
.
7
,
2
0
1
7
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
1
8
0
2
1
9
.
[
2
0
]
A
.
K
.
H
e
g
a
r
t
y
,
A
.
J.
P
e
t
r
e
l
l
a
,
M
.
J.
K
u
r
z
,
a
n
d
A
.
K
.
S
i
l
v
e
r
man
,
“
Ev
a
l
u
a
t
i
n
g
t
h
e
e
f
f
e
c
t
s
o
f
a
n
k
l
e
-
f
o
o
t
o
r
t
h
o
si
s
me
c
h
a
n
i
c
a
l
p
r
o
p
e
r
t
y
a
ssu
m
p
t
i
o
n
s
o
n
g
a
i
t
si
m
u
l
a
t
i
o
n
m
u
scl
e
f
o
r
c
e
r
e
su
l
t
s,
”
J
o
u
r
n
a
l
o
f
B
i
o
m
e
c
h
a
n
i
c
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
3
9
,
n
o
.
3
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
1
5
/
1
.
4
0
3
5
4
7
2
.
[
2
1
]
J.
T
.
B
r
y
so
n
,
X
.
J
i
n
,
a
n
d
S
.
K
.
A
g
r
a
w
a
l
,
“
O
p
t
i
m
a
l
d
e
si
g
n
o
f
c
a
b
l
e
-
d
r
i
v
e
n
ma
n
i
p
u
l
a
t
o
r
s
u
s
i
n
g
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
Me
c
h
a
n
i
sm
s
a
n
d
R
o
b
o
t
i
c
s
,
v
o
l
.
8
,
n
o
.
4
,
2
0
1
6
,
d
o
i
:
1
0
.
1
1
1
5
/
1
.
4
0
3
2
1
0
3
.
[
2
2
]
Y
.
J.
C
h
o
o
,
J.
K
.
K
i
m,
J.
H
.
K
i
m,
M
.
C
.
C
h
a
n
g
,
a
n
d
D
.
P
a
r
k
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
a
l
y
si
s t
o
p
r
e
d
i
c
t
t
h
e
n
e
e
d
f
o
r
a
n
k
l
e
f
o
o
t
o
r
t
h
o
si
s
i
n
p
a
t
i
e
n
t
s w
i
t
h
s
t
r
o
k
e
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
1
,
n
o
.
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
1
-
8
7
8
2
6
-
3.
[
2
3
]
D
.
A
d
i
p
u
t
r
a
e
t
a
l
.
,
“
A
r
e
v
i
e
w
o
n
t
h
e
c
o
n
t
r
o
l
o
f
t
h
e
me
c
h
a
n
i
c
a
l
p
r
o
p
e
r
t
i
e
s
o
f
A
n
k
l
e
F
o
o
t
O
r
t
h
o
si
s
f
o
r
g
a
i
t
a
ssi
s
t
a
n
c
e
,
”
Ac
t
u
a
t
o
rs
,
v
o
l
.
8
,
n
o
.
1
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
a
c
t
8
0
1
0
0
1
0
.
[
2
4
]
I
.
Z
.
M
.
D
a
r
u
s
a
n
d
M
.
O
.
T
o
k
h
i
,
“
P
a
r
a
me
t
r
i
c
a
n
d
n
o
n
-
p
a
r
a
me
t
r
i
c
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
a
t
w
o
d
i
me
n
s
i
o
n
a
l
f
l
e
x
i
b
l
e
st
r
u
c
t
u
r
e
,
”
J
o
u
rn
a
l
o
f
L
o
w
Fre
q
u
e
n
c
y
N
o
i
s
e
V
i
b
ra
t
i
o
n
a
n
d
Ac
t
i
v
e
C
o
n
t
r
o
l
,
v
o
l
.
2
5
,
n
o
.
2
,
p
p
.
1
1
9
–
1
4
3
,
2
0
0
6
,
d
o
i
:
1
0
.
1
2
6
0
/
0
2
6
3
0
9
2
0
6
7
7
8
4
9
4
2
7
4
.
[
2
5
]
M
.
S
.
A
mi
r
i
,
R
.
R
a
ml
i
,
M
.
F
.
I
b
r
a
h
i
m
,
D
.
A
.
W
a
h
a
b
,
a
n
d
N
.
A
l
i
man
,
“
A
d
a
p
t
i
v
e
p
a
r
t
i
c
l
e
sw
a
r
m o
p
t
i
mi
z
a
t
i
o
n
o
f
p
i
d
g
a
i
n
t
u
n
i
n
g
f
o
r
l
o
w
e
r
-
l
i
mb
h
u
ma
n
e
x
o
sk
e
l
e
t
o
n
i
n
v
i
r
t
u
a
l
e
n
v
i
r
o
n
me
n
t
,
”
M
a
t
h
e
m
a
t
i
c
s
,
v
o
l
.
8
,
n
o
.
1
1
,
p
p
.
1
–
1
6
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
m
a
t
h
8
1
1
2
0
4
0
.
[
2
6
]
D
.
Ji
n
,
Y
.
L
i
u
,
X
.
M
a
,
a
n
d
Q
.
S
o
n
g
,
“
L
o
n
g
t
i
me
p
r
e
d
i
c
t
i
o
n
o
f
h
u
ma
n
l
o
w
e
r
l
i
mb
mo
v
e
me
n
t
b
a
se
d
o
n
I
P
S
O
-
B
P
N
N
,
”
J
o
u
r
n
a
l
o
f
Ph
y
s
i
c
s:
C
o
n
f
e
r
e
n
c
e
S
e
ri
e
s
,
2
0
2
1
,
v
o
l
.
1
8
6
5
,
n
o
.
4
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
8
6
5
/
4
/
0
4
2
0
9
9
.
[
2
7
]
A
.
Jama
l
i
,
I
.
Z
.
M
.
M
.
D
a
r
u
s,
P
.
M
.
S
a
mi
n
,
a
n
d
M
.
O
.
T
o
k
h
i
,
“
I
n
t
e
l
l
i
g
e
n
t
mo
d
e
l
i
n
g
o
f
d
o
u
b
l
e
l
i
n
k
f
l
e
x
i
b
l
e
r
o
b
o
t
i
c
man
i
p
u
l
a
t
o
r
u
si
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
J
o
u
rn
a
l
o
f
Vi
b
r
o
e
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
,
n
o
.
2
,
p
p
.
1
0
2
1
–
1
0
3
4
,
2
0
1
8
,
d
o
i
:
1
0
.
2
1
5
9
5
/
j
v
e
.
2
0
1
7
.
1
8
5
7
5
.
[
2
8
]
G
.
C
a
se
l
l
a
a
n
d
R
.
L
.
B
e
r
g
e
r
,
S
t
a
t
i
st
i
c
a
l
I
n
f
e
r
e
n
c
e
,
2
n
d
e
d
.
P
a
c
i
f
i
c
G
r
o
v
e
,
C
A
,
U
S
A
:
D
u
x
b
u
r
y
,
2
0
0
2
.
[
2
9
]
A
.
G
.
G
a
d
,
“
P
a
r
t
i
c
l
e
S
w
a
r
m
O
p
t
i
mi
z
a
t
i
o
n
A
l
g
o
r
i
t
h
m
a
n
d
I
t
s
A
p
p
l
i
c
a
t
i
o
n
s:
A
S
y
st
e
mat
i
c
R
e
v
i
e
w
,
”
Arc
h
i
v
e
s
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
Me
t
h
o
d
s
i
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
9
,
n
o
.
5
,
p
p
.
2
5
3
1
–
2
5
6
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
8
3
1
-
0
2
1
-
0
9
6
9
4
-
4.
Evaluation Warning : The document was created with Spire.PDF for Python.