T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t
2020
,
p
p
.
1
9
5
4
~
1
9
6
1
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Ke
m
e
n
r
is
te
k
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
KA
.
v
1
8
i4
.
1
5
2
0
0
1954
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
Strategy
t
o
de
ter
m
ine
t
h
e f
o
o
t
pla
ntar cen
ter
o
f
pre
ss
ure
o
f
a
perso
n t
hro
u
g
h deep
lea
rni
ng
neura
l net
w
o
rk
s
H
enry
H
er
ná
nd
ez
M
a
rt
ínez
1
,
H
o
l
m
a
n M
o
ntie
l A
riza
2
,
L
uz
Andrea
G
a
v
iria
R.
3
1,
2
F
a
c
u
lt
a
d
T
e
c
n
o
l
ó
g
ica
,
Un
iv
e
rsid
a
d
Distrit
a
l
F
ra
n
c
isc
o
Jo
sé
d
e
Ca
ld
a
s,
Co
l
o
m
b
ia
3
Un
iv
e
rsid
a
d
In
ter
n
a
c
io
n
a
l
d
e
la
Rio
ja,
S
p
a
i
n
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
8
,
2
0
2
0
R
ev
i
s
ed
Ma
r
2
2
,
2
0
2
0
A
cc
ep
ted
Ma
r
1
2
,
2
0
2
0
S
o
m
e
c
a
se
s
t
u
d
i
e
s
t
r
e
a
t
e
d
b
y
p
h
y
s
i
o
t
h
e
r
a
p
i
s
t
s
o
r
o
r
t
h
o
p
e
d
i
s
t
s
to
m
e
a
s
u
r
e
t
h
e
a
l
i
g
n
m
e
n
t
o
f
t
h
e
l
o
w
e
r
e
x
t
re
m
i
t
i
e
s
d
u
r
i
n
g
a
g
a
i
t
c
y
c
l
e
a
r
e
b
a
s
e
d
o
n
e
m
p
i
r
i
c
a
l
m
e
t
h
o
d
s
o
f
v
i
s
u
a
l
o
b
s
e
rv
a
t
i
o
n
.
T
h
i
s
m
e
t
h
o
d
o
l
o
g
y
d
o
e
s
n
o
t
g
u
a
r
a
n
t
e
e
t
o
t
a
l
s
u
c
c
e
s
s
,
s
i
n
c
e
i
t
d
e
p
e
n
d
s
o
n
t
h
e
e
x
p
e
r
i
e
n
c
e
o
f
t
h
e
s
p
e
c
i
a
l
i
s
t,
w
h
a
t
c
a
n
c
a
u
s
e
i
rr
e
v
e
rs
i
b
l
e
d
a
m
a
g
e
t
o
p
a
t
i
e
n
t
s
,
s
u
c
h
a
s
:
h
i
p
d
i
s
p
l
a
c
e
m
e
n
t
,
w
e
a
r
a
n
d
o
v
e
r
l
o
a
d
o
f
t
h
e
j
o
i
n
t
s
o
f
a
s
i
n
g
le
lo
w
e
r
l
im
b
.
A
l
t
h
o
u
g
h
,
t
h
i
s
p
r
o
b
l
e
m
h
a
s
b
e
e
n
a
d
d
r
e
s
se
d
i
n
t
h
e
i
n
v
e
s
t
i
g
a
t
i
o
n
b
y
m
e
a
n
s
o
f
d
e
v
ic
e
s
im
p
lem
e
n
t
a
t
i
o
n
w
i
t
h
s
e
n
s
o
r
s
o
r
m
e
t
h
o
d
s
o
f
p
r
o
c
e
s
s
i
n
g
s
e
q
u
e
n
c
e
s
o
f
im
a
g
e
s
a
n
d
v
i
d
e
o
s
,
th
i
s
t
o
p
i
c
i
s
s
t
i
l
l
u
n
d
e
r
i
n
v
e
s
t
ig
a
t
i
o
n
b
e
c
a
u
se
th
e
c
u
r
r
e
n
t
m
e
t
h
o
d
s
d
e
p
e
n
d
o
n
m
a
n
y
e
x
t
e
r
n
a
l
e
l
e
m
e
n
t
s
a
n
d
d
a
t
a
g
iv
e
n
b
y
a
n
e
x
p
e
r
t
i
n
t
h
e
a
re
a
.
T
h
e
re
f
o
r
e
,
t
h
i
s
p
a
p
e
r
p
r
o
p
o
s
e
s
a
p
a
r
t
i
a
l
s
o
l
u
t
i
o
n
t
o
t
h
i
s
p
r
o
b
l
e
m
b
y
sy
s
tem
a
ti
z
i
n
g
t
h
e
e
x
p
e
r
i
e
n
c
e
o
f
a
s
p
e
c
ia
l
i
s
t
t
h
r
o
u
g
h
a
c
o
m
p
u
t
a
t
i
o
n
a
l
l
e
a
r
n
i
n
g
m
e
t
h
o
d
.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
C
las
s
i
f
ier
C
o
m
p
u
tatio
n
al
lear
n
i
n
g
m
et
h
o
d
Dee
p
lear
n
in
g
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
:
Ho
l
m
an
Mo
n
tiel
A
r
iza
Facu
ltad
T
ec
n
o
ló
g
ica,
Un
i
v
er
s
id
ad
Dis
tr
ital Fr
a
n
cisc
o
J
o
s
é
d
e
C
ald
as,
C
ll 6
8
D
B
is
A
S
u
r
No
.
4
9
F
–
7
0
,
B
o
g
o
tá
D.
C
,
C
o
lo
m
b
ia.
E
m
ail:
h
m
o
n
tiela
@
u
d
is
tr
ital.e
d
u
.
co
1.
I
NT
RO
D
UCT
I
O
N
Gait
an
al
y
s
i
s
ar
e
tech
n
iq
u
es
t
h
at
ar
e
b
ased
o
n
th
e
o
b
s
er
v
ati
o
n
o
f
co
n
ti
n
u
o
u
s
p
atter
n
s
o
f
m
o
v
e
m
e
n
t.
T
h
ese
p
atter
n
s
ar
e
co
m
p
ar
ed
w
it
h
a
m
o
v
e
m
e
n
t
p
atter
n
co
n
s
id
er
ed
n
o
r
m
al
to
d
eter
m
i
n
e
p
o
s
s
ib
le
p
ath
o
lo
g
ie
s
.
No
r
m
a
ll
y
,
t
h
ese
m
o
v
e
m
e
n
t
p
atter
n
s
ar
e
k
n
o
w
n
a
s
g
ait
c
y
cle
s
a
n
d
h
a
v
e
th
r
ee
d
if
f
er
en
t
p
h
a
s
es.
T
h
e
f
ir
s
t
p
h
a
s
e
is
s
u
p
p
o
r
t
an
d
co
n
s
is
t
s
o
f
s
u
p
p
o
r
tin
g
t
h
e
h
ee
l
o
n
t
h
e
g
r
o
u
n
d
,
th
e
s
ec
o
n
d
is
w
h
e
n
t
h
e
p
er
s
o
n
i
s
ab
o
u
t
to
tak
e
o
f
f
th
e
to
es
o
f
t
h
e
f
lo
o
r
an
d
,
f
in
all
y
,
t
h
e
t
h
ir
d
p
h
ase
is
w
h
e
n
th
e
p
er
s
o
n
li
f
ts
t
h
e
f
o
o
t
o
f
t
h
e
g
r
o
u
n
d
,
s
u
p
p
o
r
ts
th
e
o
th
er
f
o
o
t
an
d
s
tar
ts
th
e
c
y
cle
ag
a
in
[
1
-
3
]
.
T
h
e
g
ait
a
n
a
l
y
s
i
s
is
co
m
p
le
m
e
n
ted
b
y
a
s
t
ab
ilit
y
a
n
al
y
s
is
in
a
p
er
s
o
n
's
b
i
-
p
ed
estal
p
o
s
itio
n
,
w
h
ich
allo
w
s
d
eter
m
i
n
in
g
th
e
p
la
n
tar
ce
n
ter
o
f
p
r
ess
u
r
e
ce
n
ter
(
C
OP
)
an
d
th
e
p
atien
t
's
ce
n
ter
o
f
m
as
s
(
C
OM
)
.
T
h
e
o
b
j
ec
tiv
e
o
f
th
is
an
al
y
s
is
i
s
to
d
eter
m
i
n
e
th
e
c
h
an
g
e
p
r
o
d
u
ce
d
b
y
th
e
w
ei
g
h
t
a
n
d
m
o
r
p
h
o
lo
g
y
o
f
th
e
lo
w
er
ex
tr
e
m
it
ies,
o
n
th
e
b
o
d
y
b
alan
ce
,
in
o
r
d
er
to
in
cr
ea
s
e
th
e
a
m
o
u
n
t
o
f
av
ailab
le
d
ata
o
b
tain
ed
d
u
r
in
g
a
g
ait
an
al
y
s
is
[
4
,
5
]
.
A
lt
h
o
u
g
h
,
t
h
e
w
a
y
s
o
f
k
ee
p
in
g
tr
ac
k
o
f
th
e
r
e
s
u
l
ts
d
u
r
in
g
g
ait
an
al
y
s
is
ar
e
d
o
n
e
m
a
n
u
all
y
,
to
r
ed
u
ce
th
e
m
ar
g
i
n
o
f
er
r
o
r
,
tech
n
iq
u
es
h
a
v
e
b
ee
n
d
e
v
elo
p
ed
th
at
s
y
s
te
m
a
tize
t
h
is
p
r
o
ce
s
s
[
6
]
.
So
m
e
o
f
t
h
e
m
ar
e
b
ased
o
n
s
o
f
t
w
ar
e
an
d
i
m
p
le
m
en
t
p
h
y
s
ica
l
s
e
n
s
o
r
s
o
r
p
r
o
ce
s
s
i
n
g
o
f
i
m
a
g
es
a
n
d
v
id
eo
s
[
7
]
.
I
n
th
e
f
ir
s
t
ca
s
e,
a
g
r
o
u
p
o
f
s
en
s
o
r
s
is
co
n
n
ec
te
d
to
a
d
ev
ice
th
at
is
n
o
r
m
all
y
a
co
m
p
u
ter
a
n
d
an
atte
m
p
t i
s
m
ad
e
to
r
e
-
co
n
s
tr
u
c
t
a
s
ig
n
al
f
r
o
m
m
ea
s
u
r
e
m
e
n
t
s
.
T
h
e
r
esu
lts
o
b
tain
ed
ar
e
co
m
p
ar
ed
ag
ain
s
t
a
r
ec
o
r
d
ed
s
ig
n
al
f
r
o
m
a
p
atien
t
w
i
th
p
ar
am
eter
s
co
n
s
id
er
ed
n
o
r
m
al
o
r
co
n
tr
o
l
an
d
th
e
d
ev
iatio
n
o
f
t
h
e
o
b
tain
ed
s
ig
n
al
r
e
g
ar
d
in
g
t
h
e
co
n
tr
o
l
s
ig
n
al
is
a
n
al
y
ze
d
to
d
eter
m
i
n
e
a
p
o
s
s
ib
le
p
at
h
o
lo
g
y
[
8
]
.
A
n
alo
g
o
u
s
l
y
,
i
n
th
e
an
al
y
s
is
b
ased
o
n
i
m
a
g
e
a
n
d
v
id
eo
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
S
tr
a
teg
y
to
d
etermin
e
th
e
fo
o
t
p
la
n
ta
r
ce
n
ter o
f p
r
ess
u
r
e
o
f a
p
ers
o
n
…
(
Hen
r
y
Her
n
á
n
d
ez Ma
r
tín
ez
)
1955
p
r
o
ce
s
s
in
g
,
a
s
ig
n
al
a
s
s
o
ciat
ed
w
it
h
t
h
e
m
o
v
e
m
e
n
t
o
f
th
e
s
u
b
j
ec
t
is
r
ec
o
n
s
tr
u
cted
f
r
o
m
th
e
ca
p
t
u
r
e
o
f
a
s
eq
u
en
ce
o
f
i
m
a
g
es
a
n
d
id
en
ti
f
icatio
n
o
f
r
eg
io
n
s
o
f
i
n
ter
e
s
t,
an
d
in
t
h
e
s
a
m
e
w
a
y
i
t
is
c
o
m
p
ar
ed
w
it
h
o
th
er
da
ta
o
f
co
n
tr
o
l [
9
]
.
Un
li
k
e
th
e
s
e
tech
n
iq
u
e
s
,
th
e
s
tu
d
ie
s
o
f
th
e
C
OP
an
d
C
O
M
ar
e
m
o
s
t
l
y
n
o
t
p
er
f
o
r
m
ed
w
it
h
i
m
a
g
e
p
r
o
ce
s
s
in
g
t
e
ch
n
i
q
u
e
s
,
b
ec
au
s
e
t
h
ey
d
o
n
o
t
h
av
e
a
r
e
s
o
l
u
t
i
o
n
th
a
t
a
l
l
o
w
s
t
o
m
e
asu
r
e
th
e
an
g
l
es
o
f
d
ev
i
a
t
i
o
n
o
f
t
h
e
ex
t
r
em
i
t
ie
s
.
T
h
e
r
ef
o
r
e
,
t
ec
h
n
i
q
u
es
b
a
s
e
d
o
n
s
en
s
o
r
s
ar
e
im
p
lem
e
n
t
e
d
,
s
u
ch
as
th
e
b
a
l
a
n
c
e
p
la
tf
o
r
m
s
,
p
r
e
s
s
u
r
e
s
en
s
o
r
s
o
r
s
c
al
e
s
an
d
s
c
a
l
es
.
I
n
s
o
m
e
o
f
th
e
m
e
n
t
io
n
e
d
c
a
s
es
th
e
r
e
is
a
s
p
e
c
i
al
i
ze
d
s
o
f
t
w
a
r
e
,
w
h
i
ch
p
r
e
s
en
t
s
th
e
r
eg
i
o
n
s
o
f
t
h
e
f
e
et
a
n
d
t
h
e
ef
f
e
c
t
o
f
b
o
d
y
p
o
s
tu
r
e
o
n
t
h
em
th
r
o
u
g
h
a
c
o
l
o
r
m
a
p
i
n
a
g
r
a
p
h
i
ca
l
u
s
e
r
i
n
te
r
f
a
c
e
[
1
0
,
1
1
]
.
G
a
it
an
a
ly
s
i
s
i
s
a
w
i
d
e
ly
u
s
e
d
t
o
o
l
d
u
r
in
g
d
if
f
e
r
en
t
m
e
d
ic
a
l
e
x
am
in
a
t
io
n
s
,
s
i
n
c
e
it
al
l
o
w
s
m
e
d
i
ca
l
s
p
e
c
i
al
is
ts
,
o
r
th
o
p
e
d
is
ts
o
r
p
h
y
s
i
o
th
e
r
a
p
is
ts
t
o
d
ete
r
m
in
e
s
ev
e
r
al
g
r
o
u
p
s
o
f
p
a
th
o
l
o
g
i
es
b
as
e
d
o
n
t
h
e
v
a
r
i
at
i
o
n
s
th
a
t
th
e
w
alk
in
g
p
a
t
t
e
r
n
o
f
a
p
a
t
i
en
t
t
r
e
at
e
d
a
g
a
in
s
t
a
n
o
r
m
a
l
o
n
e
.
H
o
w
ev
e
r
,
th
is
ty
p
e
o
f
a
n
a
ly
s
i
s
is
u
s
u
al
ly
p
e
r
f
o
r
m
e
d
em
p
i
r
i
ca
l
ly
a
n
d
d
e
p
e
n
d
s
o
n
th
e
e
x
p
e
r
i
en
c
e
o
f
t
h
e
p
e
r
s
o
n
w
h
en
e
v
a
lu
a
ti
n
g
t
h
e
r
e
s
u
lt
s
t
o
is
s
u
e
a
n
o
p
in
i
o
n
.
T
h
is
m
e
an
s
th
at
,
d
e
p
e
n
d
in
g
o
n
t
h
e
o
b
s
e
r
v
at
i
o
n
s
m
a
d
e
b
y
a
s
p
e
c
ia
l
is
t
,
th
e
r
es
u
l
ts
a
r
e
s
u
b
je
c
t
t
o
m
u
l
ti
p
l
e
in
t
e
r
p
r
e
t
a
ti
o
n
s
g
iv
en
th
e
v
a
r
i
a
b
i
l
i
ty
o
f
c
o
n
c
e
p
ts
th
at
ex
is
ts
b
e
tw
ee
n
s
p
e
ci
a
l
is
ts
t
o
t
r
ea
t
a
p
a
t
i
en
t
[
1
2
]
.
T
h
is
to
p
ic
h
as
m
a
n
y
r
e
f
er
en
c
es
w
it
h
in
th
e
s
tate
o
f
th
e
ar
t
d
u
e
to
th
e
lar
g
e
n
u
m
b
er
o
f
s
p
ec
ialis
t
s
w
o
r
k
i
n
g
i
n
th
e
ar
ea
[
1
3
-
1
5
]
.
T
h
er
ef
o
r
e,
th
i
s
p
ap
er
p
r
o
p
o
s
es
a
p
ar
tial
s
o
lu
tio
n
to
t
h
e
p
r
o
b
lem
o
f
o
b
tain
in
g
an
d
r
ep
r
o
d
u
cib
ilit
y
o
f
t
h
e
r
es
u
lt
s
o
f
s
u
ch
an
al
y
s
is
,
b
y
s
y
s
te
m
at
izin
g
t
h
e
o
b
tain
i
n
g
o
f
P
OP
b
eh
av
io
r
t
h
r
o
u
g
h
a
b
io
-
in
s
p
ir
ed
co
m
p
u
tatio
n
al
le
ar
n
in
g
tec
h
n
iq
u
e,
s
i
n
ce
th
e
s
e
t
ec
h
n
iq
u
es
ar
e
r
elativ
e
l
y
s
i
m
p
l
e
to
im
p
le
m
e
n
t
an
d
h
av
e
a
lo
w
co
m
p
u
tatio
n
al
co
s
t
co
m
p
ar
ed
to
o
th
er
m
at
h
e
m
a
t
ical
o
r
an
al
y
tical
tech
n
iq
u
e
s
o
r
m
o
d
els
[
1
5
,
1
6
]
.
R
ec
ap
itu
la
tin
g
,
t
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
i
n
co
r
p
o
r
ates
a
d
ee
p
lear
n
in
g
n
e
u
r
o
n
al
n
et
w
o
r
k
,
w
h
ic
h
w
as
tr
ai
n
ed
w
it
h
r
ea
l
p
atie
n
t
d
ata
to
v
ali
d
ate
th
eir
b
eh
a
v
io
r
f
r
o
m
d
at
a
m
ea
s
u
r
ed
u
s
i
n
g
s
en
s
o
r
s
.
T
h
is
co
n
tr
ib
u
tio
n
i
s
d
escr
ib
ed
in
d
etail
in
th
e
f
o
ll
o
w
i
n
g
s
ec
tio
n
s
,
w
h
ic
h
ar
e
o
r
g
an
ized
as
f
o
llo
w
s
;
s
ec
tio
n
s
2
a
n
d
3
p
r
esen
t
th
e
g
en
er
al
d
ef
in
i
tio
n
s
an
d
m
et
h
o
d
o
lo
g
y
u
s
ed
r
esp
ec
ti
v
el
y
,
a
n
d
s
ec
tio
n
4
p
r
esen
ts
t
h
e
r
es
u
lt
s
o
b
tain
ed
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
co
n
tr
ib
u
tio
n
m
ad
e
i
s
b
ased
o
n
th
e
j
o
in
t
o
p
er
atio
n
o
f
a
W
I
I
B
alan
ce
B
o
a
r
d
p
latf
o
r
m
,
an
ap
p
licatio
n
d
e
v
elo
p
ed
en
tir
el
y
i
n
P
YT
HON
an
d
a
n
ar
ti
f
ic
ial
n
e
u
r
al
n
et
w
o
r
k
(
ANN
)
.
Ne
x
t,
a
d
escr
ip
tio
n
o
f
ea
ch
o
f
t
h
e
ele
m
e
n
t
s
u
s
ed
is
p
r
esen
ted
.
2
.
1
.
W
II
ba
la
nce
bo
a
rd
pla
t
f
o
r
m
A
p
la
n
t
a
r
p
r
e
s
s
u
r
e
p
l
a
tf
o
r
m
is
a
n
e
lem
en
t
th
a
t
a
l
l
o
w
s
a
s
p
e
c
i
al
i
s
t
t
o
m
e
as
u
r
e
th
e
p
l
an
t
a
r
p
r
ess
u
r
e
c
en
t
e
r
(
C
O
P)
t
o
e
s
tim
a
t
e
th
e
b
al
an
c
e
o
f
th
e
l
o
w
e
r
ex
t
r
em
i
t
ie
s
o
f
th
e
h
u
m
an
b
o
d
y
.
I
n
t
h
i
s
c
as
e
,
a
Nin
t
en
d
o
W
I
I
b
a
l
a
n
c
e
b
o
a
r
d
(
N
B
B
)
p
l
a
t
f
o
r
m
w
as
u
s
ed
a
s
em
u
l
at
o
r
f
o
r
t
h
i
s
ty
p
e
o
f
p
l
a
tf
o
r
m
an
d
th
u
s
t
o
d
e
t
e
r
m
in
e
th
e
c
en
t
e
r
o
f
g
r
a
v
i
ty
o
f
a
g
r
o
u
p
o
f
u
s
e
r
s
f
r
o
m
th
e
p
r
e
s
s
u
r
e
ex
e
r
t
e
d
b
y
th
e
p
la
n
t
a
r
r
eg
i
o
n
o
f
th
e
l
o
w
e
r
e
x
t
r
em
i
t
ie
s
[
1
7
,
1
8
]
.
T
h
e
N
B
B
h
a
s
f
o
u
r
s
t
r
ai
n
g
au
g
e
s
(
o
n
e
at
e
a
ch
e
n
d
)
,
a
c
o
n
t
r
o
l
c
i
r
c
u
i
t
th
a
t
al
l
o
w
s
i
t
t
o
lin
k
w
ith
o
th
e
r
d
e
v
i
c
es
th
a
t
im
p
lem
en
t
th
e
L
2
C
A
P
p
r
o
t
o
c
o
l
t
o
t
r
a
n
s
f
e
r
a
n
d
r
e
c
e
iv
e
in
f
o
r
m
a
t
i
o
n
,
th
i
s
p
r
o
t
o
c
o
l
th
a
t
a
ll
o
w
s
t
h
e
s
en
d
in
g
o
f
d
a
t
a
p
a
c
k
e
ts
d
i
r
e
ct
ly
b
y
th
e
li
n
k
m
an
ag
e
r
w
ith
o
u
t
th
e
n
e
e
d
t
o
c
o
n
n
e
c
t
t
o
a
s
e
r
v
e
r
,
s
e
e
F
ig
u
r
e
1
[
1
8
,
1
9
]
.
Fig
u
r
e
1
.
P
latf
o
r
m
N
in
te
n
d
o
W
I
I
b
alan
ce
b
o
a
r
d
(
N
B
B
)
T
h
is
p
r
o
to
co
l
is
v
er
s
atile
an
d
estab
lis
h
es
a
p
o
in
t
-
to
-
p
o
i
n
t
n
e
t
w
o
r
k
b
et
w
ee
n
t
w
o
d
ev
ices
t
h
at
allo
w
s
in
f
o
r
m
atio
n
t
h
r
o
u
g
h
d
ata
p
ac
k
ets,
w
h
ic
h
ar
e
co
d
ed
(
th
e
p
ac
k
et
i
s
d
iv
id
ed
in
to
s
ev
er
al
s
m
aller
p
ac
k
e
ts
)
i
n
to
th
e
tr
an
s
m
itter
an
d
d
ec
o
d
ed
in
to
th
e
r
ec
ei
v
er
(
th
e
p
ac
k
a
g
es
ar
e
jo
in
ed
to
g
eth
er
to
f
o
r
m
t
h
e
o
r
ig
i
n
al)
.
I
n
th
is
ca
s
e,
th
e
NB
B
f
o
r
m
s
p
ac
k
ets
o
f
3
2
-
b
it
v
al
u
es
an
d
b
ef
o
r
e
s
e
n
d
in
g
t
h
e
m
,
s
eg
m
e
n
ts
t
h
e
m
i
n
to
8
-
b
it
d
ata
g
r
o
u
p
s
an
d
th
e
co
m
p
u
ter
a
s
s
e
m
b
les
t
h
e
p
ac
k
et
a
g
ai
n
.
T
h
is
s
eg
m
e
n
t
atio
n
allo
w
s
th
e
p
r
o
to
co
l
to
h
av
e
a
r
elati
v
el
y
h
ig
h
lev
el
o
f
q
u
alit
y
o
f
s
er
v
ice
(
Q
o
S)
co
m
p
ar
ed
to
o
th
er
p
r
o
to
co
l
s
,
s
in
ce
it
f
ac
ilit
ate
s
th
e
tr
an
s
i
t
o
f
lar
g
e
v
o
lu
m
es
o
f
in
f
o
r
m
atio
n
b
y
d
iv
id
i
n
g
a
p
ac
k
et
in
to
s
m
a
ll se
g
m
e
n
t
s
.
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.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
1
9
5
4
-
1
9
6
1
1956
T
h
e
NB
B
r
e
q
u
ir
es
th
r
ee
p
h
ases
p
r
io
r
to
its
o
p
er
atio
n
t
o
s
tar
t
in
co
n
tin
u
o
u
s
o
p
er
atio
n
m
o
d
e
.
I
n
th
e
f
ir
s
t
p
h
a
s
e,
th
e
co
m
p
u
t
er
m
u
s
t
estab
lis
h
a
p
o
in
t
-
to
-
p
o
in
t
n
et
w
o
r
k
w
i
th
t
h
e
NB
B
ac
tiv
ati
n
g
th
e
L
2
C
A
P
p
r
o
to
co
l
an
d
in
d
icati
n
g
to
t
h
e
B
lu
eto
o
th
ter
m
in
al
t
h
at
t
h
e
p
h
y
s
ical
ad
d
r
ess
o
f
t
h
e
NB
B
is
t
h
e
lin
k
d
ev
ice.
I
n
th
e
s
ec
o
n
d
p
h
ase,
th
e
co
m
p
u
ter
s
en
d
s
t
w
o
s
eq
u
e
n
ce
s
o
f
in
te
g
er
s
to
s
et
a
lev
el
o
f
ze
r
o
in
ea
ch
s
e
n
s
o
r
an
d
th
u
s
ca
lib
r
ate
an
d
ad
j
u
s
t
t
h
e
NB
B
,
co
n
s
id
er
in
g
t
h
at
th
e
ele
m
en
ts
t
h
at
ar
e
o
n
it
m
u
s
t
b
e
r
e
m
o
v
ed
.
I
n
t
h
e
th
ir
d
p
h
ase,
t
h
e
co
m
p
u
ter
s
e
n
d
s
a
s
t
ar
t
b
it
to
co
n
f
ir
m
th
e
co
m
p
leti
o
n
o
f
t
h
e
ca
lib
r
at
io
n
r
o
u
ti
n
e
a
n
d
a
co
m
m
a
n
d
t
h
a
t
in
itiate
s
t
h
e
co
n
ti
n
u
o
u
s
s
e
n
d
in
g
o
f
p
ac
k
ag
e
s
w
i
th
t
h
e
s
tat
u
s
in
f
o
r
m
at
io
n
o
f
t
h
e
s
tr
ain
g
au
g
es
o
r
s
e
n
s
o
r
s
(
s
ee
A
l
g
o
r
ith
m
1
)
.
W
h
en
i
n
itiati
n
g
th
e
p
r
o
ce
s
s
o
f
co
n
tin
u
o
u
s
s
e
n
d
in
g
o
f
th
e
s
en
s
o
r
s
’
in
f
o
r
m
at
io
n
,
th
e
co
m
p
u
ter
ca
n
esti
m
ate
a
v
al
u
e
o
f
C
OP
u
s
in
g
s
o
m
e
m
at
h
e
m
atica
l
tr
an
s
f
o
r
m
atio
n
s
f
o
llo
w
i
n
g
a
p
r
o
to
co
l.
On
th
e
o
n
e
h
a
n
d
,
th
e
d
ev
elo
p
ed
tech
n
iq
u
e
d
ec
o
d
es
th
e
in
f
o
r
m
a
tio
n
o
f
t
h
e
s
e
n
s
o
r
s
(
1
)
an
d
(
2
)
to
d
eter
m
i
n
e
th
e
w
eig
h
t
i
n
k
g
d
etec
ted
b
y
ea
ch
g
a
u
g
e
(
x
[
n
]
)
.
I
t
s
h
o
u
ld
b
e
ad
d
ed
th
at
t
h
e
av
er
ag
e
o
f
1
0
0
d
ata
(
Gn
)
i
s
ta
k
en
as
a
n
e
f
f
ec
ti
v
e
m
ea
s
u
r
e
o
f
ea
ch
s
e
n
s
o
r
,
th
at
i
s
,
th
e
s
u
m
o
f
t
h
e
av
er
ag
e
o
f
ea
ch
g
a
u
g
e
(
P
t)
is
th
e
to
tal
w
eig
h
t
o
f
t
h
e
o
b
j
ec
t
th
at
is
o
n
th
e
p
lat
f
o
r
m
,
ill
u
s
tr
ated
in
(
2
)
.
[
]
=
∑
[
]
+
[
−
1
]
99
=
1
100
(
1
)
=
∑
̅
̅
̅
4
=
1
(
2
)
On
t
h
e
o
t
h
er
,
a
tec
h
n
iq
u
e
b
as
ed
o
n
th
e
la
w
o
f
u
n
iv
er
s
a
l
g
r
av
itatio
n
w
a
s
u
s
ed
to
es
ti
m
at
e
th
e
C
OP
.
T
h
is
tech
n
iq
u
e
p
r
o
p
o
s
es
to
in
cr
ea
s
e
t
h
e
lo
ad
o
n
a
s
e
n
s
o
r
th
at
i
n
cr
ea
s
es
its
attr
ac
tio
n
f
o
r
ce
o
n
a
p
ar
ticle
(
C
OP
)
,
th
er
ef
o
r
e,
h
a
v
i
n
g
4
s
e
n
s
o
r
s
ea
c
h
o
n
e
e
x
er
ts
a
d
if
f
er
en
t
attr
ac
tio
n
f
o
r
ce
o
n
th
e
p
ar
ticle
[
2
0
]
.
W
h
en
th
e
s
en
s
o
r
s
s
tab
ilize
w
it
h
a
co
n
s
ta
n
t
lo
ad
th
e
p
ar
ticle
w
ill
f
i
n
d
a
r
elativ
e
f
ix
ed
p
o
s
itio
n
.
I
n
th
i
s
ca
s
e,
th
e
f
o
r
ce
o
f
attr
ac
tio
n
(
3
)
r
esu
ltin
g
(
Fn
)
is
esti
m
ated
tak
i
n
g
i
n
to
ac
co
u
n
t
th
at
th
e
m
ass
o
f
t
h
e
p
ar
ticle
(
1
)
is
s
m
aller
th
a
n
th
e
m
as
s
o
f
an
y
s
e
n
s
o
r
(
)
,
th
e
m
as
s
o
f
ea
ch
s
en
s
o
r
ex
p
an
d
s
ac
co
r
d
in
g
to
th
e
lo
ad
p
r
esen
t
,
s
ee
Fig
u
r
e
2
(
a)
an
d
th
e
d
is
ta
n
ce
b
et
w
ee
n
t
h
e
m
a
s
s
es
(
)
is
t
h
e
m
a
g
n
it
u
d
e
b
et
w
ee
n
t
h
e
ce
n
ter
s
o
f
m
ass
,
a
s
s
h
o
w
i
n
Fig
u
r
e
2
(
b
)
[
2
1
]
.
=
(
1
∗
)
2
(
3
)
A
l
g
o
r
ith
m
1
.
I
n
itiat
io
n
o
f
t
h
e
NB
B
Start Variables;
Match devices using L2CAP ();
Start calibration of the NBB without load ();
If
Calibration completed
then
Activate continuous operation of the NBB ();
While
Bit of continuous operation = True
do
X [n] = Decode received information ();
Gt [n] = Average (X [n]);
Pt = Add (Gt);
End While
End If
(
a)
(
b
)
Fig
u
r
e
2
.
R
ep
r
esen
tatio
n
o
f
t
h
e
p
ar
ticles an
d
th
eir
m
a
s
s
e
s
;
(
a)
r
ep
r
esen
tatio
n
o
f
th
e
C
OP
,
(
b
)
d
is
tan
ce
b
et
w
ee
n
th
e
m
as
s
es
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
S
tr
a
teg
y
to
d
etermin
e
th
e
fo
o
t
p
la
n
ta
r
ce
n
ter o
f p
r
ess
u
r
e
o
f a
p
ers
o
n
…
(
Hen
r
y
Her
n
á
n
d
ez Ma
r
tín
ez
)
1957
2
.
2
.
Dee
p
lea
rning
neuro
na
l net
w
o
rk
Dee
p
lear
n
in
g
n
e
u
r
al
n
et
w
o
r
k
s
(
D
L
NN)
s
y
s
te
m
at
ize
lar
g
e
v
o
lu
m
es
o
f
i
n
f
o
r
m
atio
n
b
y
o
r
g
an
izi
n
g
co
m
p
le
x
d
ata
s
tr
u
ct
u
r
es
th
at
a
r
e
n
o
t
ac
h
ie
v
ed
w
i
th
a
n
ar
ti
f
i
cial
n
e
u
r
al
n
et
w
o
r
k
(
A
N
N)
.
I
n
ad
d
itio
n
,
D
L
N
Ns
ar
e
v
er
s
atile
en
o
u
g
h
to
b
e
i
m
p
le
m
en
ted
in
co
m
p
u
ter
s
w
i
th
o
u
t
h
ig
h
p
er
f
o
r
m
an
ce
,
b
ec
au
s
e
d
ata
s
tr
u
ctu
r
e
s
ar
e
r
ep
r
esen
ted
b
y
q
u
a
n
titat
iv
e
m
ath
e
m
atica
l
m
o
d
els
[
1
5
,
2
2
]
.
T
h
e
p
r
o
p
o
s
ed
ap
p
li
ca
tio
n
im
p
le
m
e
n
ts
t
h
e
DL
NN
ar
ch
itect
u
r
e
o
f
th
e
T
E
NSOR
F
L
OW
lib
r
ar
y
o
f
th
e
P
YT
HON
p
r
o
g
r
am
m
i
n
g
la
n
g
u
a
g
e.
T
h
is
ar
ch
itect
u
r
e
is
lik
e
A
N
N,
s
i
n
ce
i
n
p
u
t
s
i
g
n
al
s
p
r
o
p
ag
ate
f
r
o
m
i
n
p
u
t
to
o
u
tp
u
t t
h
r
o
u
g
h
la
y
er
s
co
n
s
is
t
in
g
o
f
w
ei
g
h
ts
,
t
h
r
es
h
o
ld
s
,
an
d
m
u
ltip
le
m
ath
e
m
ati
ca
l
tr
an
s
f
o
r
m
atio
n
s
[
1
6
,
23,
2
4
]
.
A
n
A
N
N
in
it
s
s
i
m
p
lest
f
o
r
m
(
Fi
g
u
r
e
3
(
a
)
)
c
o
n
s
is
t
s
o
f
;
an
in
p
u
t la
y
er
,
an
o
u
tp
u
t
la
y
er
an
d
a
h
id
d
en
la
y
er
,
w
h
ic
h
allo
w
s
y
o
u
to
m
o
d
if
y
th
e
w
eig
h
t
s
o
f
th
e
h
id
d
en
la
y
er
ac
co
r
d
in
g
to
th
e
i
n
p
u
t
v
al
u
es
an
d
th
e
m
ar
g
in
o
f
er
r
o
r
o
b
tain
ed
at
th
e
o
u
tp
u
t.
Un
lik
e
A
NN,
D
L
N
N
(
Fig
u
r
e
3
(
b
)
)
h
as
m
o
r
e
t
h
a
n
t
w
o
h
id
d
en
la
y
er
s
a
n
d
m
an
y
ca
s
ca
d
ed
n
eu
r
o
n
s
to
p
er
f
o
r
m
s
o
m
e
tr
a
n
s
f
o
r
m
atio
n
s
o
f
th
e
tr
ai
n
in
g
d
ata
f
r
o
m
th
e
i
n
p
u
t la
y
er
to
th
e
o
u
tp
u
t la
y
er
[
1
6
,
25,
2
6
]
.
Fig
u
r
e
3
.
T
o
p
o
lo
g
y
o
f
t
w
o
n
e
u
r
al
n
et
w
o
r
k
s
; (
a)
ar
tific
ial
n
e
u
r
al
n
et
w
o
r
k
,
(
b
)
n
eu
r
al
n
e
t
w
o
r
k
o
f
d
ee
p
lear
n
in
g
T
h
e
DL
NN
ca
n
b
e
tr
ain
ed
w
i
t
h
d
if
f
er
en
t
al
g
o
r
ith
m
s
,
w
h
o
s
e
m
ai
n
f
u
n
ctio
n
is
to
e
s
ti
m
ate
t
h
e
w
ei
g
h
ts
o
f
th
e
n
eu
r
o
n
s
in
t
h
e
d
if
f
er
e
n
t
la
y
er
s
o
f
t
h
e
n
et
w
o
r
k
.
I
n
itiall
y
,
th
e
tr
ai
n
i
n
g
al
g
o
r
ith
m
as
s
i
g
n
s
w
ei
g
h
ts
to
ea
ch
n
eu
r
o
n
w
ith
s
to
ch
a
s
tic
v
alu
e
s
,
ze
r
o
es
o
r
o
n
es,
w
h
ic
h
i
s
p
r
ev
io
u
s
l
y
d
ef
i
n
ed
b
y
th
e
u
s
er
.
T
h
en
,
an
o
p
ti
m
izatio
n
alg
o
r
ith
m
esti
m
ate
s
th
e
o
u
tp
u
t
v
alu
e
o
f
t
h
e
n
et
w
o
r
k
to
ad
ju
s
t
t
h
e
w
ei
g
h
ts
f
r
o
m
th
e
er
r
o
r
b
etw
ee
n
th
e
d
ata
o
b
tain
ed
an
d
th
e
tr
ain
in
g
d
ata.
Fin
all
y
,
i
f
th
e
ex
ec
u
tio
n
o
f
th
e
tr
ain
in
g
alg
o
r
it
h
m
i
s
n
o
t
s
u
cc
ess
f
u
l,
th
at
is
,
th
e
m
ar
g
in
o
f
er
r
o
r
b
etw
ee
n
t
h
e
tr
ain
i
n
g
d
ata
an
d
th
e
d
ata
o
b
tain
ed
d
o
es
n
o
t
co
n
v
er
g
e
to
ze
r
o
,
th
e
n
u
m
b
er
o
f
tr
ain
i
n
g
c
y
cles
m
u
s
t b
e
in
cr
ea
s
ed
,
o
r
th
e
tr
ain
in
g
al
g
o
r
ith
m
m
u
s
t b
e
r
ed
ef
in
ed
.
T
h
e
co
n
f
ig
u
r
atio
n
p
r
o
ce
s
s
o
f
th
e
D
L
NN
p
ar
a
m
eter
s
i
s
m
a
n
u
al,
s
i
n
ce
th
er
e
is
n
o
m
eth
o
d
o
lo
g
y
f
o
r
th
e
s
elec
tio
n
o
f
th
e
p
ar
a
m
et
er
s
f
r
o
m
th
e
tr
ain
in
g
d
ata.
T
h
er
ef
o
r
e,
th
er
e
is
a
g
r
ea
t
d
iv
er
s
it
y
o
f
tr
ain
i
n
g
alg
o
r
ith
m
s
,
ac
ti
v
atio
n
f
u
n
ctio
n
s
a
n
d
w
a
y
s
to
co
n
f
i
g
u
r
e
a
D
L
NN.
No
r
m
all
y
,
a
tr
ai
n
i
n
g
al
g
o
r
ith
m
i
s
a
s
tr
ateg
y
th
at
ad
j
u
s
t
s
t
h
e
w
ei
g
h
ts
o
f
t
h
e
n
et
w
o
r
k
u
n
til
f
i
n
d
i
n
g
a
co
n
f
i
g
u
r
atio
n
t
h
at
r
ed
u
ce
s
t
h
e
m
ar
g
in
o
f
er
r
o
r
b
et
w
ee
n
th
e
tr
ain
i
n
g
d
ata
an
d
th
e
o
u
tp
u
t
d
ata
to
ap
p
r
o
x
i
m
atel
y
ze
r
o
,
f
o
r
ex
am
p
le,
t
h
e
A
D
A
M
al
g
o
r
ith
m
t
h
at
tr
an
s
f
o
r
m
s
t
h
e
w
ei
g
h
ts
o
f
n
et
w
o
r
k
in
a
m
atr
ix
to
s
i
m
p
li
f
y
th
e
m
t
h
r
o
u
g
h
in
ter
p
o
latio
n
an
d
m
i
n
i
m
izatio
n
o
f
th
e
f
ac
to
r
s
u
s
in
g
th
e
d
escen
d
i
n
g
g
r
ad
ie
n
t.
Ho
w
e
v
er
,
t
h
e
o
u
tp
u
t
v
al
u
es
o
f
ea
c
h
n
et
w
o
r
k
a
r
e
r
estr
icted
to
t
h
e
li
m
it
s
e
s
tab
lis
h
ed
b
y
th
e
ac
ti
v
atio
n
f
u
n
ctio
n
s
.
T
h
ese
f
u
n
ct
io
n
s
e
s
tab
lis
h
t
h
e
w
a
y
in
w
h
i
ch
t
h
e
r
esp
o
n
s
e
o
f
ea
ch
n
eu
r
o
n
c
h
an
g
es
a
n
d
its
m
o
d
el
h
as
a
co
n
v
e
n
tio
n
al
f
o
r
m
li
k
e
t
h
at
o
f
m
a
th
e
m
atic
al
f
u
n
ctio
n
s
,
s
tep
,
ex
p
o
n
en
t
ial
o
r
Gau
s
s
ian
[
2
1
]
.
T
h
e
f
o
llo
w
in
g
s
ec
tio
n
w
il
l
s
tr
u
ct
u
r
all
y
s
h
o
w
t
h
e
co
n
f
i
g
u
r
atio
n
s
u
s
ed
f
o
r
th
e
D
L
NN
(
n
u
m
b
er
o
f
n
e
u
r
o
n
s
,
o
p
ti
m
izatio
n
a
lg
o
r
it
h
m
s
a
m
o
n
g
o
th
er
a
s
p
ec
ts
)
,
ad
d
itio
n
all
y
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
f
o
r
in
f
o
r
m
atio
n
p
r
o
ce
s
s
i
n
g
w
i
ll b
e
d
escr
ib
ed
in
d
etail.
3.
DE
V
E
L
O
P
M
E
NT
AND
I
M
P
L
E
M
E
NT
A
T
I
O
N
T
h
e
d
ev
elo
p
ed
tech
n
iq
u
e
i
m
p
le
m
e
n
ts
a
n
e
u
r
al
n
e
t
w
o
r
k
o
f
d
ee
p
lear
n
in
g
(
DL
NN)
,
w
h
ic
h
est
i
m
ate
s
th
e
p
o
s
itio
n
o
f
t
h
e
C
OP
u
s
i
n
g
t
h
e
s
e
n
s
o
r
r
ea
d
in
g
s
as
i
n
p
u
t
d
ata.
T
h
at
is
,
th
e
d
ata
f
r
o
m
t
h
e
s
e
n
s
o
r
s
ar
e
th
e
p
r
ed
icto
r
s
a
n
d
t
h
e
p
o
s
itio
n
o
f
t
h
e
C
OP
is
t
h
e
o
b
j
ec
tiv
e
f
u
n
ctio
n
.
W
h
en
g
r
o
u
p
in
g
t
h
e
s
e
d
ata
a
n
ar
r
a
y
o
f
1
0
,
0
0
0
in
s
tan
ce
s
w
it
h
6
attr
i
b
u
tes
w
a
s
b
u
il
t
an
d
t
h
e
D
L
N
N
tr
ain
ed
w
it
h
8
0
%
a
n
d
v
ali
d
ated
w
it
h
2
0
%
o
f
th
e
av
ai
lab
le
in
s
tan
ce
s
,
ill
u
s
tr
a
ted
in
T
ab
le
1
.
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.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
1
9
5
4
-
1
9
6
1
1958
T
ab
le
1
.
Seg
m
en
t o
f
th
e
i
n
s
tan
ce
s
u
s
ed
i
n
th
e
D
L
N
N
tr
ain
i
n
g
S
t
r
a
i
n
G
a
g
e
[
k
g
]
(
S
e
n
so
r
I
n
p
u
t
s)
C
O
P
[
c
m
]
(
O
u
t
p
u
t
)
S1
S2
S3
S4
P
o
si
t
i
o
n
X
P
o
si
t
i
o
n
Y
2
0
.
0
0
2
0
.
0
0
2
0
.
0
0
2
0
.
0
0
0
.
0
0
0
.
0
0
2
5
.
0
0
1
5
.
0
0
1
0
.
0
0
1
0
.
0
0
-
2
.
2
3
1
.
6
5
1
0
.
2
3
1
0
.
3
0
5
.
0
0
2
0
.
0
0
3
.
4
9
-
2
.
3
4
0
.
0
0
0
.
0
0
0
.
0
0
2
5
.
0
0
-
1
0
.
0
0
-
1
0
.
0
0
0
.
0
0
0
.
0
0
2
5
.
0
0
0
.
0
0
1
0
.
0
0
-
1
0
.
0
0
4
.
0
0
2
.
0
0
1
.
6
5
3
.
6
0
0
.
6
5
1
.
2
3
T
h
e
s
elec
tio
n
o
f
th
e
tr
ain
i
n
g
a
n
d
v
alid
atio
n
in
s
ta
n
ce
s
w
as
s
t
o
ch
asti
c.
A
f
ter
co
m
p
leti
n
g
th
e
s
elec
tio
n
o
f
th
e
in
s
tan
ce
s
,
th
eir
attr
ib
u
t
es
w
er
e
n
o
r
m
a
lized
,
to
r
ed
u
ce
th
e
s
ea
r
ch
s
p
ac
e
o
f
th
e
o
b
j
ec
t
iv
e
f
u
n
c
tio
n
an
d
to
s
tar
t
th
e
tr
ai
n
in
g
p
r
o
ce
s
s
.
Fi
n
all
y
,
s
ev
er
al
co
n
f
i
g
u
r
atio
n
s
o
f
th
e
D
L
NN
w
er
e
m
o
d
i
f
ied
as
th
e
n
u
m
b
er
o
f
n
eu
r
o
n
s
,
ac
ti
v
atio
n
f
u
n
ctio
n
s
,
tr
ain
i
n
g
alg
o
r
it
h
m
s
,
a
m
o
n
g
o
t
h
er
p
ar
a
m
eter
s
,
p
r
ese
n
ted
o
n
T
ab
le
2
.
T
h
e
t
r
a
in
e
d
D
L
N
N
is
e
x
p
o
r
t
e
d
a
s
a
c
l
as
s
t
o
b
e
u
s
e
d
i
n
th
e
d
e
v
el
o
p
e
d
a
p
p
l
i
c
a
t
i
o
n
.
T
h
i
s
a
p
p
l
i
c
at
i
o
n
a
n
d
t
h
e
t
r
a
in
i
n
g
o
f
t
h
e
DL
N
N
w
e
r
e
c
a
r
r
i
e
d
o
u
t
in
a
c
o
m
p
u
t
e
r
w
i
th
o
p
e
r
a
tin
g
s
y
s
t
em
U
B
U
N
T
U
1
8
.
0
4
,
a
n
I
n
t
el
in
s
i
d
e
T
M
c
o
r
e
i
3
p
r
o
c
e
s
s
o
r
,
8
G
B
o
f
R
A
M
,
a
h
a
r
d
d
r
i
v
e
o
f
2
4
0
G
B
an
d
a
B
lu
e
t
o
o
th
v
3
.
0
s
y
s
t
em
in
t
eg
r
a
t
e
d
i
n
a
W
I
F
I
c
a
r
d
o
f
b
r
a
n
d
in
t
e
l
.
T
h
e
o
p
e
r
a
ti
o
n
o
f
th
e
a
p
p
l
i
c
at
i
o
n
is
d
e
s
c
r
i
b
e
d
in
d
et
a
i
l in
A
lg
o
r
i
th
m
2
,
w
h
e
r
e
th
e
p
r
o
c
e
s
s
i
s
o
b
s
e
r
v
ed
f
r
o
m
th
e
r
e
c
e
p
t
i
o
n
o
f
t
h
e
f
r
am
e
g
iv
en
b
y
th
e
N
B
B
t
o
th
e
i
n
t
e
r
p
r
e
t
a
t
i
o
n
m
a
d
e
b
y
th
e
DL
N
N
.
T
ab
le
2
.
T
h
r
ee
DL
NN
co
n
f
i
g
u
r
atio
n
s
i
m
p
le
m
e
n
ted
to
d
eter
m
i
n
e
th
e
C
OP
C
o
n
f
i
g
u
r
a
t
i
o
n
D
e
scri
p
t
i
o
n
D
L
N
N
1
D
L
N
N
2
D
L
N
N
3
Q
u
a
n
t
i
t
y
o
f
n
e
u
r
o
n
s
1
0
0
0
1
0
0
0
1
0
0
0
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
H
y
p
e
r
b
o
l
i
c
t
a
n
g
e
n
t
S
i
g
mo
i
d
Ex
p
o
n
e
n
t
i
a
l
A
l
g
o
r
i
t
h
m
t
o
a
s
si
g
n
i
n
i
t
i
a
l
v
a
l
u
e
s t
o
w
e
i
g
h
t
s
Z
e
r
o
s
R
a
n
d
o
m w
i
t
h
u
n
i
f
o
r
m
d
i
s
t
r
i
b
u
t
i
o
n
O
n
e
s
N
u
mb
e
r
o
f
h
i
d
d
e
n
l
a
y
e
r
s
1
0
0
1
0
0
1
0
0
O
p
t
i
mi
z
i
n
g
a
l
g
o
r
i
t
h
m
N
a
d
a
m
A
d
a
m
A
d
a
g
r
a
d
S
t
r
a
t
e
g
y
t
o
e
st
i
mat
e
t
h
e
e
r
r
o
r
Er
r
o
r
a
b
so
l
u
t
e
me
d
i
u
m
s
q
u
a
r
e
Er
r
o
r
me
d
i
u
m
sq
u
a
r
e
H
i
n
g
e
A
l
g
o
r
ith
m
2
.
User
ap
p
licatio
n
Function
DLNN (Error margin)
Start variables ()
Threshold = 1 * 10 ^
-
9
Start DLNN ()
Start weights of the DLNN ()
Assign activation function to the DLNN ()
Expand hidden layers of the DLNN up to the
defined amount ()
While
Threshold less than the Error margin
do
Optimize
the weights of the DLNN ()
Estimate the margin of error
End While
Export DLNN class ()
Run GUI ()
End
DLNN
Function
GUI ()
Load libraries TKINTER, TENSORFLOW, MATPLOTLIB, MATH
Load DLNN
Start variables
Start BLUETOOTH port
Create
reception
thread from communication port
Create
sending
thread from the communication port
Start graphical interface objects
Start NBB
While
the graphic interface is active,
do
Check reception
If
reception is full
then
Decompose reception into three parts and save it in buffer
If
buffer [0] == 0
then
Battery status = buffer [1]
Pushbutton state = buffer [2]
Empty buffer
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
S
tr
a
teg
y
to
d
etermin
e
th
e
fo
o
t
p
la
n
ta
r
ce
n
ter o
f p
r
ess
u
r
e
o
f a
p
ers
o
n
…
(
Hen
r
y
Her
n
á
n
d
ez Ma
r
tín
ez
)
1959
Else if
buffer [0] == 1
then
Wait for the calibration routine to finish
Empty buffer
Else if
buffer [0] == 2
then
S1 = buffer [1] << 8
S2 = buffer [1]
S3 = buffer [2] << 8
S4 = buffer [2]
Convert S1, S2, S3, S4 in kilograms
Empty buffer
Else
Empty buffer
End if
End if
S1, S2, S3,
S4 = Normalize (S1, S2, S3, S4)
[X, Y] = DLNN (S1, S2, S3, S4)
Graph (S1, S2, S3, S4, X, Y)
End While
4.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
T
h
e
DL
NN
w
as
tr
ai
n
ed
w
it
h
t
h
e
t
h
r
ee
co
n
f
i
g
u
r
atio
n
s
i
n
d
icat
ed
in
T
ab
le
2
an
d
t
h
e
r
ec
o
r
d
s
m
en
tio
n
ed
in
t
h
e
p
r
ev
io
u
s
s
ec
tio
n
(
s
ee
T
ab
le
1
)
.
A
s
a
r
es
u
lt,
t
h
e
tr
en
d
g
r
ap
h
s
ar
e
p
r
esen
ted
in
F
ig
u
r
e
4
(
a
)
.
w
h
ic
h
r
elate
th
e
tr
ain
in
g
ti
m
e
a
n
d
th
e
m
ar
g
in
o
f
er
r
o
r
o
f
th
e
D
L
NN
i
n
ea
ch
co
n
f
ig
u
r
atio
n
.
B
ased
o
n
th
i
s
,
th
e
co
n
f
i
g
u
r
at
io
n
n
u
m
b
er
t
w
o
o
f
t
h
e
DL
NN
was
s
elec
ted
f
o
r
th
e
d
ev
elo
p
m
en
t
o
f
th
e
ap
p
licatio
n
,
s
i
n
ce
it
co
n
v
er
g
ed
m
o
r
e
q
u
ick
l
y
t
h
an
t
h
e
o
th
er
t
w
o
.
W
h
en
d
ev
elo
p
in
g
t
h
e
ap
p
licatio
n
,
th
e
D
L
NN
r
esp
o
n
s
e
w
a
s
co
m
p
ar
ed
w
it
h
th
e
r
esu
lts
o
b
tain
ed
w
h
en
i
m
p
l
e
m
en
tin
g
t
h
e
f
o
r
ce
o
f
attr
ac
tio
n
m
et
h
o
d
,
w
h
ic
h
w
as c
ar
r
ied
o
u
t in
t
w
o
w
a
y
s
:
T
h
e
C
OP
o
f
f
iv
e
d
if
f
er
en
t
p
e
o
p
le
w
a
s
f
i
x
ed
in
t
h
e
co
o
r
d
in
ate
(
0
,
0
)
an
d
it
w
a
s
v
er
i
f
ied
th
at
t
h
e
s
u
m
o
f
th
e
ch
ar
g
es i
n
ea
ch
g
au
g
e
co
r
r
esp
o
n
d
s
to
th
e
r
ea
l
w
eig
h
t r
ep
o
r
ted
b
y
a
s
ca
le
ar
e
s
h
o
w
n
o
n
T
ab
le
3
.
T
h
en
a
lo
ad
ch
a
n
g
e
w
a
s
m
a
d
e
o
n
t
h
e
p
lat
f
o
r
m
i
n
r
ea
l
ti
m
e
a
n
d
t
h
e
r
esp
o
n
s
e
o
f
b
o
th
tech
n
iq
u
e
s
w
a
s
g
r
ap
h
icall
y
co
m
p
ar
ed
.
I
t is ill
u
s
tr
ated
in
Fig
u
r
e
4
(
b
)
.
As ca
n
b
e
s
ee
n
,
th
e
attr
ac
tio
n
f
o
r
ce
m
et
h
o
d
is
h
i
g
h
l
y
r
ea
cti
v
e,
i.e
.
it r
ef
lects th
e
u
s
e
r
's
w
ei
g
h
t
in
s
h
o
r
t
ti
m
e
s
(
<
1
s
ec
o
n
d
)
.
T
h
er
ef
o
r
e,
th
is
m
eth
o
d
w
as
u
s
ed
as
a
v
alid
atio
n
p
ar
a
m
eter
to
estab
lis
h
w
h
ic
h
lear
n
i
n
g
tech
n
iq
u
e
r
ep
licates
s
en
s
o
r
in
f
o
r
m
atio
n
ap
p
r
o
p
r
iately
(
T
ab
l
e
4
)
.
T
h
is
v
alid
atio
n
w
as
ca
r
r
ied
o
u
t
th
r
o
u
g
h
th
e
W
ilco
x
o
n
tes
t,
i
n
w
h
i
ch
1
0
0
0
s
a
m
p
les
m
ea
s
u
r
ed
d
u
r
i
n
g
th
e
o
p
er
atio
n
o
f
t
h
e
ap
p
lic
atio
n
w
er
e
u
s
ed
to
i
m
p
le
m
en
t
ea
c
h
s
tr
ate
g
y
b
y
m
o
d
i
f
y
i
n
g
t
h
e
w
eig
h
t
o
n
t
h
e
p
latf
o
r
m
as
in
t
h
e
d
o
tted
lin
e
o
f
Fi
g
u
r
e
4
(
b
)
.
Fin
all
y
,
w
i
th
t
h
e
er
r
o
r
esti
m
at
ed
w
it
h
ea
c
h
tec
h
n
iq
u
e,
a
d
ia
g
r
a
m
o
f
b
o
x
es
a
n
d
w
h
is
k
er
s
w
a
s
co
n
s
tr
u
cted
,
as
s
h
o
w
i
n
Fi
g
u
r
e
5
.
(
a)
(
b
)
Fig
u
r
e
4
.
B
eh
av
io
r
o
f
th
e
Ni
n
t
en
d
o
b
alan
ce
b
o
ar
d
; (
a
)
b
eh
av
io
r
o
f
DL
NN
w
it
h
3
d
if
f
er
en
t
co
n
f
i
g
u
r
atio
n
s
,
(
b
)
b
eh
av
io
r
o
f
th
e
p
r
o
p
o
s
ed
t
ec
h
n
iq
u
e
ag
ai
n
s
t th
e
m
et
h
o
d
o
f
attr
ac
tio
n
f
o
r
ce
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.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
1
9
5
4
-
1
9
6
1
1960
T
ab
le
3
.
R
esu
lts
o
b
tain
ed
b
y
m
o
d
i
f
y
i
n
g
t
h
e
lo
ad
o
n
th
e
NB
B
R
e
p
o
r
t
e
d
w
e
i
g
h
t
[
k
g
]
M
a
r
g
i
n
o
f
e
r
r
o
r
[
%
]
B
a
sc
u
l
e
F
o
r
c
e
o
f
a
t
t
r
a
c
t
i
o
n
D
L
N
N
F
o
r
c
e
o
f
a
t
t
r
a
c
t
i
o
n
D
L
N
N
55
5
4
.
9
5
5
.
5
0
.
1
8
0
.
9
0
65
6
6
.
1
6
5
.
2
1
.
6
9
0
.
3
0
70
7
0
.
9
6
9
.
7
1
.
2
8
0
.
4
2
78
7
8
.
4
7
7
.
7
0
.
5
1
0
.
3
8
98
9
5
.
2
9
7
.
3
2
.
8
5
0
.
7
1
1
2
0
----
1
2
0
----
0
.
0
0
T
ab
le
4
.
R
esu
lts
o
b
tain
ed
b
y
c
o
m
p
ar
i
n
g
t
h
e
r
es
u
lts
o
b
tai
n
ed
w
it
h
o
th
er
m
et
h
o
d
s
an
d
th
e
f
o
r
ce
o
f
attr
ac
tio
n
u
s
i
n
g
th
e
W
ilco
x
o
n
test
C
o
mb
i
n
a
t
i
o
n
p
A
t
t
r
a
c
t
i
v
e
f
o
r
c
e
-
D
L
N
N
1
0
.
8
8
A
t
t
r
a
c
t
i
v
e
f
o
r
c
e
-
D
L
N
N
2
0
.
1
5
A
t
t
r
a
c
t
i
v
e
f
o
r
c
e
-
D
L
N
N
3
0
.
1
0
Fig
u
r
e
5
.
B
o
x
an
d
w
h
is
k
er
d
iag
r
a
m
s
o
f
as
s
ess
ed
lear
n
in
g
s
tr
ateg
ies
5.
CO
NCLU
SI
O
N
S
As
ca
n
b
e
s
ee
n
i
n
t
h
e
g
r
ap
h
in
Fig
u
r
e
4
(
a
)
,
D
L
NN
p
er
f
o
r
m
a
n
ce
i
m
p
r
o
v
es
s
ig
n
i
f
ica
n
tl
y
w
h
en
th
e
in
i
tial
w
eig
h
t
s
ar
e
co
n
f
i
g
u
r
ed
s
to
ch
asti
ca
l
l
y
a
n
d
n
o
t
w
ith
co
n
s
ta
n
t
n
u
m
b
er
s
as
in
t
h
e
o
th
er
t
w
o
ca
s
es.
Mo
r
eo
v
er
,
in
t
h
i
s
ca
s
e,
i
n
co
n
f
ig
u
r
atio
n
t
w
o
,
t
h
e
a
lg
o
r
it
h
m
o
f
w
e
ig
h
t
o
p
ti
m
izatio
n
a
n
d
th
e
w
a
y
o
f
er
r
o
r
m
ar
g
i
n
co
r
r
ec
tio
n
r
ed
u
ce
s
t
h
e
DL
NN
co
n
v
er
g
e
n
c
e
ti
m
e,
w
h
ich
i
s
ad
v
an
ta
g
eo
u
s
b
ec
au
s
e
it
r
ed
u
ce
s
th
e
co
m
p
u
tatio
n
al
ti
m
e
i
n
t
h
e
DL
N
N
tr
ai
n
in
g
t
i
m
e.
As
s
h
o
w
n
in
T
ab
le
3
w
ith
th
e
d
ev
elo
p
m
e
n
t
o
f
th
is
ap
p
licatio
n
it
w
as
p
r
o
v
ed
th
a
t
th
e
attr
ac
tio
n
f
o
r
ce
m
et
h
o
d
d
o
es
n
o
t
p
r
ed
ict
C
OP
f
o
r
p
eo
p
le
w
it
h
w
eig
h
t
s
g
r
e
ater
th
a
n
1
0
0
k
g
.
T
h
is
g
i
v
e
s
an
o
t
h
er
ad
v
a
n
ta
g
e
to
t
h
e
D
L
NN,
s
i
n
ce
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
allo
w
s
to
v
alid
ate
th
e
C
OP
o
f
p
eo
p
le
w
it
h
a
w
ei
g
h
t
o
f
u
p
to
1
2
0
k
g
.
T
h
is
w
ei
g
h
t
is
th
e
m
a
x
i
m
u
m
allo
w
ed
b
y
th
e
W
B
B
,
b
ec
au
s
e
ea
ch
s
tr
ai
n
g
a
u
g
e
d
etec
t lo
ad
s
u
p
to
3
0
kg.
F
in
a
l
ly
,
as
c
an
b
e
s
e
en
in
th
e
g
r
a
p
h
in
Fi
g
u
r
e
4
(
b
)
,
DL
NN
h
as
a
w
ai
ti
n
g
t
im
e
t
o
s
t
a
b
il
i
z
e
b
ef
o
r
e
p
r
e
d
i
c
t
in
g
th
e
C
O
P
v
a
lu
e
,
w
h
i
c
h
is
n
o
t
th
e
c
as
e
w
ith
th
e
te
c
h
n
i
q
u
e
b
as
e
d
o
n
th
e
l
a
w
o
f
a
t
t
r
a
c
t
i
o
n
.
T
h
is
is
b
e
c
a
u
s
e
t
h
e
l
a
w
o
f
at
t
r
a
ct
i
o
n
i
s
b
a
s
e
d
o
n
a
m
at
h
em
a
t
ic
a
l
t
r
a
n
s
f
o
r
m
a
t
i
o
n
w
h
o
s
e
m
o
d
el
is
m
u
ch
s
im
p
l
e
r
t
o
im
p
lem
en
t
t
h
a
n
th
a
t o
f
DL
NN
.
H
o
w
ev
e
r
,
DL
N
N
p
r
e
d
i
c
ts
v
a
lu
es
w
ith
a
h
i
g
h
e
r
r
e
s
o
lu
t
i
o
n
,
i
.
e
.
i
t
c
an
p
r
e
d
i
c
t
w
ith
t
h
r
e
e
d
e
cim
a
ls
o
f
a
c
cu
r
ac
y
an
d
t
h
e
o
th
e
r
m
e
th
o
d
w
i
th
o
n
ly
tw
o
.
I
n
a
d
d
i
t
i
o
n
,
a
s
s
h
o
w
n
in
T
a
b
l
e
4
a
n
d
F
ig
u
r
e
5
,
D
L
N
N
2
p
r
e
s
en
t
e
d
a
l
o
w
e
r
v
a
r
i
a
n
ce
,
a
h
ig
h
l
ev
e
l
o
f
c
o
in
ci
d
e
n
c
e
v
e
r
s
u
s
th
e
a
t
t
r
a
ct
i
o
n
f
o
r
c
e
m
e
th
o
d
,
a
m
a
r
g
in
o
f
e
r
r
o
r
c
l
o
s
e
t
o
z
e
r
o
,
an
d
an
a
c
cu
r
a
t
e
r
e
s
p
o
n
s
e
t
o
s
en
s
o
r
in
f
o
r
m
at
i
o
n
v
e
r
s
u
s
t
h
e
o
th
e
r
t
e
ch
n
i
q
u
es
t
es
t
e
d
.
RE
F
E
R
E
NC
E
S
[1
]
H.
M
a
a
n
d
W
.
L
iao
,
"
Hu
m
a
n
Ga
it
M
o
d
e
li
n
g
a
n
d
A
n
a
ly
sis
Us
in
g
a
S
e
m
i
-
M
a
r
k
o
v
P
r
o
c
e
ss
W
it
h
G
r
o
u
n
d
Re
a
c
ti
o
n
F
o
rc
e
s
,
"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ne
u
ra
l
S
y
ste
ms
a
n
d
Reh
a
b
il
i
ta
ti
o
n
E
n
g
i
n
e
e
rin
g
,
v
o
l
.
2
5
,
n
o
.
6
,
p
p
.
5
9
7
-
6
0
7
,
Ju
n
e
2
0
1
7
.
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
S
tr
a
teg
y
to
d
etermin
e
th
e
fo
o
t
p
la
n
ta
r
ce
n
ter o
f p
r
ess
u
r
e
o
f a
p
ers
o
n
…
(
Hen
r
y
Her
n
á
n
d
ez Ma
r
tín
ez
)
1961
[2
]
R.
G
.
Bird
a
l,
A
.
S
e
rtb
a
ş
a
n
d
B.
M
ïh
e
n
d
isli
ğ
i,
"
Hu
m
a
n
Id
e
n
ti
f
ic
a
ti
o
n
Ba
se
d
o
n
G
a
it
A
n
a
l
y
sis:
A
su
rv
e
y
,
"
2
0
1
8
3
rd
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
(
UBM
K)
,
S
a
ra
jev
o
,
p
p
.
4
8
9
-
4
9
3
,
2
0
1
8
.
[3
]
D.
T
a
o
,
X
.
L
i,
X.
W
u
a
n
d
S
.
J.
M
a
y
b
a
n
k
,
"
G
e
n
e
ra
l
T
e
n
so
r
Disc
rim
in
a
n
t
A
n
a
l
y
sis
a
n
d
G
a
b
o
r
F
e
a
tu
re
s
f
o
r
G
a
it
Re
c
o
g
n
it
io
n
,
"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Pa
t
ter
n
An
a
lys
is
a
n
d
M
a
c
h
i
n
e
In
telli
g
e
n
c
e
,
v
o
l.
2
9
,
n
o
.
1
0
,
p
p
.
1
7
0
0
-
1
7
1
5
,
Oc
t
o
b
e
r
2
0
0
7
.
[4
]
P
.
V
a
n
it
c
h
a
tch
a
v
a
n
,
"
T
e
r
m
in
a
ti
o
n
o
f
h
u
m
a
n
g
a
it
,
"
2
0
0
9
IE
EE
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
S
y
st
e
ms
,
M
a
n
a
n
d
Cy
b
e
rn
e
ti
c
s
,
S
a
n
A
n
to
n
io
,
T
X
,
p
p
.
3
1
6
9
-
3
1
7
4
,
2
0
0
9
.
[5
]
K.
A
ra
i
a
n
d
R.
A
n
d
rie,
"
Ga
it
R
e
c
o
g
n
it
io
n
M
e
t
h
o
d
Ba
se
d
o
n
Wav
e
let
T
r
a
n
sf
o
r
m
a
ti
o
n
a
n
d
it
s
E
v
a
lu
a
ti
o
n
w
it
h
Ch
in
e
se
A
c
a
d
e
m
y
o
f
S
c
ien
c
e
s
(CA
S
I
A
)
Ga
it
Da
tab
a
se
a
s
a
Hu
m
a
n
G
a
it
R
e
c
o
g
n
it
io
n
Da
tas
e
t
,
"
2
0
1
2
Ni
n
t
h
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
I
n
fo
r
ma
ti
o
n
T
e
c
h
n
o
l
o
g
y
-
Ne
w
Ge
n
e
ra
ti
o
n
s
,
L
a
s V
e
g
a
s,
NV
,
p
p
.
6
5
6
-
661
,
2
0
1
2
.
[6
]
D.
I.
S
to
ia
a
n
d
M
.
T
o
th
-
T
a
sc
a
u
,
"
In
f
lu
e
n
c
e
o
f
tr
e
a
d
m
il
l
v
e
lo
c
it
y
o
n
jo
in
t
a
n
g
les
o
f
lo
w
e
r
li
m
b
s
d
u
rin
g
h
u
m
a
n
g
a
it
,
"
2
0
1
1
E
-
He
a
lt
h
a
n
d
B
io
e
n
g
in
e
e
rin
g
Co
n
fer
e
n
c
e
(
EHB)
,
p
p
.
1
-
4
,
2
0
1
1
.
[7
]
A
.
V
ieira
e
t
a
l.
,
"
S
o
f
tw
a
re
f
o
r
h
u
m
a
n
g
a
it
a
n
a
l
y
sis
a
n
d
c
las
sif
i
c
a
ti
o
n
,
"
2
0
1
5
IE
EE
4
th
Po
rt
u
g
u
e
se
M
e
e
ti
n
g
o
n
Bi
o
e
n
g
in
e
e
rin
g
(
ENB
ENG)
,
P
o
rto
,
p
p
.
1
-
1
,
2
0
1
5
.
[8
]
R
.
M
a
r
t
í
n
-
F
é
l
e
z
,
J
.
O
r
t
e
l
ls
a
n
d
R
.
A
.
M
o
l
l
i
n
e
d
a
,
"
Ex
p
l
o
r
i
n
g
t
h
e
e
f
f
e
c
t
s
o
f
v
i
d
e
o
l
e
n
g
t
h
o
n
g
a
i
t
r
e
c
o
g
n
i
t
i
o
n
"
,
P
r
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
1
s
t
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
(
I
C
P
R
2
0
1
2
)
,
T
s
u
k
u
b
a
,
p
p
.
3
4
1
1
-
3
4
1
4
,
2
0
1
2
.
[9
]
K.
G
u
i,
H.
L
iu
a
n
d
D.
Zh
a
n
g
,
"
To
w
a
rd
M
u
lt
im
o
d
a
l
Hu
m
a
n
–
Ro
b
o
t
In
tera
c
ti
o
n
to
E
n
h
a
n
c
e
A
c
ti
v
e
P
a
rti
c
i
p
a
ti
o
n
o
f
Us
e
rs
in
G
a
it
Re
h
a
b
il
it
a
ti
o
n
,
"
I
EE
E
T
r
a
n
sa
c
ti
o
n
s
o
n
Ne
u
ra
l
S
y
ste
ms
a
n
d
Reh
a
b
il
i
ta
ti
o
n
En
g
i
n
e
e
rin
g
,
v
o
l
.
2
5
,
n
o
.
1
1
,
p
p
.
2
0
5
4
-
2
0
6
6
,
No
v
2
0
1
7
.
[1
0
]
J.
Hu
a
n
d
K.
S
u
n
,
"
Hu
m
a
n
g
a
i
t
e
s
ti
m
a
ti
o
n
u
sin
g
a
re
d
u
c
e
d
n
u
m
b
e
r
o
f
a
c
c
e
l
e
ro
m
e
ters
,
"
Pro
c
e
e
d
in
g
s
o
f
S
IC
E
An
n
u
a
l
Co
n
fer
e
n
c
e
2
0
1
0
,
T
a
ip
e
i,
p
p
.
1
9
0
5
-
1
9
0
9
,
2
0
1
0
.
[1
1
]
H.
S
o
b
ra
l
e
t
a
l.
,
"
Hu
m
a
n
g
a
it
a
n
a
l
y
sis
u
sin
g
in
stru
m
e
n
ted
sh
o
e
s
,
"
2
0
1
5
IEE
E
4
t
h
Po
r
tu
g
u
e
se
M
e
e
ti
n
g
o
n
Bi
o
e
n
g
in
e
e
rin
g
(
ENB
E
NG)
,
P
o
rto
,
p
p
.
1
-
1
,
2
0
1
5
.
[1
2
]
S
.
J
u
n
g
a
n
d
M
.
S
.
N
i
x
o
n
,
"
E
s
t
im
a
t
i
o
n
o
f
3
D
h
e
a
d
r
e
g
i
o
n
u
s
i
n
g
g
a
i
t
m
o
t
i
o
n
f
o
r
s
u
r
v
e
i
l
l
a
n
c
e
v
i
d
e
o
,
"
4
th
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
m
a
g
i
n
g
f
o
r
C
r
i
m
e
D
e
t
e
c
t
i
o
n
a
n
d
P
r
e
v
e
n
t
i
o
n
2
0
1
1
(
I
C
D
P
2
0
1
1
)
,
L
o
n
d
o
n
,
p
p
.
1
-
6
,
2
0
1
1
.
[1
3
]
M
.
Qi,
"
G
a
it
b
a
se
d
h
u
m
a
n
id
e
n
t
i
f
ica
ti
o
n
in
su
rv
e
il
lan
c
e
v
id
e
o
s
,
"
2
0
1
7
1
3
th
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Na
t
u
ra
l
Co
mp
u
t
a
ti
o
n
,
Fu
zz
y
S
y
ste
ms
a
n
d
Kn
o
wled
g
e
Disc
o
v
e
ry
(
ICNC
-
FS
KD)
,
G
u
il
in
,
p
p
.
2
3
1
7
-
2
3
2
2
,
2
0
1
7
.
[1
4
]
J.
L
u
a
n
d
Y.
T
a
n
,
"
V
iew
re
c
o
g
n
it
io
n
o
f
h
u
m
a
n
g
a
it
se
q
u
e
n
c
e
s
in
v
id
e
o
s
,
"
2
0
1
0
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ima
g
e
Pro
c
e
ss
in
g
,
Ho
n
g
Ko
n
g
,
p
p
.
2
4
5
7
-
2
4
6
0
,
2
0
1
0
.
[1
5
]
T
.
K.
Ba
jw
a
,
S
.
G
a
rg
a
n
d
K.
S
a
u
ra
b
h
,
"
GA
I
T
a
n
a
l
y
sis
fo
r
i
d
e
n
ti
f
ica
ti
o
n
b
y
u
sin
g
S
V
M
w
it
h
K
-
NN
a
n
d
NN
tec
h
n
iq
u
e
s
,
"
2
0
1
6
F
o
u
rt
h
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Pa
ra
l
l
e
l,
Distrib
u
ted
a
n
d
Gr
id
C
o
mp
u
ti
n
g
(
PDGC)
,
W
a
k
n
a
g
h
a
t,
p
p
.
2
5
9
-
2
6
3
,
2
0
1
6
.
[1
6
]
A
.
S
e
v
i
k
,
P
.
Er
d
o
g
m
u
s
a
n
d
E.
Ya
lein
,
"
F
o
n
t
a
n
d
T
u
rk
ish
L
e
tt
e
r
Re
c
o
g
n
it
io
n
i
n
Im
a
g
e
s
w
it
h
De
e
p
L
e
a
rn
in
g
"
,
2
0
1
8
In
ter
n
a
t
io
n
a
l
C
o
n
g
re
ss
o
n
B
ig
Da
ta
,
De
e
p
L
e
a
rn
i
n
g
a
n
d
Fi
g
h
ti
n
g
Cy
b
e
r
T
e
rr
o
rism
(
IBI
GD
E
L
FT
)
,
A
n
k
a
ra
,
T
u
rk
e
y
,
p
p
.
6
1
-
64
,
2
0
1
8
.
[1
7
]
J.
E.
De
u
tsc
h
,
D.
Ro
b
b
i
n
s,
J.
M
o
rriso
n
a
n
d
P
.
G
u
a
rre
ra
Bo
w
lb
y
,
"
W
ii
-
b
a
se
d
c
o
m
p
a
re
d
to
sta
n
d
a
rd
o
f
c
a
re
b
a
lan
c
e
a
n
d
m
o
b
il
it
y
re
h
a
b
il
it
a
ti
o
n
f
o
r
t
w
o
in
d
iv
id
u
a
l
p
o
st
-
stro
k
e
"
,
2
0
0
9
Vi
rtu
a
l
Reh
a
b
il
it
a
ti
o
n
I
n
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
,
Ha
ifa,
p
p
.
1
1
7
-
1
2
0
,
2
0
0
9
.
[1
8
]
G
.
D
'
A
d
d
io
,
L
.
Iu
p
p
a
riello
,
F
.
G
a
ll
o
,
P
.
Bif
u
lco
,
M
.
Ce
sa
re
ll
i
a
n
d
B.
L
a
n
z
il
lo
,
"
Co
m
p
a
riso
n
b
e
tw
e
e
n
c
li
n
ica
l
a
n
d
in
stru
m
e
n
tal
a
ss
e
s
sin
g
u
sin
g
W
ii
F
it
sy
ste
m
o
n
b
a
lan
c
e
c
o
n
tro
l
,
"
2
0
1
4
IE
EE
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m
o
n
M
e
d
ica
l
M
e
a
su
re
me
n
ts a
n
d
Ap
p
li
c
a
t
io
n
s (
M
e
M
e
A)
,
L
isb
o
a
,
p
p
.
1
-
5
,
2
0
1
4
.
[1
9
]
Y
.
Hu
a
a
n
d
Y.
Z
o
u
,
"
A
n
a
l
y
sis
o
f
th
e
p
a
c
k
e
t
tran
sf
e
rrin
g
in
L
2
CA
P
lay
e
r
o
f
Blu
e
to
o
t
h
v
2
.
x
+
EDR
,
"
2
0
0
8
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
I
n
fo
r
ma
ti
o
n
a
n
d
Au
t
o
ma
t
io
n
,
C
h
a
n
g
sh
a
,
p
p
.
7
5
3
-
7
5
8
,
2
0
0
8
.
[2
0
]
T
o
rre
s
Zam
b
ra
n
o
Je
n
n
y
,
P
é
re
z
Ju
li
á
n
,
“
Dise
ñ
o
d
e
u
n
a
h
e
r
ra
m
ien
ta
c
o
m
p
u
tac
io
n
a
l
p
a
ra
e
st
im
a
r
e
l
COP
d
e
u
n
a
p
e
rso
n
a
a
trav
é
s
d
e
u
n
a
p
lata
f
o
rm
a
W
II
Ba
lan
c
e
Bo
a
rd
,
”
Rep
o
sit
o
rio
I
n
stit
u
c
io
n
a
l
U
n
ive
rs
id
a
d
D
istrit
a
l
-
RIUD
,
Bo
g
o
tá,
2
0
1
9
.
[2
1
]
J.
L
i
a
n
d
N.
Do
n
g
,
"
G
r
a
v
it
a
ti
o
n
a
l
S
e
a
rc
h
A
l
g
o
rit
h
m
w
it
h
a
Ne
w
T
e
c
h
n
iq
u
e
,
"
2
0
1
7
1
3
t
h
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
mp
u
ta
t
io
n
a
l
I
n
telli
g
e
n
c
e
a
n
d
S
e
c
u
rity (
CIS
)
,
H
o
n
g
Ko
n
g
,
p
p
.
5
1
6
-
5
1
9
,
2
0
1
7
.
d
o
i:
1
0
.
1
1
0
9
/CIS
.
2
0
1
7
.
0
0
1
2
0
.
[2
2
]
D.
Zh
a
n
g
,
X
.
Ha
n
a
n
d
C.
De
n
g
,
"
Re
v
i
e
w
o
n
th
e
re
se
a
rc
h
a
n
d
p
ra
c
ti
c
e
o
f
d
e
e
p
lea
rn
in
g
a
n
d
re
in
f
o
rc
e
m
e
n
t
lea
rn
in
g
in
sm
a
rt
g
rid
s,"
CS
EE
J
o
u
rn
a
l
o
f
Po
we
r a
n
d
E
n
e
rg
y
S
y
ste
ms
,
v
o
l.
4
,
n
o
.
3
,
p
p
.
3
6
2
-
3
7
0
,
S
e
p
tem
b
e
r
2
0
1
8
.
[2
3
]
G
.
P
.
Zh
a
n
g
,
"
Ne
u
ra
l
n
e
tw
o
rk
s
f
o
r
c
las
sif
ic
a
ti
o
n
:
a
su
rv
e
y
"
,
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
S
y
ste
ms
M
a
n
&
Cy
b
e
rn
e
ti
c
s
Pa
rt C
A
p
p
l
ica
ti
o
n
s &
Rev
iew
s
,
v
o
l.
3
0
,
n
o
.
4
,
p
p
.
4
5
1
-
4
6
2
,
2
0
0
0
.
[2
4
]
M.
A
.
A
b
u
e
t
a
l.
,
“
A
stu
d
y
o
n
I
m
a
g
e
Clas
sif
ic
a
ti
o
n
b
a
se
d
o
n
De
e
p
Lea
rn
in
g
a
n
d
T
e
n
so
rF
lo
w
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
Res
e
a
rc
h
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
2
,
n
o
.
4
,
p
p
.
5
6
3
-
5
6
9
,
2
0
1
9
.
[2
5
]
C.
G
u
o
ji
n
,
Z.
M
ia
o
f
e
n
,
Y.
Ho
n
g
h
a
o
a
n
d
L
i
Ya
n
,
"
A
p
p
li
c
a
ti
o
n
o
f
Ne
u
ra
l
Ne
tw
o
rk
s
in
Im
a
g
e
D
e
f
in
it
i
o
n
Re
c
o
g
n
it
io
n
,
"
2
0
0
7
IEE
E
In
te
rn
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
S
ig
n
a
l
Pro
c
e
ss
in
g
a
n
d
Co
mm
u
n
ic
a
ti
o
n
s
,
Du
b
a
i
,
p
p
.
1
2
0
7
-
1
2
1
0
,
2
0
0
7
.
[2
6
]
S
u
g
iarti
e
t
a
l.
,
“
A
n
A
rti
f
i
c
ial
Ne
u
ra
l
Ne
tw
o
rk
A
p
p
ro
a
c
h
f
o
r
De
tec
ti
n
g
S
k
in
Ca
n
c
e
r
,
”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
E
lec
tro
n
ics
a
n
d
C
o
n
tr
o
l
,
v
o
l
.
1
7
,
n
o
.
2
,
p
p
.
7
8
8
-
7
9
3
,
2
0
1
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.