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
.
1
,
Feb
r
u
ar
y
2
0
2
5
,
p
p
.
1
47
~1
55
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
i1
.
2
5
9
8
8
147
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//telko
mn
ika
.
u
a
d
.
a
c.
i
d
Electroencep
ha
lo
g
ra
phy
-
ba
sed w
h
eelcha
ir nav
ig
a
tion co
ntrol
using
conv
o
lutiona
l neural ne
tw
o
rk
m
ethod
K
ha
irul Ana
m
1,
2
,
Sa
t
rio
M
a
rt
a
Wica
k
s
o
no
1,
2
,
M
ucha
m
a
d Ar
if
H
a
na
Sa
s
o
no
1,
2
,
B
im
a
Wa
hy
u
M
a
ula
na
1,
2
,
F
a
t
k
hu
l
M
ub
a
ro
k
1,
2
,
Ana
nta
P
ins
ent
i
us
Ra
h
m
a
t
P
a
m
un
g
k
a
s
1,
2
,
M
o
ch.
Rij
a
l F
a
t
o
ni
1,
2
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
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
y
o
f
Je
mb
e
r
,
Je
mb
e
r
,
I
n
d
o
n
e
si
a
2
C
e
n
t
e
r
f
o
r
D
e
v
e
l
o
p
me
n
t
o
f
A
d
v
a
n
c
e
d
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
y
o
f
Je
mb
e
r
,
Je
mb
e
r
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
2
2
,
2
0
2
4
R
ev
i
s
ed
No
v
1
0
,
2
0
2
4
A
cc
ep
ted
No
v
2
6
,
2024
A
rti
f
icia
l
in
telli
g
e
n
c
e
re
f
e
rs
to
a
c
o
m
p
u
ter
-
b
a
se
d
sy
ste
m
c
a
p
a
b
le
o
f
lea
rn
in
g
h
u
m
a
n
a
c
ti
v
it
ies
.
F
o
r
i
n
sta
n
c
e
,
in
m
e
d
ica
l
tec
h
n
o
l
o
g
y
,
A
I
c
a
n
b
e
u
se
d
f
o
r
a
th
o
u
g
h
t
-
c
o
n
tro
l
led
w
h
e
e
lch
a
ir.
Th
is stu
d
y
d
isc
u
ss
e
s th
e
u
se
o
f
d
e
e
p
lea
rn
in
g
,
sp
e
c
if
ic
a
ll
y
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
(CNN
),
in
p
re
d
ictio
n
g
o
f
th
e
u
se
r
in
ten
ti
o
n
t
o
n
a
v
ig
a
te
a
w
h
e
e
lch
a
ir.
T
h
e
train
in
g
d
a
ta
w
a
s
c
o
ll
e
c
ted
f
ro
m
a
n
EE
G
se
n
so
r
a
n
d
in
c
lu
d
e
d
th
e
w
h
e
e
lch
a
ir
’
s
m
o
v
e
m
e
n
ts
-
tu
rn
i
n
g
rig
h
t,
t
u
rn
i
n
g
lef
t,
m
o
v
in
g
f
o
r
w
a
rd
,
m
o
v
in
g
b
a
c
k
wa
rd
,
a
n
d
id
le.
T
h
e
sig
n
a
ls
w
e
r
e
th
e
n
sa
m
p
led
a
n
d
f
e
a
tu
re
-
e
x
trac
ted
u
sin
g
ro
o
t
m
e
a
n
sq
u
a
re
(RM
S
).
In
CNN
c
las
si
f
ica
ti
o
n
,
b
o
t
h
ra
w
a
n
d
R
M
S
d
a
ta
w
e
re
u
se
d
.
T
h
is
st
u
d
y
c
o
m
p
a
re
d
tw
o
d
if
fe
re
n
t
CNN
a
r
c
h
it
e
c
tu
re
s.
T
h
e
f
irst
a
rc
h
it
e
c
tu
re
h
a
s
th
re
e
c
o
n
v
o
lu
ti
o
n
a
l
la
y
e
rs
a
n
d
t
h
re
e
p
o
o
li
n
g
lay
e
r
s,
wh
il
e
t
h
e
se
c
o
n
d
h
a
s
tw
o
o
f
e
a
c
h
.
T
h
e
re
se
a
rc
h
c
o
m
p
a
re
s
th
e
a
c
c
u
ra
c
y
a
n
d
lo
ss
v
a
lu
e
s
o
f
CNN
p
re
d
ictio
n
s
u
sin
g
a
rc
h
it
e
c
tu
re
1
a
n
d
2
o
n
b
o
th
ra
w
a
n
d
RM
S
d
a
ta.
T
h
e
e
x
p
e
ri
m
e
n
tal
re
su
lt
s
in
d
ica
te
th
a
t
w
h
e
n
u
sin
g
ra
w
d
a
ta,
th
e
f
irst
CNN
a
rc
h
it
e
c
tu
re
a
c
h
iev
e
d
a
n
a
c
c
u
ra
c
y
o
f
8
5
.
1
2
%
,
a
n
d
th
e
se
c
o
n
d
m
o
d
e
l
a
c
h
iev
e
d
9
1
.
0
4
%
.
Ho
w
e
v
e
r,
w
h
e
n
u
sin
g
RM
S
d
a
ta,
t
h
e
f
irst
a
rc
h
it
e
c
tu
re
a
c
h
iev
e
d
a
n
a
c
c
u
ra
c
y
o
f
7
6
.
4
7
%
,
a
n
d
t
h
e
se
c
o
n
d
ach
iev
e
d
7
3
.
7
4
%
.
T
h
e
stu
d
y
c
o
n
c
lu
d
e
s
t
h
a
t
t
h
e
m
o
v
e
m
e
n
t
o
f
th
e
w
h
e
e
lch
a
ir
is b
e
tt
e
r
in
re
a
l
-
ti
m
e
w
h
e
n
u
sin
g
r
a
w
d
a
ta co
m
p
a
re
d
to
u
si
n
g
RM
S
d
a
ta.
K
ey
w
o
r
d
s
:
C
las
s
i
f
icatio
n
C
o
n
v
o
lu
tio
n
al
n
e
u
r
al
n
e
t
w
o
r
k
Dee
p
lear
n
in
g
E
lectr
o
en
ce
p
h
alo
g
r
ap
h
W
h
ee
lch
air
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
:
Kh
air
u
l
A
n
a
m
Dep
ar
t
m
en
t
o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
,
Fac
u
lt
y
o
f
E
n
g
i
n
ee
r
in
g
,
Un
i
v
er
s
i
t
y
o
f
J
e
m
b
er
J
em
b
er
,
I
n
d
o
n
esia
Em
ail:
k
h
a
ir
u
l
@
u
n
ej
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Dis
ea
s
e,
a
co
n
d
itio
n
o
f
ab
n
o
r
m
alit
y
i
n
t
h
e
b
o
d
y
o
r
m
i
n
d
,
ca
u
s
e
s
d
is
co
m
f
o
r
t,
d
y
s
f
u
n
ctio
n
,
o
r
d
if
f
ic
u
lt
y
f
o
r
th
e
a
f
f
ec
ted
i
n
d
iv
id
u
al
[
1
]
,
[
2
]
.
Var
io
u
s
d
is
ea
s
e
s
h
av
e
a
f
f
licted
h
u
m
a
n
s
f
o
r
ce
n
tu
r
ie
s
,
an
d
I
n
d
o
n
es
ia
is
n
o
ex
ce
p
tio
n
.
Deg
e
n
er
ati
v
e
d
is
ea
s
es
ar
e
am
o
n
g
t
h
e
h
ea
lt
h
is
s
u
es
p
r
esen
t
in
I
n
d
o
n
esia.
A
cc
o
r
d
in
g
to
th
e
W
o
r
ld
Hea
lth
Or
g
a
n
izatio
n
(
W
H
O)
r
ep
o
r
t,
d
ea
th
s
d
u
e
to
d
e
g
en
er
at
iv
e
d
is
ea
s
es
ar
e
e
x
p
ec
ted
to
c
o
n
tin
u
e
i
n
cr
ea
s
i
n
g
w
o
r
ld
w
id
e.
T
h
e
m
o
s
t
s
ig
n
i
f
ic
an
t
i
n
cr
ea
s
e
i
s
p
r
o
j
ec
ted
to
o
cc
u
r
in
d
e
v
elo
p
in
g
an
d
i
m
p
o
v
er
is
h
ed
co
u
n
tr
ies.
Stro
k
e
r
e
m
a
in
s
a
lead
i
n
g
ca
u
s
e
o
f
d
ea
th
an
d
d
is
ab
il
it
y
g
lo
b
a
ll
y
,
w
i
t
h
a
s
u
b
s
ta
n
tial
in
cr
ea
s
e
in
b
u
r
d
en
o
v
er
t
h
e
p
ast
th
r
ee
d
ec
ad
es.
R
ec
en
t
e
s
ti
m
ates
i
n
d
icate
t
h
er
e
w
er
e
1
2
.
2
m
illi
o
n
n
e
w
s
tr
o
k
e
ca
s
e
s
,
6
.
6
m
illi
o
n
d
ea
th
s
,
an
d
1
4
3
m
il
lio
n
d
i
s
ab
ilit
y
-
ad
j
u
s
te
d
lif
e
-
y
ea
r
s
lo
s
t
in
2
0
1
9
[
3
]
.
Deg
e
n
er
ativ
e
d
is
ea
s
e
s
r
es
u
lt
f
r
o
m
ch
a
n
g
es
i
n
th
e
body
’
s
ce
lls
,
w
h
ich
s
u
b
s
eq
u
en
tl
y
af
f
ec
t
o
r
g
a
n
f
u
n
c
tio
n
s
d
u
e
t
o
ag
in
g
,
lead
i
n
g
to
a
d
ec
lin
e
in
th
e
f
u
n
ctio
n
i
n
g
o
f
h
u
m
a
n
ti
s
s
u
es.
C
u
r
r
e
n
tl
y
,
tech
n
o
lo
g
ical
d
e
v
elo
p
m
e
n
ts
s
u
c
h
as
ar
tific
ial
i
n
telli
g
e
n
ce
h
a
v
e
b
ee
n
w
id
el
y
u
s
ed
to
h
elp
w
o
r
k
i
n
t
h
e
h
ea
l
th
s
ec
to
r
,
s
u
c
h
as
p
r
ed
ictin
g
d
e
m
en
t
ia
[
4
]
,
h
ea
lth
m
o
n
ito
r
in
g
[
5
]
,
d
etec
t
in
g
p
n
e
u
m
o
n
ia
d
is
ea
s
e
[
6
]
,
an
d
d
iag
n
o
s
i
n
g
C
OVI
D
-
19
[
7
]
,
ca
n
ce
r
d
etec
tio
n
[
8
]
,
au
to
m
ated
s
u
r
g
ical
s
y
s
te
m
s
[
9
]
,
r
is
k
p
r
ed
ictio
n
f
o
r
ca
r
d
io
lo
g
y
an
d
n
e
u
r
o
s
cie
n
ce
[
1
0
]
.
On
e
o
f
th
e
d
eg
e
n
er
ati
v
e
d
is
ea
s
e
s
is
s
tr
o
k
e
.
I
t
is
a
m
aj
o
r
c
au
s
e
o
f
d
ea
th
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
.
1
,
Feb
r
u
ar
y
20
25
:
1
47
-
1
55
148
an
d
ch
r
o
n
ic
d
is
ab
ilit
y
,
p
ar
ticu
lar
l
y
a
m
o
n
g
in
d
i
v
id
u
al
s
ag
ed
4
5
an
d
a
b
o
v
e,
in
I
n
d
o
n
esia
[
1
1
]
,
[
1
2
]
.
A
r
tif
icia
l
in
telli
g
e
n
ce
tech
n
o
lo
g
y
ca
n
h
e
lp
th
e
n
ee
d
s
o
f
s
tr
o
k
e
p
atien
ts
w
it
h
tr
ea
t
m
e
n
t
[
1
3
]
,
[
1
4
]
s
tr
o
k
e
d
is
ea
s
e
p
r
ed
ictio
n
[
1
5
]
,
an
d
s
tr
o
k
e
r
eh
ab
ilit
atio
n
[
1
6
]
,
[
1
7
]
.
T
h
is
s
tu
d
y
ai
m
s
to
d
ev
elo
p
a
c
o
n
tr
o
l
s
y
s
te
m
f
o
r
w
h
ee
lc
h
air
s
f
o
r
p
atien
ts
w
h
o
ar
e
co
m
p
letel
y
p
ar
aly
ze
d
d
u
e
to
s
tr
o
k
e.
T
h
e
s
y
s
te
m
o
p
er
ates
b
ased
o
n
t
h
e
u
s
er
’
s
i
n
te
n
tio
n
,
u
tili
zi
n
g
an
e
lectr
o
en
ce
p
h
alo
g
r
ap
h
(
E
E
G)
s
en
s
o
r
th
at
d
etec
ts
b
r
ain
ac
tiv
it
y
.
W
ith
E
E
G
tech
n
o
lo
g
y
,
p
atien
ts
ca
n
co
n
tr
o
l
th
e
m
o
v
e
m
e
n
t
o
f
t
h
e
w
h
ee
lc
h
air
u
s
i
n
g
t
h
eir
b
r
ain
s
i
g
n
al
s
[
1
8
]
.
I
t
is
a
d
ev
ice
th
at
r
ec
o
r
d
s
th
e
elec
t
r
ica
l
ac
tiv
it
y
i
n
th
e
b
r
ain
b
y
p
laci
n
g
elec
tr
o
d
es o
n
th
e
s
ca
lp
.
R
e
c
en
t
s
t
u
d
i
e
s
h
a
v
e
d
em
o
n
s
t
r
ate
d
t
h
e
p
o
t
en
t
ia
l
o
f
E
E
G
-
b
a
s
e
d
cl
a
s
s
if
i
ca
t
i
o
n
f
o
r
w
h
ee
l
ch
a
i
r
c
o
n
t
r
o
l
u
s
in
g
d
e
e
p
l
e
a
r
n
i
n
g
te
ch
n
i
q
u
e
s
.
A
b
d
u
l
g
h
an
i
et
a
l
.
[
1
9
]
a
c
h
i
ev
e
d
a
9
5
%
c
l
as
s
if
i
c
at
i
o
n
a
c
cu
r
a
cy
f
o
r
w
h
e
e
lc
h
a
i
r
n
av
ig
a
ti
o
n
c
o
m
m
an
d
s
u
s
in
g
a
c
o
m
b
in
a
t
io
n
o
f
w
av
e
l
et
s
c
at
t
e
r
in
g
an
d
d
e
e
p
l
e
a
r
n
i
n
g
.
S
im
il
a
r
ly
,
Ng
o
a
n
d
Ng
u
y
en
[
2
0
]
p
r
o
p
o
s
ed
a
s
em
i
-
au
to
m
atic
w
h
ee
lch
air
s
y
s
te
m
co
m
b
in
i
n
g
E
E
G
co
n
tr
o
l
w
it
h
v
ir
t
u
al
-
r
ea
l
2
D
g
r
id
m
ap
s
an
d
d
ee
p
Q
-
Net
w
o
r
k
s
f
o
r
p
ath
p
lan
n
in
g
.
Z
u
b
air
[
2
1
]
d
ev
elo
p
ed
an
o
p
ti
m
ized
m
u
lt
i
-
la
y
er
p
er
ce
p
tr
o
n
m
o
d
el
f
o
r
m
o
to
r
i
m
a
g
er
y
-
b
ased
w
h
ee
lc
h
air
c
o
n
tr
o
l,
i
m
p
r
o
v
in
g
p
er
f
o
r
m
a
n
ce
b
y
3
%
t
h
r
o
u
g
h
g
r
id
s
e
ar
ch
o
p
ti
m
izatio
n
.
As
w
i
n
et
a
l
.
[
2
2
]
c
o
m
p
a
r
e
d
a
r
t
if
i
c
ia
l
n
eu
r
a
l
n
e
tw
o
r
k
s
an
d
d
ee
p
n
eu
r
al
n
e
t
w
o
r
k
s
f
o
r
cl
a
s
s
if
y
i
n
g
E
E
G
s
ig
n
a
ls
t
o
c
o
n
t
r
o
l
w
h
e
e
l
ch
ai
r
d
i
r
e
ct
i
o
n
,
ev
a
lu
at
in
g
p
e
r
f
o
r
m
a
n
c
e
u
s
in
g
p
r
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
an
d
F1
-
s
c
o
r
e
.
Z
g
a
ll
a
i
e
t
a
l
.
[
2
3
]
t
h
i
s
p
ap
er
p
r
esen
ts
a
p
r
o
to
ty
p
e
s
m
ar
t
w
h
ee
lc
h
air
u
s
i
n
g
a
n
E
m
o
tiv
e
E
P
OC
h
ea
d
s
et
to
ass
i
s
t
b
lin
d
an
d
p
ar
aly
ze
d
in
d
iv
id
u
als.
I
t
e
m
p
lo
y
s
a
co
n
v
o
l
u
tio
n
a
l
n
e
u
r
al
n
et
w
o
r
k
(
C
NN)
to
r
ec
o
g
n
ize
f
o
u
r
m
o
v
e
m
e
n
t
s
:
le
f
t,
r
i
g
h
t,
f
o
r
w
ar
d
,
an
d
s
to
p
.
T
esti
n
g
w
i
th
te
n
v
o
l
u
n
teer
s
s
h
o
w
ed
a
s
u
cc
ess
r
ate
o
f
7
0
%
w
i
th
r
a
w
E
E
G
an
d
9
6
%
w
it
h
s
p
ec
tr
u
m
d
ata,
d
e
m
o
n
s
tr
ati
n
g
th
e
p
o
ten
tial o
f
d
ee
p
lear
n
in
g
f
o
r
E
E
G
-
b
ased
w
h
ee
lc
h
air
co
n
tr
o
l.
T
h
is
r
esear
ch
ai
m
s
to
co
n
tr
o
l
th
e
f
o
r
w
ar
d
,
b
ac
k
w
ar
d
,
an
d
s
to
p
m
o
v
e
m
e
n
ts
o
f
a
w
h
ee
lc
h
air
,
u
lti
m
atel
y
en
ab
lin
g
i
n
d
i
v
id
u
al
s
w
it
h
s
e
v
er
e
s
tr
o
k
es
to
ac
h
ie
v
e
i
n
d
ep
en
d
en
t
m
o
b
ilit
y
w
i
th
o
u
t
a
s
s
i
s
t
an
ce
.
T
h
e
g
o
al
is
to
cr
ea
te
a
r
ea
l
-
w
o
r
ld
ap
p
licatio
n
t
h
at
allo
w
s
f
o
r
m
o
v
e
m
e
n
t
a
k
in
to
w
al
k
i
n
g
.
T
h
e
m
et
h
o
d
o
lo
g
y
e
m
p
lo
y
ed
i
s
t
h
e
C
NN,
a
t
y
p
e
o
f
d
ee
p
f
ee
d
f
o
r
war
d
n
eu
r
al
n
et
w
o
r
k
f
r
eq
u
e
n
tl
y
u
tili
ze
d
i
n
co
m
p
u
ter
v
is
io
n
ta
s
k
s
,
i
n
cl
u
d
in
g
i
m
a
g
e
class
i
f
icatio
n
[
2
4
]
.
C
NN
u
s
es
co
n
v
o
lu
tio
n
b
y
s
lid
in
g
a
k
er
n
e
l o
v
er
an
i
m
a
g
e
to
ex
tr
ac
t f
ea
t
u
r
es
b
y
m
u
lt
ip
l
y
i
n
g
d
if
f
er
e
n
t
r
eg
io
n
s
.
Ne
u
r
o
n
s
ar
e
o
r
g
an
ized
in
to
a
f
ilter
o
f
s
p
e
cif
ic
d
i
m
en
s
io
n
s
.
T
h
e
p
o
o
lin
g
la
y
er
th
e
n
r
ed
u
ce
s
th
e
f
ea
tu
r
e
m
ap
’
s
s
ize
w
h
ile
p
r
eser
v
in
g
cr
itical
i
n
f
o
r
m
atio
n
[
2
5
]
.
Z
g
allai
et
a
l.
[
2
3
]
d
ev
elo
p
ed
a
s
m
ar
t
w
h
ee
lc
h
air
p
r
o
t
o
ty
p
e
f
o
r
b
lin
d
an
d
p
ar
aly
ze
d
in
d
iv
id
u
als
u
s
i
n
g
th
e
E
m
o
ti
v
e
E
P
OC
h
ea
d
s
et
f
o
r
E
E
G
s
ig
n
al
r
ec
o
g
n
itio
n
.
T
h
e
s
y
s
t
e
m
u
t
ilizes
d
ee
p
lear
n
i
n
g
to
id
en
ti
f
y
f
o
u
r
m
o
v
e
m
e
n
ts
le
f
t,
r
ig
h
t,
f
o
r
w
ar
d
,
an
d
s
to
p
w
i
th
a
C
NN
ac
h
ie
v
in
g
9
6
%
ac
cu
r
ac
y
a
f
ter
te
n
ep
o
ch
s
.
A
R
asp
b
er
r
y
P
i
h
an
d
les
s
i
g
n
al
p
r
o
ce
s
s
in
g
,
w
h
ile
a
n
A
r
d
u
in
o
Me
g
a
co
n
tr
o
ls
m
o
v
e
m
e
n
t.
U
ltra
s
o
n
ic
a
n
d
L
id
ar
s
e
n
s
o
r
s
ar
e
in
c
l
u
d
ed
f
o
r
co
llis
io
n
a
v
o
id
an
ce
,
d
em
o
n
s
tr
ati
n
g
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
w
it
h
s
p
ec
tr
u
m
d
ata
o
v
er
r
a
w
E
E
G
d
ata
.
P
r
ev
io
u
s
r
esear
ch
s
h
o
w
s
C
N
N
en
h
a
n
ce
s
E
E
G
s
i
g
n
al
p
r
o
ce
s
s
i
n
g
ac
c
u
r
ac
y
,
b
u
t
r
ea
l
-
ti
m
e
test
i
n
g
r
e
m
ai
n
s
u
n
e
x
p
lo
r
ed
,
im
p
ac
ti
n
g
f
le
x
ib
il
it
y
an
d
s
ec
u
r
it
y
.
T
h
is
s
tu
d
y
ad
v
an
ce
s
p
r
io
r
w
o
r
k
b
y
ap
p
l
y
in
g
C
NN
in
r
ea
l
-
ti
m
e
E
E
G
s
ig
n
al
clas
s
i
f
icatio
n
to
o
p
ti
m
ize
w
h
ee
lc
h
air
co
n
tr
o
l.
C
NN
’
s
p
ar
am
eter
s
i
n
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
an
d
f
ea
t
u
r
e
ex
tr
ac
tio
n
m
a
k
e
it id
ea
l f
o
r
th
i
s
p
u
r
p
o
s
e.
2.
M
E
T
H
O
D
2
.
1
.
O
v
er
a
ll
s
y
s
t
e
m
des
ig
n
T
h
e
s
y
s
te
m
s
ta
r
ts
b
y
co
llect
in
g
E
E
G
d
ata
f
r
o
m
r
esp
o
n
d
en
ts
,
f
o
llo
w
ed
b
y
p
r
e
-
p
r
o
ce
s
s
in
g
a
n
d
class
i
f
icatio
n
u
s
in
g
C
NN.
T
h
e
class
if
ica
tio
n
r
es
u
lts
ar
e
s
en
t
to
th
e
A
r
d
u
i
n
o
Me
g
a
2
5
6
0
v
ia
s
er
ial
co
m
m
u
n
icatio
n
to
co
n
tr
o
l t
h
e
w
h
ee
lc
h
air
’
s
m
o
v
e
m
en
t,
as
s
h
o
w
n
in
F
ig
u
r
e
1
.
Fig
u
r
e
1
.
T
h
e
b
lo
ck
d
iag
r
am
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
I
n
Fig
u
r
e
1
,
th
e
s
y
s
te
m
’
s
f
ir
s
t
s
tag
e
in
v
o
lv
e
s
co
llectin
g
r
a
w
d
ata
f
r
o
m
r
esp
o
n
d
en
ts
u
s
i
n
g
th
e
E
lectr
o
d
e
Ultr
a
C
o
r
tex
Ma
r
k
I
V
E
E
G
s
e
n
s
o
r
co
n
n
ec
ted
v
ia
B
lu
eto
o
t
h
.
On
ce
th
e
d
ata
co
llectio
n
p
r
o
ce
s
s
is
co
m
p
leted
,
it
p
r
o
ce
ed
s
to
th
e
s
ec
o
n
d
s
tag
e
,
i.e
.
,
p
r
e
-
p
r
o
ce
s
s
in
g
.
T
h
is
s
t
ag
e
o
cc
u
r
s
o
n
a
lap
to
p
an
d
in
cl
u
d
es
f
ilter
i
n
g
,
w
i
n
d
o
w
in
g
,
a
n
d
f
ea
t
u
r
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
es.
T
h
e
B
an
d
p
ass
f
ilter
i
s
u
s
ed
f
o
r
f
ilter
in
g
,
f
o
llo
w
ed
b
y
w
i
n
d
o
w
i
n
g
th
e
d
ata
i
n
s
e
g
m
en
ts
o
f
2
0
0
d
ata
p
o
in
ts
p
er
s
ec
o
n
d
,
an
d
r
o
o
t
m
ea
n
s
q
u
ar
e
(
R
MS)
,
i
s
e
m
p
l
o
y
ed
a
s
t
h
e
f
ea
tu
r
e
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
E
lectro
en
ce
p
h
a
lo
g
r
a
p
h
y
-
b
a
s
e
d
w
h
ee
lch
a
ir
n
a
vig
a
tio
n
co
n
tr
o
l u
s
in
g
co
n
vo
lu
tio
n
a
l n
eu
r
a
l
…
(
K
h
a
ir
u
l A
n
a
m
)
149
ex
tr
ac
tio
n
m
et
h
o
d
.
A
f
ter
co
m
p
leti
n
g
th
e
s
ec
o
n
d
s
ta
g
e,
t
h
e
p
r
o
ce
s
s
m
o
v
e
s
to
t
h
e
C
N
N
class
if
icatio
n
.
T
h
e
class
i
f
icatio
n
co
m
p
r
is
e
s
th
r
ee
ca
teg
o
r
ies:
id
le,
r
ig
h
t
o
r
f
o
r
w
ar
d
m
o
v
e
m
en
t,
a
n
d
lef
t
o
r
b
ac
k
w
ar
d
m
o
v
e
m
e
n
t.
T
h
e
o
u
tp
u
t
f
r
o
m
th
e
C
NN
is
t
h
en
co
n
n
ec
ted
to
t
h
e
A
r
d
u
i
n
o
Me
g
a
2
5
6
0
u
s
i
n
g
s
er
ial
co
m
m
u
n
ica
tio
n
to
co
n
tr
o
l
th
e
w
h
ee
lch
air
’
s
m
o
v
e
m
e
n
t
2
.
2
.
E
lect
ro
ence
ph
a
lo
g
ra
ph
s
ig
na
l a
cquis
it
io
n
E
E
G
d
ata
w
er
e
co
llected
u
s
i
n
g
th
e
Ultr
aCo
r
tex
Ma
r
k
I
V
h
ea
d
s
et
w
i
th
ei
g
h
t
d
r
y
elec
tr
o
d
e
ch
an
n
el
s
o
n
th
e
r
esp
o
n
d
en
t
’
s
s
ca
lp
.
B
r
ain
ac
tiv
it
y
s
i
g
n
als w
er
e
r
ec
o
r
d
ed
a
s
r
esp
o
n
d
en
ts
i
m
a
g
i
n
ed
f
i
v
e
m
o
to
r
ac
tio
n
s
:
r
ig
h
t,
lef
t,
f
o
r
w
ar
d
,
b
ac
k
w
ar
d
,
an
d
s
to
p
,
as
s
h
o
w
n
in
F
ig
u
r
e
s
2
(
a)
to
(
d
)
.
Data
co
llectio
n
w
as
f
ac
ilit
ated
t
h
r
o
u
g
h
Op
en
B
C
I
G
UI
co
n
n
ec
ted
to
an
A
r
d
u
i
n
o
Me
g
a
2
5
6
0
an
d
ad
h
er
ed
to
eth
ical
g
u
id
elin
e
s
ap
p
r
o
v
ed
b
y
t
h
e
Me
d
ical
R
esear
c
h
E
t
h
ic
s
C
o
m
m
ittee,
Un
i
v
er
s
ita
s
J
e
m
b
er
(
No
.
1
2
7
8
/UN2
5
.
8
/KE
P
K/DL
/2
0
2
1
)
.
T
h
e
E
E
G
E
lectr
o
d
e
Ultr
aCo
r
tex
Ma
r
k
I
V
i
n
s
ize
M
(
f
o
r
h
ea
d
cir
c
u
m
f
er
en
ce
s
5
4
-
5
8
c
m
)
w
as
e
m
p
lo
y
ed
in
t
wo
s
ce
n
ar
io
s
:
t
h
e
f
ir
s
t
in
v
o
l
v
ed
i
m
a
g
i
n
i
n
g
r
i
g
h
t
-
h
an
d
,
lef
t
-
h
an
d
m
o
v
e
m
en
ts
,
an
d
id
le
s
tates;
t
h
e
s
ec
o
n
d
in
cl
u
d
ed
b
o
th
h
an
d
s
,
b
o
th
leg
s
,
a
n
d
id
le
s
tates.
A
cq
u
ir
ed
E
E
G
d
ata
w
er
e
s
av
ed
i
n
C
S
V
f
o
r
m
at
a
n
d
p
r
o
ce
s
s
ed
in
E
x
ce
l
f
o
r
an
al
y
s
is
.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
2.
Sig
n
al
ac
q
u
is
itio
n
o
f
:
(
a)
im
a
g
i
n
i
n
g
t
h
e
r
ig
h
t
h
an
d
t
u
r
n
i
n
g
r
ig
h
t,
(
b
)
im
a
g
i
n
i
n
g
t
h
e
lef
t h
a
n
d
tu
r
n
i
n
g
lef
t,
(
c)
i
m
a
g
i
n
in
g
b
o
th
h
an
d
s
m
o
v
i
n
g
f
o
r
w
ar
d
,
an
d
(
d
)
im
a
g
in
i
n
g
b
o
th
le
g
s
m
o
v
in
g
b
ac
k
war
d
2
.
3
.
E
lect
ro
ence
ph
a
lo
g
ra
ph
s
ig
na
l pro
ce
s
s
i
ng
Sig
n
al
p
r
o
ce
s
s
i
n
g
is
ca
r
r
ied
o
u
t
a
f
ter
th
e
s
i
g
n
al
ac
q
u
is
itio
n
s
tag
e.
T
h
e
w
h
o
le
s
y
s
t
e
m
i
s
d
ep
icted
in
Fig
u
r
e
3
.
A
s
s
h
o
w
n
in
F
ig
u
r
e
3
,
th
e
p
r
o
ce
s
s
in
clu
d
es
f
il
ter
in
g
,
E
E
G
s
ig
n
al
w
in
d
o
w
i
n
g
,
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
,
lead
in
g
to
C
N
N
class
i
f
ica
tio
n
o
u
tp
u
t.
P
r
ep
r
o
ce
s
s
in
g
s
tar
t
s
w
ith
a
b
an
d
p
ass
f
il
ter
(
7
-
1
3
Hz)
,
f
o
llo
w
ed
b
y
w
i
n
d
o
w
in
g
w
it
h
a
s
ize
o
f
2
0
0
o
v
er
eig
h
t
ch
an
n
el
s
u
s
i
n
g
1
-
s
ec
o
n
d
ti
m
e
s
eg
m
en
ts
.
T
h
e
d
at
a
is
th
en
p
r
o
ce
s
s
ed
f
o
r
f
ea
t
u
r
e
ex
tr
ac
tio
n
u
s
in
g
t
h
e
R
MS,
w
h
ich
a
v
er
ag
e
s
th
e
s
q
u
ar
ed
v
alu
e
s
o
f
th
e
E
E
G
s
ig
n
als
f
r
o
m
t
h
e
eig
h
t
ch
an
n
el
s
an
d
tak
e
s
th
e
s
q
u
ar
e
r
o
o
t.
I
t is ca
lcu
lated
u
s
i
n
g
(
1
)
:
RM
S
=
√
1
∑
|
|
=
1
(
1
)
W
h
e
r
e
N
i
s
t
h
e
c
o
e
f
f
i
c
i
e
n
t
o
f
t
h
e
s
u
m
o
f
t
h
e
n
t
h
v
a
l
u
e
s
,
a
n
d
Xn
i
s
t
h
e
s
u
m
o
f
t
h
e
d
a
t
a
.
T
h
e
r
e
s
e
a
r
c
h
em
p
l
o
y
s
R
M
S
f
o
r
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
,
s
e
g
m
e
n
t
i
n
g
t
h
e
E
E
G
d
a
t
a
i
n
t
o
p
a
r
t
s
a
f
t
e
r
v
i
s
u
a
l
a
r
t
i
f
a
c
t
i
n
s
p
e
c
t
i
o
n
.
T
h
e
s
t
u
d
y
a
i
m
s
t
o
e
n
a
b
l
e
t
h
e
w
h
e
e
l
c
h
a
i
r
t
o
t
u
r
n
r
i
g
h
t
,
l
e
f
t
,
m
o
v
e
f
o
r
w
a
r
d
,
m
o
v
e
b
a
c
k
w
a
r
d
,
a
n
d
s
t
o
p
b
a
s
e
d
o
n
t
h
e
u
s
e
r
’
s
i
n
t
e
n
t
i
o
n
s
.
Fig
u
r
e
3.
Sch
e
m
atic
r
ep
r
esen
t
atio
n
an
d
m
e
th
o
d
o
lo
g
y
w
i
th
p
r
o
ce
s
s
in
g
u
s
i
n
g
t
h
e
C
N
N
m
et
h
o
d
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
.
1
,
Feb
r
u
ar
y
20
25
:
1
47
-
1
55
150
2
.
3
.
1
.
Desig
nin
g
co
nv
o
lutio
na
l neura
l net
w
o
rk
a
rc
hite
ct
u
re
C
NN
is
a
t
y
p
e
o
f
n
e
u
r
al
n
et
w
o
r
k
d
esig
n
ed
f
o
r
i
m
a
g
e
d
ata.
I
t is a
d
ee
p
-
lear
n
i
n
g
al
g
o
r
ith
m
s
p
ec
if
icall
y
cr
af
ted
f
o
r
t
w
o
-
d
i
m
en
s
io
n
a
l
d
ata
[
2
5
]
.
T
h
e
C
NN
ar
ch
itect
u
r
e
co
n
s
is
t
s
o
f
t
w
o
m
ai
n
p
ar
ts
:
t
h
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
la
y
er
,
w
h
ic
h
in
cl
u
d
es
co
n
v
o
lu
tio
n
an
d
p
o
o
lin
g
la
y
er
s
,
an
d
th
e
f
u
ll
y
co
n
n
ec
ted
la
y
er
.
T
h
e
co
n
v
o
lu
tio
n
la
y
e
r
ap
p
lies
f
ilter
s
o
f
s
p
ec
if
ic
d
i
m
e
n
s
io
n
s
to
cr
ea
te
f
ea
t
u
r
e
m
ap
s
,
w
h
ile
th
e
p
o
o
lin
g
la
y
er
s
ca
n
s
t
h
ese
m
ap
s
w
it
h
a
f
ilter
a
n
d
s
tr
id
e
to
r
ed
u
ce
d
i
m
en
s
io
n
alit
y
.
Fi
n
all
y
,
th
e
f
u
ll
y
co
n
n
ec
ted
la
y
er
r
es
h
ap
es
th
e
r
esu
lt
in
g
f
ea
t
u
r
e
m
ap
in
to
a
v
ec
to
r
f
o
r
f
u
r
th
er
p
r
o
ce
s
s
in
g
.
T
h
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
es a
r
e
d
ep
icted
in
Fig
u
r
e
s
4
an
d
5.
Fig
u
r
e
4
.
T
h
e
C
NN
a
r
ch
itectu
r
e
1
Fig
u
r
e
5
.
T
h
e
C
NN
a
r
ch
itectu
r
e
2
T
h
e
C
NN
ar
ch
itectu
r
e
co
n
s
is
t
s
o
f
cr
u
cial
co
m
p
o
n
e
n
ts
i
n
its
s
u
cc
es
s
,
in
cl
u
d
in
g
f
ea
t
u
r
e
lea
r
n
in
g
an
d
class
i
f
icatio
n
.
Feat
u
r
e
lear
n
i
n
g
co
m
p
r
is
es
s
ev
er
al
la
y
er
s
,
s
ta
r
tin
g
w
i
th
t
h
e
i
n
p
u
t
la
y
er
an
d
co
n
tin
u
i
n
g
w
it
h
th
e
co
n
v
o
lu
tio
n
p
r
o
ce
s
s
an
d
p
o
o
li
n
g
.
Me
an
w
h
i
le,
th
e
class
i
f
icat
i
o
n
p
h
ase
co
n
s
is
ts
o
f
th
e
f
latte
n
ed
,
f
u
ll
y
co
n
n
ec
ted
,
an
d
d
en
s
e
la
y
er
s
.
T
h
e
f
o
llo
w
i
n
g
i
s
a
tab
le
d
etailin
g
th
e
co
n
f
ig
u
r
at
io
n
p
ar
a
m
eter
s
o
f
th
e
C
NN
ar
ch
itect
u
r
e.
T
ab
le
1
h
ig
h
l
ig
h
ts
k
e
y
d
if
f
er
e
n
ce
s
in
C
N
N
ar
ch
itect
u
r
e
co
n
f
i
g
u
r
atio
n
s
f
o
r
r
a
w
an
d
R
MS
d
ata.
T
h
e
‘
i
n
p
u
t_
s
h
ap
e
’
f
o
r
r
a
w
d
ata
is
(
2
0
0
,
8
)
,
w
h
ile
f
o
r
R
MS
d
ata,
it
is
(
8
,
1
)
d
u
e
to
r
esh
ap
in
g
d
u
r
i
n
g
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
w
h
ic
h
av
er
ag
e
s
o
u
t
th
e
s
eq
u
e
n
tial
s
tr
u
ctu
r
e
o
f
th
e
r
a
w
d
ata
.
E
ac
h
d
ata
ty
p
e
f
r
o
m
t
h
e
t
w
o
s
ce
n
ar
io
s
is
test
ed
ac
r
o
s
s
b
o
th
ar
ch
itect
u
r
es,
r
esu
ltin
g
in
t
w
o
d
is
tin
c
t CNN
m
o
d
el
s
:
m
o
d
el
1
an
d
m
o
d
el
2
.
T
ab
le
1
.
C
NN
ar
ch
itectu
r
e
p
ar
a
m
eter
co
n
f
ig
u
r
atio
n
P
a
r
a
me
t
e
r
R
a
w
d
a
t
a
R
M
S
d
a
t
a
A
r
c
h
i
t
e
c
t
u
r
e
1
A
r
c
h
i
t
e
c
t
u
r
e
2
A
r
c
h
i
t
e
c
t
u
r
e
1
A
r
c
h
i
t
e
c
t
u
r
e
2
I
n
p
u
t
_
s
h
a
p
e
2
0
0
,
8
2
0
0
,
8
8
,
1
8
,
1
F
i
l
t
e
r
2
0
0
1
0
0
-
2
0
0
1
0
0
50
2
0
0
1
0
0
-
2
0
0
1
0
0
50
K
e
r
n
e
l
_
si
z
e
8
4
-
8
4
2
4
2
-
4
2
1
P
o
o
l
_
si
z
e
4
2
-
4
2
1
2
1
-
2
1
1
D
e
n
se
3
3
3
3
P
a
t
5
5
5
5
n
-
f
o
l
d
5
5
5
5
Ep
o
c
h
10
10
10
10
B
a
t
c
h
_
s
i
z
e
1
0
0
1
0
0
4
4
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
E
lectro
en
ce
p
h
a
lo
g
r
a
p
h
y
-
b
a
s
e
d
w
h
ee
lch
a
ir
n
a
vig
a
tio
n
co
n
tr
o
l u
s
in
g
co
n
vo
lu
tio
n
a
l n
eu
r
a
l
…
(
K
h
a
ir
u
l A
n
a
m
)
151
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
s
ec
t
io
n
,
w
e
e
v
alu
a
te
th
e
f
i
n
d
in
g
s
f
r
o
m
th
e
E
E
G
s
i
g
n
al
p
r
o
ce
s
s
i
n
g
,
w
h
ich
i
n
v
o
l
v
es
s
e
v
er
al
ess
e
n
tial
p
h
ase
s
.
W
e
b
eg
an
w
it
h
r
a
w
d
ata,
ap
p
ly
in
g
f
i
lter
in
g
t
ec
h
n
iq
u
es
to
r
ed
u
ce
n
o
is
e
an
d
en
h
a
n
ce
th
e
q
u
alit
y
o
f
th
e
s
i
g
n
al.
Nex
t,
w
e
u
s
ed
w
i
n
d
o
w
in
g
to
d
iv
id
e
th
e
d
ata
in
to
m
a
n
a
g
ea
b
le
s
eg
m
e
n
ts
f
o
r
an
al
y
s
is
.
Af
ter
th
at
,
w
e
e
x
tr
ac
ted
f
ea
t
u
r
es
to
id
en
tify
i
m
p
o
r
tan
t
p
atter
n
s
,
w
h
ic
h
w
e
r
e
later
an
al
y
ze
d
u
s
i
n
g
a
C
NN
m
o
d
el.
T
h
e
r
esu
lt
s
w
er
e
f
u
r
t
h
er
v
alid
ated
t
h
r
o
u
g
h
e
x
te
n
s
i
v
e
tes
tin
g
,
w
h
ic
h
in
cl
u
d
ed
co
llectin
g
E
E
G
d
at
a
u
n
d
er
co
n
tr
o
lled
co
n
d
itio
n
s
to
en
s
u
r
e
r
eliab
ilit
y
an
d
ac
cu
r
ac
y
.
3
.
1
.
Resul
t
3
.
1
.
1
.
O
f
f
lin
e
t
esting
o
f
co
nv
o
lutio
na
l neura
l net
w
o
rk
a
rc
hite
ct
ure
Af
ter
s
et
tin
g
t
h
e
C
NN
p
ar
a
m
e
t
er
s
an
d
ar
ch
itec
tu
r
e,
p
er
f
o
r
m
a
n
ce
test
in
g
e
v
al
u
ates
p
r
ed
ictio
n
ac
cu
r
ac
y
to
id
en
ti
f
y
th
e
o
p
ti
m
al
s
et
u
p
.
E
ac
h
ar
ch
i
tectu
r
e
is
tr
ai
n
ed
an
d
test
ed
o
n
d
ata
f
r
o
m
5
r
esp
o
n
d
e
n
ts
w
it
h
a
7
:3
tr
ai
n
-
test
s
p
lit.
R
es
u
lts
ar
e
s
h
o
w
n
i
n
T
ab
les
2
t
o
4
,
w
h
ich
co
m
p
a
r
e
test
in
g
o
u
tco
m
es
f
o
r
r
a
w
an
d
R
MS
d
ata
ac
r
o
s
s
C
NN
a
r
ch
i
tectu
r
es 1
an
d
2
,
as
w
ell
a
s
m
o
d
els 1
an
d
2
.
−
T
esti
n
g
o
f
ra
w
d
ata
f
o
r
C
NN
a
r
ch
itect
u
r
e
1
an
d
2
T
h
is
test
i
n
g
i
n
v
o
lv
e
s
r
a
w
d
at
a
w
it
h
C
NN
a
r
ch
itec
tu
r
e
1
th
at
h
as
b
ee
n
d
esi
g
n
ed
.
I
t
is
co
n
d
u
cted
to
ev
alu
a
te
th
e
ac
c
u
r
ac
y
v
alu
e
s
f
o
r
r
aw
d
ata
u
s
i
n
g
C
NN
a
r
ch
i
te
ctu
r
e
1
,
as p
r
esen
ted
in
T
ab
le
2
.
T
ab
le
2
.
E
x
p
er
im
e
n
tal
r
esu
lts
o
f
th
e
C
NN
a
r
ch
itec
tu
r
e
1
an
d
2
w
it
h
r
a
w
d
ata
No
S
u
b
j
e
c
t
R
a
w
d
a
t
a
f
o
r
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
1
R
a
w
d
a
t
a
f
o
r
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
2
M
o
d
e
l
1
M
o
d
e
l
2
M
o
d
e
l
1
M
o
d
e
l
2
L
o
ss
A
c
c
u
r
a
c
y
(
%)
L
o
ss
A
c
c
u
r
a
c
y
(
%)
L
o
ss
A
c
c
u
r
a
c
y
(
%)
L
o
ss
A
c
c
u
r
a
c
y
(
%)
1.
R1
0
.
3
8
0
4
6
1
.
9
6
0
.
0
9
4
4
9
0
.
5
6
0
.
3
5
6
2
6
4
.
3
8
0
.
0
8
1
6
9
1
.
8
4
2.
R2
0
.
0
1
4
4
9
8
.
5
6
0
.
0
2
7
1
9
7
.
2
9
0
.
0
0
1
3
9
9
.
8
7
0
.
0
1
3
7
9
8
.
6
3
3.
R3
0
.
0
0
7
9
9
9
.
2
1
0
.
0
1
3
3
9
8
.
6
7
0
.
0
0
5
8
9
9
.
4
2
0
.
0
0
6
2
9
9
.
3
8
4.
R4
0
.
0
0
9
8
9
9
.
0
2
0
.
0
1
2
1
9
8
.
7
9
0
.
0
0
3
7
9
9
.
6
3
0
.
0
0
5
9
9
9
.
4
1
5.
R5
0
.
3
1
3
2
6
8
.
6
8
0
.
3
0
3
3
6
9
.
6
7
0
.
3
7
6
9
6
2
.
3
1
0.
3
4
0
2
6
5
.
9
8
A
v
e
r
a
g
e
0
.
1
4
5
1
4
8
5
.
4
8
6
0
.
0
9
0
0
4
9
0
.
9
9
6
0
.
1
4
8
7
8
8
5
.
1
2
2
0
.
0
8
9
5
2
9
1
.
0
4
8
T
ab
le
2
p
r
esen
ts
th
e
tes
t r
esu
lt
s
o
f
r
a
w
d
ata
u
s
i
n
g
C
NN
a
r
ch
i
tectu
r
e
1
,
s
h
o
w
in
g
v
ar
iatio
n
s
i
n
lo
s
s
an
d
ac
cu
r
ac
y
ac
r
o
s
s
r
esp
o
n
d
en
t
s
.
Fo
r
r
esp
o
n
d
en
t
1
,
m
o
d
el
1
y
ield
ed
a
lo
s
s
o
f
0
.
3
8
0
4
w
it
h
6
1
.
9
6
%
ac
cu
r
ac
y
,
w
h
er
ea
s
mo
d
el
2
ac
h
iev
ed
a
lo
s
s
o
f
0
.
0
9
4
4
w
it
h
9
0
.
5
6
%
ac
cu
r
ac
y
.
I
n
co
n
tr
ast,
r
esp
o
n
d
en
t
4
’
s
r
esu
lt
s
s
h
o
w
e
d
a
lo
s
s
o
f
0
.
0
0
9
8
an
d
9
9
.
0
2
%
a
cc
u
r
ac
y
f
o
r
m
o
d
el
1
an
d
0
.
0
1
2
1
lo
s
s
w
ith
9
8
.
7
9
%
ac
cu
r
ac
y
f
o
r
m
o
d
el
2
.
T
h
ese
ac
cu
r
ac
y
v
ar
iatio
n
s
d
ir
ec
tl
y
i
m
p
ac
t
th
e
p
r
ed
ictio
n
r
eliab
il
it
y
f
o
r
w
h
ee
lch
a
ir
m
o
v
e
m
en
t
in
r
ea
l
-
ti
m
e
te
s
ts
.
Hi
g
h
e
r
ac
cu
r
ac
y
v
al
u
es,
n
ea
r
in
g
1
,
in
d
icate
g
r
ea
ter
p
r
ed
ictio
n
r
eliab
il
it
y
,
w
h
ile
lo
s
s
v
al
u
es
i
n
v
er
s
el
y
r
elate
to
ac
cu
r
ac
y
;
as
ac
cu
r
ac
y
i
m
p
r
o
v
es,
lo
s
s
d
e
cr
ea
s
es.
C
NN
a
r
ch
itec
tu
r
e
2
s
h
o
w
s
v
ar
iat
io
n
in
lo
s
s
an
d
ac
cu
r
ac
y
f
o
r
d
if
f
er
en
t
r
esp
o
n
d
en
ts
.
Fo
r
r
esp
o
n
d
en
t
3
,
m
o
d
el
1
r
ec
o
r
d
e
d
a
lo
s
s
o
f
0
.
0
0
5
8
an
d
an
ac
cu
r
ac
y
o
f
9
9
.
4
2
%,
w
h
ile
m
o
d
el
2
h
ad
a
lo
s
s
o
f
0
.
0
0
6
2
w
it
h
9
9
.
3
8
%
ac
cu
r
ac
y
.
I
n
co
n
tr
ast,
r
es
p
o
n
d
en
t
5
’
s
r
es
u
lt
s
s
h
o
w
ed
a
lo
s
s
o
f
0
.
3
7
6
9
w
it
h
6
2
.
3
1
%
ac
cu
r
ac
y
f
o
r
m
o
d
el
1
an
d
0
.
3
4
0
2
w
it
h
6
5
.
9
8
%
ac
cu
r
ac
y
f
o
r
m
o
d
el
2
.
T
h
ese
ac
cu
r
ac
y
d
if
f
er
e
n
ce
s
in
f
lu
e
n
ce
t
h
e
r
eliab
ilit
y
o
f
w
h
ee
lch
air
m
o
v
e
m
e
n
t
p
r
ed
ictio
n
s
in
r
ea
l
-
ti
m
e
te
s
ti
n
g
.
An
ac
cu
r
ac
y
v
al
u
e
clo
s
er
to
1
en
h
a
n
ce
s
p
r
ed
i
ctio
n
r
eliab
ili
t
y
,
w
h
ile
a
n
i
n
v
er
s
e
r
elatio
n
s
h
ip
is
o
b
s
er
v
ed
b
et
w
ee
n
ac
c
u
r
a
c
y
an
d
lo
s
s
-
h
i
g
h
er
ac
cu
r
ac
y
co
r
r
esp
o
n
d
s
w
it
h
lo
w
er
lo
s
s
.
−
T
esti
n
g
o
f
r
o
o
t
m
ea
n
s
q
u
ar
e
d
ata
f
o
r
C
NN
a
r
ch
itec
tu
r
e
1
an
d
2
T
h
i
s
t
es
ti
n
g
i
n
v
o
lv
es
R
M
S
d
a
t
a
w
it
h
C
N
N
a
r
ch
it
e
c
tu
r
e
1
a
n
d
C
N
N
a
r
ch
i
t
e
ct
u
r
e
2
t
o
ev
a
lu
at
e
th
e
p
e
r
f
o
r
m
an
c
e
o
f
th
e
m
o
d
e
ls
o
n
R
MS
in
p
u
t
s
.
T
a
b
l
e
3
d
i
s
p
l
ay
s
r
e
s
u
l
ts
f
o
r
R
M
S
d
at
a
u
s
in
g
C
NN
a
r
ch
i
t
e
ctu
r
e
1
,
w
ith
r
e
s
p
o
n
d
en
t
1
’
s
m
o
d
e
l
1
s
h
o
w
in
g
a
l
o
s
s
o
f
0
.
4
2
1
9
a
n
d
5
7
.
8
1
%
a
c
cu
r
a
cy
,
w
h
i
l
e
m
o
d
e
l
2
h
ad
a
l
o
s
s
o
f
0
.
3
6
9
4
a
n
d
6
3
.
0
6
%
a
c
c
u
r
a
cy
.
R
es
p
o
n
d
en
t
4
’
s
m
o
d
e
l
1
a
ch
i
ev
e
d
8
2
.
8
2
%
a
c
cu
r
a
cy
w
ith
a
l
o
s
s
o
f
0
.
1
7
1
8
,
w
h
i
l
e
m
o
d
el
2
r
e
c
o
r
d
e
d
7
5
.
7
0
%
a
c
cu
r
a
cy
w
ith
a
l
o
s
s
o
f
0
.
2
4
3
.
T
a
b
l
e
3
s
h
o
w
s
o
u
t
c
o
m
es
f
o
r
R
MS
d
a
t
a
w
ith
C
N
N
a
r
ch
i
te
c
tu
r
e
2
.
R
esp
o
n
d
en
t
2
’
s
m
o
d
el
1
ac
h
i
ev
ed
an
ac
c
u
r
ac
y
o
f
8
3
.
6
8
%
(
lo
s
s
:
0
.
1
6
3
2
)
,
an
d
m
o
d
el
2
h
ad
an
ac
c
u
r
ac
y
o
f
8
2
.
0
1
%
(
lo
s
s
:
0
.
1
7
9
9
)
.
Fo
r
r
e
s
p
o
n
d
en
t
5
,
m
o
d
el
1
r
ec
o
r
d
e
d
6
8
.
4
5
%
ac
cu
r
ac
y
(
lo
s
s
:
0
.
3
1
5
5
)
,
w
h
ile
m
o
d
el
2
ac
h
iev
ed
a
n
ac
cu
r
ac
y
o
f
6
7
.
8
0
%
(
lo
s
s
:
0
.
3
2
2
)
.
Hig
h
er
ac
cu
r
ac
y
i
m
p
r
o
v
es
d
ir
ec
tio
n
al
p
r
ed
ictio
n
r
eliab
ili
t
y
.
C
o
m
p
ar
in
g
ar
ch
itect
u
r
es
w
it
h
r
a
w
a
n
d
R
M
S
d
ata,
r
a
w
d
at
a
s
h
o
w
ed
b
ette
r
ac
cu
r
ac
y
d
u
e
to
its
s
eq
u
en
t
ial
s
tr
u
ct
u
r
e.
I
n
C
NN
ar
ch
itect
u
r
e
1
,
m
o
d
el
1
ac
h
iev
ed
an
ac
c
u
r
ac
y
o
f
8
5
.
4
8
6
%
(
lo
s
s
:
0
.
1
4
5
1
4
)
,
w
h
ile
m
o
d
el
2
r
ea
ch
ed
9
0
.
9
9
6
%
(
lo
s
s
:
0
.
0
9
0
0
4
)
.
C
NN
ar
ch
itect
u
r
e
2
p
er
f
o
r
m
ed
b
est
o
v
er
all,
w
it
h
ac
c
u
r
ac
y
af
f
ec
ted
b
y
f
ac
to
r
s
lik
e
ale
r
tn
e
s
s
an
d
h
air
t
h
ick
n
e
s
s
i
m
p
ac
ti
n
g
E
E
G
q
u
alit
y
.
A
n
A
N
OV
A
p
-
v
alu
e
ca
lc
u
latio
n
w
il
l
an
al
y
ze
th
e
m
ea
n
d
if
f
er
e
n
ce
s
b
et
w
ee
n
m
o
d
el
1
an
d
m
o
d
el
2
.
T
a
b
le
4
c
o
m
p
ar
es
p
-
v
al
u
es.
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
.
1
,
Feb
r
u
ar
y
20
25
:
1
47
-
1
55
152
T
ab
le
3
.
R
esu
l
ts
o
f
test
i
n
g
R
M
S d
ata
w
it
h
C
NN
a
r
ch
itect
u
r
e
1
an
d
2
No
S
u
b
j
e
c
t
R
a
w
d
a
t
a
f
o
r
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
1
R
a
w
d
a
t
a
f
o
r
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
2
M
o
d
e
l
1
M
o
d
e
l
2
M
o
d
e
l
1
M
o
d
e
l
2
L
o
ss
A
c
c
u
r
a
c
y
(
%)
L
o
ss
A
c
c
u
r
a
c
y
(
%)
L
o
ss
A
c
c
u
r
a
c
y
(
%)
L
o
ss
A
c
c
u
r
a
c
y
(
%)
1.
R1
0
.
4
2
1
9
5
7
.
8
1
0
.
3
6
9
4
6
3
.
0
6
0
.
3
9
4
9
6
0
.
5
1
0
.
3
6
4
7
6
3
.
5
3
2.
R2
0
.
1
8
7
3
8
1
.
2
7
0
.
1
9
0
3
8
0
.
9
7
0
.
1
6
3
2
8
3
.
6
8
0
.
1
7
9
9
8
2
.
0
1
3.
R3
0
.
1
3
9
3
8
6
.
0
7
0
.
2
3
7
6
7
6
.
2
4
0
.
1
2
9
1
8
7
.
0
9
0
.
2
0
2
7
9
.
8
0
4.
R4
0
.
1
7
1
8
8
2
.
8
2
0
.
2
4
3
7
5
.
7
0
0
.
1
7
3
7
8
2
.
6
3
0
.
2
4
4
7
5
.
6
0
5.
R5
0
.
3
3
8
6
6
.
2
0
0
.
3
4
6
6
5
.
4
0
0
.
3
1
5
5
6
8
.
45
0
.
3
2
2
6
7
.
8
0
A
v
e
r
a
g
e
0
.
2
5
1
6
6
7
4
.
8
3
4
0
.
2
7
7
2
6
7
2
.
2
7
4
0
.
2
3
5
2
8
7
6
.
4
7
2
0
.
2
6
2
5
2
7
3
.
7
4
8
T
ab
le
4
.
C
o
m
p
ar
is
o
n
o
f
p
-
v
a
l
u
e
v
al
u
es
G
r
o
u
p
1
G
r
o
u
p
2
p
-
v
a
l
u
e
M
o
d
e
l
1
r
a
w
a
r
si
t
e
k
t
u
r
1
M
o
d
e
l
2
r
a
w
a
r
si
t
e
k
t
u
r
1
0
.
6
0
7
0
7
M
o
d
e
l
1
r
ms
a
r
si
t
e
k
t
u
r
1
M
o
d
e
l
2
r
ms
a
r
si
t
e
k
t
u
r
1
0
.
7
1
4
5
0
1
M
o
d
e
l
1
r
a
w
a
r
si
t
e
k
t
u
r
2
M
o
d
e
l
2
r
a
w
a
r
si
t
e
k
t
u
r
2
0
.
6
1
5
4
3
3
M
o
d
e
l
1
r
ms
a
r
si
t
e
k
t
u
r
2
M
o
d
e
l
2
r
ms
a
r
si
t
e
k
t
u
r
2
0
.
6
8
5
4
3
T
h
e
p
-
v
a
lu
e
an
aly
s
is
in
T
a
b
l
e
4
i
n
d
ic
a
t
es
n
o
s
i
g
n
i
f
i
c
an
t
d
if
f
e
r
en
c
e
b
etw
e
en
th
e
m
o
d
el
s
,
as
th
e
p
-
v
a
lu
e
is
g
r
e
a
te
r
th
an
0
.
0
5
.
T
h
i
s
a
ll
o
w
s
f
l
ex
i
b
i
l
ity
in
ch
o
o
s
in
g
a
n
y
a
r
ch
i
te
c
tu
r
e
.
H
o
w
ev
e
r
,
s
el
e
c
ti
n
g
th
e
a
r
ch
i
t
e
ctu
r
e
w
i
th
t
h
e
h
ig
h
es
t
a
c
cu
r
a
cy
o
r
r
e
f
e
r
r
in
g
t
o
th
e
c
o
n
f
u
s
i
o
n
m
at
r
i
c
es
in
Fi
g
u
r
es
6
(
a
)
a
n
d
(
b
)
,
a
s
w
e
l
l
as
Fi
g
u
r
es
7
(
a
)
a
n
d
(
b
)
,
ca
n
p
r
o
v
id
e
ad
d
itio
n
al
g
u
id
an
ce
f
o
r
s
elec
t
i
n
g
th
e
m
o
s
t e
f
f
ec
tiv
e
m
o
d
el
.
Fig
u
r
es
6
a
n
d
7
s
h
o
w
d
is
cr
ep
an
cie
s
i
n
th
e
co
n
f
u
s
io
n
m
atr
i
x
,
w
h
er
e
s
o
m
e
co
m
m
a
n
d
s
-
id
le,
tu
r
n
r
ig
h
t,
tu
r
n
lef
t,
m
o
v
e
f
o
r
w
ar
d
,
an
d
m
o
v
e
b
ac
k
w
ar
d
-
ar
e
m
is
c
lass
if
ied
.
T
h
is
i
m
p
ac
ts
m
o
v
e
m
e
n
t
ac
c
u
r
ac
y
,
b
u
t
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
s
u
cc
es
s
f
u
ll
y
ca
p
t
u
r
es
b
r
ain
p
atter
n
s
f
o
r
th
ese
co
m
m
a
n
d
s
.
(
a)
(
b
)
(
a)
(
b
)
Fig
u
r
e
6
.
C
o
n
f
u
s
io
n
m
atr
ix
o
f
th
e:
(
a)
m
o
d
el
1
an
d
(
b
)
m
o
d
el
2
u
s
i
n
g
r
a
w
i
n
p
u
t
Fig
u
r
e
7
.
C
o
n
f
u
s
io
n
m
atr
ix
o
f
th
e:
(
a)
m
o
d
el
1
an
d
(
b
)
m
o
d
el
2
u
s
i
n
g
R
MS
i
n
p
u
t
−
T
h
e
b
est
C
NN
a
rc
h
itect
u
r
e
B
ased
o
n
p
r
ev
io
u
s
r
es
u
lt
s
,
t
h
e
s
ec
o
n
d
ar
ch
itect
u
r
e
is
th
e
o
p
ti
m
al
c
h
o
ice
f
o
r
t
h
e
m
o
d
el,
u
tili
zin
g
in
p
u
t
d
i
m
en
s
io
n
s
o
f
2
0
0
×
8
w
it
h
a
b
atch
s
ize
o
f
5
0
f
o
r
r
a
w
d
ata
a
n
d
4
f
o
r
R
MS
d
ata.
T
h
is
co
n
f
i
g
u
r
atio
n
e
f
f
ec
tiv
e
l
y
r
ed
u
ce
s
th
e
GP
U
w
o
r
k
lo
ad
d
u
r
in
g
tr
ain
i
n
g
.
T
h
e
ar
ch
itect
u
r
e
in
co
r
p
o
r
ates
t
w
o
-
d
i
m
e
n
s
io
n
al
C
NN
i
n
p
u
t
s
h
ap
es,
w
it
h
th
e
f
ir
s
t
in
p
u
t
s
h
ap
e
o
f
(
2
0
0
,
8
)
r
ep
r
esen
tin
g
E
E
G
ch
a
n
n
el
s
an
d
th
e
s
ec
o
n
d
in
p
u
t
s
h
ap
e
o
f
(
8
,
1
)
d
er
iv
ed
f
r
o
m
R
MS
f
ea
tu
r
e
e
x
tr
ac
tio
n
.
T
h
e
ar
ch
itectu
r
e
b
eg
i
n
s
w
i
th
a
f
ir
s
t
co
n
v
o
l
u
t
io
n
u
s
i
n
g
2
0
0
f
ilter
s
o
f
s
ize
8
×
8
,
p
r
o
d
u
c
in
g
a
f
ea
t
u
r
e
m
ap
o
f
d
im
en
s
io
n
s
1
9
3
×
8
af
ter
ap
p
ly
i
n
g
th
e
R
e
L
U
ac
ti
v
atio
n
f
u
n
ctio
n
.
T
h
is
is
f
o
llo
w
ed
b
y
a
p
o
o
lin
g
la
y
er
th
at
r
ed
u
ce
s
th
e
f
ea
tu
r
e
m
ap
to
4
8
×
8
u
s
in
g
m
ax
p
o
o
lin
g
.
T
h
e
s
ec
o
n
d
co
n
v
o
l
u
tio
n
u
s
es
1
0
0
f
ilter
s
a
n
d
a
k
er
n
el
s
ize
o
f
4
×
4
,
y
ield
i
n
g
a
4
5
×
8
m
a
tr
ix
,
als
o
p
r
o
c
ess
ed
w
it
h
t
h
e
R
e
L
U
ac
tiv
atio
n
f
u
n
c
tio
n
.
A
s
ec
o
n
d
m
a
x
p
o
o
lin
g
la
y
er
f
u
r
t
h
er
r
ed
u
ce
s
t
h
i
s
to
a
2
2
×
8
m
at
r
ix
.
T
h
e
th
ir
d
co
n
v
o
lu
tio
n
e
m
p
lo
y
s
5
0
f
ilter
s
w
it
h
a
2
×
2
k
er
n
el,
r
es
u
lt
in
g
i
n
a
2
1
×
8
m
atr
i
x
,
an
d
t
h
e
s
u
b
s
eq
u
e
n
t p
o
o
lin
g
la
y
er
m
ain
tain
s
t
h
i
s
s
i
ze
.
T
h
e
d
ata
is
t
h
e
n
f
latte
n
ed
in
to
a
n
e
w
m
atr
ix
w
it
h
1
0
5
0
w
e
ig
h
ts
,
lead
in
g
to
a
f
u
ll
y
co
n
n
ec
ted
lay
er
co
m
p
r
is
i
n
g
th
r
ee
d
en
s
e
lay
er
s
co
r
r
esp
o
n
d
in
g
to
t
h
e
clas
s
es
o
f
id
le,
r
ig
h
t/
f
o
r
w
ar
d
,
an
d
lef
t/b
ac
k
w
ar
d
,
u
s
i
n
g
t
h
e
s
i
g
m
o
id
ac
ti
v
atio
n
f
u
n
c
tio
n
f
o
r
cl
ass
i
f
icatio
n
.
Fi
n
all
y
,
t
h
e
C
N
N
o
u
tp
u
t
is
tr
a
n
s
m
it
ted
to
an
A
r
d
u
i
n
o
Me
g
a
2
5
6
0
v
ia
s
er
ial
co
m
m
u
n
icatio
n
f
o
r
f
u
r
t
h
er
p
r
o
ce
s
s
in
g
.
3
.
1
.
2
.
O
nli
ne
da
t
a
t
esting
Du
r
in
g
th
e
o
n
li
n
e
te
s
ti
n
g
p
h
as
e,
th
e
r
esp
o
n
d
e
n
t
w
a
s
i
n
a
w
h
e
e
lch
air
u
s
i
n
g
a
n
E
E
G
s
en
s
o
r
.
T
h
is
test
i
n
g
w
a
s
co
n
d
u
cted
to
d
eter
m
in
e
t
h
e
ac
cu
r
ac
y
o
f
p
r
ed
ictin
g
r
ea
l
-
ti
m
e
w
h
ee
lch
air
m
o
v
e
m
en
ts
.
T
a
b
le
5
s
h
o
w
s
th
e
r
esu
lt
s
o
f
t
h
e
o
n
l
in
e
te
s
ti
n
g
.
T
ab
le
5
s
h
o
w
s
t
h
at
t
h
e
a
n
ticip
at
ed
w
h
ee
lch
a
ir
m
o
v
e
m
e
n
t
s
f
o
r
r
esp
o
n
d
en
ts
1
a
n
d
5
d
id
n
o
t
o
cc
u
r
as
ex
p
ec
ted
,
w
i
th
b
o
th
ac
h
ie
v
i
n
g
lo
w
ac
cu
r
ac
y
r
ate
s
o
f
5
0
%.
I
n
co
n
tr
ast,
r
esp
o
n
d
en
ts
2
an
d
3
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
E
lectro
en
ce
p
h
a
lo
g
r
a
p
h
y
-
b
a
s
e
d
w
h
ee
lch
a
ir
n
a
vig
a
tio
n
co
n
tr
o
l u
s
in
g
co
n
vo
lu
tio
n
a
l n
eu
r
a
l
…
(
K
h
a
ir
u
l A
n
a
m
)
153
r
ea
ch
ed
8
5
%
ac
cu
r
ac
y
,
attr
ib
u
ted
to
th
eir
b
etter
p
h
y
s
ical
co
n
d
itio
n
an
d
f
o
c
u
s
ed
b
r
ain
ac
tiv
it
y
d
u
r
in
g
d
ata
ac
q
u
is
itio
n
.
T
h
e
less
f
o
cu
s
ed
s
tates
o
f
r
e
s
p
o
n
d
en
t
s
1
an
d
5
co
n
tr
ib
u
ted
to
th
eir
lo
w
er
ac
c
u
r
ac
y
.
Facto
r
s
li
k
e
p
h
y
s
ical
co
n
d
itio
n
a
n
d
b
r
ain
r
esti
n
g
s
ta
te
ar
e
cr
u
cial
f
o
r
o
p
tim
al
d
ata
ac
q
u
is
it
io
n
r
esu
lts
,
an
d
h
air
th
ick
n
es
s
ca
n
also
af
f
ec
t
E
E
G
s
i
g
n
al
q
u
alit
y
,
w
it
h
t
h
in
n
er
o
r
b
ald
h
air
y
ie
ld
in
g
b
ette
r
d
ata.
B
o
th
o
n
li
n
e
an
d
o
f
f
lin
e
t
e
s
ti
n
g
y
ield
ed
h
i
g
h
er
ac
c
u
r
ac
y
d
u
r
in
g
o
f
f
li
n
e
s
e
s
s
io
n
s
d
u
e
to
t
h
e
co
n
s
i
s
te
n
c
y
o
f
b
r
ain
s
i
g
n
al
d
ata,
w
h
ile
o
n
lin
e
test
i
n
g
f
ac
ed
f
l
u
ct
u
atio
n
s
in
t
h
e
r
ea
l
-
ti
m
e
s
i
g
n
al
co
llectio
n
.
T
ab
le
5
.
R
esu
lts
o
f
o
n
li
n
e
t
esti
n
g
R
e
sp
o
n
d
e
n
t
A
c
c
u
r
a
c
y
(
%
)
R
e
sp
o
n
d
e
n
t
1
50
R
e
sp
o
n
d
e
n
t
2
85
R
e
sp
o
n
d
e
n
t
3
85
R
e
sp
o
n
d
e
n
t
4
80
R
e
sp
o
n
d
e
n
t
5
50
A
v
e
r
a
g
e
70
3
.
2
.
Dis
cus
s
io
n
T
h
is
s
tu
d
y
ac
h
ie
v
ed
h
i
g
h
ac
c
u
r
ac
y
i
n
p
r
ed
ictin
g
f
o
u
r
w
h
ee
lc
h
air
co
n
tr
o
l
m
o
tio
n
s
u
s
i
n
g
a
C
NN
m
o
d
el,
w
it
h
a
n
av
er
a
g
e
r
ea
l
-
ti
m
e
ac
c
u
r
ac
y
o
f
7
0
%
ac
r
o
s
s
f
i
v
e
r
esp
o
n
d
en
ts
.
Ho
w
e
v
er
,
i
m
p
r
o
v
e
m
en
ts
ar
e
n
ee
d
ed
f
o
r
r
ea
l
-
ti
m
e
p
er
f
o
r
m
a
n
ce
,
a
co
m
m
o
n
c
h
alle
n
g
e
i
n
E
E
G
-
b
ase
d
ap
p
licatio
n
s
.
A
d
v
a
n
ce
d
m
et
h
o
d
s
in
th
e
f
ield
ar
e
ex
p
lo
r
in
g
r
ec
u
r
r
en
t
n
e
u
r
al
n
e
t
w
o
r
k
s
(
R
N
Ns)
a
n
d
h
y
b
r
id
s
y
s
te
m
s
th
a
t
co
m
b
i
n
e
E
E
G
w
it
h
o
th
er
b
io
s
ig
n
als
to
ad
d
r
ess
th
e
v
ar
iab
ili
t
y
a
n
d
in
s
tab
ilit
y
i
n
E
E
G
d
ata,
a
w
ell
-
k
n
o
w
n
l
i
m
itatio
n
.
A
d
d
itio
n
a
ll
y
,
w
h
ile
t
h
i
s
r
esear
ch
f
o
cu
s
es o
n
f
o
u
r
b
asic
m
o
tio
n
s
,
m
o
r
e
co
m
p
le
x
s
ta
te
-
of
-
th
e
-
ar
t
s
y
s
te
m
s
o
f
f
er
f
i
n
er
co
n
tr
o
l o
p
tio
n
s
,
li
k
e
v
ar
iab
le
s
p
e
ed
s
o
r
m
u
ltid
i
m
en
s
io
n
al
co
m
m
an
d
s
,
to
en
h
an
ce
u
s
er
i
n
ter
ac
tio
n
.
T
h
u
s
,
w
h
i
le
th
e
C
NN
m
o
d
el
s
h
o
w
s
s
tr
o
n
g
p
r
ed
ictiv
e
ca
p
ab
ilit
ies,
f
u
r
t
h
e
r
w
o
r
k
in
i
m
p
r
o
v
i
n
g
r
ea
l
-
ti
m
e
ac
cu
r
ac
y
,
ad
ap
ti
n
g
to
s
i
g
n
al
d
y
n
a
m
ic
s
,
an
d
ac
h
iev
in
g
g
r
ea
ter
co
n
tr
o
l
f
le
x
i
b
ilit
y
i
s
n
ec
es
s
ar
y
to
m
a
k
e
E
E
G
-
b
ased
w
h
ee
lc
h
air
s
y
s
te
m
s
f
ea
s
ib
le
f
o
r
b
r
o
ad
er
,
r
ea
l
-
w
o
r
ld
u
s
e.
4.
CO
NCLU
SI
O
N
T
h
e
im
p
ac
t
o
f
C
NN
o
n
E
E
G
-
b
ased
w
h
ee
lch
a
ir
p
er
f
o
r
m
a
n
ce
is
co
n
s
id
er
ed
ef
f
ec
tiv
e
in
ac
cu
r
atel
y
p
r
ed
ictin
g
th
e
d
ir
ec
tio
n
o
f
t
h
e
w
h
ee
lc
h
air
.
T
h
is
is
d
o
n
e
u
s
i
n
g
r
a
w
d
ata
an
d
th
e
s
ec
o
n
d
C
NN
ar
ch
itectu
r
e
d
u
r
i
n
g
o
n
lin
e
o
r
r
ea
l
-
ti
m
e
test
i
n
g
.
T
h
e
o
f
f
li
n
e
d
ata
test
w
as
b
ased
o
n
r
a
w
an
d
R
M
S
d
ata
w
it
h
b
o
th
C
NN
a
r
ch
itec
tu
r
e
1
an
d
C
NN
a
r
ch
itectu
r
e
2
,
a
s
w
ell
as
m
o
d
el
1
an
d
m
o
d
el
2
.
I
n
C
NN
test
in
g
w
it
h
r
aw
d
ata
u
s
i
n
g
C
NN
ar
ch
itect
u
r
e
1
,
th
e
h
i
g
h
est
r
es
u
lts
o
b
tai
n
ed
w
er
e
8
5
.
4
8
6
%
in
m
o
d
el
1
an
d
9
0
.
9
9
6
%
in
m
o
d
el
2
.
I
n
th
e
o
n
lin
e
test
i
n
g
p
h
a
s
e,
it
w
as
o
b
s
er
v
ed
th
at
t
h
e
w
h
ee
lch
air
ca
n
n
o
t
b
e
s
aid
to
m
o
v
e
ac
co
r
d
in
g
to
th
e
d
esire
d
co
m
m
an
d
.
Sev
er
al
i
n
f
lu
e
n
ci
n
g
f
ac
to
r
s
,
s
u
ch
as
h
air
th
ic
k
n
es
s
an
d
t
h
e
p
h
y
s
ical
co
n
d
itio
n
o
f
th
e
r
esp
o
n
d
en
t,
w
er
e
id
en
ti
f
ied
as p
o
s
s
ib
le
ca
u
s
e
s
.
RE
F
E
R
E
NC
E
S
[
1
]
L
.
C
u
mm
i
n
g
s,
“
P
a
r
k
i
n
so
n
’
s
D
i
se
a
se
D
e
me
n
t
i
a
,
”
i
n
L
a
n
g
u
a
g
e
i
n
D
e
m
e
n
t
i
a
,
C
a
mb
r
i
d
g
e
U
n
i
v
e
r
si
t
y
P
r
e
ss,
2
0
2
0
,
p
p
.
9
5
–
1
3
2
.
d
o
i
:
1
0
.
1
0
1
7
/
9
7
8
1
1
0
8
5
8
7
9
2
1
.
0
0
5
.
[
2
]
D
.
T
.
C
o
r
r
e
i
a
,
D
.
S
t
o
y
a
n
o
v
,
a
n
d
H
.
G
.
R
.
N
e
t
o
,
“
H
o
w
t
o
d
e
f
i
n
e
t
o
d
a
y
a
me
d
i
c
a
l
d
i
so
r
d
e
r
?
B
i
o
l
o
g
i
c
a
l
a
n
d
p
sy
c
h
o
so
c
i
a
l
d
i
s
a
d
v
a
n
t
a
g
e
s
a
s
t
h
e
p
a
r
a
mo
u
n
t
c
r
i
t
e
r
i
a
,
”
J
o
u
rn
a
l
o
f
Ev
a
l
u
a
t
i
o
n
i
n
C
l
i
n
i
c
a
l
Pr
a
c
t
i
c
e
,
v
o
l
.
2
8
,
n
o
.
6
,
p
p
.
1
1
9
5
–
1
2
0
4
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
1
1
/
j
e
p
.
1
3
5
9
2
.
[
3
]
e
C
l
i
n
i
c
a
l
M
e
d
i
c
i
n
e
,
“
T
h
e
r
i
si
n
g
g
l
o
b
a
l
b
u
r
d
e
n
o
f
st
r
o
k
e
,
”
e
C
l
i
n
i
c
a
l
Me
d
i
c
i
n
e
,
v
o
l
.
5
9
,
p
.
1
0
2
0
2
8
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
c
l
i
n
m
.
2
0
2
3
.
1
0
2
0
2
8
.
[
4
]
S
.
R
a
j
a
y
y
a
n
a
n
d
S
.
M
.
M
.
M
u
s
t
a
f
a
,
“
P
r
e
d
i
c
t
i
o
n
o
f
d
e
me
n
t
i
a
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
a
n
d
p
e
r
f
o
r
man
c
e
i
mp
r
o
v
e
me
n
t
w
i
t
h
c
u
c
k
o
o
a
l
g
o
r
i
t
h
m,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
(
I
J
E
C
E)
,
v
o
l
.
1
3
,
n
o
.
4
,
p
p
.
4
6
2
3
–
4
6
3
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
4
.
p
p
4
6
2
3
-
4
6
3
2
.
[
5
]
A
.
A
.
A
b
d
u
l
h
u
sse
i
n
,
O
.
A
.
H
a
sse
n
,
C
.
G
u
p
t
a
,
D
.
V
i
r
m
a
n
i
,
A
.
N
a
i
r
,
a
n
d
P
.
R
a
n
i
,
“
H
e
a
l
t
h
mo
n
i
t
o
r
i
n
g
c
a
t
a
l
o
g
u
e
b
a
se
d
o
n
h
u
ma
n
a
c
t
i
v
i
t
y
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
(
I
J
EC
E)
,
v
o
l
.
1
2
,
n
o
.
4
,
p
p
.
3
9
7
0
–
3
9
8
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
2
i
4
.
p
p
3
9
7
0
-
3
9
8
0
.
[
6
]
Z
.
R
u
s
t
a
m
,
R
.
P
.
Y
u
d
a
,
H
.
A
l
a
t
a
s,
a
n
d
C
.
A
r
o
e
f
,
“
P
u
l
mo
n
a
r
y
r
o
n
t
g
e
n
c
l
a
ssi
f
i
c
a
t
i
o
n
t
o
d
e
t
e
c
t
p
n
e
u
mo
n
i
a
d
i
se
a
se
u
si
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
T
e
l
k
o
m
n
i
k
a
(
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
El
e
c
t
r
o
n
i
c
s
a
n
d
C
o
n
t
ro
l
)
,
v
o
l
.
1
8
,
n
o
.
3
,
p
p
.
1
5
2
2
–
1
5
2
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
2
9
2
8
/
T
EL
K
O
M
N
I
K
A
.
v
1
8
i
3
.
1
4
8
3
9
.
[
7
]
A
.
N
.
H
u
sse
i
n
,
S
.
V
.
A
l
-
D
i
n
M
a
k
k
i
,
a
n
d
A
.
A
l
-
S
a
b
b
a
g
h
,
“
C
o
mp
r
e
h
e
n
s
i
v
e
st
u
d
y
:
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
C
O
V
I
D
-
19
d
i
a
g
n
o
si
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
(
I
J
EC
E)
,
v
o
l
.
1
3
,
n
o
.
5
,
p
p
.
5
6
8
1
–
5
6
9
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
5
.
p
p
5
6
8
1
-
5
6
9
5
.
[
8
]
E.
E
.
T
.
M
a
mm
a
d
o
v
,
H
.
P
.
I
man
l
i
,
a
n
d
E.
N
.
H
u
se
y
n
,
“
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
P
r
a
c
t
i
c
e
s I
n
T
h
e
H
e
a
l
t
h
S
e
c
t
o
r
,
”
N
a
t
u
re
a
n
d
S
c
i
e
n
c
e
,
v
o
l
.
0
4
,
n
o
.
0
5
,
p
p
.
2
1
–
2
9
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
3
6
7
1
9
/
2
7
0
7
-
1
1
4
6
/
0
5
/
2
1
-
2
9
.
[
9
]
F
.
S
.
A
k
z
a
t
r
i
a
,
“
I
mp
l
e
me
n
t
a
t
i
o
n
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
H
e
a
l
t
h
c
a
r
e
,
”
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
T
e
c
h
n
o
l
o
g
y
a
n
d
Mu
l
t
i
d
i
sc
i
p
l
i
n
e
(
J
ATM)
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
6
1
–
6
6
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
2
0
4
7
3
/
j
a
t
m
.
v
2
i
2
.
4
7
0
9
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.
23
,
No
.
1
,
Feb
r
u
ar
y
20
25
:
1
47
-
1
55
154
[
1
0
]
S
.
P
.
G
o
l
h
a
r
a
n
d
S
.
S
.
K
e
k
a
p
u
r
e
,
“
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
H
e
a
l
t
h
c
a
r
e
-
A
R
e
v
i
e
w
,
”
I
n
t
.
J
.
S
c
i
.
Re
s
.
S
c
i
.
T
e
c
h
n
o
l
.
,
p
p
.
3
8
1
–
3
8
7
,
Ju
l
.
2
0
2
2
,
d
o
i
:
1
0
.
3
2
6
2
8
/
I
JS
R
S
T
2
2
9
4
5
4
.
[
1
1
]
N
.
V
e
n
k
e
t
a
su
b
r
a
m
a
n
i
a
n
,
F
.
L
.
Y
u
d
i
a
r
t
o
,
a
n
d
D
.
T
u
g
a
sw
o
r
o
,
“
S
t
r
o
k
e
B
u
r
d
e
n
a
n
d
S
t
r
o
k
e
S
e
r
v
i
c
e
s
i
n
I
n
d
o
n
e
si
a
,
”
C
e
re
b
r
o
v
a
sc
u
l
a
r
D
i
sea
ses
E
x
t
ra
,
v
o
l
.
1
2
,
n
o
.
1
,
p
p
.
5
3
–
5
7
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
/
0
0
0
5
2
4
1
6
1
.
[
1
2
]
A
.
S
e
t
i
a
w
a
n
,
A
.
A
l
F
i
t
r
i
,
N
.
S
a
’
a
d
a
h
,
N
.
A
z
-
Z
u
h
r
y
,
a
n
d
K
i
smi
a
n
t
i
n
i
,
“
M
u
l
t
i
l
e
v
e
l
l
o
g
i
st
i
c
r
e
g
r
e
ssi
o
n
a
n
a
l
y
si
s
o
n
d
e
t
e
r
mi
n
a
n
t
s
o
f
a
d
u
l
t
s
t
r
o
k
e
i
n
c
i
d
e
n
c
e
i
n
I
n
d
o
n
e
si
a
,
”
AI
P
C
o
n
f
e
r
e
n
c
e
Pr
o
c
e
e
d
i
n
g
s
,
2
0
2
4
,
p
.
1
1
0
0
0
1
.
d
o
i
:
1
0
.
1
0
6
3
/
5
.
0
1
3
3
8
6
3
.
[
1
3
]
N
.
H
.
A
l
i
,
A
.
R
.
A
b
d
u
l
l
a
h
,
N
.
M
.
S
a
a
d
,
a
n
d
A
.
S
.
M
u
d
a
,
“
B
r
a
i
n
c
o
n
e
b
e
a
m
c
o
mp
u
t
e
d
t
o
mo
g
r
a
p
h
y
i
mag
e
a
n
a
l
y
si
s
u
s
i
n
g
R
e
sN
e
t
5
0
f
o
r
c
o
l
l
a
t
e
r
a
l
c
i
r
c
u
l
a
t
i
o
n
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r E
n
g
i
n
e
e
ri
n
g
(
I
J
E
C
E)
,
v
o
l
.
1
3
,
n
o
.
5
,
p
p
.
5
8
4
3
–
5
8
5
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
5
.
p
p
5
8
4
3
-
5
8
5
2
.
[
1
4
]
L
.
P
.
D
r
e
ss
e
r
a
n
d
M
.
A
.
K
o
h
n
,
“
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
t
h
e
Ev
a
l
u
a
t
i
o
n
a
n
d
T
r
e
a
t
me
n
t
o
f
S
t
r
o
k
e
,
”
D
e
l
a
w
a
r
e
J
o
u
r
n
a
l
o
f
Pu
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
9
,
n
o
.
3
,
p
p
.
8
2
–
8
4
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
3
2
4
8
1
/
d
j
p
h
.
2
0
2
3
.
0
8
.
0
1
4
.
[
1
5
]
A
.
A
h
m
a
d
,
M
.
U
s
a
m
a
,
a
n
d
Y
.
N
i
a
z
K
h
a
n
,
“
E
a
r
l
y
s
t
r
o
k
e
d
i
s
e
a
se
p
r
e
d
i
c
t
i
o
n
w
i
t
h
f
a
c
i
a
l
f
e
a
t
u
r
e
s
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
m
o
d
e
l
,
”
I
A
E
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
I
J
-
A
I
)
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
9
3
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
3
.
i
1
.
p
p
9
3
3
-
9
4
0
.
[
1
6
]
D
.
S
.
K
o
r
t
i
a
n
d
Z
.
S
l
i
m
a
n
e
,
“
U
n
o
b
t
r
u
s
i
v
e
h
a
n
d
g
e
s
t
u
r
e
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
u
l
t
r
a
-
w
i
d
e
b
a
n
d
r
a
d
a
r
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
(
I
J
E
C
E
)
,
v
o
l
.
1
3
,
n
o
.
6
,
p
p
.
6
8
7
2
–
6
8
8
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
6
.
p
p
6
8
7
2
-
6
8
8
1
.
[
1
7
]
E.
C
.
D
j
a
mal
,
D
.
P
.
G
u
st
i
a
w
a
n
,
a
n
d
D
.
D
j
a
j
a
sasm
i
t
a
,
“
S
i
g
n
i
f
i
c
a
n
t
v
a
r
i
a
b
l
e
s
e
x
t
r
a
c
t
i
o
n
o
f
p
o
st
-
s
t
r
o
k
e
EEG
s
i
g
n
a
l
u
si
n
g
w
a
v
e
l
e
t
a
n
d
S
O
M
k
o
h
o
n
e
n
,
”
T
e
l
k
o
m
n
i
k
a
(
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
El
e
c
t
r
o
n
i
c
s
a
n
d
C
o
n
t
r
o
l
)
,
v
o
l
.
1
7
,
n
o
.
3
,
p
p
.
1
1
4
9
–
1
1
5
8
,
2
0
1
9
,
d
o
i
:
1
0
.
1
2
9
2
8
/
T
EL
K
O
M
N
I
K
A
.
V
1
7
I
3
.
1
1
7
7
6
.
[
1
8
]
E.
B
o
u
r
e
l
-
P
o
n
c
h
e
l
e
t
a
l
.
,
“
N
o
r
mal
EE
G
d
u
r
i
n
g
t
h
e
n
e
o
n
a
t
a
l
p
e
r
i
o
d
:
mat
u
r
a
t
i
o
n
a
l
a
s
p
e
c
t
s
f
r
o
m
p
r
e
ma
t
u
r
e
t
o
f
u
l
l
-
t
e
r
m
n
e
w
b
o
r
n
s,”
N
e
u
ro
p
h
y
s
i
o
l
o
g
i
e
C
l
i
n
i
q
u
e
,
p
p
.
1
–
1
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
l
i
.
2
0
2
0
.
1
0
.
0
0
4
.
[
1
9
]
M
.
M
.
A
b
d
u
l
g
h
a
n
i
,
W
.
L
.
W
a
l
t
e
r
s,
a
n
d
K
.
H
.
A
b
e
d
,
“
EEG
C
l
a
ssi
f
i
e
r
U
si
n
g
W
a
v
e
l
e
t
S
c
a
t
t
e
r
i
n
g
T
r
a
n
sf
o
r
m
-
B
a
se
d
F
e
a
t
u
r
e
s
a
n
d
D
e
e
p
L
e
a
r
n
i
n
g
f
o
r
W
h
e
e
l
c
h
a
i
r
S
t
e
e
r
i
n
g
,
”
i
n
2
0
2
2
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
S
c
i
e
n
c
e
a
n
d
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
C
S
C
I
)
,
I
EEE,
D
e
c
.
2
0
2
2
,
p
p
.
4
0
1
–
4
0
5
.
d
o
i
:
1
0
.
1
1
0
9
/
C
S
C
I
5
8
1
2
4
.
2
0
2
2
.
0
0
0
7
7
.
[
2
0
]
B.
-
V
.
N
g
o
a
n
d
T
.
-
H
.
N
g
u
y
e
n
,
“
A
S
e
mi
-
A
u
t
o
mat
i
c
W
h
e
e
l
c
h
a
i
r
w
i
t
h
N
a
v
i
g
a
t
i
o
n
B
a
se
d
o
n
V
i
r
t
u
a
l
-
R
e
a
l
2
D
G
r
i
d
M
a
p
s
a
n
d
EEG
S
i
g
n
a
l
s,”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
1
7
,
p
.
8
8
8
0
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
1
7
8
8
8
0
.
[
2
1
]
Z
.
R
.
S
.
Z
u
b
a
i
r
,
“
A
D
e
e
p
L
e
a
r
n
i
n
g
b
a
se
d
O
p
t
i
mi
z
a
t
i
o
n
M
o
d
e
l
f
o
r
B
a
se
d
C
o
mp
u
t
e
r
I
n
t
e
r
f
a
c
e
o
f
W
h
e
e
l
c
h
a
i
r
D
i
r
e
c
t
i
o
n
a
l
C
o
n
t
r
o
l
,
”
T
i
k
ri
t
J
o
u
r
n
a
l
o
f
Pu
re
S
c
i
e
n
c
e
,
v
o
l
.
2
6
,
n
o
.
1
,
p
p
.
1
0
8
–
1
1
2
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
2
5
1
3
0
/
t
j
p
s
.
v
2
6
i
1
.
1
0
7
.
[
2
2
]
K
.
S
.
A
s
w
i
n
,
M
.
P
u
r
u
s
h
o
t
h
a
ma
n
,
P
.
S
r
i
t
h
a
r
a
n
i
a
n
d
A
.
T
.
S
,
"
A
N
N
a
n
d
D
e
e
p
L
e
a
r
n
i
n
g
C
l
a
ss
i
f
i
e
r
s
f
o
r
B
C
I
a
p
p
l
i
c
a
t
i
o
n
s,"
2
0
2
2
T
h
i
r
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
i
n
g
I
n
st
r
u
m
e
n
t
a
t
i
o
n
a
n
d
C
o
n
t
r
o
l
T
e
c
h
n
o
l
o
g
i
e
s
(
I
C
I
C
I
C
T
)
,
K
a
n
n
u
r
,
I
n
d
i
a
,
2
0
2
2
,
p
p
.
1
6
0
3
-
1
6
0
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
I
C
T
5
4
5
5
7
.
2
0
2
2
.
9
9
1
7
8
3
4
.
[
2
3
]
W
.
Z
.
e
t
a
l
.
,
“
D
e
e
p
L
e
a
r
n
i
n
g
A
I
A
p
p
l
i
c
a
t
i
o
n
t
o
a
n
EEG
d
r
i
v
e
n
B
C
I
S
mart
W
h
e
e
l
c
h
a
i
r
,
”
i
n
2
0
1
9
A
d
v
a
n
c
e
s
i
n
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
y
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
s (A
S
ET)
,
2
0
1
9
,
p
p
.
1
–
5
.
d
o
i
:
0
.
1
1
0
9
/
I
C
A
S
E
T
.
2
0
1
9
.
8
7
1
4
3
7
3
.
[
2
4
]
A
.
A
.
El
n
g
a
r
e
t
a
l
.
,
“
I
mag
e
C
l
a
ssi
f
i
c
a
t
i
o
n
B
a
se
d
O
n
C
N
N
:
A
S
u
r
v
e
y
,
”
J
o
u
r
n
a
l
o
f
C
y
b
e
rs
e
c
u
ri
t
y
a
n
d
I
n
f
o
rm
a
t
i
o
n
Ma
n
a
g
e
m
e
n
t
, p
p
.
18
-
5
0
,
2
0
2
1
,
d
o
i
:
1
0
.
5
4
2
1
6
/
JC
I
M
.
0
6
0
1
0
2
.
[
2
5
]
A
.
D
e
r
r
y
,
M
.
K
r
z
y
w
i
n
sk
i
,
a
n
d
N
.
A
l
t
man
,
“
C
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
N
a
t
u
re
M
e
t
h
o
d
s
,
v
o
l
.
2
0
,
n
o
.
9
,
p
p
.
1
2
6
9
–
1
2
7
0
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
2
-
0
2
3
-
0
1
9
7
3
-
1.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
K
h
a
iru
l
A
n
a
m
is
a
L
e
c
tu
re
r
a
t
t
h
e
De
p
a
rtm
e
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
Un
iv
e
rsit
y
o
f
Je
m
b
e
r,
In
d
o
n
e
sia
.
He
h
o
ld
s a
P
h
.
D
.
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
w
it
h
sp
e
c
ializa
ti
o
n
i
n
Re
h
a
b
il
it
a
ti
o
n
R
o
b
o
t
a
t
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
a
n
d
IT
,
U
n
iv
e
rsity
o
f
T
e
c
h
n
o
lo
g
y
S
y
d
n
e
y
,
A
u
stra
li
a
.
His
re
se
a
r
c
h
a
re
a
s
a
re
in
telli
g
e
n
t
c
o
n
tr
o
l
sy
ste
m
,
ro
b
o
t
lea
rn
in
g
,
b
i
o
-
sig
n
a
l
p
r
o
c
e
ss
in
g
,
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
,
a
n
d
d
e
e
p
lea
rn
in
g
.
He
is
th
e
h
e
a
d
o
f
In
telli
g
e
n
t
S
y
ste
m
a
n
d
Ro
b
o
ti
c
s
L
a
b
o
ra
to
ry
-
CD
A
S
T
Re
se
a
rc
h
Lab
o
f
Je
m
b
e
r
Un
iv
e
rsity
.
He
is
th
e
re
c
ip
ien
t
o
f
v
a
rio
u
s
a
wa
rd
s
su
c
h
a
s
th
e
b
e
st
p
a
p
e
r
a
w
a
rd
a
t
th
e
3
rd
I
n
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
on
S
o
f
t
Co
m
p
u
ti
n
g
in
D
a
ta
S
c
ien
c
e
2
0
1
7
(S
CDS2
0
1
7
),
a
w
a
rd
s
sa
t
y
a
l
a
n
c
a
n
a
k
a
r
y
a
sa
t
y
a
o
f
th
e
y
e
a
r
x
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
h
a
iru
l@u
n
e
j.
a
c
.
id
.
S
a
tr
io
M
a
r
ta
W
ica
k
s
o
n
o
b
o
r
n
o
n
M
a
rc
h
8
,
1
9
9
9
,
in
Ke
n
d
a
l,
Ce
n
tral
Ja
v
a
,
he
is
a
Ba
c
h
e
lo
r
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
f
ro
m
th
e
Un
iv
e
rsit
y
o
f
Je
m
b
e
r,
sp
e
c
ia
li
z
in
g
in
Co
n
tr
o
l
S
y
st
e
m
s
a
n
d
El
e
c
tro
n
ics
(2
0
1
7
).
He
jo
in
e
d
t
h
e
In
telli
g
e
n
t
S
y
ste
m
a
n
d
Ro
b
o
ti
c
s
L
a
b
,
se
rv
e
d
a
s
a
Co
n
tro
l
S
y
ste
m
L
a
b
A
ss
ista
n
t,
a
n
d
a
c
ti
v
e
ly
p
a
rti
c
ip
a
ted
in
st
u
d
e
n
t
a
c
ti
v
it
y
u
n
it
s
.
He
is
p
re
p
a
re
d
t
o
c
o
n
tri
b
u
te
t
o
in
d
u
stry
4
.
0
th
r
o
u
g
h
A
I
s
y
st
e
m
d
e
v
e
lo
p
m
e
n
t
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
tri
o
m
a
rta0
8
@g
m
a
il
.
c
o
m
.
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
E
lectro
en
ce
p
h
a
lo
g
r
a
p
h
y
-
b
a
s
e
d
w
h
ee
lch
a
ir
n
a
vig
a
tio
n
co
n
tr
o
l u
s
in
g
co
n
vo
lu
tio
n
a
l n
eu
r
a
l
…
(
K
h
a
ir
u
l A
n
a
m
)
155
M
u
c
h
a
m
a
d
Ar
if
H
a
n
a
S
a
so
n
o
b
o
r
n
o
n
No
v
e
m
b
e
r
2
3
,
1
9
9
9
,
in
M
o
jo
k
e
rto
,
Eas
t
Ja
v
a
,
is
a
d
e
d
ica
ted
M
a
ste
r
’
s
stu
d
e
n
t
i
n
El
e
c
tri
c
a
l
E
n
g
in
e
e
rin
g
a
t
th
e
Un
iv
e
rsity
o
f
Je
m
b
e
r.
He
se
r
v
e
s
a
s
a
re
se
a
rc
h
a
ss
istan
t
a
t
t
h
e
I
n
telli
g
e
n
t
S
y
ste
m
s
a
n
d
Ro
b
o
ti
c
s
L
a
b
,
w
it
h
a
f
o
c
u
s
o
n
d
e
v
e
lo
p
in
g
i
n
telli
g
e
n
t
sy
ste
m
s
a
n
d
r
o
b
o
ti
c
s.
H
o
ld
in
g
a
Ba
c
h
e
lo
r
’
s
d
e
g
re
e
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
(2
0
1
8
-
2
0
2
2
)
f
ro
m
th
e
sa
m
e
u
n
iv
e
rsity
,
he
h
a
s
c
o
n
siste
n
tl
y
e
x
c
e
ll
e
d
i
n
h
is
stu
d
ies
.
Driv
e
n
b
y
a
p
a
ss
io
n
f
o
r
A
I
a
n
d
it
s
p
o
ten
t
ial
to
e
n
h
a
n
c
e
d
a
il
y
li
fe
,
h
e
is
p
re
p
a
re
d
t
o
m
a
k
e
i
m
p
a
c
tf
u
l
c
o
n
tri
b
u
t
io
n
s
to
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
a
n
d
A
I
f
ield
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
rif
h
a
n
a
0
4
@g
m
a
il
.
c
o
m
.
B
im
a
W
a
h
y
u
M
a
u
l
a
n
a
is
a
M
a
ste
r
’
s
stu
d
e
n
t
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
n
d
re
se
a
rc
h
e
r
in
th
e
In
telli
g
e
n
t
S
y
ste
m
s
a
n
d
Ro
b
o
ti
c
s
L
a
b
a
t
th
e
Un
iv
e
rsity
o
f
Je
m
b
e
r.
He
h
o
ld
s
a
Ba
c
h
e
lo
r
’
s
in
P
h
y
sic
s,
f
o
c
u
se
d
o
n
E
lec
tro
n
ics
a
n
d
I
n
stru
m
e
n
tatio
n
.
Bo
rn
in
Je
m
b
e
r
o
n
M
a
y
8
,
1
9
9
9
,
h
e
is
c
u
rre
n
tl
y
re
se
a
rc
h
in
g
EE
G
-
b
a
se
d
m
o
to
r
im
a
g
e
r
y
w
it
h
CNN
sy
ste
m
s,
a
im
in
g
to
a
p
p
ly
in
telli
g
e
n
t
ro
b
o
ti
c
s
so
lu
ti
o
n
s
a
c
ro
ss
I
n
d
o
n
e
sia
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
im
a
w
a
h
y
u
m
a
u
lan
a
@g
m
a
il
.
c
o
m
.
Fa
t
k
h
u
l
M
u
b
a
r
o
k
is
a
n
u
n
d
e
r
g
ra
d
u
a
te
stu
d
e
n
t
in
El
e
c
tri
c
a
l
E
n
g
in
e
e
rin
g
a
t
th
e
Un
iv
e
rsit
y
o
f
Je
m
b
e
r
,
w
h
e
re
h
e
b
e
g
a
n
h
is
st
u
d
ies
in
2
0
2
1
.
He
is
a
re
se
a
rc
h
a
ss
istan
t
in
th
e
In
telli
g
e
n
t
S
y
ste
m
s
a
n
d
Ro
b
o
ti
c
s
L
a
b
o
ra
to
ry
a
t
CD
A
S
T
.
Bo
rn
o
n
Ja
n
u
a
ry
2
4
,
2
0
0
3
,
in
Ke
d
iri
,
Eas
t
Ja
v
a
,
h
e
is
p
a
ss
io
n
a
te
a
b
o
u
t
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
a
n
d
ro
b
o
t
ics
.
His
c
u
rre
n
t
re
se
a
rc
h
f
o
c
u
se
s
o
n
d
e
v
e
lo
p
in
g
i
n
telli
g
e
n
t
sy
st
e
m
s
a
n
d
ro
b
o
ti
c
s,
d
riv
e
n
b
y
a
d
e
sire
to
e
x
p
lo
re
t
h
e
p
o
ten
ti
a
l
o
f
a
rti
f
icia
l
in
telli
g
e
n
c
e
to
e
n
h
a
n
c
e
d
a
il
y
li
f
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
f
a
t
k
h
u
lm
u
b
a
ro
k
0
8
@g
m
a
il
.
c
o
m
.
An
a
n
t
a
Pi
n
se
n
tiu
s
R
a
h
m
a
t
Pa
m
u
n
g
k
a
s
a
n
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
stu
d
e
n
t
a
t
th
e
Un
iv
e
rsit
y
o
f
Je
m
b
e
r,
f
o
c
u
s
e
d
o
n
ro
b
o
t
ics
,
a
u
t
o
m
a
ti
o
n
,
a
n
d
A
I.
W
it
h
e
x
p
e
rien
c
e
i
n
ro
b
o
ti
c
s
c
o
m
p
e
ti
ti
o
n
s,
h
e
c
o
n
tri
b
u
tes
a
s
a
re
se
a
rc
h
a
ss
istan
t
in
t
h
e
In
telli
g
e
n
t
S
y
ste
m
a
n
d
Ro
b
o
ti
c
s
L
a
b
.
A
s
tea
m
lea
d
e
r
o
f
t
h
e
u
n
iv
e
r
sity
’s
so
c
c
e
r
ro
b
o
t
T
e
a
m
,
h
e
w
o
rk
s
o
n
a
d
v
a
n
c
in
g
a
u
to
n
o
m
o
u
s
so
c
c
e
r
r
o
b
o
ts
t
h
r
o
u
g
h
A
I
in
teg
ra
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
a
n
tav
in
c
e
n
t1
@g
m
a
il
.
c
o
m
.
M
o
c
h
.
Rija
l
Fa
to
n
i
Ba
c
h
e
lo
r
’
s
d
e
g
re
e
in
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
,
sp
e
c
ializin
g
in
Co
n
tr
o
l
S
y
ste
m
s
a
n
d
El
e
c
tro
n
ics
,
f
ro
m
th
e
Un
iv
e
rsity
o
f
J
e
m
b
e
r.
Bo
rn
o
n
A
u
g
u
st
1
0
,
2
0
0
1
,
in
P
r
o
b
o
li
n
g
g
o
,
Eas
t
Ja
v
a
,
Rij
a
l
jo
in
e
d
in
2
0
2
0
a
n
d
h
a
s
b
e
e
n
a
n
a
c
ti
v
e
m
e
m
b
e
r
o
f
th
e
Ro
b
o
t
ics
T
e
a
m
,
re
p
re
s
e
n
ti
n
g
th
e
u
n
iv
e
rsit
y
n
a
ti
o
n
a
ll
y
.
As
a
re
se
a
rc
h
a
ss
istan
t
in
t
h
e
In
telli
g
e
n
t
S
y
ste
m
a
n
d
Ro
b
o
ti
c
s
L
a
b
,
h
e
f
o
c
u
se
s
o
n
in
telli
g
e
n
t
c
o
n
tro
l
sy
ste
m
s
a
n
d
ro
b
o
ti
c
s
to
e
n
h
a
n
c
e
h
u
m
a
n
a
c
ti
v
it
y
.
W
it
h
a
c
o
m
m
it
m
e
n
t
to
AI d
e
v
e
lo
p
m
e
n
t,
h
e
is p
re
p
a
re
d
to
c
o
n
tri
b
u
te
to
t
h
e
f
u
tu
re
o
f
In
d
u
stry
4
.
0
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
rij
a
lf
a
to
o
n
i@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.