I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l
I
nte
llig
ence
(
I
J
-
AI
)
Vo
l.
7
,
No
.
2
,
J
u
n
e
201
8
,
p
p
.
105
~
1
1
0
I
SS
N:
2252
-
8938
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ai.
v
7
.
i2
.
p
p
105
-
1
1
0
105
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JA
I
Security So
lu
tion
s Using
Bra
in Sig
na
ls
Anup
a
m
a
.
H
.
S
1
,
Anu
s
ha
M
2
,
Apa
rna
J
o
s
hi
3
,
Apo
o
rv
a
N
4
,
N.
K
.
Ca
uv
er
y
5
,
L
ing
a
ra
j
u.G
.
M
6
1
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Sc.
an
d
E
n
g
in
ee
r
i
n
g
,
R
.
V.
C
o
lleg
e
o
f
E
n
g
g
.
,
B
an
g
a
lo
r
e,
I
n
d
ia
2,
3,
4,
5
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
Sc.
an
d
E
n
g
i
n
ee
r
in
g
,
R
.
V.
C
o
lleg
e
o
f
E
n
g
g
.
,
B
an
g
alo
r
e,
I
n
d
ia
6
Dep
ar
t
m
en
t o
f
I
n
f
o
r
m
atio
n
S
c.
,
M.
S.
R
a
m
aiah
I
n
s
ti
tu
te
o
f
T
ec
h
.
,
B
an
g
alo
r
e,
I
n
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
2
1
,
2
0
1
8
R
ev
i
s
ed
Mar
7
,
2
0
1
8
A
cc
ep
ted
Mar
19
,
2
0
1
8
A
b
ra
in
c
o
m
p
u
ter
i
n
terf
a
c
e
is
a
d
irec
t
n
e
u
ra
l
in
terf
a
c
e
o
r
a
b
ra
in
–
m
a
c
h
in
e
in
terf
a
c
e
.
It
p
ro
v
id
e
s
a
c
o
m
m
u
n
ica
ti
o
n
p
a
t
h
b
e
tw
e
e
n
h
u
m
a
n
b
ra
in
a
n
d
th
e
c
o
m
p
u
ter
s
y
st
e
m
.
It
a
i
m
s
to
c
o
n
v
e
y
p
e
o
p
le'
s
in
ten
ti
o
n
s
to
th
e
o
u
t
sid
e
w
o
rld
d
irec
tl
y
f
ro
m
th
e
ir
th
o
u
g
h
ts.
T
h
is
p
a
p
e
r
f
o
c
u
se
s
o
n
c
u
rre
n
t
m
o
d
e
l
w
h
ich
u
se
s
b
ra
in
sig
n
a
ls
f
o
r
th
e
a
u
th
e
n
ti
c
a
ti
o
n
o
f
u
se
rs.
T
h
e
El
e
c
tro
-
e
n
c
e
p
h
a
lo
g
ra
m
(EE
G
)
si
g
n
a
ls
a
re
re
c
o
rd
e
d
f
ro
m
th
e
n
e
u
ro
h
e
a
d
se
t
w
h
e
n
a
u
se
r
i
s
sh
o
w
n
a
ke
y
i
m
a
g
e
(sig
n
a
tu
re
i
m
a
g
e
).
Th
e
se
sig
n
a
ls
a
re
f
u
rth
e
r
p
ro
c
e
ss
e
d
a
n
d
a
re
in
terp
re
ted
to
o
b
tain
th
e
t
h
o
u
g
h
t
p
a
tt
e
rn
o
f
th
e
u
se
r
to
m
a
tch
th
e
m
to
th
e
sto
re
d
p
a
ss
w
o
rd
in
t
h
e
sy
st
e
m
.
Ev
e
n
if
o
th
e
r
p
e
rso
n
is
p
re
se
n
ted
w
it
h
th
e
sa
m
e
k
e
y
i
m
a
g
e
it
f
a
il
s
to
a
u
th
e
n
ti
c
a
te
a
s
th
e
c
o
rti
c
a
l
f
o
ld
s
o
f
th
e
b
ra
in
a
re
u
n
i
q
u
e
t
o
e
a
c
h
h
u
m
a
n
b
e
in
g
ju
st
l
ik
e
a
f
in
g
e
rp
rin
t
o
r
DN
A
.
K
ey
w
o
r
d
:
B
r
ain
Sig
n
als
Secu
r
it
y
So
lu
tio
n
s
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
An
u
p
a
m
a.
H.
S
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Sc.
a
n
d
E
n
g
in
ee
r
i
n
g
,
R
.
V.
C
o
lleg
e
o
f
E
n
g
g
.
,
B
an
g
a
lo
r
e,
I
n
d
ia
E
m
ail:
a
n
u
p
a
m
ah
s
@
r
v
ce
.
ed
u
.
i
n
1.
I
NT
RO
D
UCT
I
O
N
A
B
r
ain
-
C
o
m
p
u
ter
I
n
ter
f
ac
e
(
B
C
I
)
,
o
f
ten
ca
l
led
a
Mi
n
d
-
Ma
ch
i
n
e
I
n
ter
f
ac
e
(
MM
I
)
,
o
r
s
o
m
et
i
m
e
s
ca
lled
a
b
r
ain
–
m
ac
h
i
n
e
in
ter
f
a
ce
(
B
MI
)
is
a
d
ir
ec
t
c
o
m
m
u
n
i
ca
tio
n
p
ath
w
a
y
b
et
w
ee
n
th
e
b
r
ain
an
d
an
e
x
ter
n
al
d
ev
ice
[
1
]
.
B
r
ain
-
co
m
p
u
ter
i
n
ter
f
ac
e
(
B
C
I
)
is
a
n
e
m
er
g
i
n
g
tec
h
n
o
lo
g
y
w
h
ic
h
ai
m
s
t
o
co
n
v
e
y
p
eo
p
le's
in
te
n
tio
n
s
to
th
e
o
u
ts
id
e
w
o
r
ld
d
ir
ec
tl
y
f
r
o
m
t
h
eir
t
h
o
u
g
h
t
s
[
2
]
,
en
h
an
ci
n
g
co
g
n
iti
v
e
ca
p
ab
ilit
ies.
B
C
I
s
ar
e
o
f
ten
d
ir
ec
ted
at
ass
is
ti
n
g
,
au
g
m
e
n
ti
n
g
o
r
r
ep
air
i
n
g
h
u
m
a
n
co
g
n
iti
v
e
o
r
s
en
s
o
r
y
-
m
o
to
r
f
u
n
ctio
n
s
.
B
C
I
s
ar
e
u
s
ed
in
v
ar
io
u
s
ap
p
licatio
n
s
,
s
u
c
h
a
s
w
h
ee
lch
a
i
r
,
r
o
b
o
tic
ar
m
co
n
tr
o
ller
s
,
m
en
tal
s
p
eller
s
a
n
d
n
eu
r
o
p
r
o
s
th
etic
s
ap
p
licatio
n
s
w
h
ic
h
ai
m
at
r
es
to
r
in
g
d
a
m
a
g
ed
h
ea
r
in
g
,
s
ig
h
t a
n
d
m
o
v
e
m
e
n
t [
3
]
.
B
C
I
is
co
llab
o
r
atio
n
b
et
w
ee
n
a
b
r
ain
an
d
a
d
ev
ice
th
at
en
ab
les
s
ig
n
al
s
f
r
o
m
th
e
b
r
ain
to
d
ir
ec
t
s
o
m
e
ex
ter
n
al
ac
ti
v
it
y
.
B
y
r
ea
d
in
g
s
ig
n
al
s
f
r
o
m
a
n
ar
r
ay
o
f
n
e
u
r
o
n
s
an
d
u
s
in
g
co
m
p
u
ter
ch
ip
s
an
d
p
r
o
g
r
a
m
s
to
tr
an
s
late
th
e
s
i
g
n
al
s
i
n
to
ac
tio
n
,
B
C
I
ca
n
e
n
ab
le
a
p
er
s
o
n
s
u
f
f
er
in
g
f
r
o
m
p
ar
al
y
s
is
to
w
r
ite
a
b
o
o
k
o
r
co
n
tr
o
l
a
m
o
to
r
ized
w
h
ee
lc
h
air
o
r
p
r
o
s
th
etic
li
m
b
t
h
r
o
u
g
h
t
h
o
u
g
h
t
al
o
n
e.
E
E
G
is
th
e
s
i
g
n
a
l
t
h
at
i
s
u
s
ed
to
ac
q
u
ir
e
th
e
s
ig
n
al
s
f
r
o
m
th
e
b
r
ain
.
E
E
G
is
a
r
ec
o
r
d
o
f
th
e
elec
tr
ic
s
ig
n
al
g
e
n
er
ated
b
y
th
e
co
o
p
er
ativ
e
ac
tio
n
o
f
b
r
ain
ce
lls
,
o
r
m
o
r
e
p
r
ec
is
el
y
,
t
h
e
ti
m
e
co
u
r
s
e
o
f
ex
tr
ac
ell
u
lar
f
ield
p
o
ten
tial
s
g
e
n
er
ated
b
y
th
eir
s
y
n
c
h
r
o
n
o
u
s
ac
tio
n
.
Neu
r
o
n
s
ar
e
r
esp
o
n
s
ib
le
f
o
r
s
e
n
d
in
g
t
h
e
i
n
s
tr
u
ctio
n
s
g
en
er
ated
b
y
b
r
ai
n
to
v
ar
io
u
s
p
ar
ts
o
f
th
e
b
o
d
y
.
T
h
ese
n
eu
r
o
n
s
w
il
l
p
ass
th
e
i
n
s
tr
u
ctio
n
s
f
r
o
m
o
n
e
to
an
o
th
er
,
d
u
r
in
g
th
i
s
co
u
r
s
e
o
f
ac
tio
n
Na+
an
d
K+
io
n
s
w
il
l
r
ea
ct
lead
in
g
to
th
e
g
en
er
atio
n
o
f
an
elec
tr
ic
p
o
ten
tial.
Du
r
in
g
ev
er
y
ac
ti
v
it
y
s
u
c
h
a
p
o
ten
tial
is
g
en
er
a
ted
w
h
ic
h
is
m
ea
s
u
r
ed
as E
E
G.
Secu
r
it
y
s
y
s
te
m
s
i
n
v
o
lv
e
k
n
o
w
led
g
e
b
ased
,
o
b
j
ec
t
b
ased
an
d
/o
r
b
io
m
etr
ics
b
ased
au
t
h
en
t
icatio
n
.
T
h
ey
h
a
v
e
s
h
o
w
n
to
b
e
v
u
ln
er
ab
le
to
s
ev
er
al
d
r
a
w
b
ac
k
s
s
u
c
h
as
s
i
m
p
le
in
s
ec
u
r
e
p
ass
w
o
r
d
,
s
h
o
u
ld
er
s
u
r
f
i
n
g
,
th
e
f
t
cr
i
m
e,
an
d
ca
n
ce
lab
le
b
io
m
e
tr
ics
[
1
5
]
.
C
o
g
n
iti
v
e
b
io
m
e
tr
ics
o
r
elec
tr
o
p
h
y
s
i
o
lo
g
y
,
w
h
er
e
o
n
l
y
m
o
d
ali
ties
u
s
in
g
b
io
s
ig
n
al
s
(
s
u
c
h
a
s
b
r
ain
s
i
g
n
a
ls
)
ar
e
u
s
ed
as
s
o
u
r
ce
s
o
f
id
en
tit
y
in
f
o
r
m
atio
n
,
g
iv
e
s
a
s
o
lu
tio
n
f
o
r
th
o
s
e
v
u
l
n
er
ab
ilit
ies
[
1
6
]
an
d
[
1
7
]
.
T
h
e
m
o
tiv
a
tio
n
b
eh
i
n
d
ex
p
lo
r
in
g
th
e
f
ea
s
ib
ili
t
y
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
7
,
No
.
2
,
J
u
n
e
20
1
8
:
1
0
5
–
1
1
0
106
elec
tr
o
p
h
y
s
io
lo
g
y
is
t
h
at
b
io
s
ig
n
a
ls
ca
n
n
o
t
b
e
ca
s
u
all
y
ac
q
u
ir
ed
b
y
e
x
ter
n
a
l
o
b
s
er
v
er
s
.
T
h
ey
also
ca
n
b
e
o
f
g
r
ea
t
v
a
lu
e
f
o
r
d
is
ab
led
p
atie
n
ts
o
r
u
s
er
s
m
is
s
in
g
t
h
e
a
s
s
o
c
iated
p
h
y
s
ical
tr
ait
[
1
8
]
.
T
h
is
m
ak
e
s
s
u
c
h
s
ig
n
al
s
d
if
f
ic
u
lt
to
s
y
n
t
h
esize
a
n
d
t
h
er
ef
o
r
e
i
m
p
r
o
v
e
s
th
e
r
e
s
is
t
an
ce
o
f
b
io
m
etr
ic
s
y
s
te
m
s
t
o
s
p
o
o
f
in
g
at
tack
s
.
B
esid
es
elec
tr
o
en
ce
p
h
alo
g
r
a
m
(
E
E
G)
,
as
a
b
io
m
etr
ic
m
o
d
al
it
y
,
co
u
ld
b
e
u
s
ed
to
s
en
d
co
v
er
t
w
ar
n
i
n
g
w
h
e
n
th
e
au
t
h
o
r
ized
u
s
er
is
u
n
d
e
r
ex
ter
n
al
f
o
r
ci
n
g
co
n
d
it
io
n
s
,
as i
m
p
le
m
e
n
ted
i
n
[
1
9
]
.
2.
P
URP
O
SE
/S
CO
P
E
/M
O
T
I
V
AT
I
O
N
T
h
e
p
u
r
p
o
s
e
o
f
th
is
w
o
r
k
is
to
d
ev
elo
p
a
b
io
m
etr
ic
s
ec
u
r
it
y
s
y
s
te
m
.
A
n
e
w
id
ea
h
as b
ee
n
p
r
o
p
o
s
ed
to
d
ev
elo
p
th
is
s
y
s
te
m
.
T
h
is
s
y
s
te
m
ta
k
es
E
E
G
s
i
g
n
als
r
ec
o
r
d
ed
d
u
r
in
g
a
u
s
er
'
s
ac
t
i
v
it
y
as
in
p
u
t
a
n
d
au
th
e
n
tica
tes
t
h
e
u
s
er
.
T
h
e
in
p
u
t
E
E
G
w
av
e
s
ar
e
p
r
o
ce
s
s
ed
an
d
a
u
n
iq
u
e
s
ig
n
at
u
r
e
is
g
e
n
er
ated
.
T
h
is
s
ig
n
at
u
r
e
i
s
u
s
ed
f
o
r
u
s
er
id
en
ti
f
icatio
n
.
T
h
e
n
ee
d
f
o
r
r
o
b
u
s
t
s
ec
u
r
it
y
s
y
s
te
m
is
i
n
cr
ea
s
i
n
g
d
a
y
b
y
d
a
y
.
T
h
e
ex
is
t
in
g
s
ec
u
r
it
y
s
y
s
te
m
s
s
u
ch
a
s
p
ass
w
o
r
d
s
,
P
er
s
o
n
al
I
d
en
tific
atio
n
Nu
m
b
er
s
(
P
I
N)
,
b
io
m
etr
ic
s
y
s
te
m
s
w
h
ic
h
in
cl
u
d
e
f
i
n
g
er
p
r
in
t
tec
h
n
o
lo
g
y
,
r
eti
n
al
s
ca
n
ar
e
b
e
co
m
in
g
v
u
l
n
er
ab
le
to
attac
k
s
.
T
h
is
is
b
ec
au
s
e,
p
ass
w
o
r
d
s
an
d
P
I
Ns
ca
n
b
e
g
u
e
s
s
ed
b
y
b
r
u
te
f
o
r
ce
ap
p
r
o
ac
h
,
f
in
g
er
p
r
in
t
s
ca
n
b
e
o
b
tain
ed
w
h
en
an
u
s
er
to
u
ch
e
s
a
n
y
p
h
y
s
ica
l
o
b
j
ec
t.
Ho
w
e
v
er
,
E
E
G
w
a
v
es
e
m
er
g
i
n
g
f
r
o
m
b
r
ain
ca
n
n
eit
h
er
b
e
g
u
e
s
s
ed
n
o
r
co
p
ied
.
T
h
e
co
r
tical
f
o
ld
s
o
f
t
h
e
b
r
ai
n
ar
e
u
n
iq
u
e
to
ea
c
h
h
u
m
an
b
ein
g
j
u
s
t
l
ik
e
a
f
i
n
g
er
p
r
in
t
o
r
DN
A
[
1
0
]
.
E
v
en
th
o
u
g
h
th
e
elec
tr
o
d
es
ar
e
p
lace
d
o
n
th
e
s
a
m
e
p
o
s
itio
n
o
n
th
e
b
r
ain
,
th
e
E
E
G
s
i
g
n
a
ls
f
o
r
th
o
u
g
h
ts
o
r
ac
tio
n
s
o
r
ig
in
ate
f
r
o
m
d
if
f
er
en
t
p
ar
ts
o
f
th
e
b
r
ain
lead
in
g
to
a
u
n
iq
u
e
s
ig
n
a
tu
r
e
o
f
a
u
s
er
.
T
h
is
w
a
s
th
e
m
o
tiv
a
tio
n
f
o
r
th
is
w
o
r
k
.
T
h
e
f
ac
t
t
h
at
th
o
u
g
h
t
o
f
a
p
er
s
o
n
is
u
n
iq
u
e
ca
n
b
e
u
s
ed
a
s
a
p
as
s
w
o
r
d
to
o
p
en
a
lo
ck
li
k
e
a
b
an
k
v
au
l
t o
r
o
th
er
s
y
s
te
m
s
w
h
er
e
h
ig
h
le
v
el
o
f
en
cr
y
p
tio
n
is
n
ec
e
s
s
ar
y
.
3.
M
E
T
H
O
DO
L
O
G
Y
T
h
e
d
if
f
er
en
t
s
ta
g
es
o
f
B
C
I
ar
e
s
ig
n
al
ac
q
u
is
it
io
n
,
f
il
ter
in
g
,
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
clas
s
i
f
i
ca
tio
n
an
d
ex
ter
n
al
ap
p
licatio
n
.
T
h
e
y
ar
e
ex
p
lain
ed
b
elo
w
.
Sig
na
l
Acqui
s
it
io
n:
E
lectr
o
en
ce
p
h
alo
g
r
ap
h
y
(
E
E
G)
s
i
g
n
a
ls
ar
e
ac
q
u
ir
ed
f
r
o
m
n
o
n
i
n
v
asiv
e
h
ea
d
s
et
s
an
d
th
es
e
r
ea
d
in
g
s
ar
e
s
to
r
ed
in
a
f
ile
f
o
r
f
u
r
t
h
er
p
r
o
ce
s
s
in
g
.
Si
g
n
als
ca
n
b
e
ac
q
u
ir
ed
f
r
o
m
eith
er
d
r
y
elec
tr
o
d
es
o
r
g
el
elec
tr
o
d
es.
Her
e
in
t
h
i
s
w
o
r
k
h
ea
d
s
et
u
s
ed
i
s
B
E
SS
(
B
r
ain
E
lectr
ical
Scan
S
y
s
te
m
)
w
h
ich
i
s
o
f
1
6
elec
tr
o
d
es.
B
r
ain
E
lectr
ical
Sc
an
S
y
s
te
m
-
BE
SS
,
b
u
ilt
o
v
er
y
ea
r
s
o
f
r
e
s
ea
r
ch
,
is
a
h
i
g
h
l
y
s
o
p
h
is
ticated
E
E
G
-
E
R
P
s
y
s
te
m
t
h
at
ac
q
u
ir
e
s
p
r
o
ce
s
s
es
an
d
a
n
al
y
ze
s
b
io
elec
tr
ical
ac
tiv
it
y
w
it
h
i
n
t
h
e
b
r
ain
.
T
h
is
s
y
s
te
m
i
s
s
u
p
p
lied
w
it
h
s
ali
n
e
elec
tr
o
d
es,
w
h
ic
h
ca
p
tu
r
e
th
e
elec
tr
i
ca
l
ac
tiv
it
y
i
n
1
6
ch
an
n
el
co
n
f
ig
u
r
atio
n
w
it
h
2
ea
r
lo
b
e
elec
tr
o
d
es a
n
d
1
g
r
o
u
n
d
elec
tr
o
d
e
as sh
o
w
n
in
F
ig
u
r
e
1
.
Fig
u
r
e1
.
B
E
SS
s
alin
e
elec
tr
o
d
es
T
h
is
s
y
s
te
m
co
n
tai
n
s
f
ea
tu
r
e
s
to
p
r
o
v
id
e
t
h
e
s
ti
m
u
l
u
s
in
m
u
lti
-
m
o
d
alit
y
s
p
ec
tr
u
m
.
I
t
is
u
s
ed
i
n
f
ield
o
f
r
esear
ch
an
d
h
a
s
s
i
g
n
i
f
ican
t
clin
ical
ap
p
licatio
n
.
I
t
ca
n
b
e
e
m
p
lo
y
e
d
i
n
s
ec
to
r
s
s
u
c
h
as
co
r
p
o
r
ate,
ar
m
ed
f
o
r
ce
s
as
w
ell.
F
ilte
ring
:
On
ce
th
e
s
i
g
n
al
s
ar
e
ac
q
u
ir
ed
it
is
n
ec
e
s
s
ar
y
to
f
ilter
th
e
m
i
n
o
r
d
er
to
r
em
o
v
e
th
e
n
o
i
s
e,
ex
ter
n
al
an
d
in
ter
n
al
ar
ti
f
ac
ts
.
Ma
th
e
m
atica
l
a
n
d
s
ta
tis
tica
l
m
e
th
o
d
s
ar
e
u
s
ed
to
r
ed
u
ce
t
h
e
n
o
is
e
p
r
esen
t
in
t
h
e
s
e
s
ig
n
al
s
.
T
h
e
d
ig
ita
lized
E
E
G
d
ata
m
u
s
t
b
e
f
ilter
ed
to
r
e
m
o
v
e
n
o
is
e
an
d
o
t
h
er
ar
ti
f
ac
ts
u
s
i
n
g
E
E
G
L
A
B
.
A
f
ter
th
e
r
e
m
o
v
al
o
f
n
o
i
s
e,
E
E
G
d
ata
co
m
i
n
g
f
r
o
m
in
d
i
v
id
u
al
b
r
ain
ac
ti
v
it
y
m
u
s
t
b
e
s
ep
ar
ated
an
d
th
e
r
e
m
ai
n
i
n
g
ar
tif
ac
ts
m
u
s
t
b
e
r
e
m
o
v
ed
.
R
u
n
n
i
n
g
R
UNI
C
A
m
o
d
u
le
i
n
E
E
GL
A
B
p
r
o
v
es
t
h
at
t
h
e
test
ca
s
e
is
a
s
u
cc
e
s
s
.
T
h
e
R
UNI
C
A
m
o
d
u
le
ap
p
lies
I
C
A
o
n
t
h
e
s
elec
ted
E
E
G
c
h
a
n
n
e
ls
;
th
i
s
d
ata
a
f
ter
i
n
d
ep
en
d
en
t
c
o
m
p
o
n
en
t
an
al
y
s
is
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
S
ec
u
r
ity
S
o
lu
tio
n
s
Usi
n
g
B
r
a
i
n
S
ig
n
a
ls
(
A
n
u
p
a
ma
.
H.
S
)
107
m
u
s
t b
e
o
b
tain
ed
in
m
atr
ix
f
o
r
m
.
I
f
t
h
e
w
eig
h
ted
m
atr
ix
i
s
o
b
tain
ed
th
e
n
th
e
te
s
t c
ase
is
a
s
u
cc
es
s
.
F
ea
t
ure
ex
t
ra
ct
io
n:
Featu
r
e
ex
tr
ac
tio
n
is
t
h
e
p
r
o
ce
s
s
o
f
a
n
al
y
zi
n
g
th
e
s
i
g
n
a
ls
to
d
is
tin
g
u
is
h
p
er
ti
n
en
t
s
i
g
n
al
ch
ar
ac
ter
is
tic
s
.
T
h
ese
f
ea
t
u
r
es
f
o
r
m
a
f
ea
t
u
r
e
v
ec
to
r
w
h
ic
h
is
u
s
ed
a
s
a
u
n
iq
u
e
s
i
g
n
a
tu
r
e.
T
h
e
f
ilter
ed
a
n
d
p
r
o
ce
s
s
ed
E
E
G
d
ata
m
u
s
t
b
e
tr
an
s
f
o
r
m
ed
in
to
f
r
eq
u
en
c
y
d
o
m
ai
n
,
u
s
i
n
g
w
av
e
let
tr
an
s
f
o
r
m
at
io
n
.
T
h
e
m
ea
n
s
ig
n
al
v
a
lu
e
w
ill
b
e
o
b
tain
ed
af
ter
w
av
ele
t
tr
an
s
f
o
r
m
atio
n
.
T
h
e
E
E
G
s
ig
n
als
o
b
tain
ed
f
r
o
m
m
u
ltip
le
c
h
an
n
el
s
ac
ts
a
s
2
D
d
ata,
w
h
e
r
ea
s
t
h
e
w
a
v
elet
tr
an
s
f
o
r
m
atio
n
ca
n
b
e
ap
p
lied
o
n
l
y
o
n
1
D
s
i
g
n
al.
T
h
u
s
d
ata
m
u
s
t
b
e
g
iv
e
n
i
n
m
atr
i
x
f
o
r
m
at
a
n
d
2
D
w
av
ele
t
tr
an
s
f
o
r
m
at
io
n
f
u
n
ctio
n
m
u
s
t
b
e
u
s
ed
o
n
m
atr
i
x
.
T
h
e
d
ata
o
b
tain
ed
af
ter
f
ilter
i
n
g
m
u
s
t
b
e
p
r
o
ce
s
s
ed
f
u
r
th
er
to
o
b
tain
f
ea
tu
r
es
an
d
h
e
n
ce
g
en
er
ate
s
i
g
n
at
u
r
e.
T
h
e
s
ig
n
at
u
r
e
f
o
r
ea
ch
o
f
th
e
p
er
s
o
n
is
g
e
n
er
ated
s
ep
ar
atel
y
.
Cla
s
s
if
ica
t
io
n:
T
h
e
class
if
icat
io
n
s
tep
ai
m
s
at
a
u
to
m
at
icall
y
esti
m
at
in
g
th
e
cla
s
s
o
f
d
ata
as
r
ep
r
esen
ted
b
y
a
f
ea
t
u
r
e
v
ec
to
r
.
C
las
s
if
icatio
n
o
f
t
h
e
d
ata
i
s
d
o
n
e
u
s
i
n
g
m
a
ch
in
e
lear
n
i
n
g
al
g
o
r
ith
m
s
.
L
a
te
lear
n
er
s
o
r
ea
r
l
y
lear
n
er
s
ap
p
r
o
ac
h
ca
n
b
e
u
s
ed
to
class
if
y
t
h
e
d
ata.
A
clas
s
i
f
i
ca
tio
n
m
o
d
el
is
cr
ea
ted
o
n
l
y
w
h
e
n
a
d
ata
ele
m
en
t
is
b
ein
g
clas
s
i
f
ied
in
late
lear
n
er
s
ap
p
r
o
ac
h
.
T
h
e
k
-
Nea
r
est
Ne
i
g
h
b
o
r
alg
o
r
ith
m
f
alls
in
to
t
h
is
ca
teg
o
r
y
[
1
1
,
1
2
]
.
E
x
t
er
na
l A
pp
lica
t
io
n:
T
h
e
co
m
m
a
n
d
s
f
r
o
m
t
h
e
class
if
ica
ti
o
n
alg
o
r
ith
m
ar
e
p
r
o
v
id
ed
to
e
x
ter
n
al
d
e
v
ices.
4.
SYST
E
M
ARCH
I
T
E
CT
U
R
E
E
E
G
b
ased
b
io
m
etr
ic
s
ec
u
r
it
y
s
y
s
te
m
i
s
d
ec
o
m
p
o
s
ed
i
n
to
s
u
b
-
s
y
s
te
m
s
t
h
at
p
r
o
v
id
e
s
o
m
e
r
elate
d
s
e
t
o
f
s
er
v
ice
s
.
T
h
e
d
esig
n
p
r
o
ce
s
s
b
ased
o
n
s
y
s
te
m
ar
ch
itect
u
r
e
is
co
n
ce
r
n
ed
w
ith
e
s
tab
lis
h
i
n
g
a
b
asic
s
tr
u
ct
u
r
al
f
r
a
m
e
w
o
r
k
f
o
r
a
s
y
s
te
m
.
I
t
i
n
v
o
l
v
es
id
e
n
ti
f
y
in
g
t
h
e
m
aj
o
r
ele
m
en
t
s
o
f
t
h
e
s
y
s
te
m
a
n
d
co
m
m
u
n
icat
io
n
s
b
et
w
ee
n
th
e
s
e
ele
m
en
t
s
.
Fi
g
u
r
e
2
s
h
o
w
s
th
e
e
x
is
t
in
g
s
y
s
te
m
ar
ch
itect
u
r
e.
Fig
u
r
e
2
.
S
y
s
te
m
A
r
c
h
itect
u
r
e
Salin
e
elec
tr
o
d
es
alo
n
g
w
it
h
th
e
B
E
SS
s
o
f
t
w
ar
e
is
u
s
ed
to
r
ec
o
r
d
E
E
G
s
ig
n
a
l
tr
an
s
m
i
s
s
io
n
.
T
h
e
r
a
w
E
E
G
d
ata
f
r
o
m
elec
tr
o
d
es a
r
e
r
ea
d
u
s
in
g
E
E
G
L
A
B
to
o
lb
o
x
.
T
h
ese
r
a
w
d
ata,
tr
ea
ted
as si
g
n
als ar
e
f
ilter
ed
an
d
th
en
s
en
t
f
o
r
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
.
T
h
e
f
ea
tu
r
es
e
x
tr
ac
ted
f
r
o
m
a
f
ea
t
u
r
e
v
ec
to
r
w
h
ich
i
s
u
s
ed
as
a
u
n
iq
u
e
s
ig
n
at
u
r
e.
T
h
e
f
in
al
s
tep
is
w
h
er
e
th
e
e
x
tr
ac
ted
d
ata
is
class
i
f
ied
in
r
ea
l
ti
m
e
u
s
in
g
th
e
class
i
f
icat
io
n
alg
o
r
ith
m
s
.
T
h
e
f
ee
d
b
ac
k
i
s
s
e
n
t b
ac
k
to
th
e
u
s
er
.
E
lectr
o
en
ce
p
h
alo
g
r
ap
h
y
(
E
E
G)
s
ig
n
al
s
ar
e
o
b
tain
ed
f
r
o
m
t
h
e
elec
tr
o
d
es
i
n
t
h
e
f
o
r
m
o
f
s
e
n
s
o
r
r
ea
d
in
g
s
a
n
d
s
to
r
ed
in
t
h
e
f
il
e
E
E
G.
tx
t.
O
n
l
y
7
ch
a
n
n
el
v
alu
es
ar
e
ta
k
e
n
i
n
to
co
n
s
id
er
atio
n
.
Me
an
o
f
ea
c
h
co
lu
m
n
o
f
t
h
ese
elec
tr
o
d
e
r
ea
d
in
g
s
i
s
ta
k
en
an
d
s
to
r
ed
in
th
e
d
atab
ase.
On
ce
th
e
s
e
m
ea
n
v
alu
e
s
ar
e
s
to
r
ed
i
n
th
e
d
atab
ase,
t
h
e
s
y
s
te
m
is
r
e
ad
y
f
o
r
p
r
ed
ictio
n
.
T
h
e
class
i
f
icatio
n
al
g
o
r
ith
m
s
u
s
ed
i
s
k
-
Nea
r
est
Nei
g
h
b
o
u
r
alg
o
r
ith
m
.
T
h
e
u
s
er
f
ir
s
t
tr
ai
n
s
th
e
d
e
v
ic
e
f
o
r
m
e
n
tio
n
ed
n
u
m
b
er
o
f
o
b
j
ec
t
s
.
No
t
all
th
e
v
al
u
es
ar
e
s
t
o
r
ed
in
th
e
d
atab
ase
f
o
r
f
u
t
u
r
e
r
ef
er
e
n
ce
.
T
o
in
cr
ea
s
e
d
ec
r
ea
s
e
th
e
co
m
p
u
tin
g
t
i
m
e
o
f
t
h
e
o
v
er
all
s
y
s
t
e
m
,
o
n
l
y
t
h
e
m
ea
n
v
alu
e
o
f
1
6
elec
tr
o
d
e
v
al
u
es
ar
e
tak
en
in
to
co
n
s
id
er
atio
n
a
n
d
th
i
s
s
eq
u
en
ce
o
f
m
ea
n
v
al
u
es
ar
e
s
to
r
ed
as
1
t
u
p
le
in
th
e
d
atab
ase.
T
o
en
s
u
r
e
th
at
a
g
o
o
d
d
ata
s
et
is
ac
q
u
ir
ed
,
th
e
p
r
o
ce
s
s
o
f
tr
ain
i
n
g
will
b
e
r
ep
ea
ted
f
o
r
th
e
s
a
m
e
o
b
j
ec
t
m
u
ltip
le
ti
m
es
w
it
h
th
e
s
a
m
e
u
s
er
as
w
el
l
as
d
if
f
er
e
n
t
u
s
er
s
.
Af
ter
tr
ain
in
g
th
e
d
ev
ice
th
e
u
s
e
r
ca
n
u
s
e
t
h
e
d
ev
ice
f
o
r
p
r
ed
icti
o
n
.
T
h
e
C
lass
i
f
y
cla
s
s
is
u
s
ed
f
o
r
p
r
ed
ictio
n
.
W
h
en
th
e
u
s
er
u
s
e
s
th
e
d
ev
ice
f
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
7
,
No
.
2
,
J
u
n
e
20
1
8
:
1
0
5
–
1
1
0
108
p
r
ed
ictio
n
,
th
e
co
m
p
ar
e
f
u
n
cti
o
n
class
if
ies
t
h
e
o
b
tain
ed
d
ata
in
to
o
n
e
o
f
t
h
e
tr
ai
n
ed
o
b
j
ec
t
s
b
y
u
s
i
n
g
t
h
e
u
s
er
s
p
ec
if
ied
clas
s
i
f
icatio
n
al
g
o
r
it
h
m
.
T
h
e
o
b
tain
ed
r
esu
lt is
s
en
t
as a
f
ee
d
b
ac
k
to
u
s
er
th
r
o
u
g
h
u
s
er
i
n
ter
f
ac
e.
T
h
e
u
s
er
ca
n
tr
ain
a
n
d
p
r
ed
ict
f
o
r
an
y
o
b
j
ec
t
an
y
n
u
m
b
er
o
f
ti
m
es.
T
h
e
i
m
p
le
m
e
n
ted
s
ec
u
r
i
t
y
s
o
l
u
tio
n
ca
n
b
e
b
r
o
ad
ly
r
ep
r
esen
ted
in
t
h
e
f
o
r
m
o
f
a
f
lo
w
c
h
ar
t a
s
s
h
o
w
n
in
F
ig
u
r
e
3
.
Fig
u
r
e
3
.
Flo
w
c
h
ar
t o
f
t
h
e
o
v
e
r
all
b
r
ain
s
ig
n
al
s
ec
u
r
it
y
s
o
lu
ti
o
n
s
y
s
te
m
Fig
u
r
e
3
r
ep
r
esen
ts
f
lo
w
c
h
ar
t
o
f
t
h
e
e
n
tire
s
y
s
te
m
.
T
h
e
s
y
s
te
m
b
e
g
in
s
w
i
th
p
r
o
to
co
l d
ev
elo
p
m
e
n
t
f
o
r
th
e
co
llectio
n
o
f
E
E
G
s
i
g
n
a
ls
u
s
i
n
g
SS
VE
P
.
T
h
is
is
f
o
llo
w
e
d
b
y
u
s
in
g
t
h
e
p
r
o
to
co
l
to
ac
q
u
ir
e
r
a
w
E
E
G
d
at
a,
an
d
f
u
r
t
h
er
th
i
s
d
ata
is
d
ig
ital
ized
,
an
d
n
o
is
e
in
E
E
G
s
ig
n
al
s
is
s
i
m
u
ltan
eo
u
s
l
y
r
e
m
o
v
ed
.
Nex
t
s
tep
in
c
lu
d
es
f
ea
t
u
r
e
ex
tr
ac
tio
n
a
n
d
s
ig
n
a
tu
r
e
g
e
n
er
atio
n
.
T
h
e
s
ig
n
at
u
r
e
f
o
r
ea
ch
u
s
er
is
u
n
iq
u
e
w
h
ic
h
is
u
s
ed
in
au
th
e
n
tica
tin
g
t
h
e
u
s
er
.
5.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
is
a
n
i
m
p
o
r
tan
t
s
ta
g
e
o
f
an
al
y
s
i
s
w
h
er
e
t
h
e
r
e
s
u
l
ts
ar
e
an
al
y
ze
d
f
o
r
co
r
r
ec
tn
ess
an
d
m
atc
h
ed
w
it
h
t
h
e
e
x
p
ec
ted
o
u
tp
u
t
f
o
r
an
y
a
n
o
m
al
y
.
I
n
Fi
g
u
r
e
4
,
r
aw
E
E
G
d
ata
w
h
ic
h
ar
e
ac
q
u
ir
ed
w
h
en
t
h
e
u
s
er
i
s
d
is
p
la
y
ed
w
ith
SS
VE
P
p
r
o
to
c
o
l is sh
o
w
n
.
Fig
u
r
e
4
.
E
E
G
d
ata
d
u
r
in
g
ac
q
u
is
i
tio
n
s
ta
te
Fig
u
r
e
5
.
E
E
G
d
ata
af
ter
f
ilter
i
n
g
T
h
e
E
E
G
s
ig
n
als
i
n
th
e
f
o
r
m
o
f
s
in
u
s
o
id
al
w
a
v
es
ar
e
ac
q
u
ir
ed
d
ir
ec
tly
f
r
o
m
t
h
e
u
s
er
an
d
ar
e
s
to
r
ed
.
I
n
Fi
g
u
r
e
5
,
th
e
E
E
G
d
ata
af
te
r
s
u
b
j
ec
tin
g
to
f
ilter
i
n
g
a
n
d
I
C
A
u
s
i
n
g
M
A
T
L
A
B
is
s
h
o
w
n
.
T
h
e
r
aw
E
E
G
d
ata
is
f
ir
s
t
s
u
b
j
ec
ted
to
f
ilter
i
n
g
t
o
r
em
o
v
e
n
o
is
e
a
n
d
th
e
n
I
C
A
is
ap
p
lied
w
h
ic
h
g
i
v
es
a
w
ei
g
h
ted
m
atr
i
x
.
Af
ter
f
ilter
i
n
g
,
f
ea
tu
r
es
ar
e
e
x
tr
ac
te
d
f
r
o
m
th
e
d
ata.
Fi
g
u
r
e
6
r
ep
r
esen
t
s
t
h
e
f
ea
t
u
r
e
v
ec
to
r
v
al
u
es
f
o
r
th
e
au
t
h
e
n
tic
u
s
er
.
I
t
is
s
ee
n
t
h
at
t
h
e
f
ea
tu
r
es
m
ea
n
,
s
ta
n
d
ar
d
d
ev
iatio
n
,
v
ar
ian
ce
,
m
a
x
i
m
u
m
,
m
in
i
m
u
m
,
ze
r
o
cr
o
s
s
in
g
r
ate
an
d
w
a
v
elet
tr
an
s
f
o
r
m
a
tio
n
m
ea
n
d
i
f
f
er
s
w
h
en
t
h
e
v
al
u
es
ar
e
tak
e
n
b
ef
o
r
e
f
o
o
d
an
d
a
f
ter
f
o
o
d
.
T
h
e
b
r
ain
s
ig
n
al
s
g
e
n
er
ated
af
ter
f
o
o
d
f
o
r
th
e
s
a
m
e
p
r
o
to
co
l is d
if
f
er
en
t f
r
o
m
t
h
at
w
h
ich
ar
e
g
e
n
er
ate
d
b
ef
o
r
e
f
o
o
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
S
ec
u
r
ity
S
o
lu
tio
n
s
Usi
n
g
B
r
a
i
n
S
ig
n
a
ls
(
A
n
u
p
a
ma
.
H.
S
)
109
Fig
u
r
e
6
.
A
g
r
ap
h
s
h
o
w
i
n
g
co
m
p
ar
i
s
o
n
b
et
w
ee
n
f
ea
t
u
r
e
v
ec
to
r
v
al
u
es
f
o
r
au
th
e
n
tic
u
s
er
b
ef
o
r
e
an
d
af
ter
f
o
o
d
Fig
u
r
e
7
.
A
g
r
ap
h
s
h
o
w
i
n
g
tr
u
e
p
o
s
itiv
e,
tr
u
e
n
eg
at
iv
e,
f
alse p
o
s
iti
v
e
a
n
d
f
al
s
e
n
e
g
ati
v
e
v
al
u
es
f
o
r
k
NN
al
g
o
r
ith
m
T
h
e
f
ea
tu
r
e
ex
tr
ac
tio
n
i
s
d
o
n
e
f
o
r
s
ev
er
al
o
th
er
u
s
er
s
w
h
o
s
e
E
E
G
d
ata
w
er
e
co
llected
.
I
t
i
s
s
ee
n
t
h
a
t
th
e
f
ea
t
u
r
es
m
ea
n
,
s
tan
d
ar
d
d
ev
iatio
n
,
v
ar
ia
n
ce
,
m
a
x
i
m
u
m
,
m
i
n
i
m
u
m
,
ze
r
o
cr
o
s
s
in
g
r
ate
an
d
w
a
v
elet
tr
an
s
f
o
r
m
atio
n
m
e
a
n
d
if
f
er
s
f
r
o
m
o
n
e
u
s
er
to
an
o
th
er
.
I
t
ca
n
b
e
o
b
s
er
v
ed
th
at
v
ar
ian
ce
o
f
th
r
ee
u
s
er
s
d
if
f
er
s
th
e
m
o
s
t.
Fi
g
u
r
e
7
d
ep
icts
a
g
r
ap
h
s
h
o
w
i
n
g
tr
u
e
p
o
s
iti
v
e,
tr
u
e
n
e
g
ati
v
e,
f
alse
p
o
s
iti
v
e
an
d
f
al
s
e
n
e
g
ati
v
e
v
alu
e
s
o
b
tain
ed
b
y
ap
p
l
y
i
n
g
k
NN
alg
o
r
ith
m
.
Fro
m
Fi
g
u
r
e
7
,
it i
s
s
ee
n
t
h
at
t
h
e
tr
u
e
p
o
s
iti
v
e
v
alu
e
f
o
r
k
NN
is
7
2
.
2
2
%,
tr
u
e
n
eg
at
iv
e
is
1
0
0
%.
Fals
e
p
o
s
itiv
e
i
s
2
7
.
7
8
%
an
d
f
al
s
e
n
eg
at
iv
e
is
0
%.
T
h
is
s
h
o
w
s
t
h
at,
t
h
e
p
er
ce
n
ta
g
e
o
f
t
i
m
e
s
s
y
s
te
m
allo
w
s
w
r
o
n
g
u
s
er
to
au
t
h
en
t
icate
is
0
%.
H
o
w
e
v
er
,
n
ea
r
l
y
2
7
.
7
8
%
o
f
th
e
ti
m
es
t
h
e
r
ig
h
t
u
s
er
also
w
o
n
’
t
b
e
class
i
f
ied
as
au
th
e
n
tic
u
s
er
b
y
k
NN.
I
t
is
s
ee
n
t
h
at
th
e
to
tal
ac
c
u
r
a
c
y
o
f
th
e
s
y
s
te
m
is
7
7
.
7
8
%.
T
h
e
p
er
ce
n
tag
e
o
f
ti
m
e
s
y
s
te
m
id
en
ti
f
ie
s
r
ig
h
t
u
s
er
co
r
r
ec
tl
y
a
n
d
d
en
ie
s
w
r
o
n
g
u
s
er
i
s
7
7
.
7
8
%.
Ho
w
ev
er
,
n
ea
r
l
y
2
2
.
2
2
%
o
f
t
h
e
t
i
m
es,
s
y
s
te
m
f
ail
s
to
id
en
ti
f
y
th
e
u
s
er
co
r
r
ec
tl
y
.
T
h
e
i
m
p
le
m
e
n
ted
w
o
r
k
is
ab
le
to
g
e
n
er
ate
a
u
n
iq
u
e
s
i
g
n
at
u
r
e
f
o
r
th
e
m
ai
n
s
u
b
j
ec
t
an
d
au
th
e
n
ticate
h
is
id
en
ti
t
y
s
u
cc
es
s
f
u
ll
y
b
y
m
atc
h
i
n
g
t
h
e
s
to
r
ed
s
ig
n
atu
r
e
w
it
h
th
e
s
i
g
n
a
ls
r
ec
o
r
d
ed
d
u
r
in
g
test
i
n
g
/r
u
n
ti
m
e
.
T
h
e
m
atc
h
is
s
u
cc
e
s
s
f
u
l
r
eg
ar
d
less
o
f
ex
ter
n
al
co
n
d
itio
n
s
s
u
ch
as
ti
m
e
o
f
t
h
e
d
a
y
an
d
in
ter
n
al
co
n
d
itio
n
s
s
u
c
h
as
an
x
iet
y
,
h
u
n
g
er
etc.
T
h
e
s
y
s
te
m
g
iv
e
s
a
n
eg
ati
v
e
r
esu
l
t
f
o
r
th
e
s
ig
n
al
s
f
o
r
th
e
r
e
m
ain
in
g
t
w
o
s
u
b
j
ec
ts
,
th
u
s
g
iv
i
n
g
a
tr
u
e
n
eg
ati
v
e
ac
c
u
r
ac
y
o
f
1
0
0
%.
6.
CO
NCLU
SI
O
N
AND
L
I
M
I
T
AT
I
O
NS
Ov
er
th
e
co
u
r
s
e
o
f
t
h
e
p
r
o
j
ec
t,
lear
n
in
g
o
n
d
i
f
f
er
e
n
t
s
ig
n
al
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
e
s
,
d
if
f
er
en
t
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
o
lo
g
ies,
d
if
f
er
en
t
clas
s
i
f
icatio
n
s
tr
ateg
ie
s
etc.
,
h
as
b
ee
n
d
o
n
e.
T
h
e
w
o
r
k
p
r
esen
t
s
th
e
tech
n
iq
u
es
th
a
t
ca
n
b
e
u
s
ed
to
o
b
tain
E
E
G
s
i
g
n
als
an
d
d
ev
e
l
o
p
an
en
d
to
e
n
d
ap
p
licatio
n
b
y
p
r
o
ce
s
s
i
n
g
th
e
s
e
s
ig
n
al
s
.
T
h
is
p
r
o
v
id
es
m
et
h
o
d
s
to
ef
f
icie
n
tl
y
p
r
o
ce
s
s
E
E
G
s
ig
n
als,
r
e
m
o
v
e
ar
ti
f
ac
ts
w
i
t
h
o
u
t
lo
s
i
n
g
r
elev
a
n
t
in
f
o
r
m
atio
n
,
an
d
o
b
tain
f
ea
t
u
r
es
f
r
o
m
t
h
ese
s
i
g
n
al
s
an
d
cl
ass
i
f
y
b
ased
o
n
o
b
j
ec
tiv
e.
M
u
ltip
le
f
il
ter
in
g
a
n
d
f
ea
t
u
r
e
ex
tr
ac
tio
n
tech
n
iq
u
es
h
as
b
ee
n
u
s
ed
to
o
b
tain
an
er
r
o
r
f
r
ee
,
n
o
is
e
f
r
ee
,
lar
g
e
s
ig
n
a
tu
r
e,
w
h
ic
h
h
elp
s
i
n
b
etter
class
if
icatio
n
.
T
h
e
li
m
ita
tio
n
s
o
f
t
h
e
p
r
o
d
u
ct
ar
e
n
o
t
n
e
g
ati
v
e
a
s
p
ec
ts
to
th
e
w
o
r
k
d
o
n
e.
Ho
w
e
v
er
,
n
o
p
r
o
d
u
ct
ca
n
f
u
lf
i
ll
all
th
e
n
ee
d
s
o
f
t
h
e
u
s
e
r
.
W
ith
r
esp
ec
t
to
th
is
,
th
e
f
o
l
lo
w
i
n
g
m
i
g
h
t
b
e
th
e
li
m
ita
tio
n
s
o
f
th
is
s
o
f
t
w
ar
e
p
ac
k
ag
e.
So
m
e
i
m
p
o
r
tan
t li
m
i
tatio
n
s
as
f
o
llo
w
s
:
a.
T
h
e
s
y
s
te
m
is
d
esi
g
n
ed
to
id
en
ti
f
y
a
li
m
i
ted
n
u
m
b
er
o
f
u
s
er
s
o
n
l
y
.
b.
T
h
e
o
b
tain
ed
d
ata
f
r
o
m
t
h
e
d
ev
ice
s
h
o
u
ld
b
e
in
E
DF/
AS
C
I
I
f
o
r
m
at
o
n
l
y
.
c.
As
th
e
E
E
G
w
av
e
s
v
ar
y
w
it
h
ev
er
y
ac
ti
v
it
y
o
f
th
e
u
s
er
,
tr
ain
in
g
t
h
e
u
s
er
f
o
r
d
ata
ac
q
u
i
s
it
io
n
b
ef
o
r
eh
a
n
d
is
n
ec
es
s
ar
y
.
RE
F
E
R
E
NC
E
S
[1
]
Av
id
Ro
m
a
n
-
G
o
n
z
a
lez
,
“
EE
G
S
ig
n
a
l
P
r
o
c
e
ss
in
g
f
o
r
BCI
A
p
p
li
c
a
ti
o
n
s,
Hu
m
a
n
Co
m
p
u
ter
S
y
ste
m
s
In
tera
c
ti
o
n
:
Ba
c
k
g
ro
u
n
d
s a
n
d
A
p
p
l
ica
ti
o
n
s
”
,
Ad
v
a
n
c
e
s i
n
In
tell
ig
e
n
t
a
n
d
S
o
ft
Co
mp
u
t
in
g
,
2
0
1
2
.
[2
]
A
n
u
p
a
m
a
,
H.S
,
Ca
u
v
e
ry
,
N.K
a
n
d
L
in
g
a
ra
ju
,
G
.
M
,
“
B
ra
in
c
o
m
p
u
t
e
r
in
terf
a
c
e
a
n
d
it
s
ty
p
e
s
-
a
stu
d
y
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
s in
En
g
in
e
e
ri
n
g
&
T
e
c
h
n
o
lo
g
y
,
M
a
y
2
0
1
2
.
[3
]
P
a
tri
c
k
Ca
rb
e
rry
,
“
Bra
in
Co
m
p
u
ter
In
terfa
c
e
s
(BCI)
a
n
d
Ne
u
ro
p
r
o
sth
e
ti
c
s”
,
Bi
o
me
d
ica
l
En
g
in
e
e
rin
g
,
S
e
m
in
a
r
III,
A
p
ril
7
,
2
0
0
8
.
[
4
]
.
M
.
T
e
p
lan
,
“
F
u
n
d
a
m
e
n
tals
o
f
EE
G
m
e
a
su
re
m
e
n
t”,
In
stit
u
te
o
f
M
e
a
su
re
me
n
t
S
c
ien
c
e
,
S
lo
v
a
k
A
c
a
d
e
m
y
o
f
S
c
ien
c
e
s,
Dú
b
ra
v
sk
á
c
e
sta
9
,
8
4
1
0
4
Bra
ti
sl
a
v
a
,
S
lo
v
a
k
ia,
2
0
0
2
.
[5
]
.
G
ra
n
t
S
.
T
a
y
lo
r
a
n
d
Ch
rist
in
a
S
c
h
m
id
t,
“
Emp
irica
l
Eva
l
u
a
ti
o
n
o
f
th
e
Emo
ti
v
EP
OC
BCI
H
e
a
d
se
t
f
o
r
th
e
De
tec
ti
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
7
,
No
.
2
,
J
u
n
e
20
1
8
:
1
0
5
–
1
1
0
110
o
f
M
e
n
ta
l
Actio
n
s”
,
9
t
h
W
o
rk
in
g
IEE
E/
IF
I
P
Co
n
f
e
re
n
c
e
o
n
S
o
f
tw
a
re
A
rc
h
it
e
c
tu
re
(W
ICS
A
),
1
8
7
-
1
9
3
,
2
0
1
1
.
[6
]
“
Bra
in
-
Co
m
p
u
ter
In
ter
fa
c
e
s,
Ap
p
lyin
g
o
u
r
M
in
d
s
t
o
Hu
ma
n
-
Co
mp
u
ter
In
ter
a
c
ti
o
n
”
,
S
p
ri
n
g
e
r
Lo
n
d
o
n
Do
rd
re
c
h
t
He
id
e
lb
e
rg
Ne
w
Yo
rk
-
v
o
l.
1
,
S
p
r
in
g
e
r
-
V
e
rlag
L
o
n
d
o
n
L
im
it
e
d
,
2
0
1
0
.
[7
]
M
a
u
ss
,
I.
B.
a
n
d
Ro
b
in
s
o
n
,
M
.
D.,
“
M
e
a
su
re
s
o
f
e
m
o
ti
o
n
:
A
re
v
iew
,
”
Co
g
n
it
io
n
a
n
d
Em
o
ti
o
n
,
v
o
l.
2
3
,
2
0
0
9
,
p
p
.
209
-
2
3
7
.
[8
]
R.
P
a
ra
n
ja
p
e
,
J.
M
a
h
o
v
sk
y
,
L
.
B
e
n
e
d
ice
n
ti
,
Z.
Ko
les
,
“
T
h
e
e
lec
tr
o
e
n
c
e
p
h
a
lo
g
ra
m
a
s
a
b
io
me
tric
”
,
P
r
o
c
e
e
d
in
g
s
o
f
th
e
Ca
n
a
d
ian
Co
n
f
e
re
n
c
e
o
n
El
e
c
tri
c
a
l
a
n
d
C
o
m
p
u
ter E
n
g
in
e
e
rin
g
,
2
:1
3
6
3
–
1
3
6
6
,
2
0
0
1
.
[9
]
J.
T
h
o
rp
e
,
P
.
C.
v
a
n
Oo
rsc
h
o
t,
a
n
d
A
.
S
o
m
a
y
a
ji
,
“
Pa
ss
-
th
o
u
g
h
ts:
a
u
th
e
n
ti
c
a
ti
n
g
wit
h
o
u
r mi
n
d
s
”
,
P
r
o
c
e
e
d
in
g
s o
f
th
e
2
0
0
5
w
o
rk
sh
o
p
o
n
Ne
w
se
c
u
rit
y
p
a
ra
d
ig
m
s,
Ne
w
Yo
rk
,
2
0
1
2
.
[1
0
]
L
o
tt
e
F
.
,
Co
n
g
e
d
o
M
.
,
L
e
c
u
y
e
r
A
,
“
A
r
e
v
ie
w
o
f
c
la
ss
i
f
ica
ti
o
n
a
lg
o
rit
h
m
s
f
o
r
EE
G
-
A
n
a
l
y
sis
o
f
Bra
in
S
ig
n
a
ls
Re
fe
re
n
c
e
s
De
p
t.
o
f
IS
E,
R
V
CE
2
0
1
5
-
1
6
5
9
b
a
se
d
b
ra
in
-
c
o
m
p
u
ter
in
terf
a
c
e
s”
,
J
o
u
rn
a
l
o
f
Ne
u
r
a
l
E
n
g
i
n
e
e
rin
g
,
Vo
l
4
,
p
p
R1
-
R
1
3
,
2
0
0
7
.
[1
1
]
K
-
Ne
a
re
stN
e
ig
h
b
o
u
r
h
tt
p
:/
/sa
ra
v
a
n
a
n
th
iru
m
u
ru
g
a
n
a
th
a
n
.
w
o
rd
p
re
ss
.
c
o
m
/2
0
1
0
/
0
5
/
1
7
/a
-
d
e
tailed
-
in
tr
o
d
u
c
t
io
n
-
to
-
k
-
n
e
a
re
st
-
n
e
ig
h
b
o
r
-
knn
-
a
lg
o
rit
h
m
/
a
s o
n
M
a
rc
h
1
2
th
,
2
0
1
5
.
[1
2
]
Oliv
e
r
S
u
tt
o
n
,
“
In
tro
d
u
c
ti
o
n
to
k
Ne
a
re
stNe
ig
h
b
o
u
r
Cla
ss
if
ic
a
ti
o
n
a
n
d
Co
n
d
e
n
se
d
Ne
a
re
st
N
e
ig
h
b
o
u
r
Da
t
a
Red
u
c
ti
o
n
”
,
F
e
b
ru
a
ry
,
2
0
1
2
.
[1
3
]
Ha
id
e
r
Hu
ss
e
in
A
l
wa
siti
,
Ish
a
k
A
ris
a
n
d
A
d
z
n
a
n
Ja
n
tan
,
“
Bra
in
Co
m
p
u
ter
In
terf
a
c
e
D
e
sig
n
a
n
d
A
p
p
li
c
a
ti
o
n
s
:
Ch
a
ll
e
n
g
e
s a
n
d
F
u
tu
re
”
,
W
o
rl
d
A
p
p
li
e
d
S
c
ien
c
e
s J
o
u
rn
a
l
1
1
,
v
o
l
7
,
IDO
S
I
P
u
b
li
c
a
ti
o
n
s,
2
0
1
0
.
[1
4
]
P
f
u
rtsc
h
e
ll
e
r
e
t
a
l.
,
“
C
u
rre
n
t
tren
d
s
in
b
ra
in
c
o
m
p
u
ter
i
n
terf
a
c
e
(
BCI)
re
se
a
rc
h
,
”
IEE
E
T
ra
n
s
Reh
a
b
.
En
g
.
,
v
o
l
.
8
,
p
p
.
2
1
6
–
2
1
9
,
J
u
n
e
2
0
0
0
.
[1
5
]
Kh
a
li
f
a
W
,
S
a
le
m
A
,
Ro
u
sh
d
y
M
,
Re
v
e
tt
K,
“
A
s
u
rv
e
y
o
f
E
EG
b
a
se
d
u
se
r
a
u
th
e
n
ti
c
a
t
io
n
sc
h
e
m
e
s”
,
In
f
o
rm
a
ti
c
s
a
n
d
S
y
ste
m
s (INF
OS),
8
th
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
,
IEE
E,
p
.
BIO
–
5
5
,
2
0
1
2
.
[1
6
]
Ka
rth
ik
e
y
a
n
D
T
,
S
a
b
a
rig
iri
B,
“
E
n
h
a
n
c
e
m
e
n
t
o
f
m
u
lt
i
-
m
o
d
a
l
b
io
m
e
tri
c
a
u
th
e
n
ti
c
a
ti
o
n
b
a
se
d
o
n
ir
is an
d
b
ra
in
n
e
u
ro
im
a
g
e
c
o
d
in
g
”
,
In
t
J
Bi
o
me
trics
Bi
o
in
f
o
rm
(
IJ
BB
)
2
0
1
1
;
5
(
5
):2
4
9
–
5
6
.
[1
7
]
S
v
o
g
o
r
I,
Kisa
so
n
d
i
T
,
“
T
wo
fa
c
to
r
a
u
th
e
n
ti
c
a
ti
o
n
u
si
n
g
EE
G
a
u
g
me
n
ted
p
a
ss
wo
rd
s
”
,
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
In
terf
a
c
e
s (IT
I),
P
ro
c
e
e
d
in
g
s
o
f
th
e
IT
I
3
4
th
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
,
IEE
E,
2
0
1
2
.
[1
8
]
Re
v
e
Re
v
e
tt
K,
De
ra
v
i
F
,
S
irl
a
n
tzis
K,
“
Bi
o
si
g
n
a
ls
f
o
r
u
se
r
a
u
t
h
e
n
ti
c
a
ti
o
n
t
o
wa
rd
s
c
o
g
n
it
iv
e
b
io
me
trics
?
”
Em
e
r
g
in
g
S
e
c
u
rit
y
T
e
c
h
n
o
l
o
g
ies
(ES
T
),
2
0
1
0
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
,
IEE
E,
p
.
7
1
–
7
6
,
2
0
1
0
.
[1
9
]
S
u
F
,
Zh
o
u
H,
F
e
n
g
Z,
M
a
J.
,
“
A
b
io
me
tric
-
b
a
se
d
c
o
v
e
rt
wa
rn
i
n
g
sy
ste
m
u
sin
g
EE
G
”
,
In
:
Bio
m
e
tri
c
s
(ICB),
2
0
1
2
5
th
I
A
P
R
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
IE
EE
,
2
0
1
2
.
[2
0
]
P
o
u
l
o
s,
M
.
,
Ra
n
g
o
u
ss
i,
M
.
N.,
A
le
x
a
n
d
ris,
A
.
a
n
d
Ev
a
n
g
e
lo
u
,
“
On
th
e
u
se
o
f
EE
G
fe
a
tu
re
s
t
o
w
a
rd
s
p
e
rso
n
id
e
n
ti
f
ica
ti
o
n
v
ia n
e
u
ra
l
n
e
tw
o
rk
s”
,
M
e
d
ica
l
In
f
o
rm
a
ti
c
s &
th
e
In
ter
n
e
t
in
M
e
d
ici
n
e
,
2
0
0
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.