I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI)
Vo
l.
10
,
No
.
2
,
J
u
n
e
2021
,
p
p
.
5
01
~
5
09
I
SS
N:
2
2
5
2
-
8938
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ai.
v
10
.i
2
.
p
p
5
01
-
5
09
501
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
EE
G
sig
na
l clas
sifica
tion for
drow
s
iness
det
e
ction usi
ng
w
a
v
elet
trans
for
m
and su
ppo
rt
v
ector
m
a
c
hine
No
v
ie
T
here
s
ia
B
r.
P
a
s
a
ribu,
T
i
m
o
t
ius
H
a
li
m
,
Ra
t
na
dew
i,
Ag
us
P
rij
o
no
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
Un
iv
e
rsitas
Kriste
n
M
a
ra
n
a
t
h
a
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
M
ar
18
,
2
0
2
0
R
ev
i
s
ed
M
ar
1
7
,
2
0
2
1
A
cc
ep
ted
A
p
r
2
9
,
2
0
2
1
T
h
e
re
a
re
s
e
v
e
ra
l
c
a
te
g
o
ries
to
d
e
tec
t
a
n
d
m
e
a
su
re
d
riv
e
r
d
ro
ws
in
e
ss
su
c
h
a
s
p
h
y
sio
lo
g
ica
l
m
e
th
o
d
s,
su
b
jec
ti
v
e
m
e
th
o
d
s
a
n
d
b
e
h
a
v
io
ra
l
m
e
th
o
d
s.
T
h
e
m
o
st
o
b
jec
ti
v
e
m
e
th
o
d
f
o
r
d
ro
w
s
in
e
ss
d
e
tec
ti
o
n
is
th
e
p
h
y
sio
lo
g
ica
l
m
e
th
o
d
.
On
e
o
f
th
e
p
h
y
sio
lo
g
ica
l
m
e
th
o
d
s
u
se
d
is
a
n
e
lec
tro
e
n
c
e
p
h
a
l
o
g
ra
m
(EE
G
).
In
th
is
re
se
a
rc
h
w
a
v
e
let
tran
s
f
o
rm
is
u
se
d
a
s
a
f
e
a
tu
re
e
x
tra
c
ti
o
n
a
n
d
u
sin
g
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM)
a
s
a
c
las
si
f
ier.
W
e
p
ro
p
o
se
d
a
n
e
x
p
e
rime
n
t
o
f
re
tri
e
v
a
l
d
a
ta
w
h
ich
is
d
e
sig
n
e
d
b
y
u
sin
g
m
o
d
if
ied
-
E
A
R
a
n
d
EE
G
si
g
n
a
l.
F
ro
m
th
e
S
V
M
train
in
g
p
ro
c
e
ss
,
w
it
h
th
e
5
-
f
o
ld
c
ro
ss
v
a
li
d
a
ti
o
n
,
Qu
a
d
ra
ti
c
k
e
rn
e
l
h
a
s
th
e
h
ig
h
e
st
a
c
c
u
ra
c
y
8
4
.
5
%
t
h
e
n
o
th
e
rs.
I
n
tes
t
in
g
Driv
in
g
-
2
p
ro
c
e
ss
7
re
sp
o
n
d
e
n
ts
w
e
re
d
e
te
c
ted
a
s
d
ro
w
sin
e
ss
c
la
ss
,
a
n
d
3
re
sp
o
n
d
e
n
ts
w
e
r
e
d
e
tec
ted
a
s
a
wa
k
e
c
las
s.
In
t
h
e
tes
ti
n
g
o
f
Driv
in
g
-
3
p
ro
c
e
ss
,
6
re
sp
o
n
d
e
n
ts
w
e
re
d
e
tec
ted
a
s
d
ro
w
sin
e
ss
c
las
s,
a
n
d
4
re
sp
o
n
d
e
n
ts
w
e
r
e
d
e
tec
ted
a
s a
wa
k
e
c
l
a
ss
.
K
ey
w
o
r
d
s
:
Dr
o
w
s
i
n
es
s
E
lectr
o
en
ce
p
h
alo
g
r
a
m
Su
p
p
o
r
t v
ec
to
r
m
ac
h
i
n
e
W
av
elet
tr
an
s
f
o
r
m
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
:
No
v
ie
T
h
er
esia B
r
.
P
asar
ib
u
Dep
ar
t
m
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
Un
i
v
er
s
ita
s
Kr
is
te
n
Ma
r
an
at
h
a
J
l.
Su
r
y
a
S
u
m
a
n
tr
i N
o
.
6
5
,
B
an
d
u
n
g
,
I
n
d
o
n
esia
E
m
ail:
n
o
v
ie.
t
h
er
esia
@
e
n
g
.
m
ar
an
ath
a.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
ev
er
y
d
a
y
ac
ti
v
itie
s
o
f
h
u
m
an
li
f
e
r
eq
u
ir
e
tr
an
s
p
o
r
tatio
n
.
T
r
an
s
p
o
r
tatio
n
is
u
s
ed
to
t
r
av
el
f
r
o
m
o
n
e
p
lace
to
an
o
th
er
.
On
e
o
f
th
e
tr
an
s
p
o
r
tatio
n
m
et
h
o
d
s
i
s
d
o
n
e
b
y
ca
r
.
Dr
iv
i
n
g
a
ca
r
is
an
ac
ti
v
it
y
t
h
at
r
eq
u
ir
es
h
i
g
h
lev
el
o
f
co
n
ce
n
tr
atio
n
,
b
ec
au
s
e
d
r
iv
i
n
g
f
o
r
a
lo
n
g
ti
m
e
ca
n
ca
u
s
e
f
a
tig
u
e.
Fati
g
u
e
ca
u
s
e
s
d
r
o
w
s
i
n
ess
w
h
ic
h
r
es
u
lt
s
i
n
a
d
ec
r
ea
s
ed
lev
el
o
f
co
n
ce
n
tr
atio
n
i
n
th
e
d
r
iv
er
w
h
ich
ca
n
r
esu
lt
i
n
a
tr
af
f
ic
ac
cid
en
t.
On
e
ef
f
o
r
t
t
h
at
ca
n
b
e
d
o
n
e
to
p
r
ev
en
t
tr
a
f
f
ic
a
cc
id
en
ts
d
u
e
to
d
r
o
w
s
in
e
s
s
o
n
t
h
e
d
r
iv
er
i
s
b
y
d
etec
tin
g
d
r
o
w
s
i
n
es
s
b
ef
o
r
e
th
e
ac
cid
en
t o
cc
u
r
s
.
T
h
er
e
ar
e
s
ev
er
al
ca
teg
o
r
ies
to
d
etec
t
an
d
m
ea
s
u
r
e
d
r
iv
er
d
r
o
w
s
in
e
s
s
s
u
c
h
a
s
p
h
y
s
io
lo
g
ical
m
et
h
o
d
s
,
s
u
b
j
ec
tiv
e
m
et
h
o
d
s
an
d
b
eh
av
io
r
al
m
et
h
o
d
s
[
1
]
.
T
h
er
e
a
r
e
s
ev
er
al
s
u
b
j
ec
tiv
e
m
e
th
o
d
s
,
tes
tin
g
th
e
r
esp
o
n
d
en
t
b
ased
o
n
th
e
ir
s
u
b
j
ec
tiv
e
ass
e
s
t
m
e
n
t
s
u
ch
as
k
ar
o
lin
s
k
a
s
lee
p
in
ess
s
ca
le
(
KS
S)
an
d
s
tan
f
o
r
d
s
leep
in
ess
s
ca
le
(
SS
S).
B
r
o
w
n
et
a
l
.
[
2
]
u
s
ed
KSS
to
o
b
s
er
v
e
th
e
s
ca
le
o
f
s
leep
in
es
s
i
n
n
u
r
s
es
W
o
r
ld
Hea
lth
Or
g
a
n
izatio
n
w
o
r
k
ed
af
ter
s
h
i
f
t
s
o
r
w
h
en
s
h
i
f
ts
w
er
e
ca
r
r
ied
o
u
t,
an
d
th
e
r
esu
lt
w
as
t
h
at
n
u
r
s
e
s
w
er
e
d
etec
ted
to
f
ee
l
m
o
r
e
d
r
o
w
s
y
w
h
e
n
th
er
e
w
as
a
s
h
if
t
i
n
co
m
p
ar
ed
to
af
ter
a
s
h
if
t.
J
e
w
ett
et
a
l
.
[
3
]
,
in
th
e
s
t
u
d
y
o
f
d
r
o
w
s
in
e
s
s
d
etec
tio
n
w
it
h
th
e
S
SS
a
n
d
p
s
y
ch
o
m
o
to
r
v
i
g
ila
n
ce
tas
k
(
P
V
T
)
,
in
f
o
r
m
atio
n
i
s
o
b
tain
e
d
b
y
o
b
s
er
v
i
n
g
th
e
s
lo
w
-
m
o
tio
n
r
esp
o
n
s
e
i
n
h
u
m
an
s
w
h
en
d
r
o
w
s
y
w
it
h
v
ar
y
in
g
s
leep
ti
m
e
s
.
I
n
a
d
r
o
w
s
y
co
n
d
itio
n
,
h
u
m
a
n
r
esp
o
n
s
e
is
s
lo
w
er
th
a
n
t
h
e
a
w
a
k
e
co
n
d
itio
n
.
P
VT
h
as
b
etter
p
er
f
o
r
m
an
ce
t
h
a
n
S
SS
p
er
f
o
r
m
a
n
ce
.
So
m
e
ev
id
en
ce
u
s
ed
in
th
e
P
VT
test
s
a
w
t
h
at
a
p
er
s
o
n
w
h
o
is
d
r
o
w
s
y
u
s
u
all
y
h
as
d
ec
r
ea
s
ed
e
y
e
p
u
p
il
an
d
s
lo
w
er
m
o
to
r
ic
r
ea
ctio
n
s
p
ee
d
.
T
h
e
PVT
test
o
b
s
er
v
es
th
e
r
ea
ctio
n
o
f
th
e
r
esp
o
n
d
en
t
o
n
lo
o
k
in
g
n
u
m
b
er
o
n
d
is
p
la
y
.
I
n
o
u
r
r
esear
ch
[
4
]
o
b
s
er
v
ed
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
f
e
m
ale
a
n
d
m
ale
d
r
iv
er
s
in
P
VT
-
b
ased
d
r
iv
i
n
g
.
P
er
f
o
r
m
a
n
ce
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
10
,
No
.
2
,
J
u
n
e
20
21
:
5
01
–
5
09
502
test
f
r
o
m
f
e
m
ale
a
n
d
m
ale
d
r
i
v
er
h
a
v
e
th
e
s
a
m
e
f
ati
g
u
e
r
es
u
lt,
t
h
at
f
e
m
ale
d
r
i
v
er
’
s
co
lli
s
io
n
s
ar
e
h
i
g
h
er
th
a
n
m
ale
d
r
iv
er
’
s
co
llis
io
n
s
.
Dr
o
w
s
i
n
es
s
d
etec
tio
n
a
n
d
m
e
asu
r
e
m
en
t
u
s
in
g
b
eh
a
v
io
r
al
m
et
h
o
d
s
,
f
o
cu
s
in
f
ac
ial
ex
p
r
ess
io
n
s
u
c
h
as:
h
ea
d
a
n
d
e
y
e
p
o
s
itio
n
/
s
tat
e
an
d
f
r
eq
u
e
n
t
y
a
w
n
i
n
g
[
1
]
.
Me
asu
r
e
d
r
o
w
s
i
n
es
s
u
s
in
g
e
y
e
asp
ec
t
r
atio
(
E
AR
)
is
o
n
e
o
f
th
e
b
eh
a
v
io
u
r
m
et
h
o
d
s
.
I
n
th
e
r
esear
ch
b
y
Me
h
t
a
[
5
]
,
a
m
ild
d
r
o
w
s
i
n
es
s
d
etec
tio
n
s
y
s
te
m
u
s
in
g
An
d
r
o
id
w
a
s
d
ev
elo
p
ed
th
at
ca
n
b
e
u
s
ed
in
r
ea
l
-
t
i
m
e.
T
h
e
m
et
h
o
d
u
s
ed
i
s
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
o
n
r
ec
o
r
d
ed
v
id
eo
f
r
a
m
e
s
,
to
d
etec
t f
ac
e
s
u
s
in
g
la
n
d
m
ar
k
s
,
t
h
en
ca
lcu
la
ti
n
g
th
e
E
AR
a
n
d
e
y
e
clo
s
u
r
e
r
atio
(
E
C
R
)
to
d
etec
t
d
r
iv
er
s
leep
in
es
s
b
ased
o
n
ad
ap
tiv
e
th
r
e
s
h
o
ld
i
n
g
w
i
th
a
t
h
r
es
h
o
ld
v
al
u
e
o
f
0
.
2
5
.
I
f
th
e
E
AR
v
al
u
e
is
less
t
h
a
n
th
e
t
h
r
es
h
o
ld
v
al
u
e,
it
i
n
d
icat
es
a
s
tate
o
f
f
ati
g
u
e.
T
h
e
r
an
d
o
m
f
o
r
est
clas
s
if
ier
is
u
s
ed
a
s
a
class
i
f
ier
w
i
th
an
ac
cu
r
ac
y
o
f
8
4
%.
I
n
o
u
r
r
esea
r
ch
p
r
o
p
o
s
ed
a
m
o
d
i
f
icatio
n
o
f
E
AR
,
b
y
u
s
i
n
g
E
AR
th
r
es
h
o
ld
th
at
ca
lcu
lati
n
g
f
r
o
m
E
AR
m
i
n
d
an
E
AR
m
ax
d
e
s
ig
n
f
o
r
in
d
iv
id
u
all
y
d
r
i
v
er
[
6
]
.
T
h
e
m
o
s
t
o
b
j
ec
tiv
e
m
et
h
o
d
f
o
r
d
r
o
w
s
i
n
ess
d
etec
tio
n
is
th
e
p
h
y
s
io
lo
g
ical
m
et
h
o
d
[
1
]
.
On
e
o
f
th
e
p
h
y
s
io
lo
g
ical
m
e
th
o
d
s
u
s
ed
is
an
elec
tr
o
en
ce
p
h
alo
g
r
a
m
(
E
E
G)
.
E
E
G
is
d
o
n
e
b
y
r
ec
o
r
d
in
g
h
u
m
an
b
r
ai
n
s
ig
n
al
s
.
T
h
er
e
ar
e
s
e
v
er
al
r
es
ea
r
ch
an
a
l
y
s
i
n
g
E
E
G
s
ig
n
als
f
o
r
d
r
iv
er
'
s
d
r
o
w
s
i
n
es
s
d
etec
t
io
n
[
7
]
-
[
1
6
]
.
E
E
G
s
ig
n
al
s
ca
n
b
e
e
x
tr
ac
ted
w
it
h
a
v
ar
iet
y
o
f
m
et
h
o
d
s
s
u
c
h
a
s
w
a
v
elet
tr
an
s
f
o
r
m
s
[
1
7
]
-
[
1
8
]
,
f
ast
f
o
u
r
ie
r
tr
an
s
f
o
r
m
(
FF
T
)
[
1
8
]
,
d
an
au
to
r
eg
r
ess
i
v
e
m
o
d
el
(
AR
)
[
1
9
]
.
I
n
th
e
r
esear
ch
b
y
L
i
an
d
C
h
u
n
g
[
1
8
]
,
d
esig
n
an
d
d
ev
elo
p
m
en
t
d
r
o
w
s
i
n
es
s
d
etec
tio
n
s
y
s
te
m
a
n
d
co
m
b
i
n
es
w
it
h
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
s
(
SVM)
.
Har
d
w
ar
e
d
esig
n
u
s
in
g
p
h
o
to
p
leth
y
s
m
o
g
r
ap
h
y
(
P
P
G)
s
en
s
o
r
an
d
h
ea
r
t
r
ate
v
ar
iab
ilit
y
(
HR
V)
,
v
er
if
ied
b
ased
o
n
th
e
p
er
ce
n
tag
e
o
f
e
y
el
id
clo
s
u
r
e
(
P
E
R
C
L
OS)
p
u
p
il.
P
P
G
s
ig
n
al
an
d
th
e
n
clas
s
i
f
y
d
r
iv
er
as
d
r
o
w
s
y
o
r
aler
t.
Fro
m
th
i
s
r
esear
ch
class
i
f
icat
io
n
u
s
in
g
wav
elet
f
ea
t
u
r
e
h
a
v
e
h
ig
h
er
ac
cu
r
ac
y
t
h
an
f
ast
f
o
u
r
ier
tr
an
s
f
o
r
m
(
FF
T
)
.
I
n
P
au
l
y
r
esear
ch
in
d
r
o
w
s
i
n
es
s
d
etec
ti
o
n
u
s
ed
a
w
eb
ca
m
ca
m
er
a
th
at
h
as
a
lo
w
r
eso
l
u
tio
n
to
s
u
p
p
o
r
t
d
etec
t
p
er
ce
n
tag
e
o
f
e
y
elid
clo
s
u
r
e
(
P
E
R
C
L
OS)
,
co
m
b
i
n
in
g
h
is
to
g
r
a
m
o
f
o
r
ien
ted
g
r
ad
ie
n
ts
(
HOG)
an
d
SVM.
T
h
e
f
i
n
al
r
esu
l
ts
f
r
o
m
t
h
e
s
y
s
te
m
ar
e
co
m
p
ar
ed
w
it
h
o
b
s
er
v
atio
n
s
b
y
e
y
es
[
2
0
]
.
I
n
Z
h
an
g
r
esear
ch
,
d
esi
g
n
in
g
d
r
o
w
s
in
e
s
s
d
etec
tio
n
f
o
r
h
i
g
h
-
s
p
ee
d
tr
ain
s
b
ased
o
n
d
r
iv
er
s
u
s
in
g
w
ir
eles
s
E
E
G,
u
s
in
g
FF
T
an
d
th
e
cla
s
s
i
f
icatio
n
w
it
h
SVM
r
ea
ch
e
s
9
0
.
7
0
% [
2
1
]
.
T
h
er
ef
o
r
e
in
th
is
r
esear
ch
,
we
p
r
o
p
o
s
e
an
ex
p
er
i
m
en
t
o
f
d
ata
r
etr
iev
al
w
h
ic
h
is
d
esi
g
n
e
d
b
y
u
s
in
g
m
o
d
i
f
ied
-
E
A
R
a
n
d
E
E
G
s
i
g
n
al.
I
n
th
i
s
r
esear
ch
,
u
s
i
n
g
t
h
e
n
eu
r
o
h
ea
d
s
et
e
m
o
ti
v
E
P
OC
t
o
s
ee
th
e
b
eh
a
v
io
u
r
E
E
G
s
ig
n
als
to
E
AR
's
d
r
iv
er
.
E
E
G
s
ig
n
al
w
i
ll
class
if
y
b
y
u
s
i
n
g
SVM
an
d
w
av
e
let
tr
an
s
f
o
r
m
a
s
a
f
ea
tu
r
e
ex
tr
ac
tio
n
f
o
r
d
r
o
w
s
i
n
es
s
d
ete
ctio
n
.
T
h
e
ea
r
l
y
d
r
o
w
s
in
e
s
s
d
e
tectio
n
s
y
s
te
m
i
s
d
esi
g
n
ed
,
s
o
A
lp
h
a
w
a
v
es,
B
eta
w
a
v
es
a
n
d
T
h
eta
w
av
e
s
f
r
o
m
E
E
G
s
ig
n
al
u
s
ed
i
n
t
h
is
r
ese
ar
ch
(
s
tar
t
f
r
o
m
t
h
e
co
n
d
itio
n
s
’
s
s
o
m
eo
n
e
i
s
s
ti
ll
aller
tn
es
s
,
r
elax
co
n
d
itio
n
u
n
ti
l th
e
li
g
h
t
s
leep
)
.
2.
T
H
E
O
RY
AN
D
DE
SI
G
N
S
YST
E
M
DRO
WSI
NE
SS
D
E
T
E
C
T
I
O
N
2
.
1
.
T
heo
ry
T
h
e
f
o
llo
w
in
g
ar
e
th
eo
r
ies
u
s
ed
in
t
h
e
p
r
o
ce
s
s
o
f
d
r
o
w
s
in
e
s
s
d
etec
tio
n
b
ased
o
n
E
E
G
s
i
g
n
al
s
u
s
in
g
SVM:
E
E
G,
w
a
v
elet
tr
a
n
s
f
o
r
m
an
d
SVM
.
2
.
1
.
1
.
E
lect
ro
ence
ph
a
lo
g
ra
m
(
E
E
G
)
E
lectr
o
en
ce
p
h
alo
g
r
a
m
(
E
E
G)
is
an
i
n
s
tr
u
m
e
n
t
to
ca
p
tu
r
e
ele
ctr
ical
ac
tiv
it
y
i
n
t
h
e
b
r
ain
.
E
E
G
s
ig
n
al
s
ar
e
d
iv
id
ed
in
to
s
i
x
g
r
o
u
p
s
o
f
b
r
ain
w
a
v
e
s
th
a
t
h
a
v
e
d
i
f
f
er
e
n
t
f
r
eq
u
e
n
c
y
r
a
n
g
es.
T
h
e
s
i
x
m
ain
g
r
o
u
p
s
o
f
E
E
G
s
ig
n
al
s
,
n
a
m
el
y
[
2
2
]
:
-
Delta
w
a
v
e
s
(
<4
Hz)
,
r
elate
d
t
o
d
ee
p
s
leep
.
-
T
h
eta
w
av
e
s
(
4
-
8
Hz)
,
ap
p
ea
r
s
w
h
en
s
o
m
eo
n
e
i
s
i
n
a
s
tate
o
f
s
leep
in
es
s
an
d
li
g
h
t sleep
.
-
A
lp
h
a
w
a
v
es
(
8
-
13
Hz)
,
ap
p
ea
r
s
w
h
e
n
s
o
m
eo
n
e
i
s
i
n
a
r
elax
ed
s
tate
a
n
d
t
h
e
s
tr
o
n
g
e
s
t e
n
er
g
y
o
cc
u
r
s
in
t
h
e
f
r
o
n
tal
a
n
d
o
cc
ip
ital c
o
r
tex
.
-
Mu
w
av
e
(
8
-
1
2
Hz)
,
r
elate
d
to
m
o
to
r
ac
tiv
it
y
an
d
ca
n
b
e
u
s
ed
to
r
ec
o
g
n
ize
th
e
p
u
r
p
o
s
e
o
f
o
n
e's
m
o
v
e
m
e
n
ts
.
-
B
eta
w
av
e
s
(
1
3
-
3
0
Hz)
,
r
elate
d
t
o
th
e
lev
el
o
f
aler
t
n
ess
a
n
d
co
n
ce
n
tr
atio
n
o
f
a
p
er
s
o
n
.
-
Ga
m
m
a
w
a
v
es
(
3
0
-
5
0
Hz)
,
ar
e
ass
o
ciate
d
w
it
h
o
n
e
'
s
m
e
n
tal
ac
ti
v
ities
s
u
c
h
as
cr
ea
tiv
it
y
a
n
d
p
r
o
b
le
m
s
o
lv
i
n
g
.
2
.
1
.
2
.
Wa
v
elet
t
ra
ns
f
o
r
m
a
t
io
n
W
av
elet
tr
an
s
f
o
r
m
atio
n
is
th
e
d
ev
elo
p
m
en
t
o
f
th
e
f
o
u
r
ier
tr
a
n
s
f
o
r
m
atio
n
s
o
th
at
it
h
as
th
e
s
a
m
e
w
a
y
o
f
w
o
r
k
i
n
g
w
h
ic
h
i
s
to
b
r
ea
k
t
h
e
s
i
g
n
a
l
i
n
to
s
ev
er
al
p
ar
ts
.
T
h
e
d
i
f
f
er
e
n
ce
i
s
t
h
at
t
h
e
Fo
u
r
ier
tr
a
n
s
f
o
r
m
p
r
o
v
id
es
th
e
f
r
eq
u
en
c
y
i
n
f
o
r
m
atio
n
o
f
t
h
e
s
ig
n
al
b
u
t
d
o
es
n
o
t
p
r
o
v
id
e
t
h
e
ti
m
e
i
n
f
o
r
m
atio
n
,
w
h
er
ea
s
t
h
e
w
a
v
elet
tr
an
s
f
o
r
m
p
r
o
v
id
es
th
e
ti
m
e
an
d
f
r
eq
u
en
c
y
in
f
o
r
m
a
t
io
n
o
f
th
e
s
ig
n
al.
W
av
elet
tr
an
s
f
o
r
m
i
s
s
u
itab
le
to
an
al
y
ze
n
o
n
-
s
tatio
n
ar
y
s
i
g
n
a
ls
,
d
if
f
er
en
t f
r
o
m
f
o
u
r
ier
tr
an
s
f
o
r
m
is
n
o
t su
i
tab
le
f
o
r
n
o
n
-
s
tati
o
n
ar
y
s
i
g
n
als [
2
3
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
E
E
G
s
ig
n
a
l c
la
s
s
ifica
tio
n
fo
r
d
r
o
w
s
in
ess
d
etec
tio
n
u
s
in
g
w
a
ve
let
tr
a
n
s
fo
r
m…
(
N
o
vie
Th
er
esia
B
r
.
P
a
s
a
r
ib
u
)
503
W
av
elets
ar
e
a
f
a
m
il
y
o
f
f
u
n
c
t
io
n
s
p
r
o
d
u
ce
d
b
y
t
h
e
b
asis
w
a
v
elets
ca
lled
m
o
t
h
er
w
a
v
elets
[
2
4
]
.
T
h
e
t
w
o
m
a
in
o
p
er
atio
n
s
t
h
at
u
n
d
er
lie
th
e
w
av
e
let
ar
e
tr
an
s
latio
n
a
n
d
s
ca
lin
g
.
T
r
an
s
latio
n
is
a
f
o
r
m
o
f
tr
an
s
f
o
r
m
atio
n
o
f
t
h
e
ti
m
e
d
o
m
ai
n
.
Scali
n
g
is
a
f
o
r
m
o
f
tr
an
s
f
o
r
m
atio
n
o
f
f
r
eq
u
e
n
c
y
,
with
t
h
e
s
c
ale
v
al
u
e
in
v
er
s
el
y
p
r
o
p
o
r
tio
n
al
to
th
e
f
r
eq
u
en
c
y
v
al
u
e.
Ma
th
e
m
atica
l
l
y
,
th
e
b
asic
f
u
n
c
tio
n
s
o
f
w
av
elets
ar
e
w
r
it
ten
a
s
(
1
)
[
2
4
]
:
(
1
)
w
h
er
e
b=
l
o
ca
tio
n
p
ar
a
m
eter
,
a=
s
ca
lin
g
p
ar
a
m
eter
,
t=ti
m
e.
W
av
elet
tr
an
s
f
o
r
m
also
co
n
s
is
t
s
o
f
s
ev
er
al
t
y
p
es
o
f
f
a
m
ilies
,
n
a
m
el
y
Da
u
b
ec
h
ies,
S
y
m
let
s
,
C
o
if
lets
,
an
d
o
th
er
s
[
2
4
]
.
2
.
1
.
3
.
Su
pp
o
rt
v
ec
t
o
r
m
a
chi
ne
(
SVM
)
Su
p
p
o
r
t
v
ec
t
o
r
m
ac
h
i
n
e
(
S
V
M)
w
a
s
f
ir
s
t
in
tr
o
d
u
ce
d
b
y
V
ap
n
ik
a
s
a
s
u
p
er
io
r
m
eth
o
d
i
n
th
e
f
ield
o
f
p
atter
n
r
ec
o
g
n
i
tio
n
[
2
5
]
.
SVM
is
a
cla
s
s
i
f
ier
b
ased
o
n
a
l
in
ea
r
d
is
cr
i
m
in
a
n
t
f
u
n
c
tio
n
,
t
h
at
ca
n
b
e
u
s
ed
as
a
b
in
ar
y
clas
s
if
ier
[
2
6
]
.
T
h
e
co
n
ce
p
t
o
f
SVM
is
tr
y
in
g
to
f
i
n
d
t
h
e
b
est
h
y
p
er
p
la
n
e
th
at
f
u
n
ct
io
n
s
as
a
s
ep
ar
ato
r
o
f
t
w
o
c
lass
e
s
i
n
th
e
in
p
u
t sp
a
ce
.
H
y
p
er
p
lan
e
is
a
h
o
r
izo
n
tal
p
lan
e
th
at
f
u
n
ctio
n
s
as a
cla
s
s
s
ep
ar
ato
r
.
T
h
e
b
est
s
ep
ar
atin
g
h
y
p
er
p
lan
e
is
o
b
tai
n
ed
b
y
f
in
d
i
n
g
th
e
m
a
x
i
m
u
m
m
ar
g
i
n
.
Ma
r
g
i
n
is
th
e
d
is
ta
n
c
e
o
f
th
e
h
y
p
er
p
lan
e
f
r
o
m
t
h
e
clo
s
est
p
atter
n
co
m
m
o
n
l
y
ca
lled
a
s
u
p
p
o
r
t
v
ec
to
r
[
2
7
]
.
T
h
er
e
ar
e
tw
o
p
atter
n
(
p
o
s
itiv
e
o
b
j
ec
ts
an
d
n
eg
at
iv
e
o
b
j
ec
ts
)
w
h
ic
h
w
ill
s
ep
ar
ate
in
to
t
w
o
class
e
s
,
Fig
u
r
e
1
s
h
o
w
s
s
o
m
e
p
atter
n
s
th
at
a
r
e
m
e
m
b
er
s
o
f
t
w
o
class
es,
n
a
m
el
y
-
1
an
d
+1
.
T
h
e
p
atter
n
s
in
co
r
p
o
r
ated
in
clas
s
-
1
ca
n
b
e
f
o
r
m
u
lated
as
:
Fig
u
r
e
1
.
SVM
h
y
p
er
p
lan
e
t
h
a
t
s
ep
ar
ates th
e
t
w
o
clas
s
es
[
2
7
]
(
2
)
W
h
ile
th
e
p
atter
n
s
i
n
co
r
p
o
r
ate
d
i
n
+1
class
ca
n
b
e
f
o
r
m
u
late
d
as (
3
)
.
(
3
)
T
o
s
ep
ar
ate
th
e
t
w
o
p
atter
n
s
p
er
f
ec
tl
y
i
t ta
k
e
s
a
h
y
p
er
p
la
n
e
o
f
d
i
m
e
n
s
io
n
d
w
h
ic
h
is
f
o
r
m
u
lated
as
(
4
)
.
(
4
)
⃗
:
I
n
p
u
t v
ec
to
r
⃗
⃗
⃗
:
W
eig
h
t
v
ec
to
r
:
B
ias
C
ases
t
h
at
o
cc
u
r
in
th
e
r
ea
l
wo
r
ld
ar
e
r
ar
ely
lin
ea
r
l
y
s
ep
ar
ab
le;
to
o
v
er
co
m
e
th
is
p
r
o
b
le
m
th
e
SVM
w
a
s
m
o
d
i
f
ied
b
y
i
n
cl
u
d
in
g
k
e
r
n
el
f
u
n
ctio
n
s
.
I
n
n
o
n
-
li
n
ea
r
SVM,
th
e
d
ata
⃗
is
f
ir
s
t
m
ap
p
ed
b
y
t
h
e
f
u
n
ctio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
10
,
No
.
2
,
J
u
n
e
20
21
:
5
01
–
5
09
504
(
)
to
th
e
h
ig
h
er
d
i
m
e
n
s
io
n
al
v
ec
to
r
s
p
ac
e
[
2
3
]
.
I
n
th
is
n
e
w
v
ec
to
r
s
p
ac
e,
th
e
h
y
p
er
p
lan
e
t
h
at
s
ep
ar
ates
th
e
t
w
o
clas
s
es c
a
n
o
n
l
y
b
e
co
n
s
tr
u
cted
.
T
h
is
co
n
ce
p
t c
an
b
e
s
ee
n
in
Fig
u
r
e
2
.
Fig
u
r
e
2
.
T
h
e
id
ea
o
f
k
er
n
el
tr
ick
SVM
[
2
7
]
I
n
Fig
u
r
e
2
,
it
is
s
h
o
w
n
t
h
at
t
h
e
d
ata
in
th
e
t
w
o
d
i
m
en
s
io
n
s
i
n
p
u
t
s
p
ac
e
ca
n
n
o
t
b
e
lin
ea
r
l
y
s
ep
ar
ated
,
an
d
th
en
t
h
e
f
u
n
ctio
n
ϕ
m
ap
s
ea
ch
d
ata
to
a
h
ig
h
er
d
i
m
e
n
s
io
n
,
s
o
th
at
th
e
t
w
o
clas
s
e
s
ca
n
b
e
s
ep
ar
ated
lin
ea
r
l
y
.
T
h
en
t
h
e
tr
ai
n
i
n
g
p
r
o
ce
s
s
is
th
e
s
a
m
e
a
s
i
n
t
h
e
l
i
n
ea
r
SVM.
T
h
e
o
p
ti
m
izatio
n
p
r
o
ce
s
s
in
th
is
p
h
ase
r
eq
u
ir
es
th
e
ca
lc
u
latio
n
o
f
th
e
d
o
t
p
r
o
d
u
ct
t
w
o
ex
a
m
p
les
i
n
t
h
e
n
e
w
v
ec
to
r
s
p
ac
e.
T
h
e
d
o
t p
r
o
d
u
cts
o
f
th
e
t
w
o
v
ec
to
r
s
(
x
i
)
an
d
(
x
j
)
ar
e
d
en
o
ted
as
Φ
(
x
i
)
.
Φ
(
x
j
)
.
T
h
e
d
o
t
p
r
o
d
u
ct
v
al
u
es
o
f
t
h
ese
t
w
o
v
ec
to
r
s
ca
n
b
e
ca
lcu
lated
in
d
ir
ec
tl
y
,
th
at
is
,
w
i
th
o
u
t
k
n
o
w
i
n
g
th
e
tr
an
s
f
o
r
m
atio
n
f
u
n
ctio
n
Φ
.
T
h
is
co
m
p
u
tatio
n
al
tech
n
iq
u
e
i
s
ca
lled
Ker
n
el
T
r
ick
,
w
h
ich
ca
lcu
late
s
t
h
e
d
o
t
p
r
o
d
u
ct
o
f
t
w
o
v
ec
to
r
s
in
a
n
e
w
v
ec
to
r
s
p
ac
e
b
y
u
s
in
g
t
h
e
co
m
p
o
n
e
n
t
s
o
f
b
o
th
v
ec
to
r
s
in
th
e
o
r
ig
i
n
al
v
ec
to
r
s
p
ac
e.
Sev
er
al
ty
p
es
o
f
k
er
n
e
ls
in
t
h
e
SVM
:
li
n
ea
r
k
er
n
el,
p
o
ly
n
n
o
m
ial
k
er
n
el
a
n
d
g
a
u
s
s
ian
k
er
n
el
[
2
6
]
.
2
.
2
.
Desig
n
s
y
s
t
e
m
dro
w
s
ines
s
de
t
ec
t
io
n
2
.
2
.
1
.
Da
t
a
co
llect
io
n scena
rio
s
B
ased
o
n
th
e
ac
cid
en
t
tr
af
f
ic
d
ata
f
r
o
m
Ko
r
lan
ta
s
I
n
d
o
n
e
s
ia
i
n
2
0
1
8
,
th
er
e
ar
e
t
h
r
ee
g
r
o
u
p
s
o
f
ac
cid
en
t
v
icti
m
s
n
a
m
el
y
at
th
e
ag
e
o
f
1
5
-
1
9
y
ea
r
s
o
ld
,
2
0
-
2
4
y
ea
r
s
o
ld
an
d
2
5
-
2
9
y
ea
r
s
o
ld
[
1
5
]
.
A
n
d
also
f
r
o
m
t
h
e
Nat
io
n
al
H
ig
h
w
a
y
T
r
af
f
ic
Sa
f
et
y
A
d
m
i
n
i
s
tr
atio
n
(
NHT
SA
)
,
cr
ash
e
s
o
cc
u
r
r
ed
d
u
r
in
g
t
h
e
p
er
io
d
b
et
w
ee
n
1
9
8
9
an
d
1
9
9
3
in
th
e
Un
ited
State
s
,
th
er
e
ar
e
ap
p
r
o
x
i
m
atel
y
1
0
0
,
0
0
0
c
r
ash
es p
er
y
ea
r
id
en
ti
f
ied
w
it
h
d
r
o
w
s
i
n
ess
,
th
e
h
ig
h
es
t
r
o
ad
t
r
af
f
ic
d
ea
th
b
y
a
g
e
r
a
n
g
e
ar
e
1
5
-
2
9
[
1
]
.
T
h
er
ef
o
r
e
in
t
h
is
ex
p
er
im
e
n
t,
th
e
ag
e
s
r
an
g
e
o
f
r
esp
o
n
d
e
n
t
ar
e
1
9
-
2
6
y
ea
r
s
o
ld
,
w
it
h
a
to
tal
o
f
te
n
r
esp
o
n
d
en
t
i
n
g
o
o
d
h
ea
lt
h
an
d
h
a
v
e
s
u
f
f
icie
n
t
s
leep
.
T
h
e
s
ce
n
ar
io
o
f
d
r
o
w
s
i
n
ess
d
etec
tio
n
e
x
p
er
i
m
e
n
t d
esi
g
n
is
s
u
m
m
ar
ized
in
Fi
g
u
r
e
3
:
Fig
u
r
e
3
.
Scen
ar
io
o
f
d
r
o
w
s
i
n
ess
d
etec
tio
n
e
x
p
er
i
m
e
n
t
First
s
ta
g
e,
th
e
en
tire
r
esp
o
n
d
en
t
d
id
Dr
iv
in
g
-
1
p
r
o
ce
s
s
(
d
u
r
atio
n
:
2
m
in
u
tes),
th
is
is
t
h
e
b
aselin
e
co
n
d
itio
n
o
f
r
esp
o
n
d
en
t
.
Seco
n
d
s
ta
g
e
is
co
n
ti
n
u
in
g
to
Dr
i
v
in
g
-
2
p
r
o
ce
s
s
(
d
u
r
atio
n
:
1
0
m
i
n
u
te
s
)
.
T
h
ir
d
s
tag
e
is
ar
it
h
m
et
ic
-
s
tr
es
s
p
r
o
ce
s
s
(
d
u
r
atio
n
:
3
0
m
i
n
u
te
s
)
,
t
h
e
o
b
j
e
ctiv
e
o
f
t
h
is
p
r
o
ce
s
s
is
to
m
a
k
e
it
t
h
e
r
esp
o
n
d
en
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
E
E
G
s
ig
n
a
l c
la
s
s
ifica
tio
n
fo
r
d
r
o
w
s
in
ess
d
etec
tio
n
u
s
in
g
w
a
ve
let
tr
a
n
s
fo
r
m…
(
N
o
vie
Th
er
esia
B
r
.
P
a
s
a
r
ib
u
)
505
f
ee
l
f
a
tig
u
e.
T
h
e
last
s
ta
g
e
is
Dr
iv
i
n
g
-
2
p
r
o
ce
s
s
(
d
u
r
atio
n
:
1
0
m
i
n
u
tes).
T
o
tal
d
u
r
atio
n
tim
es
o
f
e
x
p
er
i
m
e
n
t
ar
e
5
2
m
in
u
te
s
.
R
esp
o
n
d
en
t
in
t
h
is
r
esear
c
h
u
s
i
n
g
d
r
iv
er
s
i
m
u
lato
r
,
an
d
th
e
ca
m
er
a
is
p
lace
d
in
f
r
o
n
t
o
f
th
e
r
esp
o
n
d
en
t
'
s
f
ac
e,
s
o
t
h
e
e
y
e
o
f
a
s
p
ec
t
ar
ea
(
E
A
R
)
r
esp
o
n
d
en
t
ca
n
b
e
o
b
s
er
v
ed
an
d
ca
lc
u
l
ated
.
W
h
ile
d
r
iv
in
g
p
r
o
ce
s
s
,
r
esp
o
n
d
en
t
also
u
s
in
g
th
e
n
e
u
r
o
h
ea
d
s
et
e
m
o
tiv
E
P
OC
,
to
r
ec
o
r
d
E
E
G
s
ig
n
als.
E
m
o
ti
v
E
P
OC
1
4
ch
an
n
el
s
ar
e
d
ev
ices
f
o
r
r
ec
o
r
d
in
g
elec
tr
ical
ac
tiv
it
y
in
t
h
e
b
r
ain
,
an
d
th
e
lo
ca
tio
n
o
f
th
e
elec
tr
o
d
es
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
4
[
2
8
]
.
Fig
u
r
e
4
.
Neu
r
o
h
ea
d
s
et
e
m
o
t
i
v
E
P
OC
1
4
e
lectr
o
d
e
ch
an
n
els
an
d
lo
ca
tio
n
s
E
m
o
tiv
E
P
OC
h
as
s
ev
er
al
co
m
p
o
n
en
ts
,
n
a
m
el
y
,
a
h
ea
d
s
et,
u
n
i
v
er
s
al
USB
r
ec
eiv
er
,
an
d
m
i
n
i
-
B
to
A
USB
ca
b
le.
T
h
e
h
ea
d
s
et
m
u
s
t
b
e
m
o
u
n
ted
i
n
t
h
e
r
ig
h
t
p
o
s
iti
o
n
o
n
t
h
e
r
esp
o
n
d
e
n
t
'
s
h
ea
d
a
n
d
co
n
n
ec
ted
to
t
h
e
E
m
o
tiv
P
R
O
s
o
f
t
w
ar
e
v
ia
a
u
n
i
v
er
s
al
USB
r
ec
eiv
er
.
T
h
e
r
esu
lt
s
o
f
t
h
is
e
x
p
er
i
m
e
n
t
a
r
e
th
en
s
av
ed
.
T
h
e
Dr
iv
i
n
g
-
1
p
r
o
ce
s
s
is
co
n
s
id
er
ed
a
b
aseli
n
e
co
n
d
itio
n
,
i
s
t
h
e
r
esp
o
n
d
en
t
's
co
n
d
itio
n
i
s
co
n
s
id
er
ed
a
w
a
k
e.
T
h
e
d
r
o
w
s
i
n
ess
co
n
d
itio
n
o
f
t
h
e
d
r
iv
er
w
a
s
o
b
s
er
v
ed
b
ased
o
n
th
e
E
y
e
Asp
ec
t
r
atio
(
E
A
R
)
a
n
d
th
e
r
esp
o
n
d
en
t
'
s
E
E
G
s
ig
n
al
b
e
h
av
io
r
f
r
o
m
Dr
iv
i
n
g
-
2
p
r
o
ce
s
s
an
d
Dr
i
v
in
g
-
3
p
r
o
ce
s
s
.
E
E
G
s
i
g
n
al
r
ec
o
r
d
in
g
is
d
o
n
e
s
i
m
u
lta
n
e
o
u
s
l
y
w
it
h
E
AR
ca
l
cu
lated
.
B
lo
ck
d
ia
g
r
a
m
o
f
t
h
e
d
esig
n
o
f
d
r
o
w
s
in
e
s
s
d
etec
tio
n
s
y
s
te
m
s
u
s
i
n
g
SVM
ca
n
b
e
s
ee
n
i
n
F
ig
u
r
e
5
,
w
h
ic
h
co
n
s
i
s
ts
o
f
s
e
v
er
al
p
r
o
ce
s
s
es,
n
a
m
el
y
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
t
u
r
e
e
x
tr
ac
tio
n
,
an
d
class
i
f
icat
io
n
.
Fig
u
r
e
5
.
Dr
o
w
s
i
n
es
s
d
etec
tio
n
u
s
in
g
w
a
v
elet
tr
an
s
f
o
r
m
an
d
SVM
s
y
s
te
m
b
lo
ck
d
iag
r
a
m
2
.
2
.
2
.
P
re
pro
ce
s
s
ing
I
n
th
i
s
r
esear
ch
,
E
E
G
s
ig
n
als
w
er
e
r
ec
o
r
d
ed
u
s
in
g
1
4
ch
an
n
el
E
m
o
ti
v
E
P
OC
Neu
r
o
h
ea
d
s
et,
u
s
i
n
g
f
r
o
n
tal
c
h
a
n
n
e
ls
(
F3
,
F4
,
F7
,
F8
)
an
d
o
cc
ip
ital
(
O1
an
d
O2
)
.
T
h
e
s
ig
n
al
s
u
s
ed
i
n
t
h
is
r
ese
ar
ch
ar
e
alp
h
a,
h
i
g
h
b
eta,
lo
w
b
eta
a
n
d
t
h
eta
.
Di
s
p
la
y
o
f
E
E
G
s
ig
n
al
r
ec
o
r
d
in
g
i
n
E
m
o
t
iv
P
R
O
s
o
f
t
w
ar
e
ca
n
b
e
s
ee
n
in
Fi
g
u
r
e
6
.
A
t
th
e
p
r
ep
r
o
ce
s
s
in
g
s
ta
g
e,
t
h
e
d
ata
o
f
E
E
G
s
i
g
n
al
s
s
ep
ar
ated
to
tr
ain
i
n
g
d
ata
an
d
te
s
ti
n
g
d
ata.
Fo
r
tr
ain
i
n
g
d
ata,
EEG
s
ig
n
al
s
ar
e
g
r
o
u
p
ed
in
to
d
r
o
w
s
in
e
s
s
s
ig
n
al
s
an
d
n
o
n
-
d
r
o
w
s
i
n
es
s
s
i
g
n
als
b
ase
d
o
n
E
A
R
.
Aw
a
k
e
co
n
d
itio
n
s
i
g
n
al
w
as
ta
k
e
n
f
r
o
m
t
h
e
Dr
iv
i
n
g
-
1
p
r
o
ce
s
s
,
th
e
n
th
e
d
r
o
w
s
i
n
e
s
s
co
n
d
itio
n
s
i
g
n
al
w
as
ta
k
e
n
f
r
o
m
Dr
iv
i
n
g
-
2
p
r
o
ce
s
s
an
d
Dr
i
v
e
-
3
p
r
o
ce
s
s
.
I
f
th
e
E
AR
is
b
elo
w
t
h
e
t
h
r
es
h
o
ld
f
o
r
1
.
5
s
ec
o
n
d
s
o
r
3
8
co
n
s
ec
u
ti
v
e
f
r
a
m
e
s
,
th
e
n
t
h
e
r
esp
o
n
d
en
t
is
co
n
s
id
er
ed
d
r
o
w
s
y
[
6
]
.
T
h
en
th
e
E
E
G
s
i
g
n
al
is
s
eg
m
e
n
ted
ea
ch
2
m
i
n
u
tes,
s
o
f
r
o
m
Dr
i
v
in
g
-
2
p
r
o
ce
s
s
an
d
Dr
iv
in
g
-
3
p
r
o
ce
s
s
th
er
e
ar
e
f
iv
e
s
eg
m
en
ted
d
ata
p
er
2
m
i
n
u
te
s
(
f
r
o
m
1
0
m
in
u
te
s
E
E
G
s
ig
n
al)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
10
,
No
.
2
,
J
u
n
e
20
21
:
5
01
–
5
09
506
Fig
u
r
e
6
.
Dis
p
la
y
o
f
E
E
G
s
ig
n
al
r
ec
o
r
d
in
g
in
e
m
o
t
iv
P
R
O
s
o
f
t
w
ar
e
2
.
2
.
3
.
F
ea
t
ure
e
x
t
ra
ct
i
o
n
Af
ter
t
h
e
s
i
g
n
al
p
r
e
-
p
r
o
ce
s
s
in
g
s
ta
g
e
p
r
o
ce
s
s
,
th
e
n
ex
t
s
tep
is
f
ea
t
u
r
e
ex
tr
ac
tio
n
.
Featu
r
e
ex
tr
ac
tio
n
u
s
ed
in
t
h
is
r
esear
c
h
is
w
a
v
ele
t
tr
an
s
f
o
r
m
.
T
h
e
w
a
v
elet
t
y
p
e
u
s
ed
is
Da
u
b
ec
h
ie
s
(
Db
4
)
at
l
ev
el
4
.
L
ev
el
4
w
as
ch
o
s
en
b
ec
au
s
e
at
t
h
is
lev
e
l
th
e
s
i
g
n
al
d
ec
o
m
p
o
s
itio
n
r
esu
lt
s
m
o
s
t
c
lo
s
el
y
r
ese
m
b
le
th
e
o
r
ig
i
n
al
s
i
g
n
a
l.
Fig
u
r
e
7
(
a)
is
th
e
r
a
w
d
ata
s
i
g
n
al
E
E
G
F3
A
lp
h
a,
th
e
n
a
f
t
er
th
e
w
a
v
elet
tr
an
s
f
o
r
m
p
r
o
ce
s
s
ca
n
b
e
s
ee
n
i
n
Fig
u
r
e
7
(
b
)
.
W
av
elet
co
ef
f
icie
n
ts
f
r
o
m
ea
c
h
ch
a
n
n
e
l E
E
G
s
i
g
n
al
u
s
ed
as
f
ea
t
u
r
e
ex
tr
ac
tio
n.
(
a)
(
b
)
Fig
u
r
e
7
.
E
E
G
s
ig
n
al
o
f
F
3
al
p
h
a
; (
a)
r
a
w
d
ata
,
(
b
)
af
ter
w
a
v
elet
tr
an
s
f
o
r
m
2
.
2
.
4
.
Cla
s
s
if
ica
t
io
n
I
n
th
is
r
esear
ch
t
h
e
class
if
ica
ti
o
n
m
et
h
o
d
u
s
ed
is
SVM.
T
h
e
v
alid
atio
n
tec
h
n
iq
u
e
u
s
ed
is
k
-
f
o
ld
cr
o
s
s
v
alid
atio
n
w
it
h
k
=5
,
c
h
o
s
e
n
b
ec
au
s
e
f
o
r
ea
ch
d
r
iv
i
n
g
p
r
o
ce
s
s
h
av
e
5
s
et
d
ata.
I
n
K
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
,
d
ataset
X
i
s
r
a
n
d
o
m
l
y
d
iv
id
e
d
in
to
K
p
ar
ts
o
f
eq
u
al
m
a
g
n
i
tu
d
e
X_
i,
i
=
1
,
2
,
.
.
.
K.
T
o
p
r
o
d
u
ce
ea
ch
p
air
o
f
d
ata
is
to
s
to
r
e
o
n
e
o
f
th
e
K
p
ar
ts
in
to
a
v
alid
atio
n
s
e
t,
th
e
n
co
m
b
i
n
e
w
it
h
p
ar
ts
th
e
r
e
m
ai
n
in
g
K
-
1
is
to
f
o
r
m
th
e
tr
ain
in
g
s
et.
Do
n
e
K
t
i
m
e
s
(
E
th
e
m
)
:
1
=
1
,
1
=
2
∪
3
∪
⋯
∪
2
=
2
,
2
=
1
∪
3
∪
⋯
∪
⋮
=
,
=
1
∪
2
∪
⋯
∪
−
1
(
5
)
I
n
tr
ai
n
in
g
p
r
o
ce
s
s
,
s
e
v
er
al
k
er
n
el
cla
s
s
i
f
ier
S
VM
te
s
ti
n
g
t
o
ch
o
o
s
en
th
e
h
ig
h
est
ac
c
u
r
atio
n
.
T
h
en
f
r
o
m
t
h
e
b
est
k
er
n
el
c
h
o
s
en
,
co
n
tin
u
ed
to
tr
ain
i
n
g
p
r
o
ce
s
s
.
Data
clas
s
i
f
y
in
to
t
w
o
class
es,
n
a
m
el
y
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
E
E
G
s
ig
n
a
l c
la
s
s
ifica
tio
n
fo
r
d
r
o
w
s
in
ess
d
etec
tio
n
u
s
in
g
w
a
ve
let
tr
a
n
s
fo
r
m…
(
N
o
vie
Th
er
esia
B
r
.
P
a
s
a
r
ib
u
)
507
(
d
r
o
w
s
in
e
s
s
clas
s
)
an
d
-
1
(
n
o
t
d
r
o
w
s
in
e
s
s
/
a
w
a
k
e
clas
s
)
.
Af
ter
th
e
S
VM
test
i
n
g
p
r
o
ce
s
s
,
co
n
tai
n
s
a
clas
s
p
r
ed
ictio
n
f
o
r
ea
ch
d
ata
co
n
s
is
ti
n
g
o
f
6
6
o
u
tp
u
ts
is
th
e
r
e
s
u
lt
o
f
c
lass
if
ica
tio
n
co
n
s
i
s
ti
n
g
o
f
1
(
d
r
o
w
s
i
n
es
s
class
)
a
n
d
-
1
(
n
o
t
d
r
o
w
s
i
n
e
s
s
/
a
w
ak
e
clas
s
)
.
I
n
t
h
i
s
r
e
s
ea
r
c
h
,
i
n
d
icatio
n
o
f
d
r
o
w
s
i
n
es
s
r
esp
o
n
d
en
t
is
d
eter
m
in
ed
if
at
least
2
/3
o
f
th
e
6
6
o
u
tp
u
ts
(
th
er
e
ar
e
4
4
o
u
tp
u
t)
s
tated
"
1
"
(
d
r
o
w
s
i
n
es
s
class
)
,
2
/3
(
6
6
%)
ch
o
s
en
b
ec
au
s
e
th
i
s
d
ec
is
io
n
g
r
ea
ter
th
an
5
0
%
SVM
o
u
tp
u
t
in
o
r
d
er
t
o
d
ete
r
m
i
n
e
a
clea
r
class
if
ica
tio
n
f
o
r
ea
ch
class
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
W
av
elet
co
ef
f
icien
ts
u
s
ed
in
th
is
r
esear
c
h
w
er
e
6
6
co
ef
f
ic
ien
ts
u
s
ed
as
in
p
u
t
to
th
e
S
VM
in
th
e
tr
ain
i
n
g
an
d
te
s
ti
n
g
p
r
o
ce
s
s
.
I
n
t
h
e
cla
s
s
i
f
icatio
n
tr
ai
n
i
n
g
p
r
o
ce
s
s
u
s
i
n
g
SVM,
th
e
v
a
lid
ati
o
n
tech
n
iq
u
e
u
s
ed
i
s
5
-
f
o
ld
cr
o
s
s
v
alid
atio
n
.
Fro
m
v
ar
io
u
s
k
er
n
e
ls
test
ed
,
it
w
a
s
f
o
u
n
d
th
at
th
e
h
ig
h
es
t
lev
el
o
f
ac
cu
r
ac
y
in
th
e
SVM
tr
ai
n
i
n
g
p
r
o
ce
s
s
u
s
i
n
g
a
q
u
ad
r
atic
k
er
n
el
r
ea
ch
ed
8
4
.
5
%.
T
h
u
s
t
h
e
k
er
n
e
l
u
s
ed
i
s
t
h
e
Qu
ad
r
atic
k
er
n
el,
s
ee
T
ab
le
1
.
T
ab
le
1
.
Ker
n
el
a
cc
u
r
atio
n
K
e
r
n
e
l
A
c
c
u
r
a
t
i
o
n
L
i
n
e
a
r
7
1
.
8
%
Q
u
a
d
r
a
t
i
c
8
4
.
5
%
C
u
b
i
c
5
2
.
3
%
F
i
n
e
G
a
u
ssi
a
n
7
2
.
2
%
M
e
d
i
u
m G
a
u
ss
i
a
n
7
0
.
2
%
C
o
a
r
se
G
a
u
ssi
a
n
5
9
.
6
%
Af
ter
t
h
e
tr
ai
n
i
n
g
p
r
o
ce
s
s
t
h
e
n
p
r
o
ce
ed
to
th
e
te
s
ti
n
g
p
r
o
ce
s
s
,
w
h
ic
h
i
s
ca
r
r
ied
o
u
t
o
n
D
r
iv
i
n
g
-
2
p
r
o
ce
s
s
an
d
D
r
i
v
in
g
-
3
p
r
o
ce
s
s
.
I
n
th
e
D
r
iv
in
g
-
2
p
r
o
ce
s
s
th
e
r
es
u
lt
s
o
f
t
h
e
SVM
c
l
ass
i
f
icatio
n
o
f
1
0
r
esp
o
n
d
en
ts
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
8
(
a)
.
I
f
t
h
e
to
tal
SVM
o
u
t
p
u
t is
g
r
ea
ter
t
h
a
n
2
/3
f
r
o
m
o
u
tp
u
t S
VM
,
t
h
en
th
e
class
is
d
ec
lar
ed
as
d
r
o
w
s
i
n
e
s
s
(
1
)
,
else
th
e
class
i
s
d
ec
lar
ed
as
a
w
ak
e
(
-
1
)
,
p
er
f
o
r
m
ed
o
n
all
f
i
v
e
d
ata
f
o
r
ea
ch
r
esp
o
n
d
en
t
in
t
h
e
Dr
iv
in
g
-
2
P
r
o
ce
s
s
,
s
ee
Fig
u
r
e
8
(
b
)
.
Fo
r
ex
a
m
p
le
f
o
r
r
esp
o
n
d
en
t
R
1
,
r
esp
o
n
d
en
t
w
a
s
d
etec
ted
d
r
o
w
s
in
e
s
s
i
n
t
h
e
D
ata2
-
2
,
Data
2
-
3
an
d
Da
ta2
-
4
.
W
h
er
ea
s
in
th
e
Data
2
-
1
a
n
d
Data
2
-
5
d
etec
ted
in
th
e
a
w
a
k
e
co
n
d
it
io
n
s
(
n
o
d
r
o
w
s
in
e
s
s
)
.
So
,
to
tall
y
i
n
1
0
m
i
n
u
te
s
p
r
o
ce
s
s
,
t
h
e
d
r
iv
er
i
s
m
aj
o
r
ity
d
r
o
w
s
y
(
R
1
,
R
2
,
R
5
,
R
6
,
R
7
,
R
9
,
an
d
R
1
0
)
.
An
d
th
er
e
3
r
esp
o
n
d
en
ts
w
er
e
d
etec
ted
as
a
w
ak
e
cla
s
s
(
R
3
,
R
4
,
an
d
R8
)
.
(
a)
(
b
)
Fig
u
r
e
8
.
SVM
c
lass
i
f
icat
io
n
a
n
d
f
i
n
al
clas
s
i
f
icatio
n
f
r
o
m
D
r
iv
i
n
g
-
2
p
r
o
ce
s
s
; (
a)
SVM
c
las
s
if
ica
tio
n
,
(
b
)
f
in
al
clas
s
if
icatio
n
I
n
t
h
e
Dr
i
v
e
-
3
p
r
o
ce
s
s
th
e
r
esu
lt
s
o
f
t
h
e
SV
M
c
las
s
i
f
ica
tio
n
o
f
1
0
r
esp
o
n
d
en
ts
ca
n
b
e
s
ee
n
i
n
Fig
u
r
e
9
(
a)
.
T
h
en
th
e
f
i
n
al
cla
s
s
i
f
icatio
n
,
s
ee
F
ig
u
r
e
9
(
b
)
.
T
h
e
f
in
a
l
clas
s
i
f
icatio
n
r
esu
lts
c
an
b
e
s
ee
n
t
h
at
t
h
e
r
esu
lt
s
o
f
t
h
e
m
aj
o
r
it
y
d
r
o
w
s
y
ar
e
r
esp
o
n
d
en
t
s
R
1
,
R
2
,
R
5
,
R
6
,
R
7
,
a
n
d
R
9
,
a
n
d
t
h
e
r
e
s
p
o
n
d
en
t
id
e
n
ti
f
ied
a
s
n
o
t
d
r
o
w
s
y
/ a
w
a
k
e
ar
e
r
esp
o
n
d
en
t
s
R
3
,
R
4
,
R
8
an
d
R
1
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
10
,
No
.
2
,
J
u
n
e
20
21
:
5
01
–
5
09
508
(
a)
(
b
)
Fig
u
r
e
9
.
SVM
class
i
f
icat
io
n
a
n
d
f
i
n
al
clas
s
i
f
icatio
n
f
r
o
m
D
r
iv
i
n
g
-
3
P
r
o
ce
s
s
; (
a)
SVM
c
las
s
if
ica
tio
n
,
(
b
)
f
in
al
clas
s
if
icatio
n
4.
CO
NCLU
SI
O
N
I
n
th
is
r
esear
c
h
h
as
s
u
cc
es
s
f
u
l
l
y
u
s
ed
E
E
G
s
ig
n
al
s
b
ased
o
n
m
o
d
i
f
ied
E
A
R
f
o
r
d
r
o
w
s
i
n
es
s
d
etec
tio
n
b
y
u
s
i
n
g
w
av
ele
t
tr
an
s
f
o
r
m
as
a
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
SV
M
as
a
class
i
f
ier
.
W
ith
5
-
f
o
ld
cr
o
s
s
v
alid
atio
n
,
i
n
th
is
r
e
s
ea
r
ch
q
u
ad
r
atic
k
er
n
el
(
8
4
.
5
%)
p
r
o
d
u
ce
s
th
e
b
est
l
ev
el
o
f
ac
c
u
r
ac
y
co
m
p
ar
ed
to
th
e
t
y
p
e
o
f
l
i
n
ea
r
k
er
n
el
(
7
2
.
2
%),
c
u
b
ic
(
5
2
.
3
%),
f
i
n
e
g
a
u
s
s
ia
n
(
7
2
.
2
%),
m
ed
iu
m
g
a
u
s
s
ia
n
(
7
0
.
2
%),
an
d
c
o
ar
s
e
g
au
s
s
ia
n
(
5
9
.
6
%)
.
I
n
t
esti
n
g
D
r
i
v
i
n
g
-
2
p
r
o
ce
s
s
d
ata
r
esu
lts
,
7
r
esp
o
n
d
en
ts
w
er
e
d
etec
ted
as
d
r
o
w
s
i
n
ess
clas
s
(
R
1
,
R
2
,
R
5
,
R
6
,
R
7
,
R
9
,
an
d
R
1
0
)
,
an
d
3
r
esp
o
n
d
en
ts
w
er
e
d
etec
te
d
as
a
w
a
k
e
class
(
R
3
,
R
4
,
an
d
R8
)
.
I
n
D
r
iv
in
g
-
3
p
r
o
ce
s
s
th
er
e
6
r
esp
o
n
d
en
ts
w
er
e
d
etec
ted
a
s
d
r
o
w
s
in
e
s
s
clas
s
(
R
1
,
R
2
,
R
5
,
R
6
,
R
7
,
an
d
R9
),
an
d
4
r
esp
o
n
d
en
ts
w
er
e
d
etec
ted
as
a
w
ak
e
clas
s
(
R
3
,
R
4
,
R
8
an
d
R
10)
.
B
ec
au
s
e
in
th
is
ex
p
e
r
i
m
en
t
d
r
o
w
s
i
n
ess
d
etec
tio
n
w
a
s
o
b
s
er
v
ed
in
a
ce
r
tain
ti
m
e
p
er
io
d
,
s
o
f
o
r
th
e
n
e
x
t
r
esear
ch
to
d
ev
elo
p
d
r
o
w
s
i
n
es
s
d
etec
tio
n
w
it
h
a
s
h
o
r
t
ti
m
e
i
n
r
ea
l ti
m
e,
b
y
u
t
ilizin
g
s
e
v
er
al
o
th
er
co
m
b
i
n
ati
o
n
m
et
h
o
d
s
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
an
k
s
to
U
n
i
v
er
s
itas
Kr
i
s
te
n
Ma
r
an
ath
a
f
o
r
f
u
n
d
i
n
g
t
h
i
s
r
es
ea
r
ch
.
RE
F
E
R
E
NC
E
S
[1
]
A
.
Čo
li
ć
,
O.
M
a
rq
u
e
s,
a
n
d
B.
F
u
rh
t,
"
Driv
e
r
Dro
w
sin
e
ss
De
tec
ti
o
n
,
"
S
p
rin
g
e
r
In
ter
n
a
ti
o
n
a
l
Pu
b
li
s
h
in
g
,
2
0
1
4
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
1
1
5
3
5
-
1
.
[2
]
J.
G
.
Bro
w
n
,
M
.
W
iero
n
e
y
,
L
.
B
lair,
S
.
Zh
u
,
J.
W
a
rre
n
,
S
.
M
.
S
c
h
a
rf
e
t
a
l.
,
“
M
e
a
su
rin
g
s
u
b
jec
ti
v
e
sle
e
p
in
e
ss
a
t
w
o
rk
in
h
o
sp
it
a
l
n
u
rse
s: v
a
li
d
a
ti
o
n
o
f
a
m
o
d
i
f
ied
d
e
li
v
e
r
y
f
o
r
m
a
t
o
f
th
e
Ka
r
o
li
n
sk
a
S
lee
p
in
e
ss
S
c
a
le,
”
S
lee
p
Bre
a
th
,
v
o
l.
1
8
,
n
o
.
4
,
p
p
.
7
3
1
-
7
3
9
,
2
0
1
4
,
d
o
i:
1
0
.
1
0
0
7
/s1
1
3
2
5
-
0
1
3
-
0
9
3
5
-
z
.
[3
]
M
.
E.
Je
w
e
tt
,
D.
J.
Dijk
,
R
.
E.
Kr
o
n
a
u
e
r,
a
n
d
D.
F
.
Di
n
g
e
s,
“
Do
se
-
re
sp
o
n
se
re
latio
n
sh
i
p
b
e
tw
e
e
n
sle
e
p
d
u
ra
ti
o
n
a
n
d
h
u
m
a
n
p
sy
c
h
o
m
o
to
r
v
ig
il
a
n
c
e
a
n
d
su
b
jec
ti
v
e
a
lertn
e
ss
,
”
S
lee
p
,
v
o
l.
2
2
,
n
o
.
2
,
p
p
.
1
7
1
-
1
7
9
,
1
9
9
9
,
d
o
i
:
1
0
.
1
0
9
3
/slee
p
/
2
2
.
2
.
1
7
1
.
[4
]
N.
T
.
Br
P
a
sa
rib
u
,
Ra
tn
a
d
e
w
i,
A.
P
rij
o
n
o
,
R.
P
.
A
d
h
ie,
W
.
Ha
li
m
,
a
n
d
R.
M
.
He
ry
a
n
to
,
“
P
e
rf
o
rm
a
n
c
e
m
a
le
a
n
d
f
e
m
a
le
d
riv
e
rs
in
d
ro
w
sin
e
ss
sy
ste
m
b
a
se
d
o
n
p
sy
c
h
o
m
o
to
r
v
ig
il
a
n
c
e
tas
k
tes
t,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
,
v
o
l.
7
,
n
o
.
2
.
1
3
,
p
p
.
4
2
1
-
4
2
4
,
2
0
1
8
,
d
o
i:
1
0
.
1
4
4
1
9
/i
jet.
v
7
i2
.
1
3
.
1
6
9
3
7
[5
]
S
.
M
e
h
ta,
S
.
Da
d
h
ic
h
,
S
.
G
u
m
b
e
r,
a
n
d
A
.
J
.
Bh
a
tt
,
“
Re
a
l
-
T
i
m
e
Driv
e
r
Dro
w
sin
e
ss
De
tec
ti
o
n
S
y
ste
m
Us
in
g
E
y
e
A
sp
e
c
t
R
a
ti
o
a
n
d
Ey
e
Clo
su
re
Ra
ti
o
,
”
Pro
c
e
e
d
in
g
s
o
f
in
ter
n
a
ti
o
n
a
l
c
o
n
fer
e
n
c
e
o
n
s
u
sta
i
n
a
b
le
c
o
mp
u
ti
n
g
i
n
sc
ien
c
e
,
tec
h
n
o
lo
g
y
a
n
d
ma
n
a
g
e
me
n
t
(
S
US
COM
),
Amit
y
Un
ive
rs
it
y
Ra
ja
st
h
a
n
,
J
a
i
p
u
r
-
I
n
d
i
a
,
2
0
1
9
,
p
p
.
1
3
3
3
-
1
3
3
9
,
d
o
i:
1
0
.
2
1
3
9
/ssrn
.
3
3
5
6
4
0
1
.
[6
]
N.
T
.
P
a
sa
rib
u
,
Ra
tn
a
d
e
w
i,
A
.
P
ri
jo
n
o
,
R.
P
.
A
d
h
ie
,
“
Dro
w
sin
e
ss
d
e
tec
ti
o
n
sy
ste
m
d
e
sig
n
b
a
se
d
o
n
i
n
d
iv
id
u
a
l
d
riv
e
r,
”
AIP
Co
n
fer
e
n
c
e
Pro
c
e
e
d
i
n
g
s
,
v
o
l
.
2
0
9
7
,
n
o
.
1
,
2
0
1
9
,
A
rt.
n
o
.
0
3
0
1
0
4
,
d
o
i:
1
0
.
1
0
6
3
/
1
.
5
0
9
8
2
7
9
.
[7
]
T
.
V
e
ss
e
len
y
i,
S
.
M
o
c
a
,
A
.
Ru
s,
T
.
M
it
ra
n
,
a
n
d
M
.
B.
T
ǎ
taru
,
“
Driv
e
r
d
ro
w
sin
e
ss
d
e
tec
ti
o
n
u
sin
g
A
N
N
ima
g
e
p
ro
c
e
ss
in
g
,
”
IOP
Co
n
fer
e
n
c
e
S
e
rie
s
M
a
ter
ia
ls
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
v
o
l.
2
5
2
,
n
o
.
1
,
2
0
1
7
,
A
rt.
n
o
.
0
1
2
0
9
7
,
d
o
i:
1
0
.
1
0
8
8
/1
7
5
7
-
8
9
9
X
/
2
5
2
/
1
/0
1
2
0
9
7
.
[8
]
M
.
Og
in
o
a
n
d
Y.
M
it
s
u
k
u
ra
,
“
P
o
rtab
le
d
r
o
w
sin
e
ss
d
e
tec
ti
o
n
th
r
o
u
g
h
u
se
o
f
a
p
re
f
ro
n
tal
sin
g
le
-
c
h
a
n
n
e
l
e
lec
tro
e
n
c
e
p
h
a
lo
g
ra
m
,
”
S
e
n
so
rs
,
v
o
l.
1
8
,
n
o
.
1
2
,
p
p
.
1
-
1
9
,
2
0
1
8
,
A
rt.
n
o
.
4
4
7
7
,
d
o
i:
1
0
.
3
3
9
0
/s1
8
1
2
4
4
7
7
.
[9
]
N.
G
u
ru
d
a
th
a
n
d
H.
B
.
Ril
e
y
,
“
D
ro
w
s
y
d
riv
in
g
d
e
tec
ti
o
n
b
y
EE
G
a
n
a
ly
sis
u
sin
g
W
a
v
e
let
T
ra
n
s
f
o
r
m
a
n
d
K
-
m
e
a
n
s
c
lu
ste
rin
g
,
”
Pro
c
e
d
ia
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
3
4
,
p
p
.
4
0
0
-
4
0
9
,
2
0
1
4
,
d
o
i:
1
0
.
1
0
1
6
/j
.
p
ro
c
s.
2
0
1
4
.
0
7
.
0
4
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
E
E
G
s
ig
n
a
l c
la
s
s
ifica
tio
n
fo
r
d
r
o
w
s
in
ess
d
etec
tio
n
u
s
in
g
w
a
ve
let
tr
a
n
s
fo
r
m…
(
N
o
vie
Th
er
esia
B
r
.
P
a
s
a
r
ib
u
)
509
[1
0
]
M
.
A
wa
is,
N.
Ba
d
ru
d
d
i
n
,
a
n
d
M
.
Drie
b
e
rg
,
“
Driv
e
r
d
ro
w
sin
e
ss
d
e
t
e
c
ti
o
n
u
sin
g
EE
G
p
o
w
e
r
sp
e
c
t
ru
m
a
n
a
l
y
sis,”
2
0
1
4
IE
EE
Reg
io
n
1
0
S
y
mp
o
si
u
m
,
2
0
1
4
,
p
p
.
2
4
4
-
2
4
7
,
d
o
i:
1
0
.
1
1
0
9
/t
e
n
c
o
n
s
p
rin
g
.
2
0
1
4
.
6
8
6
3
0
3
5
.
[1
1
]
M
.
A
wa
is,
N.
Ba
d
ru
d
d
i
n
,
a
n
d
M
.
Drie
b
e
rg
,
“
A
h
y
b
rid
a
p
p
ro
a
c
h
to
d
e
tec
t
d
riv
e
r
d
r
o
w
sin
e
ss
u
ti
li
z
in
g
p
h
y
sio
lo
g
ica
l
sig
n
a
l
s to
im
p
ro
v
e
s
y
ste
m
p
e
r
f
o
r
m
a
n
c
e
a
n
d
W
e
a
ra
b
il
it
y
,
”
S
e
n
so
rs
,
v
o
l.
1
7
,
n
o
.
9
,
p
p
.
1
-
1
6
,
2
0
1
7
,
A
rt.
n
o
.
1
9
9
1
,
d
o
i
:
1
0
.
3
3
9
0
/s
1
7
0
9
1
9
9
1
.
[1
2
]
G
.
L
i
a
n
d
W
.
Y.
Ch
u
n
g
,
“
A
c
o
n
t
e
x
t
-
a
w
a
r
e
EE
G
h
e
a
d
se
t
s
y
ste
m
fo
r
e
a
rly
d
e
tec
ti
o
n
o
f
d
riv
e
r
d
r
o
w
s
in
e
ss
,
”
S
e
n
so
rs
,
v
o
l.
1
5
,
n
o
.
8
,
p
p
.
2
0
8
7
3
-
2
0
8
9
3
,
2
0
1
5
,
d
o
i:
1
0
.
3
3
9
0
/s1
5
0
8
2
0
8
7
3
.
[1
3
]
T
.
H
w
a
n
g
,
M
.
Kim
,
S
.
Ho
n
g
,
a
n
d
K.
S
.
P
a
rk
,
“
Driv
e
r
d
ro
w
sin
e
ss
d
e
tec
ti
o
n
u
si
n
g
th
e
i
n
-
e
a
r
EE
G
,
”
2
0
1
6
3
8
t
h
An
n
u
a
l
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
f
th
e
IEE
E
E
n
g
i
n
e
e
rin
g
i
n
M
e
d
icin
e
a
n
d
Bi
o
lo
g
y
S
o
c
iety
(
E
M
BC)
,
2
0
1
6
,
p
p
.
4
6
4
6
-
4
6
4
9
,
d
o
i:
1
0
.
1
1
0
9
/
EM
BC.
2
0
1
6
.
7
5
9
1
7
6
3
.
[1
4
]
S
.
H.
Hw
a
n
g
,
M
.
P
a
rk
,
J.
Kim
,
Y.
Yu
n
,
a
n
d
J.
S
o
n
,
"
Driv
e
r
d
ro
w
sin
e
ss
d
e
tec
ti
o
n
u
sin
g
EE
G
f
e
a
tu
re
s,
"
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
H
u
ma
n
-
C
o
mp
u
ter
In
ter
a
c
ti
o
n
-
HCI
2
0
1
8
,
v
o
l.
8
5
2
,
2
0
1
8
,
p
p
.
3
6
7
-
3
7
4
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
9
2
2
8
5
-
0
_
4
9
.
[1
5
]
Ko
rlan
tas
,
“
k
o
rlan
tas
.
”
2
0
1
8
,
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
:
//
k
o
rlan
tas
-
i
rs
m
s.in
f
o
/g
ra
p
h
/ac
c
id
e
n
tDa
ta.
[1
6
]
J.
N.
M
in
d
o
ro
,
C.
D.
Ca
su
a
t,
A
.
S
.
A
lo
n
,
M
.
A
.
F
.
M
a
lb
o
g
,
a
n
d
J.
A
.
B.
S
u
sa
,
“
Dro
w
s
y
o
r
n
o
t?Ea
rly
d
ro
w
sin
e
ss
d
e
tec
ti
o
n
u
ti
li
z
in
g
a
rd
u
in
o
b
a
se
d
o
n
e
lec
tro
e
n
c
e
p
h
a
lo
g
ra
m
(e
e
g
)
n
e
u
ro
-
sig
n
a
l,
”
I
n
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
T
re
n
d
s
in
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
v
o
l.
9
,
n
o
.
2
,
p
p
.
2
2
2
1
-
2
2
2
6
,
2
0
2
0
,
d
o
i:
1
0
.
3
0
5
3
4
/i
jatc
se
/2
0
2
0
/2
0
0
9
2
2
0
2
0
.
[1
7
]
M
.
Ak
in
,
M
.
B.
Ku
rt,
N.
S
e
z
g
in
,
a
n
d
M
.
Ba
y
ra
m
,
“
Esti
m
a
ti
n
g
v
i
g
il
a
n
c
e
le
v
e
l
b
y
u
sin
g
EE
G
a
n
d
EM
G
si
g
n
a
ls,”
Ne
u
ra
l
Co
m
p
u
t
in
g
a
n
d
Ap
p
li
c
a
t
io
n
s
,
v
o
l.
1
7
,
n
o
.
3
,
p
p
.
2
2
7
-
2
3
6
,
2
0
0
8
,
d
o
i:
1
0
.
1
0
0
7
/s
0
0
5
2
1
-
0
0
7
-
0
1
1
7
-
7
.
[1
8
]
G
.
L
i
a
n
d
W
.
Y.
Ch
u
n
g
,
“
De
tec
ti
o
n
o
f
Driv
e
r
Dro
w
sin
e
ss
u
sin
g
W
a
v
e
let
A
n
a
l
y
sis
o
f
He
a
rt
Ra
te
V
a
riab
il
i
ty
a
n
d
a
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
Clas
sif
ie
r,
”
S
e
n
so
rs
,
v
o
l.
1
3
,
n
o
.
1
2
,
p
p
.
1
6
4
9
4
-
1
6
5
1
1
,
2
0
1
3
,
d
o
i:
1
0
.
3
3
9
0
/s
1
3
1
2
1
6
4
9
4
.
[1
9
]
Y.
Zh
a
n
g
,
B.
L
iu
,
X
.
Ji
,
a
n
d
D.
Hu
a
n
g
,
“
Clas
sif
ica
ti
o
n
o
f
EE
G
S
ig
n
a
ls
Ba
s
e
d
o
n
A
u
to
re
g
re
ss
iv
e
M
o
d
e
l
a
n
d
W
a
v
e
let
P
a
c
k
e
t
De
c
o
m
p
o
siti
o
n
,
”
Ne
u
ra
l
Pr
o
c
e
ss
in
g
L
e
tt
e
rs
,
v
o
l.
4
5
,
n
o
.
2
,
p
p
.
3
6
5
-
3
7
8
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
0
7
/s
1
1
0
6
3
-
0
1
6
-
9
5
3
0
-
1
.
[2
0
]
L
.
P
a
u
ly
a
n
d
D.
S
a
n
k
a
r,
“
De
tec
ti
o
n
o
f
d
ro
w
sin
e
ss
b
a
se
d
o
n
H
OG
f
e
a
tu
re
s
a
n
d
S
V
M
Clas
sif
ie
rs,”
2
0
1
5
I
EE
E
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Res
e
a
rc
h
in
C
o
mp
u
ta
ti
o
n
a
l
In
tell
ig
e
n
c
e
a
n
d
Co
mm
u
n
ica
ti
o
n
Ne
two
r
k
s
(
ICRCICN),
2
0
1
5
,
p
p
.
1
8
1
-
1
8
6
,
d
o
i:
1
0
.
1
1
0
9
/I
CRCICN
.
2
0
1
5
.
7
4
3
4
2
3
2
.
[2
1
]
X
.
Z
h
a
n
g
,
J
.
L
i,
Y
.
L
iu
,
Z
.
Zh
a
n
g
,
Z
.
W
a
n
g
,
D
.
L
u
o
e
t
a
l
.
,
“
De
sig
n
o
f
a
f
a
ti
g
u
e
d
e
tec
ti
o
n
sy
ste
m
f
o
r
h
ig
h
-
sp
e
e
d
train
s
b
a
se
d
o
n
d
riv
e
r
v
ig
il
a
n
c
e
u
sin
g
a
w
irele
ss
w
e
a
r
a
b
le
EE
G
,
”
S
e
n
so
rs
,
v
o
l.
1
7
,
n
o
.
3
,
2
0
1
7
,
A
rt.
n
o
.
4
8
6
,
d
o
i:
1
0
.
3
3
9
0
/s
1
7
0
3
0
4
8
6
.
[2
2
]
N.
Ka
sa
b
o
v
,
"
S
p
ri
n
g
e
r
h
a
n
d
b
o
o
k
o
f
b
i
o
-
/n
e
u
ro
i
n
f
o
rm
a
ti
c
s,"
Ber
li
n
,
He
id
e
lb
e
rg
:
S
p
rin
g
e
r
Ber
li
n
He
id
e
lb
e
rg
,
2
0
1
4
,
d
o
i:
1
0
.
1
0
0
7
/9
7
8
-
3
-
6
4
2
-
3
0
5
7
4
-
0
.
[2
3
]
R.
P
o
li
k
a
r,
“
T
h
e
W
a
v
e
l
e
t
T
u
to
rial,
”
2
0
0
6
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
:
:/
/u
se
rs.r
o
w
a
n
.
e
d
u
/~
p
o
li
k
a
r/
WA
V
EL
ET
S
/
WT
tu
to
rial.
h
tm
l.
[2
4
]
K.
P
.
S
o
m
a
n
,
N.
G
.
Re
s
m
i,
a
n
d
K.
I.
Ra
m
a
c
h
a
n
d
ra
n
,
“
In
sig
h
t
I
n
to
W
a
v
e
lets:
F
ro
m
T
h
e
o
r
y
to
P
ra
c
ti
c
e
,
”
PHI
L
e
a
rn
in
g
Pvt
.
L
t
d
.
,
2
0
1
0
.
[2
5
]
C.
Co
rtes
a
n
d
V
.
V
a
p
n
ik
,
“
S
u
p
p
o
rt
-
v
e
c
to
r
n
e
tw
o
rk
s,”
M
a
c
h
in
e
L
a
n
g
u
a
g
e
,
v
o
l.
2
0
,
n
o
.
3
,
p
p
.
2
7
3
-
2
9
7
,
1
9
9
5
,
d
o
i:
1
0
.
1
0
0
7
/B
F
0
0
9
9
4
0
1
8
.
[2
6
]
M
.
N.
M
u
r
ty
a
n
d
R.
Ra
g
h
a
v
a
,
"
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
s
a
n
d
P
e
rc
e
p
tro
n
s,"
S
p
ri
n
g
e
r
In
ter
n
a
ti
o
n
a
l
P
u
b
l
ish
i
n
g
,
20
1
6
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
4
1
0
6
3
-
0
.
[2
7
]
A
.
S
tatn
ik
o
v
,
C.
F
.
A
li
f
e
ris,
D.
P
.
Ha
rd
in
,
a
n
d
I.
G
u
y
o
n
,
"
A
G
e
n
tl
e
In
tr
o
d
u
c
ti
o
n
to
S
u
p
p
o
r
t
V
e
c
to
r
M
a
c
h
in
e
s
i
n
Bio
m
e
d
icin
e
,
"
W
o
rld
S
c
ien
ti
f
ic
,
2
0
1
1
,
d
o
i:
10
.
1
1
4
2
/7
9
2
2
[2
8
]
F
.
E.
-
Z.
F
o
u
a
d
,
F
.
El
-
Za
h
ra
a
M
o
h
a
m
m
a
e
d
,
“
Us
in
g
E
m
o
ti
v
E
P
OC
Ne
u
r
o
h
e
a
d
se
t
T
o
A
c
q
u
ire
Da
ta
In
Bra
in
-
Co
m
p
u
ter In
terf
a
c
e
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Res
e
a
rc
h
,
v
o
l.
3
,
n
o
.
1
1
,
p
p
.
1
0
1
2
-
1
0
1
7
,
2
0
1
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.