I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Ro
bo
t
ics a
nd
Aut
o
m
a
t
io
n
(
I
J
RA)
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
,
p
p
.
1
90
~
1
99
I
SS
N:
2722
-
2
5
8
6
,
DOI
:
1
0
.
1
1
5
9
1
/i
jr
a
.
v
1
5
i
1
.
pp
1
90
-
1
99
190
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
a
.
ia
esco
r
e.
co
m
Em
o
tion recog
nit
io
n and
clas
sifica
t
io
n using
Incept
io
n
Efficien
tNe
t
ba
se
d on
elec
troencep
ha
lo
g
ra
phy
sig
na
l
s
J
a
na
nee
J
1
,
E
m
er
s
o
n So
lo
mo
n F
1
,
Su
nd
a
r
Ra
j
M
2
1
D
e
p
a
r
t
me
n
t
o
f
B
i
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
B
h
a
r
a
t
h
I
n
st
i
t
u
t
e
o
f
H
i
g
h
e
r
E
d
u
c
a
t
i
o
n
a
n
d
R
e
s
e
a
r
c
h
,
C
h
e
n
n
a
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
B
i
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
P
P
G
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
C
o
i
mb
a
t
o
r
e
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
2
3
,
2
0
2
5
R
ev
is
ed
Dec
2
7
,
2
0
2
5
Acc
ep
ted
Feb
0
9
,
2
0
2
6
Em
o
t
i
o
n
s
a
re
i
n
tr
ica
t
e
p
s
y
c
h
o
l
o
g
i
c
a
l
p
h
e
n
o
m
e
n
a
a
r
is
i
n
g
fr
o
m
t
h
e
i
n
t
e
ra
c
ti
o
n
o
f
i
n
te
r
n
a
l
c
o
g
n
it
i
v
e
st
a
te
s
a
n
d
e
x
t
e
r
n
a
l
e
n
v
ir
o
n
m
e
n
ta
l
i
n
p
u
t
s.
T
h
e
m
a
n
u
a
l
e
x
trac
ti
o
n
o
f
e
lec
tr
o
e
n
c
e
p
h
a
l
o
g
ra
p
h
y
(
E
EG
)
si
g
n
a
ls
re
s
u
lt
s
i
n
les
s
o
p
ti
m
a
l
p
e
r
f
o
rm
a
n
c
e
o
f
lea
r
n
i
n
g
m
o
d
e
ls
.
T
o
o
v
e
rc
o
m
e
t
h
i
s,
a
n
o
v
e
l
E
EG
-
b
a
se
d
e
m
o
ti
o
n
re
c
o
g
n
it
i
o
n
a
n
d
c
las
s
i
fica
ti
o
n
(
E
EG
-
E
M
R
E)
m
o
d
e
l
h
a
s
b
e
e
n
p
r
o
p
o
se
d
f
o
r
th
e
d
e
tec
ti
o
n
a
n
d
c
l
a
ss
i
fica
t
io
n
o
f
e
m
o
t
i
o
n
s
.
I
n
i
t
ial
l
y
,
t
h
e
i
n
p
u
t
EEG
-
S
i
g
n
a
ls
a
re
p
re
-
p
r
o
c
e
ss
e
d
u
s
i
n
g
q
u
a
n
t
u
m
s
i
g
n
a
l
p
r
o
c
e
ss
i
n
g
(Q
S
P
)
t
o
en
h
a
n
c
e
t
h
e
q
u
a
li
t
y
b
y
re
m
o
v
i
n
g
t
h
e
n
o
is
e
fr
o
m
t
h
e
s
i
g
n
a
l
.
T
h
e
e
n
h
a
n
c
e
d
si
g
n
a
l
s
a
r
e
fe
d
i
n
t
o
a
n
im
p
r
o
v
e
d
I
n
c
e
p
t
i
o
n
Ef
fic
ie
n
t
Ne
t
f
o
r
e
x
t
r
a
c
ti
n
g
t
h
e
re
le
v
a
n
t
f
e
a
t
u
re
s
.
Th
e
P
e
n
ta
t
y
p
e
s
o
f
e
m
o
ti
o
n
s
,
su
c
h
a
s
h
a
p
p
y
,
s
a
d
,
a
n
g
e
r
,
sc
a
re
d
,
a
n
d
a
n
x
iet
y
,
a
re
c
las
s
if
ie
d
u
si
n
g
a
b
i
d
irec
t
i
o
n
a
l
-
k
n
e
a
re
s
t
n
e
i
g
h
b
o
rs
(KN
N
)
c
las
si
fica
t
io
n
n
e
tw
o
r
k
.
T
h
e
p
e
r
f
o
rm
a
n
c
e
o
f
t
h
e
p
r
o
p
o
se
d
E
EG
-
E
M
R
E
a
p
p
r
o
a
c
h
is
e
v
a
l
u
a
te
d
u
s
i
n
g
t
h
e
F
1
-
S
c
o
re
,
re
c
a
l
l
,
sp
e
c
i
fic
i
t
y
,
a
c
c
u
ra
c
y
,
a
n
d
p
re
c
is
i
o
n
.
T
h
e
p
r
o
p
o
se
d
I
n
c
e
p
ti
o
n
E
ff
ic
ie
n
tN
e
t
f
o
r
fe
a
t
u
re
e
x
trac
t
i
o
n
n
e
t
wo
r
k
im
p
r
o
v
e
s
t
h
e
o
v
e
ra
l
l
a
c
c
u
ra
c
y
b
y
0
.
4
1
%
,
1
.
5
2
%
,
0
.
6
3
%
,
1
.
5
5
%
b
e
tt
e
r
t
h
a
n
Re
sN
e
t,
A
le
x
Ne
t,
G
o
o
g
leN
e
t,
a
n
d
De
n
se
Ne
t
.
T
h
e
p
r
o
p
o
se
d
E
EG
-
E
M
R
E
m
e
t
h
o
d
a
c
h
ie
v
e
s
a
n
o
v
e
ra
ll
a
c
c
u
ra
c
y
b
y
0
.
6
8
%
,
1
.
7
7
%
,
a
n
d
0
.
5
2
%
b
e
tt
e
r
t
h
a
n
th
e
l
in
e
a
r
f
o
rm
u
la
t
io
n
o
f
d
if
fe
re
n
t
ia
l
e
n
t
r
o
p
y
(L
F
-
Df
E)
,
e
x
tr
e
m
e
le
a
r
n
in
g
m
a
c
h
i
n
e
wa
v
e
le
t
a
u
t
o
e
n
c
o
d
e
r
(
EL
M
-
W
-
AE
),
a
n
d
a
t
te
n
t
io
n
-
b
a
se
d
c
o
n
v
o
l
u
ti
o
n
a
l
t
ra
n
sf
o
rm
e
r
n
e
u
r
a
l
n
e
tw
o
r
k
(A
CT
NN
)
,
re
sp
e
c
t
i
v
e
l
y
.
K
ey
w
o
r
d
s
:
B
id
ir
ec
tio
n
al
-
k
-
n
ea
r
est
n
eig
h
b
o
r
s
E
lectr
o
en
ce
p
h
al
o
g
r
a
p
h
y
s
ig
n
a
l
E
m
o
tio
n
r
ec
o
g
n
itio
n
I
n
ce
p
tio
n
E
f
f
icien
tNet
Qu
an
tu
m
s
ig
n
al
p
r
o
ce
s
s
in
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC BY
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
J
an
an
ee
J
Dep
ar
tm
en
t o
f
B
io
m
ed
ical
E
n
g
in
ee
r
in
g
,
B
h
ar
ath
I
n
s
titu
te
o
f
Hig
h
er
E
d
u
ca
tio
n
a
n
d
R
esear
ch
C
h
en
n
ai,
T
am
il Na
d
u
6
0
0
0
7
3
,
I
n
d
ia
E
m
ail: ja
n
an
ee
7
3
0
j@
o
u
tlo
o
k
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
E
m
o
tio
n
s
p
lay
a
cr
itical
r
o
le
in
h
u
m
an
d
ec
is
io
n
-
m
ak
in
g
,
in
ter
ac
tio
n
,
an
d
th
o
u
g
h
t
p
r
o
ce
s
s
es.
Au
to
m
atic
em
o
tio
n
r
ec
o
g
n
itio
n
s
y
s
tem
s
ar
e
b
ec
o
m
in
g
m
o
r
e
an
d
m
o
r
e
f
ea
s
ib
le
as
tech
n
o
lo
g
y
an
d
o
u
r
k
n
o
wled
g
e
o
f
em
o
tio
n
s
p
r
o
g
r
ess
[
1
]
.
Nu
m
e
r
o
u
s
s
tu
d
ies
u
s
e
th
e
d
is
cr
ete
em
o
tio
n
m
o
d
el
,
th
is
in
clu
d
es
jo
y
,
s
o
r
r
o
w,
s
u
r
p
r
is
e,
r
ag
e,
f
ea
r
,
an
d
d
is
g
u
s
t
[
2
]
.
T
h
e
d
y
n
am
i
c
p
r
o
ce
s
s
o
f
em
o
tio
n
r
ec
o
g
n
i
tio
n
f
o
c
u
s
es
o
n
an
in
d
iv
id
u
al'
s
em
o
tio
n
al
s
tate,
t
h
er
ef
o
r
e
th
e
f
ee
lin
g
s
th
at
co
r
r
esp
o
n
d
to
th
ei
r
b
e
h
av
io
r
s
v
a
r
y
f
r
o
m
p
er
s
o
n
to
p
er
s
o
n
[
3
]
.
Hu
m
a
n
s
g
e
n
er
ally
u
s
e
a
v
ar
iety
o
f
m
et
h
o
d
s
to
e
x
p
r
ess
th
eir
em
o
tio
n
s
.
I
t
is
im
p
o
r
tan
t
to
i
n
ter
p
r
et
em
o
tio
n
s
ac
cu
r
ately
in
o
r
d
er
t
o
en
s
u
r
e
m
ea
n
in
g
f
u
l
c
o
m
m
u
n
icatio
n
[
4
]
.
I
t
is
im
p
o
r
tan
t
to
r
ec
o
g
n
ize
em
o
tio
n
s
in
o
u
r
e
v
er
y
d
ay
liv
es b
ec
au
s
e
th
ey
in
f
lu
e
n
ce
s
o
cial
co
n
tact
a
n
d
h
u
m
an
d
ec
is
io
n
-
m
ak
in
g
.
Peo
p
le
co
m
m
u
n
icate
th
eir
em
o
tio
n
s
in
a
v
ar
iety
o
f
way
s
,
s
u
ch
as
th
r
o
u
g
h
b
o
d
y
la
n
g
u
ag
e
,
f
ac
ial
e
x
p
r
ess
io
n
s
,
an
d
ex
p
r
ess
iv
e
s
p
ee
ch
[
5
]
.
T
h
e
em
o
tio
n
al
s
tate
o
f
a
s
u
b
ject
ca
n
also
b
e
p
r
ed
icted
b
y
u
s
in
g
s
ig
n
als
f
r
o
m
m
u
ltip
le
m
o
d
alities
[
6
]
.
I
t
is
im
p
o
s
s
ib
le
to
d
eter
m
in
e
s
o
m
e
o
n
e'
s
em
o
tio
n
al
s
tate
b
ased
o
n
ly
o
n
wh
at
is
in
f
r
o
n
t
o
f
o
u
r
e
y
es.
T
h
is
is
am
o
n
g
th
e
ar
g
u
m
e
n
ts
in
f
av
o
r
o
f
tr
ea
t
in
g
em
o
tio
n
al
r
ec
o
g
n
itio
n
as a
m
u
ltimo
d
al
is
s
u
e.
[
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
E
mo
tio
n
r
ec
o
g
n
itio
n
a
n
d
cla
s
s
ifica
tio
n
u
s
in
g
I
n
ce
p
tio
n
E
ffici
en
tN
et
… (
Ja
n
a
n
ee
J
)
191
E
lectr
o
en
ce
p
h
al
o
g
r
a
p
h
y
(
E
E
G)
-
b
ased
em
o
tio
n
al
an
aly
s
is
h
as
p
r
o
v
e
n
ef
f
ec
tiv
e
i
n
h
u
m
a
n
-
co
m
p
u
ter
in
ter
f
ac
e,
s
ec
u
r
ity
,
an
d
m
ed
ic
al
s
cien
ce
.
E
E
G
is
a
s
u
itab
le
t
ec
h
n
iq
u
e
f
o
r
ca
p
tu
r
i
n
g
h
u
m
an
em
o
tio
n
b
ec
au
s
e
it
h
as
b
ee
n
ap
p
lied
in
a
n
u
m
b
er
o
f
s
tu
d
ies
to
u
n
d
er
s
tan
d
h
u
m
an
em
o
tio
n
[
8
]
.
T
h
e
i
d
en
tifi
ca
tio
n
o
f
em
o
tio
n
al
ch
an
g
es
f
r
o
m
E
E
G
s
ig
n
als
h
a
s
r
ec
en
tly
attr
ac
ted
th
e
atten
tio
n
o
f
r
esear
ch
e
r
s
in
th
e
f
ield
o
f
b
r
ai
n
co
m
p
u
ter
in
ter
f
ac
es
(
B
C
I
)
.
Dir
ec
t
attac
h
m
en
t
o
f
E
E
G
s
ig
n
als
to
th
e
s
ca
lp
allo
ws
f
o
r
th
e
r
ea
d
in
g
o
f
ch
an
g
es
in
b
r
ain
ac
tiv
ity
at
th
e
co
m
m
en
ce
m
e
n
t
o
f
em
o
tio
n
al
s
tate
ch
a
n
g
es,
p
r
o
v
id
in
g
m
o
r
e
ac
cu
r
ate
in
f
o
r
m
atio
n
[
9
]
,
[
1
0
]
.
E
E
G
d
ata
em
o
tio
n
ass
ess
m
en
t
r
elies
o
n
a
v
ar
iety
o
f
f
ac
to
r
s
,
in
clu
d
in
g
f
r
eq
u
en
cy
b
a
n
d
s
,
n
u
m
b
er
o
f
c
h
an
n
els,
s
tatis
t
ical
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
s
,
an
d
ch
a
r
ac
ter
is
tics
[
1
1
]
,
[
1
2
]
.
Ho
wev
er
,
th
e
e
x
is
tin
g
E
E
G
-
b
ased
em
o
tio
n
r
ec
o
g
n
itio
n
h
as
ac
h
i
ev
ed
g
o
o
d
ac
cu
r
ac
y
,
th
ey
s
till
s
u
f
f
er
f
r
o
m
n
o
is
e
s
en
s
itiv
ity
,
lim
ited
f
ea
tu
r
e
d
iv
er
s
ity
,
an
d
p
o
o
r
g
e
n
er
aliz
atio
n
ac
r
o
s
s
s
u
b
jects
.
Mo
s
t
co
n
v
en
tio
n
al
p
r
e
-
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
f
ail
to
ef
f
ec
tiv
ely
d
e
n
o
is
e
co
m
p
lex
E
E
G
s
ig
n
als.
Ad
d
itio
n
ally
,
d
e
ep
m
o
d
els
o
f
ten
r
eq
u
i
r
e
h
ig
h
co
m
p
u
tatio
n
al
co
s
t
an
d
lack
ad
ap
ta
b
ilit
y
to
r
ea
l
-
tim
e
em
o
tio
n
v
a
r
iatio
n
s
.
T
o
o
v
er
co
m
e
th
ese
c
h
allen
g
es,
a
n
o
v
el
E
E
G
-
E
MRE
h
a
s
b
ee
n
p
r
o
p
o
s
ed
f
o
r
d
etec
tin
g
a
n
d
class
if
icatio
n
em
o
tio
n
s
b
ased
o
n
E
E
G
s
ig
n
als.
T
h
e
m
ain
co
n
tr
ib
u
tio
n
s
o
f
th
e
p
r
o
p
o
s
ed
wo
r
k
ar
e
s
u
m
m
ar
ize
d
as:
i)
th
e
q
u
an
tu
m
s
ig
n
al
p
r
o
ce
s
s
in
g
(
QSP)
tech
n
iq
u
e
is
u
s
ed
to
p
r
e
-
p
r
o
ce
s
s
E
E
G
s
ig
n
als
f
o
r
en
ab
lin
g
q
u
a
n
tu
m
-
in
s
p
ir
ed
e
n
h
an
ce
m
en
t
a
n
d
ef
f
ec
tiv
e
r
e
m
o
v
al
o
f
ex
ter
n
al
n
o
is
e,
ii)
a
h
y
b
r
id
ar
ch
itectu
r
e
in
teg
r
ates
th
e
ab
i
lity
to
ca
p
tu
r
e
m
o
r
e
s
ca
les
co
n
cu
r
r
e
n
tly
o
f
I
n
ce
p
tio
n
m
o
d
u
les
an
d
co
m
p
o
u
n
d
s
ca
lin
g
ef
f
icien
cy
o
f
E
f
f
icien
t
Net
r
esu
ltin
g
in
th
e
r
elev
an
t
an
d
m
o
r
e
co
m
p
ac
t
E
E
G
f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
,
iii)
b
id
ir
ec
tio
n
al
-
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN)
class
if
ier
in
v
o
lv
es
a
f
o
r
war
d
an
d
b
ac
k
war
d
p
r
o
ce
s
s
in
g
o
f
f
ea
tu
r
es
d
ep
en
d
e
n
cies
to
en
h
an
ce
r
ec
o
g
n
itio
n
an
d
id
e
n
tific
atio
n
o
f
co
m
p
lex
em
o
ti
o
n
s
,
an
d
iv
)
th
is
co
m
b
in
atio
n
o
f
th
ese
th
r
ee
-
d
i
s
tin
ct
co
m
p
o
n
e
n
ts
in
a
s
in
g
le
d
ee
p
f
r
am
ew
o
r
k
th
at
r
e
d
u
ce
th
e
m
an
u
al
f
ea
tu
r
e
en
g
in
ee
r
in
g
an
d
ass
u
r
e
u
n
if
o
r
m
lear
n
in
g
ac
r
o
s
s
th
e
s
tag
es.
Ad
d
itio
n
ally
,
th
e
s
cien
tific
q
u
esti
o
n
th
at
will
g
u
id
e
th
is
s
tu
d
y
is
h
o
w
E
E
G
-
b
ased
em
o
tio
n
r
ec
o
g
n
itio
n
ca
n
b
e
im
p
r
o
v
e
d
u
s
in
g
ad
v
a
n
ce
d
s
ig
n
al
p
r
o
ce
s
s
in
g
an
d
h
y
b
r
id
d
ee
p
lear
n
i
n
g
a
r
ch
itectu
r
es.
I
n
p
ar
ticu
lar
,
it
ex
p
lo
r
es
th
r
ee
i
m
p
o
r
tan
t
asp
ec
ts
:
i)
Ho
w
ca
n
QSP
en
h
a
n
ce
E
E
G
s
ig
n
al
q
u
ality
f
o
r
ac
c
u
r
ate
em
o
tio
n
d
etec
tio
n
?
ii)
C
an
a
h
y
b
r
id
I
n
ce
p
tio
n
–
E
f
f
icien
tNet
ar
ch
itectu
r
e
ef
f
ec
ti
v
ely
ex
tr
a
ct
m
u
lti
-
s
ca
le
E
E
G
f
ea
tu
r
es
f
o
r
e
m
o
tio
n
class
if
icatio
n
?
iii)
Do
es
th
e
b
id
ir
ec
tio
n
al
-
KNN
class
if
ier
i
m
p
r
o
v
e
r
ec
o
g
n
itio
n
p
er
f
o
r
m
an
ce
co
m
p
ar
e
d
to
co
n
v
en
tio
n
al
E
E
G
-
b
ased
em
o
tio
n
r
ec
o
g
n
itio
n
m
o
d
els?
Ma
n
y
s
tu
d
ies
h
av
e
b
ee
n
c
o
n
d
u
cted
i
n
r
ec
en
t
y
ea
r
s
to
a
p
p
ly
m
ac
h
in
e
lear
n
i
n
g
(
ML
)
an
d
d
ee
p
lear
n
in
g
(
DL
)
ap
p
r
o
ac
h
es
f
o
r
class
if
y
in
g
d
if
f
er
en
t
e
m
o
tio
n
a
l
ty
p
es
in
E
E
G
d
ata.
T
h
ese
a
p
p
r
o
ac
h
es
f
o
cu
s
o
n
au
to
m
atica
lly
lear
n
in
g
d
is
cr
im
in
ativ
e
tem
p
o
r
al
an
d
s
p
atial
p
atter
n
s
f
r
o
m
E
E
G
s
ig
n
als
to
im
p
r
o
v
e
r
ec
o
g
n
itio
n
p
er
f
o
r
m
an
ce
.
T
h
is
co
m
p
r
e
h
en
s
iv
e
o
v
er
v
iew
o
f
s
ev
er
al
r
ec
e
n
t
in
v
esti
g
atio
n
s
h
ig
h
lig
h
ts
th
e
ev
o
lu
tio
n
o
f
ML
an
d
DL
m
o
d
els
f
o
r
E
E
G
-
b
as
ed
em
o
tio
n
class
if
icatio
n
.
Yin
et
a
l.
[
1
3
]
s
u
g
g
ested
a
cu
tt
in
g
-
ed
g
e
DL
m
o
d
el
(
E
R
DL
)
as
a
r
ev
o
lu
tio
n
ar
y
tech
n
iq
u
e
f
o
r
d
etec
tin
g
em
o
tio
n
s
in
E
E
G
d
ata.
T
h
e
f
u
s
io
n
m
o
d
el
ex
tr
ac
ts
g
r
a
p
h
d
o
m
ain
in
f
o
r
m
atio
n
u
s
in
g
m
u
ltip
le
GC
NNs,
wh
ile
tem
p
o
r
al
asp
ec
ts
ar
e
e
x
tr
ac
ted
u
s
in
g
L
STM
ce
lls
th
at
m
o
n
ito
r
c
h
an
g
es
in
t
h
e
in
ter
ac
tio
n
b
etwe
en
two
c
h
an
n
els
o
v
er
tim
e.
J
o
s
h
i
an
d
G
h
o
n
g
ad
e
[
1
4
]
p
r
o
p
o
s
ed
lin
ea
r
f
o
r
m
u
latio
n
o
f
d
i
f
f
er
en
tial
e
n
tr
o
p
y
(
L
F
-
Df
E
)
f
ea
t
u
r
e
e
x
tr
ac
to
r
in
co
n
ju
n
ctio
n
with
th
e
b
id
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
B
iLST
M)
n
etwo
r
k
class
if
ier
to
id
e
n
tify
em
o
tio
n
s
in
E
E
G
r
ec
o
r
d
in
g
s
.
E
x
p
e
r
im
en
tal
f
in
d
in
g
s
f
r
o
m
th
e
p
r
o
p
o
s
ed
f
e
atu
r
e
ex
tr
ac
to
r
L
F
-
Df
E
em
p
l
o
y
in
g
th
e
B
iLST
M
n
etwo
r
k
we
r
e
s
u
p
er
io
r
t
o
th
o
s
e
f
r
o
m
p
r
e
v
io
u
s
tech
n
iq
u
es.
Ar
i
et
a
l.
[
1
5
]
p
r
o
p
o
s
ed
an
ex
tr
e
m
e
lear
n
in
g
m
ac
h
in
e
wav
elet
au
to
en
co
d
er
(
E
L
M
-
W
-
AE
)
f
o
r
E
f
f
icien
t
E
m
o
tio
n
R
ec
o
g
n
itio
n
Usi
n
g
E
E
G
R
ec
o
r
d
in
g
s
.
T
h
e
GGW
ac
tiv
atio
n
f
u
n
ctio
n
r
ec
ei
v
ed
th
e
h
ig
h
est
ass
ess
m
en
t
s
co
r
es
wh
en
th
e
E
L
M
-
W
-
AE
s
tr
u
ctu
r
e'
s
ac
co
m
p
lis
h
m
en
ts
o
f
th
e
d
if
f
er
en
t
ac
tiv
atio
n
f
u
n
ctio
n
s
wer
e
i
n
v
esti
g
ated
.
B
ag
h
er
za
d
eh
et
a
l.
[
1
6
]
s
u
g
g
ested
a
n
ew
em
o
tio
n
r
ec
o
g
n
itio
n
s
y
s
tem
u
s
in
g
m
u
ltich
an
n
el
E
E
G
s
ig
n
als
an
d
f
in
e
-
tu
n
ed
C
NNs
b
ased
o
n
ef
f
ec
tiv
e
co
n
n
ec
tio
n
.
T
h
e
R
esNet
-
5
0
wo
r
k
s
b
est
wh
en
u
s
ed
o
n
d
DT
F im
ag
es in
th
e
alp
h
a
b
an
d
e
x
p
er
im
e
n
ts
in
o
r
d
er
t
o
ca
teg
o
r
ize
th
e
f
iv
e
e
m
o
tio
n
al
s
tates.
Siam
et
a
l.
[
1
7
]
s
u
g
g
ested
a
r
ea
l
-
tim
e
tech
n
iq
u
e
t
o
im
p
l
em
en
t
em
o
tio
n
id
e
n
tific
atio
n
in
r
o
b
o
tic
v
is
io
n
ap
p
licatio
n
s
.
T
h
e
r
esu
lt
s
o
f
th
e
s
im
u
latio
n
d
em
o
n
s
tr
a
te
th
at
th
ey
o
u
tp
e
r
f
o
r
m
p
r
e
v
io
u
s
attem
p
ts
in
th
is
f
ield
,
with
a
9
7
%
ac
cu
r
ac
y
r
a
te
in
id
e
n
tify
in
g
h
u
m
an
em
o
ti
o
n
s
.
Z
h
o
u
et
a
l.
[
1
8
]
d
ev
el
o
p
ed
a
n
o
v
el
tr
an
s
f
er
lear
n
in
g
p
a
r
ad
ig
m
f
o
r
E
E
G
s
ig
n
al
-
b
ased
em
o
tio
n
id
e
n
tific
atio
n
.
Pair
wis
e
lear
n
in
g
u
s
in
g
an
ad
ap
tiv
e
p
s
eu
d
o
lab
elin
g
tech
n
iq
u
e
is
b
ased
o
n
th
e
alig
n
ed
f
ea
tu
r
e
r
ep
r
esen
ta
tio
n
s
,
wh
ich
r
ed
u
ce
th
e
i
m
p
ac
t
o
f
la
b
el
n
o
is
e
o
n
m
o
d
ellin
g
b
y
en
co
d
in
g
th
e
p
r
o
x
im
ity
c
o
n
n
ec
tio
n
s
b
etwe
en
s
am
p
les.
Go
n
g
et
a
l.
[
1
9
]
p
r
o
p
o
s
ed
a
n
o
v
el
E
E
G
-
b
ased
atten
tio
n
-
b
ased
co
n
v
o
l
u
tio
n
al
tr
an
s
f
o
r
m
e
r
n
eu
r
al
n
etwo
r
k
(
AC
T
NN)
f
o
r
em
o
tio
n
r
ec
o
g
n
itio
n
.
T
h
e
atten
tio
n
weig
h
t
d
is
tr
ib
u
tio
n
s
u
g
g
ests
th
at
th
e
g
am
m
a
b
an
d
o
f
E
E
G
s
ig
n
als
an
d
th
e
b
r
ain
'
s
p
r
ef
r
o
n
tal
an
d
later
al
tem
p
o
r
al
lo
b
es m
ay
b
e
m
o
r
e
s
tr
o
n
g
ly
lin
k
e
d
to
h
u
m
a
n
em
o
tio
n
.
Yan
et
a
l.
[
2
0
]
p
r
e
s
en
ted
th
e
X
-
GW
O
-
SVM
tech
n
iq
u
e,
th
at
im
p
r
o
v
e
s
th
e
p
o
s
s
ib
ilit
y
f
o
r
r
esear
c
h
a
n
d
ex
p
lo
itatio
n
o
f
em
o
tio
n
r
ec
o
g
n
itio
n
b
ased
o
n
a
s
in
g
le
ch
an
n
el.
T
h
e
iR
ea
lcar
e
an
d
W
E
SAD
d
atasets
h
av
e
m
ea
n
ac
cu
r
ac
y
o
f
9
3
.
3
7
%
an
d
9
5
.
9
3
%,
f
r
o
m
th
is
leav
e
-
s
in
g
le
-
s
u
b
ject
-
o
u
t
cr
o
s
s
-
v
alid
atio
n
.
Sev
er
al
d
ee
p
lear
n
in
g
tec
h
n
iq
u
es
wer
e
e
m
p
lo
y
ed
in
th
e
liter
atu
r
e
r
ev
iew
f
o
r
th
e
p
r
e
d
ictio
n
a
n
d
class
if
icatio
n
o
f
em
o
tio
n
s
.
T
h
e
h
ig
h
s
en
s
itiv
ity
o
f
E
E
G
-
b
ased
em
o
tio
n
r
ec
o
g
n
itio
n
to
p
h
y
s
io
lo
g
ical
a
b
n
o
r
m
alities
an
d
a
m
b
ien
t
n
o
is
e
af
f
ec
ts
th
e
d
ata
q
u
ality
.
T
o
a
d
d
r
ess
th
is
a
n
o
v
el
EEG
-
E
MRE
h
as b
ee
n
p
r
o
p
o
s
e
d
f
o
r
t
h
e
d
etec
tio
n
an
d
class
if
icatio
n
o
f
em
o
tio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
1
90
-
1
99
192
T
h
e
s
tr
u
ctu
r
e
o
f
th
is
d
o
cu
m
e
n
t
is
a
s
f
o
llo
ws.
T
h
e
p
r
o
p
o
s
ed
E
E
G
-
E
MRE
f
o
r
em
o
tio
n
ca
te
g
o
r
izatio
n
is
ex
p
lain
ed
in
s
ec
tio
n
2
,
an
d
s
ec
tio
n
3
p
r
esen
ts
th
e
f
i
n
d
i
n
g
s
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
.
T
h
e
co
n
cl
u
s
io
n
an
d
p
r
o
p
o
s
als f
o
r
ad
d
itio
n
al
r
esear
ch
ar
e
in
clu
d
ed
in
s
ec
tio
n
4
.
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
I
n
th
is
r
esear
ch
a
n
o
v
el
E
E
G
-
E
MRE
h
as
b
ee
n
p
r
o
p
o
s
ed
f
o
r
th
e
d
etec
tio
n
a
n
d
class
if
icatio
n
o
f
em
o
tio
n
s
.
I
n
itially
th
e
g
ath
e
r
ed
E
E
G
s
ig
n
als
d
ata
ar
e
p
r
e
-
p
r
o
ce
s
s
ed
u
s
in
g
QSP
to
r
e
m
o
v
e
th
e
n
o
is
e
an
d
en
h
an
ce
th
e
q
u
ality
o
f
t
h
e
s
ig
n
al.
T
h
en
th
e
I
n
ce
p
tio
n
E
f
f
ici
en
tNet
is
u
s
ed
to
ex
tr
ac
t
t
h
e
r
e
lev
an
t
f
ea
tu
r
es
f
r
o
m
n
o
is
e
f
r
ee
en
h
a
n
ce
d
s
ig
n
als.
T
h
e
Pen
ta
ty
p
es
o
f
em
o
tio
n
s
s
u
ch
as
h
ap
p
y
,
s
ad
,
a
n
g
er
,
s
c
ar
ed
an
d
a
n
x
iety
ar
e
class
if
ied
u
s
in
g
b
id
ir
ec
tio
n
al
-
KNN
class
if
ier
.
Fig
u
r
e
1
illu
s
tr
ates
th
e
p
r
o
p
o
s
ed
E
E
G
-
E
MRE
m
eth
o
d
.
Fig
u
r
e
1
.
Pro
p
o
s
ed
E
E
G
-
E
MRE
m
eth
o
d
2
.
1
.
Q
ua
ntu
m
s
ig
na
l pro
ce
s
s
ing
T
h
e
QSP
to
o
lb
o
x
ca
n
b
e
u
s
ed
to
d
esig
n
q
u
an
t
u
m
alg
o
r
ith
m
s
with
asy
m
p
to
tically
o
p
tim
al
co
s
ts
.
T
h
e
f
o
r
m
u
latio
n
o
f
q
u
an
tu
m
s
ig
n
a
l
p
r
o
ce
s
s
in
g
is
o
f
te
n
d
o
n
e
ac
c
o
r
d
in
g
to
two
co
n
v
en
tio
n
s
.
T
h
e
f
ir
s
t
o
n
e
in
v
o
l
v
es
th
e
ex
p
r
ess
io
n
o
f
t
h
e
s
ig
n
al
o
p
er
ato
r
in
th
e
b
asis
an
d
th
e
s
ig
n
al
p
r
o
ce
s
s
in
g
in
th
e
b
asis
.
T
h
e
s
ec
o
n
d
o
n
e
in
v
o
lv
es
th
e
e
x
p
r
ess
io
n
o
f
th
e
s
ig
n
al
o
p
er
ato
r
in
th
e
b
asis
an
d
th
e
s
ig
n
al
p
r
o
ce
s
s
in
g
in
th
e
b
asis
.
T
h
e
s
ig
n
al
o
p
er
ato
r
in
th
e
b
asis
is
d
efin
ed
as:
=
[
0
0
−
]
(
1
)
A
Had
am
ar
d
g
ate
a
p
p
lied
to
b
o
th
s
id
es
o
f
th
e
An
cilla
Qu
b
it
allo
ws
th
e
ex
p
r
ess
io
n
o
f
th
e
s
ig
n
al
o
p
er
ato
r
o
n
th
e
b
asis
.
=
[
c
os
(
)
s
in
(
)
s
in
(
)
c
os
(
)
]
(
2
)
I
t
d
em
o
n
s
tr
ates
th
at
b
o
th
o
f
th
ese
f
o
r
m
alis
m
s
ar
e
n
ea
r
ly
th
e
s
am
e
at
a
h
ig
h
lev
el,
ev
en
t
h
o
u
g
h
th
e
s
h
ap
es
o
f
th
e
p
o
l
y
n
o
m
ials
th
at
ca
n
b
e
co
n
s
tr
u
cte
d
in
b
o
t
h
b
ases
d
if
f
e
r
.
I
n
th
e
f
o
r
m
alis
m
,
th
e
QSP
f
in
d
in
g
s
ar
e
f
r
eq
u
en
tly
ex
p
r
es
s
ed
as (
3
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
E
mo
tio
n
r
ec
o
g
n
itio
n
a
n
d
cla
s
s
ifica
tio
n
u
s
in
g
I
n
ce
p
tio
n
E
ffici
en
tN
et
… (
Ja
n
a
n
ee
J
)
193
[
(
(
)
)
−
(
(
)
)
s
in
(
)
(
(
)
)
s
in
(
)
(
c
os
(
)
)
]
=
(
∏
=
1
(
)
)
(
0
)
(
3
)
I
m
p
lem
en
tin
g
Had
a
m
ar
d
to
An
cilla
p
r
io
r
to
an
d
f
o
llo
win
g
th
e
QSP
s
eq
u
en
ce
ca
n
g
et
ar
o
u
n
d
th
is
r
estrictio
n
an
d
b
asically
tu
r
n
i
t
in
to
th
e
f
o
r
m
alis
m
.
T
h
is
illu
s
tr
ates
th
at
an
y
r
ea
l
p
o
ly
n
o
m
i
al
with
p
ar
ity
d
m
o
d
2
ca
n
b
e
im
p
lem
en
ted
i
n
s
u
ch
a
way
t
h
at
de
g
(
)
≤
an
d
(
4
)
.
(
)
−
(
)
†
(
)
(
)
†
=
(
∏
(
)
=
1
)
(
0
)
(
4
)
T
h
e
n
u
m
b
er
o
f
th
e
c
o
n
s
tr
ain
ts
m
en
tio
n
ed
ab
o
v
e
ar
e
less
en
ed
b
y
th
e
f
o
r
m
alis
m
m
e
n
tio
n
ed
ab
o
v
e.
B
u
t
b
ec
a
u
s
e
th
e
p
o
ly
n
o
m
ial
m
u
s
t
b
e
r
ea
l
an
d
h
av
e
d
ef
in
ite
p
ar
ity
,
f
o
u
r
d
is
tin
ct
in
s
tan
ce
s
to
p
r
o
d
u
ce
an
ar
b
itra
r
y
co
m
p
lex
p
o
ly
n
o
m
ial
with
d
ef
i
n
ite
p
ar
ity
,
th
e
li
n
ea
r
co
m
b
in
a
tio
n
o
f
u
n
itar
ies (
L
C
U)
o
f
QS
P m
u
s
t b
e
ap
p
lied
.
2
.
2
.
I
ncept
io
n E
f
f
icient
Net
I
n
th
is
s
ec
tio
n
th
e
I
n
ce
p
tio
n
E
f
f
icien
tNet
is
p
r
o
ce
s
s
ed
to
ex
tr
ac
t
th
e
f
ea
tu
r
es
f
r
o
m
th
e
n
o
is
e
f
r
ee
en
h
an
ce
d
s
ig
n
als.
T
h
e
I
n
ce
p
t
io
n
m
o
d
u
le
is
cr
u
cial
f
o
r
th
e
p
r
o
p
o
s
ed
s
ig
n
r
ec
o
g
n
itio
n
m
o
d
el,
d
esig
n
e
d
to
ca
p
tu
r
e
in
p
u
t
f
r
am
e
ch
a
r
ac
ter
i
s
tics
ac
r
o
s
s
d
if
f
er
en
t
s
ca
les
an
d
r
eso
lu
tio
n
s
.
I
t
u
tili
ze
s
co
n
v
o
lu
tio
n
al
la
y
er
s
to
ex
tr
ac
t
f
ea
tu
r
es
with
v
ar
y
in
g
f
ilter
s
izes.
MBC
o
n
v
em
p
l
o
y
s
d
ir
ec
t
co
n
n
ec
tio
n
s
am
o
n
g
b
o
ttlen
ec
k
s
th
at
in
v
o
lv
es
f
ewe
r
ch
an
n
els
d
u
e
t
o
a
co
m
p
r
ess
io
n
lay
e
r
f
o
llo
win
g
th
e
ch
an
n
el
ex
ten
s
io
n
.
T
h
is
ar
ch
itectu
r
e'
s
d
ee
p
s
ep
ar
ab
le
co
n
v
o
lu
tio
n
s
s
ig
n
if
i
ca
n
tly
r
ed
u
ce
ca
lcu
latio
n
s
b
y
a
f
ac
to
r
o
f
k
²
c
o
m
p
ar
e
d
to
s
tan
d
ar
d
lay
er
s
,
wh
e
r
e
k
r
ep
r
esen
ts
th
e
k
e
r
n
el
s
ize
o
f
th
e
2
D
c
o
n
v
o
lu
tio
n
win
d
o
w.
Ar
ch
itectu
r
e
o
f
I
n
ce
p
ti
o
n
E
f
f
icien
tNet
is
d
escr
ib
ed
in
Fig
u
r
e
2
.
Fig
u
r
e
2
.
Ar
c
h
itectu
r
e
o
f
I
n
ce
p
tio
n
E
f
f
icien
tNet
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
1
90
-
1
99
194
I
n
co
m
p
o
u
n
d
s
ca
lin
g
,
d
e
p
th
,
b
r
ea
d
th
,
a
n
d
r
eso
lu
tio
n
ar
e
all
s
ca
led
eq
u
ally
u
s
in
g
th
e
co
m
p
o
u
n
d
co
ef
f
icien
t φ
an
d
th
e
g
u
id
elin
e
s
p
r
o
v
id
ed
.
ℎ
:
=
(
5
)
ℎ
:
=
(
6
)
:
=
(
7
)
≥
1
,
≥
1
,
≥
1
(
8
)
wh
er
e
th
e
co
n
s
tan
ts
ca
n
b
e
f
o
u
n
d
th
r
o
u
g
h
g
r
i
d
s
ea
r
ch
,
.
T
h
e
n
u
m
b
er
o
f
r
eso
u
r
ce
s
av
ailab
le
i
s
m
an
ag
ed
b
y
th
e
u
s
er
-
d
ef
in
e
d
co
ef
f
icien
t
f
o
r
m
o
d
el
s
ca
lin
g
,
an
d
th
e
d
is
tr
ib
u
tio
n
o
f
th
ese
ex
tr
a
r
eso
u
r
ce
s
o
v
er
t
h
e
n
etwo
r
k
'
s
r
eso
lu
tio
n
,
d
ep
th
,
an
d
wid
th
is
d
eter
m
in
ed
b
y
,
r
esp
ec
tiv
ely
.
T
h
e
f
lo
ati
n
g
-
p
o
in
t
o
p
er
atio
n
s
(
FLOPs)
in
a
ty
p
ic
al
co
n
v
o
l
u
tio
n
o
p
er
atio
n
a
r
e
p
r
o
p
o
r
ti
o
n
al
to
,
2
,
2
.
Par
tial
ch
an
n
els
ar
e
n
o
t
alter
ed
b
y
I
n
ce
p
tio
n
Net
ar
e
id
en
tifi
ed
as
a
b
r
an
ch
o
f
id
en
tity
m
a
p
p
in
g
.
Fo
r
th
e
p
r
o
ce
s
s
in
g
ch
a
n
n
els,
I
n
ce
p
tio
n
Net
u
s
es
3
×
3
,
1
×
,
×
1
k
er
n
els
as
b
r
a
n
ch
es
to
d
ec
o
m
p
o
s
e
th
e
d
ep
th
wis
e
o
p
er
atio
n
s
in
th
e
I
n
ce
p
tio
n
s
ty
le.
I
n
p
ar
ticu
lar
,
th
ey
d
iv
id
ed
in
p
u
t
X
in
to
f
o
u
r
g
r
o
u
p
s
b
ased
o
n
th
e
ch
an
n
el
d
im
e
n
s
io
n
,
,
,
,
=
(
)
(
9
)
w
h
e
r
e
g
i
s
t
h
e
c
o
n
v
o
l
u
t
i
o
n
b
r
a
n
c
h
e
s
'
c
h
a
n
n
e
l
n
u
m
b
e
r
s
.
T
o
f
i
n
d
t
h
e
b
r
a
n
c
h
c
h
a
n
n
e
l
n
u
m
b
e
r
s
u
s
i
n
g
=
s
e
t
r
a
t
i
o
.
T
h
e
n
e
c
e
s
s
a
r
y
f
e
at
u
r
e
s
ar
e
e
x
t
r
a
c
t
e
d
w
h
e
n
t
h
e
s
p
l
it
t
i
n
g
i
n
p
u
t
s
a
r
e
g
i
v
e
n
i
n
t
o
s
e
v
e
r
a
l
p
ar
a
l
l
e
l
b
r
a
n
c
h
es
.
2
.
3
.
B
idi
re
ct
io
na
l
-
K
NN
f
o
r
cla
s
s
if
ica
t
io
n
T
h
e
KNN
s
u
p
p
lem
en
ted
t
h
e
b
en
ef
its
o
f
th
ese
tech
n
i
q
u
es
a
r
e
co
m
b
in
e
d
with
B
iLST
M
to
cr
ea
te
an
ef
f
icien
t
cy
b
er
s
ec
u
r
ity
r
eso
u
r
c
e
f
o
r
attac
k
g
r
a
p
h
co
n
s
tr
u
ctio
n
.
Ass
u
m
e
f
o
r
th
e
m
o
m
en
t
th
at
th
e
attac
k
tr
ain
in
g
s
et
=
{
(
,
)
}
=
1
ξ
is
p
r
o
v
id
ed
,
with
ℝ
b
ein
g
th
e
_
_
_
th
in
p
u
t
v
ec
to
r
wh
ile
s
e
r
v
in
g
as
th
e
o
u
t
p
u
t
v
ar
iab
le'
s
lab
el
v
ec
to
r
.
T
h
r
o
u
g
h
th
e
u
s
e
o
f
g
r
a
p
h
=
∀
(
:
)
,
wh
er
e
∀
is
th
e
tr
an
s
f
o
r
m
atio
n
f
u
n
ctio
n
,
e
ac
h
in
p
u
t v
ec
to
r
is
r
eb
u
ilt u
s
in
g
th
is
m
an
n
er
.
T
h
e
two
h
y
p
e
r
p
ar
a
m
eter
s
th
at
n
ee
d
to
b
e
ascer
tain
ed
th
e
an
d
ℵ
th
e
lear
n
in
g
p
r
o
ce
d
u
r
e
do
n
o
t
e
x
p
licitly
m
ak
e
u
s
e
o
f
th
e
d
is
tan
ce
f
u
n
ctio
n
o
r
t
h
e
n
ea
r
est
n
eig
h
b
o
r
n
u
m
b
er
s
;
r
ath
er
,
th
e
y
ar
e
ju
s
t
u
s
ed
to
r
u
n
th
e
KNN
s
ea
r
ch
'
s
tr
an
s
f
o
r
m
atio
n
f
u
n
ctio
n
∀
f
r
o
m
.
E
v
e
r
y
KNN
o
cc
u
r
r
en
ce
is
lo
o
k
ed
f
o
r
f
r
o
m
∖
{
(
,
)
}
en
tr
en
ch
e
d
o
n
th
e
d
is
tan
ce
f
u
n
ctio
n
ℵ
,
as sh
o
wn
b
y
(
1
0
)
.
℘
(
)
=
{
(
(
)
,
(
)
)
}
=
1
(
1
0
)
T
h
e
B
iLST
M
is
co
n
s
tr
u
cted
t
o
co
n
d
u
ct
g
r
ap
h
r
ep
r
esen
tatio
n
=
∀
(
:
)
f
o
r
in
p
u
t
v
ec
t
o
r
a
n
d
o
f
f
er
th
e
tr
ain
in
g
to
id
en
tify
th
e
e
q
u
iv
alen
t
la
b
el
v
e
cto
r
as
=
ℓ
(
)
=
ℓ
(
∀
(
;
)
in
o
r
d
er
t
o
d
is
co
v
er
t
h
e
KNN
r
eg
u
latio
n
f
r
o
m
th
e
attac
k
tr
ain
in
g
s
et.
W
h
en
was
f
ir
s
t
em
b
ed
d
ed
in
to
a
d
im
en
s
io
n
al
s
tar
tin
g
n
o
d
e,
a
v
ec
to
r
u
s
in
g
th
e
em
b
ed
d
ed
f
u
n
ctio
n
as
(
0
)
,
=
(
)
,
=
0
,
…
.
.
was
in
d
icate
d
.
T
h
e
u
p
d
ate
an
d
m
ess
ag
e
f
u
n
ctio
n
s
an
d
ar
e
th
e
two
p
r
im
a
r
y
f
u
n
ctio
n
s
t
h
at
ar
e
u
s
ed
to
p
er
f
o
r
m
a
m
ess
ag
e
p
ass
in
g
p
r
o
ce
d
u
r
e
to
g
r
ap
h
co
n
s
tr
u
cts.
Vec
to
r
s
(
)
,
h
av
e
th
eir
n
o
d
e
r
ep
r
esen
tatio
n
ch
an
g
e
d
as (
1
1
)
an
d
(
1
2
)
.
(
)
,
=
∑
(
,
)
(
−
1
)
,
|
ℷ
/
,
(
1
1
)
(
)
,
=
(
(
−
1
)
,
,
(
)
,
)
,
(
1
2
)
F
u
r
t
h
e
r
m
o
r
e
,
t
h
e
m
e
t
h
o
d
i
d
e
n
t
i
f
i
e
s
a
s
p
e
ci
f
i
e
d
t
as
k
K
N
N
r
u
l
e
u
n
d
e
r
t
h
e
a
t
t
a
c
k
t
r
a
i
n
i
n
g
d
a
t
a
=
{
(
,
)
}
=
1
.
T
h
e
f
o
r
w
a
r
d
h
i
d
d
e
n
s
t
a
t
es
(
H
)
a
n
d
t
h
e
b
a
c
k
w
a
r
d
h
i
d
d
e
n
s
t
at
e
s
a
r
e
c
a
l
c
u
l
at
e
d
b
y
u
s
i
n
g
t
h
e
(
1
3
)
t
o
(
1
5
)
.
⃗
=
(
⃗
+
⃗
⃗
⃗
−
1
+
⃗
)
(
1
3
)
⃖
⃗
=
(
ℎ
⃖
⃗
⃗
+
⃖
⃗
⃖
⃗
⃖
⃗
−
1
+
⃖
⃗
)
(
1
4
)
ℋ
=
⃗
+
⃖
⃗
⃗
+
(
1
5
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
E
mo
tio
n
r
ec
o
g
n
itio
n
a
n
d
cla
s
s
ifica
tio
n
u
s
in
g
I
n
ce
p
tio
n
E
ffici
en
tN
et
… (
Ja
n
a
n
ee
J
)
195
T
h
e
B
i
-
L
STM
p
r
o
ce
s
s
es
in
te
g
r
ated
attac
k
s
tag
es
⃖
⃗
d
u
r
in
g
t
r
ain
in
g
an
d
test
in
g
.
Mo
r
eo
v
e
r
,
th
e
d
ev
elo
p
ed
attac
k
g
r
ap
h
was
in
s
talled
in
th
e
lin
e
o
f
led
g
er
s
,
en
h
an
cin
g
n
etwo
r
k
s
ec
u
r
ity
b
y
m
ak
in
g
h
ac
k
er
s
u
n
ab
le
to
ac
ce
s
s
o
r
ed
it in
f
o
r
m
atio
n
.
3.
RE
SU
L
T
S
AND
D
I
SCU
SI
O
N
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
E
E
G
-
E
MRE
ap
p
r
o
ac
h
is
a
s
s
es
s
ed
in
th
is
s
ec
tio
n
u
s
in
g
a
v
ar
iety
o
f
ev
alu
atio
n
cr
iter
ia.
A
W
in
d
o
w
s
co
m
p
u
ter
with
a
n
I
n
tel
C
o
r
e
i7
C
PU
an
d
1
6
GB
o
f
R
AM
is
u
s
ed
to
b
u
ild
an
d
test
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
u
s
in
g
th
e
Py
th
o
n
p
r
o
g
r
am
m
in
g
lan
g
u
ag
e
an
d
its
lib
r
ar
ies.
T
h
e
p
r
o
p
o
s
ed
E
E
G
-
E
MRE
f
r
am
ewo
r
k
was
im
p
l
em
en
ted
an
d
ev
alu
ate
d
o
n
t
h
e
SJ
T
U
em
o
tio
n
E
E
G
d
ata
s
et
(
SEE
D)
an
d
its
p
er
f
o
r
m
an
ce
was
v
alid
ate
d
u
s
in
g
s
tan
d
ar
d
s
tatis
tical
m
etr
ics
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
s
p
ec
if
icity
,
an
d
F1
-
s
co
r
e.
C
o
m
p
ar
ativ
e
r
e
s
u
lts
ag
ain
s
t
ex
is
tin
g
m
o
d
els
d
em
o
n
s
tr
ate
th
e
s
u
p
er
io
r
ac
c
u
r
ac
y
an
d
r
o
b
u
s
tn
ess
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
,
p
r
o
v
i
d
in
g
q
u
an
titativ
e
ev
id
e
n
ce
f
o
r
its
ef
f
ec
tiv
en
ess
.
3
.
1
.
Da
t
a
s
et
des
cr
iptio
n
T
h
e
SEE
D
Data
s
et
was
g
ath
er
ed
b
y
Sh
an
g
h
ai
J
iao
T
o
n
g
Un
iv
er
s
ity
'
s
B
r
ain
an
d
C
o
g
n
itio
n
L
ab
o
r
ato
r
y
f
o
r
th
e
p
u
r
p
o
s
e
o
f
class
if
y
in
g
em
o
tio
n
s
u
s
in
g
E
E
G
s
ig
n
als.
I
t
in
clu
d
es
1
5
s
u
b
je
cts
'
E
E
G
d
ata
af
ter
th
ey
v
iewe
d
1
5
ca
r
ef
u
lly
ch
o
s
en
m
o
v
ie
s
eg
m
e
n
ts
m
ea
n
t
to
ev
o
k
e
th
r
ee
d
if
f
er
e
n
t
em
o
tio
n
al
s
tates:
p
o
s
itiv
e,
n
eu
tr
al,
a
n
d
n
eg
ativ
e.
A
6
2
-
c
h
an
n
el
E
E
G
d
ev
ice
was
u
s
ed
to
r
ec
o
r
d
d
ata
,
wh
ich
was
th
e
n
d
o
w
n
s
am
p
led
to
2
0
0
Hz
f
r
o
m
th
e
in
itial
1
0
0
0
Hz
s
am
p
lin
g
r
ate.
T
h
e
d
ataset
co
n
s
is
t
s
o
f
p
r
ep
r
o
ce
s
s
ed
E
E
G
s
ig
n
als
wi
th
d
if
f
er
en
tial
en
t
r
o
p
y
(
DE
)
ch
ar
ac
ter
is
tics
th
at
ar
e
f
r
eq
u
en
tly
em
p
lo
y
ed
in
task
s
in
v
o
lv
in
g
th
e
class
if
icatio
n
o
f
em
o
tio
n
s
.
SEE
D
h
as b
ee
n
wid
ely
u
s
ed
f
o
r
af
f
ec
tiv
e
c
o
m
p
u
tin
g
an
d
d
ee
p
lear
n
in
g
-
b
ased
e
m
o
tio
n
r
ec
o
g
n
itio
n
.
3
.
2
.
P
er
f
o
r
m
a
nce
a
na
ly
s
is
T
h
e
ef
f
ec
tiv
e
n
ess
o
f
th
e
class
if
icatio
n
tech
n
iq
u
e
is
ev
alu
a
ted
u
s
in
g
s
tatis
tical
m
etr
ics:
F1
s
co
r
e,
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
s
p
ec
if
icity
.
=
+
+
−
+
+
−
+
+
+
−
(
1
6
)
=
+
+
+
+
(
1
7
)
=
+
+
+
−
(
1
8
)
=
−
−
+
+
(
1
9
)
1
−
=
2
(
∗
)
(
+
)
(
2
0
)
wh
er
e
tr
u
e
-
p
o
s
itiv
e,
f
alse
-
p
o
s
i
tiv
e,
tr
u
e
-
n
e
g
ativ
e,
an
d
tr
u
e
-
p
o
s
itiv
e
ar
e
all
r
ep
r
esen
ted
b
y
t
h
e
s
y
m
b
o
ls
+
,
−
,
+
,
an
d
−
,
ac
co
r
d
i
n
g
to
th
ei
r
s
eq
u
en
ce
.
T
h
e
ef
f
ec
tiv
e
n
ess
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
f
o
r
em
o
tio
n
class
if
y
in
g
s
u
ch
as
h
ap
p
y
,
s
ad
,
an
g
e
r
,
s
ca
r
ed
an
d
an
x
iety
ar
e
d
em
o
n
s
tr
ated
i
n
T
ab
le
1
.
Ov
er
all
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
s
p
ec
if
icity
,
an
d
F1
-
Sco
r
e
v
alu
es
ar
e
attain
ed
b
y
th
e
s
u
g
g
ested
ap
p
r
o
ac
h
o
f
9
9
.
3
6
%,
9
7
.
1
6
%,
9
7
.
2
8
%,
9
0
.
6
8
% a
n
d
9
0
.
7
3
%,
r
esp
ec
tiv
ely
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
an
aly
s
is
o
f
p
r
o
p
o
s
ed
m
eth
o
d
C
l
a
s
ses
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
S
p
e
c
i
f
i
c
i
t
y
F1
-
S
c
o
r
e
H
a
p
p
y
9
8
.
6
5
%
9
7
.
4
1
%
9
7
.
4
5
%
9
0
.
2
8
%
9
2
.
8
5
%
S
a
d
9
8
.
9
2
%
9
5
.
7
2
%
9
5
.
8
2
%
8
9
.
7
1
%
8
8
.
6
9
%
A
n
g
e
r
9
9
.
7
8
%
9
6
.
6
4
%
9
6
.
7
3
%
9
2
.
6
5
%
9
0
.
8
7
%
S
c
a
r
e
d
9
9
.
6
3
%
9
7
.
5
2
%
9
7
.
6
8
%
8
8
.
9
2
%
8
7
.
5
3
%
A
n
x
i
e
t
y
9
9
.
8
1
%
9
8
.
5
2
%
9
8
.
7
2
%
9
1
.
8
5
%
9
3
.
6
9
%
B
ased
o
n
1
0
0
ep
o
c
h
s
an
d
a
p
r
ed
ef
in
ed
ac
cu
r
ac
y
r
an
g
e,
th
e
ac
cu
r
ac
y
c
u
r
v
e
was
s
h
o
wn
i
n
Fig
u
r
e
3
.
Mo
r
e
ep
o
ch
s
in
th
e
im
a
g
e
in
cr
ea
s
e
th
e
ac
cu
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
f
o
r
ca
teg
o
r
izin
g
h
u
m
an
em
o
tio
n
s
.
Fig
u
r
e
4
d
em
o
n
s
tr
ates
th
e
d
ec
r
ea
s
e
in
lo
s
s
as
th
e
p
r
o
p
o
s
ed
m
o
d
el
r
u
n
s
th
r
o
u
g
h
a
d
d
itio
n
al
ep
o
ch
s
.
I
t
d
is
p
lay
s
th
e
ep
o
ch
s
to
g
eth
er
with
th
e
co
r
r
esp
o
n
d
in
g
l
o
s
s
r
an
g
e.
Dif
f
er
en
t
ty
p
es
o
f
f
ac
e
em
o
tio
n
s
ar
e
class
if
ied
u
s
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
1
90
-
1
99
196
th
e
p
r
o
p
o
s
ed
m
eth
o
d
.
Fo
llo
wi
n
g
1
0
0
tr
ain
in
g
ep
o
ch
s
,
9
9
.
4
7
%
d
etec
tio
n
ac
cu
r
ac
y
an
d
a
m
in
im
al
er
r
o
r
r
ate
ar
e
d
em
o
n
s
tr
ated
b
y
th
e
p
r
o
p
o
s
ed
m
o
d
el.
Fig
u
r
e
3
.
Acc
u
r
ac
y
g
r
ap
h
o
f
t
h
e
p
r
o
p
o
s
ed
E
E
G
-
E
MRE
m
eth
o
d
Fig
u
r
e
4
.
L
o
s
s
g
r
ap
h
o
f
th
e
p
r
o
p
o
s
ed
E
E
G
-
E
MRE
m
eth
o
d
3
.
3
.
Co
m
pa
ra
t
i
v
e
a
na
ly
s
is
B
ased
o
n
s
ev
er
al
f
ea
tu
r
e
ex
t
r
ac
tio
n
n
etwo
r
k
s
th
e
p
r
o
p
o
s
ed
m
eth
o
d
h
as
b
ee
n
co
m
p
ar
ed
with
o
th
er
tr
ad
itio
n
al
n
etwo
r
k
.
T
h
e
o
u
tco
m
e
o
f
a
c
o
m
p
ar
is
o
n
o
f
f
ea
t
u
r
e
ex
tr
ac
tio
n
m
eth
o
d
s
is
d
is
p
lay
ed
in
T
ab
le
2
.
T
h
e
tab
le
co
m
p
ar
es
th
e
p
r
o
p
o
s
ed
I
n
ce
p
tio
n
E
f
f
icien
tNet
to
o
th
er
tr
ad
itio
n
al
d
ee
p
n
eu
r
al
n
etwo
r
k
s
.
T
h
e
p
r
o
p
o
s
ed
I
n
ce
p
tio
n
E
f
f
icien
tNet
is
m
o
r
e
ef
f
ec
tiv
e
th
an
a
h
ig
h
ac
cu
r
ac
y
r
ate
co
m
p
ar
ed
t
o
an
o
t
h
er
f
ea
tu
r
e
ex
tr
ac
tio
n
n
etwo
r
k
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
e
l
in
cr
ea
s
es
th
e
o
v
er
all
ac
cu
r
a
cy
b
y
0
.
4
1
%,
1
.
5
2
%,
0
.
6
3
%,
1
.
5
5
%
an
d
2
.
5
6
%
b
etter
th
an
R
esNet,
Alex
Net,
Go
o
g
leNe
t,
Den
s
eNe
t
an
d
M
o
b
ileNet,
r
esp
ec
tiv
ely
.
Acc
o
r
d
in
g
t
o
T
a
b
le
3
th
e
p
r
o
p
o
s
ed
im
p
r
o
v
es
th
e
o
v
er
al
l
ac
cu
r
ac
y
b
y
0
.
6
8
%,
1
.
7
7
%
an
d
0
.
5
2
%
b
etter
th
an
L
F
-
Df
E
,
E
L
M
-
W
-
AE
,
an
d
AC
T
NN,
r
esp
ec
tiv
ely
.
T
h
e
ac
cu
r
ac
y
o
f
th
is
m
o
d
el
is
9
9
.
3
6
%,
th
at
is
b
etter
th
an
o
th
e
r
m
o
d
els
in
p
r
o
d
u
cin
g
ac
cu
r
ate
r
esu
lts
.
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
with
an
o
th
er
n
eu
r
al
n
etwo
r
k
M
e
t
h
o
d
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
R
e
sN
e
t
[
2
1
]
9
8
.
9
5
%
9
5
.
8
5
%
9
4
.
8
5
%
A
l
e
x
N
e
t
[
2
2
]
9
7
.
8
4
%
9
6
.
5
1
%
8
9
.
8
3
%
G
o
o
g
l
e
N
e
t
[
2
3
]
9
8
.
7
3
%
9
0
.
8
3
%
9
5
.
7
3
%
D
e
n
seN
e
t
[
2
4
]
9
7
.
8
1
%
9
5
.
7
9
%
9
6
.
2
6
%
M
o
b
i
l
e
N
e
t
[
2
5
]
8
8
.
1
1
%
8
4
.
2
5
%
8
4
.
0
5
%
I
n
c
e
p
t
i
o
n
Ef
f
i
c
i
e
n
t
N
e
t
(
p
r
o
p
o
se
d
)
9
9
.
3
6
%
9
7
.
1
6
%
9
7
.
2
8
%
T
ab
le
3
.
Acc
u
r
ac
y
co
m
p
ar
is
o
n
o
f
ex
is
tin
g
tech
n
iq
u
es a
n
d
p
r
o
p
o
s
ed
tech
n
iq
u
es
A
u
t
h
o
r
Te
c
h
n
i
q
u
e
A
c
c
u
r
a
c
y
Jo
sh
i
a
n
d
G
h
o
n
g
a
d
e
[
1
4
]
LF
-
DfE
9
8
.
6
8
%
A
r
i
e
t
a
l
.
[
1
5
]
ELM
-
W
-
AE
9
7
.
5
9
%
G
o
n
g
e
t
a
l
.
[
1
9
]
A
C
TN
N
9
8
.
8
4
%
P
r
o
p
o
se
d
m
e
t
h
o
d
EEG
-
EM
R
E
9
9
.
3
6
%
3
.
4
.
Dis
cus
s
io
n
T
h
e
p
r
o
p
o
s
ed
E
E
G
-
E
MRE
f
r
am
ewo
r
k
d
em
o
n
s
tr
ated
a
s
i
g
n
if
ican
t
im
p
r
o
v
em
e
n
t
in
E
E
G
-
b
ased
em
o
tio
n
r
ec
o
g
n
itio
n
p
er
f
o
r
m
a
n
ce
th
r
o
u
g
h
th
e
in
teg
r
atio
n
o
f
QSP,
I
n
ce
p
tio
n
–
E
f
f
icien
tNet,
an
d
b
id
ir
ec
tio
n
al
-
KNN
co
m
p
o
n
en
ts
.
T
h
e
r
eliab
ilit
y
o
f
f
ea
tu
r
e
ex
tr
ac
tio
n
was
im
p
r
o
v
ed
b
y
th
e
QSP
m
o
d
u
le
b
y
r
ed
u
cin
g
th
e
n
o
is
e
an
d
p
r
eser
v
in
g
k
ey
b
r
a
in
f
ea
tu
r
es,
wh
ich
im
p
r
o
v
ed
s
ig
n
al
q
u
ality
.
T
h
e
b
id
ir
ec
tio
n
al
–
KNN
class
if
ier
im
p
r
o
v
e
d
th
e
i
d
en
tific
atio
n
o
f
in
tr
icate
em
o
tio
n
al
tr
an
s
itio
n
s
,
wh
ile
th
e
h
y
b
r
id
I
n
ce
p
tio
n
–
E
f
f
icien
tNet
m
o
d
el
ef
f
ec
tiv
ely
ex
tr
ac
ted
m
u
lti
-
s
ca
le
tem
p
o
r
al
–
s
p
atial
in
f
o
r
m
atio
n
f
r
o
m
E
E
G
s
ig
n
als.
T
h
e
r
e
s
u
ltin
g
ac
cu
r
ac
y
o
f
9
9
.
3
6
%
o
n
th
e
SEE
D
d
ataset
co
n
f
ir
m
s
t
h
e
s
u
p
e
r
io
r
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
co
m
p
ar
e
d
with
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
E
mo
tio
n
r
ec
o
g
n
itio
n
a
n
d
cla
s
s
ifica
tio
n
u
s
in
g
I
n
ce
p
tio
n
E
ffici
en
tN
et
… (
Ja
n
a
n
ee
J
)
197
co
n
v
en
tio
n
al
m
o
d
els.
Mo
r
e
o
v
er
,
th
e
p
r
o
p
o
s
ed
m
o
d
el
i
m
p
r
o
v
es
th
e
o
v
er
all
ac
c
u
r
ac
y
b
y
0
.
6
8
%,
1
.
7
7
%
an
d
0
.
5
2
% b
etter
t
h
an
L
F
-
Df
E
,
E
L
M
-
W
-
AE
,
an
d
AC
T
NN,
r
esp
ec
tiv
ely
.
T
h
e
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
p
r
o
v
id
es
a
m
o
r
e
c
o
h
esiv
e
an
d
co
m
p
r
e
h
en
s
ib
le
p
ip
elin
e
f
o
r
em
o
tio
n
class
if
icatio
n
in
co
n
t
r
ast
to
p
r
ev
io
u
s
s
tu
d
ies.
I
n
co
n
tr
ast
t
o
co
n
v
en
tio
n
al
m
o
d
els
th
at
r
ely
m
o
s
tly
o
n
m
an
u
al
f
ea
tu
r
e
e
n
g
in
ee
r
in
g
o
r
s
in
g
l
e
-
lev
el
d
ee
p
lear
n
i
n
g
f
r
am
e
wo
r
k
s
,
E
E
G
-
E
MRE
im
p
r
o
v
es
ef
f
icien
cy
a
n
d
r
esil
ien
ce
b
y
c
o
m
b
in
i
n
g
c
o
m
p
o
u
n
d
-
s
ca
led
f
ea
tu
r
e
ex
t
r
ac
tio
n
with
q
u
an
t
u
m
-
in
s
p
ir
ed
p
r
e
-
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
.
T
h
e
p
r
o
p
o
s
ed
w
o
r
k
is
s
ig
n
if
ican
t
b
ec
au
s
e
it
h
as
th
e
p
o
ten
tial
to
co
m
b
in
e
d
ee
p
lear
n
in
g
an
d
q
u
an
tu
m
s
ig
n
al
p
r
o
ce
s
s
in
g
f
o
r
em
o
tio
n
-
awa
r
e
r
o
b
o
tics
.
T
h
e
f
in
d
in
g
s
en
h
an
ce
th
e
p
r
ec
is
io
n
o
f
em
o
tio
n
r
ec
o
g
n
itio
n
an
d
s
y
s
tem
f
lex
ib
ilit
y
,
wh
ich
ad
v
an
ce
s
th
e
d
o
m
ain
s
o
f
af
f
ec
tiv
e
co
m
p
u
tin
g
an
d
h
u
m
a
n
–
r
o
b
o
t
in
ter
ac
tio
n
.
Fu
r
t
h
er
m
o
r
e,
th
es
e
r
esu
lts
ca
n
h
el
p
with
t
h
e
cr
e
atio
n
o
f
em
o
tio
n
-
r
esp
o
n
s
iv
e
a
u
to
m
atio
n
s
y
s
tem
s
,
in
tellig
en
t a
s
s
is
t
iv
e
r
o
b
o
ts
,
an
d
p
er
s
o
n
alize
d
h
ea
lth
ca
r
e
m
o
n
ito
r
in
g
.
Desp
ite
it
s
p
r
o
m
is
in
g
r
esu
lts
,
th
e
p
r
o
p
o
s
ed
E
E
G
-
E
MRE
f
r
am
ewo
r
k
h
as
lim
ited
g
en
er
aliza
b
ilit
y
ac
r
o
s
s
d
if
f
er
en
t
s
ettin
g
s
d
u
e
to
its
s
o
lely
ev
alu
atio
n
o
n
th
e
S
E
E
D
d
ataset.
T
h
e
ef
f
icac
y
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
m
ay
b
e
im
p
ac
ted
b
y
d
if
f
er
en
ce
s
in
elec
tr
o
d
e
lo
ca
tio
n
s
,
E
E
G
ac
q
u
is
itio
n
m
eth
o
d
s
,
an
d
p
er
s
o
n
al
em
o
tio
n
s
in
p
r
ac
tical
ap
p
licatio
n
s
.
Fu
tu
r
e
r
esear
ch
will
f
o
cu
s
o
n
v
alid
at
in
g
th
e
m
o
d
el
u
s
in
g
m
u
ltip
le
p
u
b
licly
a
v
ailab
le
an
d
r
ea
l
-
tim
e
E
E
G
d
atasets
to
en
h
a
n
ce
cr
o
s
s
-
s
u
b
ject
r
o
b
u
s
tn
ess
.
Ad
d
itio
n
ally
,
th
e
QSP
m
o
d
u
le
i
n
cr
ea
s
es
co
m
p
u
tatio
n
al
r
eq
u
ir
e
m
en
ts
th
at
will
b
e
r
ed
u
ce
d
b
y
o
p
tim
izin
g
it
f
o
r
lig
h
tweig
h
t
p
r
o
ce
s
s
in
g
.
Fu
r
th
er
m
o
r
e,
r
ea
l
-
tim
e
im
p
lem
en
tatio
n
o
n
wea
r
ab
le
o
r
r
o
b
o
tic
p
latf
o
r
m
s
will
b
e
ex
p
lo
r
e
d
to
e
v
alu
ate
its
ad
ap
tab
ilit
y
f
o
r
em
o
tio
n
-
awa
r
e
a
u
to
m
atio
n
an
d
h
u
m
a
n
–
r
o
b
o
t in
te
r
ac
tio
n
en
v
ir
o
n
m
e
n
ts
.
4.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
a
n
o
v
el
E
E
G
-
E
MRE
h
as
b
ee
n
p
r
o
p
o
s
ed
f
o
r
th
e
d
etec
tio
n
an
d
class
if
icatio
n
o
f
em
o
tio
n
s
.
T
h
e
E
E
G
s
ig
n
als
ar
e
p
r
e
-
p
r
o
ce
s
s
ed
u
s
in
g
QSP
to
r
em
o
v
e
th
e
n
o
is
e
f
r
o
m
th
e
s
ig
n
al.
T
h
e
p
r
o
p
o
s
ed
EEG
-
E
MRE
m
eth
o
d
u
s
es
an
im
p
r
o
v
ed
I
n
ce
p
tio
n
E
f
f
icie
n
tNet
f
o
r
ex
tr
ac
tin
g
th
e
f
ea
tu
r
es
f
r
o
m
n
o
is
e
f
r
ee
en
h
an
ce
d
s
ig
n
als.
T
h
e
B
id
ir
ec
tio
n
al
-
KNN
class
if
ica
tio
n
n
etwo
r
k
is
u
s
ed
to
class
if
y
th
e
Pen
ta
ty
p
es
o
f
em
o
tio
n
s
s
u
ch
as
h
a
p
p
y
,
s
ad
,
an
g
er
,
s
ca
r
ed
a
n
d
an
x
iety
.
T
h
e
p
r
o
p
o
s
ed
E
E
G
-
E
MRE
m
eth
o
d
'
s
p
er
f
o
r
m
a
n
ce
is
ass
es
s
ed
u
s
in
g
F1
-
Sco
r
e,
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
s
p
e
cif
icity
.
T
h
e
p
r
o
p
o
s
ed
I
n
ce
p
ti
o
n
E
f
f
icien
tNet
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
n
etwo
r
k
im
p
r
o
v
es
th
e
o
v
e
r
all
ac
cu
r
ac
y
b
y
0
.
4
1
%,
1
.
5
2
%,
0
.
6
3
%,
1
.
5
5
%,
an
d
2
.
5
6
%
b
ette
r
th
an
th
e
R
esNet,
Alex
Net,
Go
o
g
leNe
t,
Den
s
eNe
t,
an
d
Mo
b
ileNet.
T
h
e
p
r
o
p
o
s
ed
E
E
G
-
E
MRE
m
eth
o
d
ac
h
iev
es
o
v
er
all
ac
cu
r
ac
y
b
y
0
.
6
8
%,
1
.
7
7
%,
an
d
0
.
5
2
%
b
etter
th
an
L
F
-
Df
E
,
E
L
M
-
W
-
AE
,
an
d
AC
T
NN.
Fu
tu
r
e
r
esear
ch
co
u
ld
co
n
ce
n
t
r
ate
o
n
im
p
r
o
v
i
n
g
class
if
icati
o
n
ac
cu
r
ac
y
th
r
o
u
g
h
th
e
u
s
e
o
f
cu
ttin
g
-
ed
g
e
d
ee
p
lear
n
in
g
m
o
d
els an
d
q
u
a
n
tu
m
s
ig
n
al
p
r
o
ce
s
s
in
g
o
p
tim
izatio
n
f
o
r
em
o
tio
n
r
ec
o
g
n
itio
n
b
ase
d
o
n
r
ea
l
-
tim
e
E
E
G
d
ata.
Ad
d
itio
n
ally
,
th
e
p
r
o
p
o
s
ed
f
r
am
ew
o
r
k
ca
n
b
e
u
s
ed
i
n
r
o
b
o
tic
a
n
d
em
o
tio
n
-
awa
r
e
au
to
m
atio
n
s
y
s
tem
s
,
wh
er
e
r
ea
l
-
tim
e
em
o
tio
n
d
ete
ctio
n
is
ess
en
tial
f
o
r
en
h
an
cin
g
h
u
m
a
n
-
m
ac
h
in
e
co
o
p
er
atio
n
.
T
h
e
au
to
m
ate
d
o
r
r
o
b
o
tic
s
y
s
tem
s
th
at
u
s
e
s
th
e
p
r
o
p
o
s
ed
E
E
G
-
E
MRE
s
y
s
tem
ca
n
h
av
e
em
o
tio
n
-
b
ased
c
o
n
tr
o
l
s
y
s
tem
s
th
at
allo
w
th
em
t
o
m
o
d
if
y
th
eir
b
eh
av
io
r
b
ased
o
n
th
e
em
o
tio
n
al
s
tate
o
f
th
e
in
d
iv
id
u
al.
T
h
is
in
cr
ea
s
es
th
e
ap
p
licab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
b
ey
o
n
d
em
o
tio
n
cla
s
s
if
icatio
n
to
p
r
ac
tical
au
to
m
a
tio
n
an
d
in
tellig
en
t
r
o
b
o
tics
co
n
te
x
ts
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
t
h
o
r
wo
u
ld
lik
e
to
ex
p
r
ess
h
is
h
ea
r
tf
elt
g
r
atitu
d
e
t
o
th
e
s
u
p
er
v
is
o
r
f
o
r
h
is
g
u
i
d
an
ce
a
n
d
u
n
wav
er
in
g
s
u
p
p
o
r
t d
u
r
in
g
t
h
is
r
esear
ch
f
o
r
h
is
g
u
id
an
ce
an
d
s
u
p
p
o
r
t.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
No
t a
p
p
licab
le.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
J
an
an
ee
J
✓
✓
✓
E
m
er
s
o
n
So
lo
m
o
n
F
✓
✓
✓
✓
✓
Su
n
d
ar
R
aj
M
✓
✓
✓
✓
✓
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
1
90
-
1
99
198
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
t
h
o
r
s
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
k
n
o
wn
c
o
m
p
etin
g
f
in
an
cial
in
ter
ests
o
r
p
er
s
o
n
al
r
el
atio
n
s
h
ip
s
th
at
co
u
ld
h
av
e
ap
p
ea
r
ed
t
o
in
f
lu
en
ce
th
e
wo
r
k
r
e
p
o
r
te
d
in
t
h
is
p
ap
er
.
I
NF
O
RM
E
D
CO
NS
E
N
T
I
ce
r
tify
th
at
I
h
a
v
e
ex
p
lain
e
d
th
e
n
atu
r
e
an
d
p
u
r
p
o
s
e
o
f
th
i
s
s
tu
d
y
to
th
e
ab
o
v
e
-
n
am
ed
i
n
d
iv
id
u
al,
an
d
I
h
av
e
d
is
cu
s
s
ed
th
e
p
o
te
n
tial
b
en
ef
its
o
f
th
is
s
tu
d
y
p
ar
ticip
atio
n
.
T
h
e
q
u
esti
o
n
s
th
e
i
n
d
iv
id
u
al
h
ad
ab
o
u
t
th
is
s
tu
d
y
h
av
e
b
ee
n
an
s
wer
ed
,
an
d
we
will a
lway
s
b
e
av
aila
b
le
to
ad
d
r
ess
f
u
tu
r
e
q
u
esti
o
n
s
.
E
T
H
I
CAL AP
P
RO
V
AL
My
r
esear
ch
g
u
id
e
r
e
v
iewe
d
a
n
d
eth
ically
ap
p
r
o
v
ed
th
is
m
a
n
u
s
cr
ip
t f
o
r
p
u
b
lis
h
in
g
in
th
is
jo
u
r
n
al
.
DATA AV
AI
L
AB
I
L
I
T
Y
Data
s
h
ar
in
g
is
n
o
t
ap
p
licab
l
e
to
th
is
ar
ticle
as
n
o
d
atasets
wer
e
g
en
er
ated
o
r
an
aly
ze
d
d
u
r
in
g
th
e
cu
r
r
en
t stu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
S
p
e
z
i
a
l
e
t
t
i
,
G
.
P
l
a
c
i
d
i
,
a
n
d
S
.
R
o
ss
i
,
“
Em
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
f
o
r
h
u
ma
n
-
r
o
b
o
t
i
n
t
e
r
a
c
t
i
o
n
:
r
e
c
e
n
t
a
d
v
a
n
c
e
s
a
n
d
f
u
t
u
r
e
p
e
r
s
p
e
c
t
i
v
e
s
,
”
Fr
o
n
t
i
e
rs i
n
Ro
b
o
t
i
c
s
a
n
d
AI
,
v
o
l
.
7
,
p
.
5
3
2
2
7
9
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
8
9
/
f
r
o
b
t
.
2
0
2
0
.
5
3
2
2
7
9
.
[
2
]
S
.
P
a
l
,
S
.
M
u
k
h
o
p
a
d
h
y
a
y
,
a
n
d
N
.
S
u
r
y
a
d
e
v
a
r
a
,
“
D
e
v
e
l
o
p
m
e
n
t
a
n
d
p
r
o
g
r
e
ss
i
n
s
e
n
s
o
r
s
a
n
d
t
e
c
h
n
o
l
o
g
i
e
s
f
o
r
h
u
ma
n
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
1
,
n
o
.
1
6
,
p
.
5
5
5
4
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
1
1
6
5
5
5
4
.
[
3
]
A
.
B
i
n
d
h
u
e
t
a
l
.
,
“
S
k
i
n
c
a
n
c
e
r
d
i
a
g
n
o
si
s
u
si
n
g
h
i
g
h
-
p
e
r
f
o
r
ma
n
c
e
d
e
e
p
l
e
a
r
n
i
n
g
a
r
c
h
i
t
e
c
t
u
r
e
s,”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Em
e
rg
e
n
t
C
o
n
v
e
r
g
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
Bi
o
m
e
d
i
c
a
l
S
y
s
t
e
m
s
,
2
0
2
3
,
p
p
.
6
9
3
–
7
0
3
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
99
-
8
6
4
6
-
0
_
5
4
.
[
4
]
K
.
G
a
y
a
t
h
r
i
,
K
.
P
.
A
.
G
l
a
d
i
s
,
a
n
d
A
.
A
.
M
a
r
y
,
“
R
e
a
l
t
i
me
ma
sk
e
d
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
b
a
s
e
d
y
o
l
o
v
4
n
e
t
w
o
r
k
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
D
a
t
a
S
c
i
e
n
c
e
a
n
d
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
,
n
o
.
0
1
,
p
p
.
2
6
–
3
2
,
2
0
2
3
.
[
5
]
M
.
E
g
g
e
r
,
M
.
Le
y
,
a
n
d
S
.
H
a
n
k
e
,
“
Emo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
f
r
o
m
p
h
y
s
i
o
l
o
g
i
c
a
l
s
i
g
n
a
l
a
n
a
l
y
si
s
:
a
r
e
v
i
e
w
,
”
E
l
e
c
t
r
o
n
i
c
N
o
t
e
s
i
n
T
h
e
o
re
t
i
c
a
l
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
4
3
,
p
p
.
3
5
–
5
5
,
M
a
y
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
t
c
s.
2
0
1
9
.
0
4
.
0
0
9
.
[
6
]
C
.
J
.
C
l
e
m
e
n
t
s
i
n
g
h
a
n
d
S
.
S
u
m
a
t
h
i
,
“
F
a
c
e
r
e
g
e
n
e
r
a
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
b
a
s
e
d
si
f
t
-
h
o
g
a
ssi
st
e
d
g
a
n
mo
d
e
l
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
D
a
t
a
S
c
i
e
n
c
e
a
n
d
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
2
,
p
p
.
1
4
2
–
1
4
8
,
2
0
2
4
.
[
7
]
S
.
M
.
A
l
a
r
c
a
o
a
n
d
M
.
J
.
F
o
n
se
c
a
,
“
E
mo
t
i
o
n
s
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
E
EG
si
g
n
a
l
s:
a
s
u
r
v
e
y
,
”
I
EE
E
T
r
a
n
sa
c
t
i
o
n
s
o
n
A
f
f
e
c
t
i
v
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
0
,
n
o
.
3
,
p
p
.
3
7
4
–
3
9
3
,
J
u
l
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
TA
F
F
C
.
2
0
1
7
.
2
7
1
4
6
7
1
.
[
8
]
O
.
B
a
z
g
i
r
,
Z
.
M
o
h
a
mm
a
d
i
,
a
n
d
S
.
A
.
H
.
H
a
b
i
b
i
,
“
Em
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
u
s
i
n
g
E
EG
si
g
n
a
l
s,”
i
n
2
0
1
8
2
5
t
h
N
a
t
i
o
n
a
l
a
n
d
3
r
d
I
n
t
e
rn
a
t
i
o
n
a
l
I
ra
n
i
a
n
C
o
n
f
e
re
n
c
e
o
n
B
i
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
(
I
C
B
ME
)
,
I
EEE,
N
o
v
.
2
0
1
8
,
p
p
.
1
–
5
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
B
M
E.
2
0
1
8
.
8
7
0
3
5
5
9
.
[
9
]
D
.
W
.
P
r
a
b
o
w
o
,
H
.
A
.
N
u
g
r
o
h
o
,
N
.
A
.
S
e
t
i
a
w
a
n
,
a
n
d
J.
D
e
b
a
y
l
e
,
“
A
sy
s
t
e
mat
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
o
f
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
EEG
si
g
n
a
l
s,”
C
o
g
n
i
t
i
v
e
S
y
st
e
m
s R
e
s
e
a
r
c
h
,
v
o
l
.
8
2
,
p
.
1
0
1
1
5
2
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
g
s
y
s.
2
0
2
3
.
1
0
1
1
5
2
.
[
1
0
]
M
.
J
a
f
a
r
i
e
t
a
l
.
,
“
Em
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
i
n
EEG
s
i
g
n
a
l
s
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
:
a
r
e
v
i
e
w
,
”
C
o
m
p
u
t
e
rs
i
n
Bi
o
l
o
g
y
a
n
d
Me
d
i
c
i
n
e
,
v
o
l
.
1
6
5
,
p
.
1
0
7
4
5
0
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
b
i
o
me
d
.
2
0
2
3
.
1
0
7
4
5
0
.
[
1
1
]
M
.
S
o
l
e
y
m
a
n
i
,
S
.
A
s
g
h
a
r
i
-
Esf
e
d
e
n
,
M
.
P
a
n
t
i
c
,
a
n
d
Y
.
F
u
,
“
C
o
n
t
i
n
u
o
u
s
e
m
o
t
i
o
n
d
e
t
e
c
t
i
o
n
u
s
i
n
g
E
EG
si
g
n
a
l
s
a
n
d
f
a
c
i
a
l
e
x
p
r
e
ss
i
o
n
s,
”
i
n
2
0
1
4
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
M
u
l
t
i
m
e
d
i
a
a
n
d
E
x
p
o
(
I
C
M
E)
,
I
EEE,
Ju
l
.
2
0
1
4
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
M
E.
2
0
1
4
.
6
8
9
0
3
0
1
.
[
1
2
]
W
e
i
-
L
o
n
g
Zh
e
n
g
,
B
o
-
N
a
n
D
o
n
g
,
a
n
d
B
a
o
-
Li
a
n
g
L
u
,
“
M
u
l
t
i
m
o
d
a
l
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
EEG
a
n
d
e
y
e
t
r
a
c
k
i
n
g
d
a
t
a
,
”
i
n
2
0
1
4
3
6
t
h
A
n
n
u
a
l
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
f
t
h
e
I
EE
E
E
n
g
i
n
e
e
ri
n
g
i
n
M
e
d
i
c
i
n
e
a
n
d
Bi
o
l
o
g
y
S
o
c
i
e
t
y
,
I
EEE,
A
u
g
.
2
0
1
4
,
p
p
.
5
0
4
0
–
5
0
4
3
.
d
o
i
:
1
0
.
1
1
0
9
/
E
M
B
C
.
2
0
1
4
.
6
9
4
4
7
5
7
.
[
1
3
]
Y
.
Y
i
n
,
X
.
Z
h
e
n
g
,
B
.
H
u
,
Y
.
Zh
a
n
g
,
a
n
d
X
.
C
u
i
,
“
E
EG
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
f
u
s
i
o
n
m
o
d
e
l
o
f
g
r
a
p
h
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 a
n
d
LST
M
,
”
Ap
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
0
0
,
p
.
1
0
6
9
5
4
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
2
0
.
1
0
6
9
5
4
.
[
1
4
]
V
.
M
.
Jo
s
h
i
a
n
d
R
.
B
.
G
h
o
n
g
a
d
e
,
“
EEG
b
a
se
d
e
m
o
t
i
o
n
d
e
t
e
c
t
i
o
n
u
si
n
g
f
o
u
r
t
h
o
r
d
e
r
s
p
e
c
t
r
a
l
mo
me
n
t
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Bi
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pr
o
c
e
s
si
n
g
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
6
8
,
p
.
1
0
2
7
5
5
,
J
u
l
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
2
1
.
1
0
2
7
5
5
.
[
1
5
]
B
.
A
r
i
,
K
.
S
i
d
d
i
q
u
e
,
O
.
F
.
A
l
c
i
n
,
M
.
A
sl
a
n
,
A
.
S
e
n
g
u
r
,
a
n
d
R
.
M
.
M
e
h
m
o
o
d
,
“
W
a
v
e
l
e
t
EL
M
-
A
E
b
a
se
d
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
e
f
f
i
c
i
e
n
t
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
EEG
r
e
c
o
r
d
i
n
g
s,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
7
2
1
7
1
–
7
2
1
8
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
8
1
8
8
7
.
[
1
6
]
S
.
B
a
g
h
e
r
z
a
d
e
h
,
K
.
M
a
g
h
o
o
l
i
,
A
.
S
h
a
l
b
a
f
,
a
n
d
A
.
M
a
g
h
so
u
d
i
,
“
Em
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
e
f
f
e
c
t
i
v
e
c
o
n
n
e
c
t
i
v
i
t
y
a
n
d
p
r
e
-
t
r
a
i
n
e
d
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
i
n
E
EG
si
g
n
a
l
s,
”
C
o
g
n
i
t
i
v
e
N
e
u
ro
d
y
n
a
m
i
c
s
,
v
o
l
.
1
6
,
n
o
.
5
,
p
p
.
1
0
8
7
–
1
1
0
6
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
5
7
1
-
0
2
1
-
0
9
7
5
6
-
0.
[
1
7
]
A
.
I
.
S
i
a
m,
N
.
F
.
S
o
l
i
ma
n
,
A
.
D
.
A
l
g
a
r
n
i
,
F
.
E.
A
b
d
El
-
S
a
mi
e
,
a
n
d
A
.
S
e
d
i
k
,
“
D
e
p
l
o
y
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
h
u
ma
n
e
mo
t
i
o
n
d
e
t
e
c
t
i
o
n
,
”
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
a
n
d
N
e
u
r
o
sc
i
e
n
c
e
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
1
6
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
8
0
3
2
6
7
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
E
mo
tio
n
r
ec
o
g
n
itio
n
a
n
d
cla
s
s
ifica
tio
n
u
s
in
g
I
n
ce
p
tio
n
E
ffici
en
tN
et
… (
Ja
n
a
n
ee
J
)
199
[
1
8
]
R
.
Zh
o
u
e
t
a
l
.
,
“
P
R
-
P
L
:
a
n
o
v
e
l
p
r
o
t
o
t
y
p
i
c
a
l
r
e
p
r
e
s
e
n
t
a
t
i
o
n
b
a
se
d
p
a
i
r
w
i
se
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
f
o
r
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
EEG
si
g
n
a
l
s,
”
I
EEE
T
r
a
n
sa
c
t
i
o
n
s
o
n
A
f
f
e
c
t
i
v
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
5
,
n
o
.
2
,
p
p
.
6
5
7
–
6
7
0
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TA
F
F
C
.
2
0
2
3
.
3
2
8
8
1
1
8
.
[
1
9
]
L.
G
o
n
g
,
M
.
Li
,
T
.
Z
h
a
n
g
,
a
n
d
W
.
C
h
e
n
,
“
EEG
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
a
t
t
e
n
t
i
o
n
-
b
a
se
d
c
o
n
v
o
l
u
t
i
o
n
a
l
t
r
a
n
sf
o
r
m
e
r
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
Bi
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pro
c
e
ss
i
n
g
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
8
4
,
p
.
1
0
4
8
3
5
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
2
3
.
1
0
4
8
3
5
.
[
2
0
]
X
.
Y
a
n
,
Z.
L
i
n
,
Z
.
Li
n
,
a
n
d
B
.
V
u
c
e
t
i
c
,
“
A
n
o
v
e
l
e
x
p
l
o
i
t
a
t
i
v
e
a
n
d
e
x
p
l
o
r
a
t
i
v
e
G
W
O
-
S
V
M
a
l
g
o
r
i
t
h
m
f
o
r
smar
t
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
,
”
I
EEE
I
n
t
e
rn
e
t
o
f
T
h
i
n
g
s
J
o
u
rn
a
l
,
v
o
l
.
1
0
,
n
o
.
1
1
,
p
p
.
9
9
9
9
–
1
0
0
1
1
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T.
2
0
2
3
.
3
2
3
5
3
5
6
.
[
2
1
]
L.
N
.
B
.
S
i
n
g
so
n
,
M
.
T
.
U
.
R
.
S
a
n
c
h
e
z
,
a
n
d
J.
F
.
V
i
l
l
a
v
e
r
d
e
,
“
Em
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
sh
o
r
t
-
t
e
r
m
a
n
a
l
y
si
s
o
f
h
e
a
r
t
r
a
t
e
v
a
r
i
a
b
i
l
i
t
y
a
n
d
R
e
sN
e
t
a
r
c
h
i
t
e
c
t
u
r
e
,
”
i
n
2
0
2
1
1
3
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
a
n
d
Au
t
o
m
a
t
i
o
n
En
g
i
n
e
e
ri
n
g
(
I
C
C
AE)
,
I
EEE,
M
a
r
.
2
0
2
1
,
p
p
.
1
5
–
1
8
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
A
E
5
1
8
7
6
.
2
0
2
1
.
9
4
2
6
0
9
4
.
[
2
2
]
S
.
A
.
-
P
.
R
a
j
a
S
e
k
a
r
a
n
,
C
.
P
o
o
Le
e
,
a
n
d
K
.
M
.
L
i
m,
“
F
a
c
i
a
l
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
o
f
A
l
e
x
N
e
t
,
”
i
n
2
0
2
1
9
t
h
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
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
I
C
o
I
C
T
)
,
I
EEE,
A
u
g
.
2
0
2
1
,
p
p
.
1
7
0
–
1
7
4
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
o
I
C
T5
2
0
2
1
.
2
0
2
1
.
9
5
2
7
5
1
2
.
[
2
3
]
T.
R
a
m
u
a
n
d
A
.
M
u
t
h
u
k
u
m
a
r
,
“
A
G
o
o
g
l
e
N
e
t
a
r
c
h
i
t
e
c
t
u
r
e
b
a
se
d
f
a
c
i
a
l
e
mo
t
i
o
n
s
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
EEG
d
a
t
a
f
o
r
f
u
t
u
r
e
a
p
p
l
i
c
a
t
i
o
n
s,
”
i
n
2
0
2
2
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
I
n
f
o
rm
a
t
i
c
s
(
I
C
C
C
I
)
,
I
EEE,
Jan
.
2
0
2
2
,
p
p
.
1
–
7
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
C
I
5
4
3
7
9
.
2
0
2
2
.
9
7
4
0
8
6
4
.
[
2
4
]
N
.
P
u
s
a
r
l
a
,
A
.
S
i
n
g
h
,
a
n
d
S
.
Tr
i
p
a
t
h
i
,
“
Le
a
r
n
i
n
g
D
e
n
seNe
t
f
e
a
t
u
r
e
s
f
r
o
m
EEG
b
a
se
d
sp
e
c
t
r
o
g
r
a
ms
f
o
r
s
u
b
j
e
c
t
i
n
d
e
p
e
n
d
e
n
t
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
,
”
Bi
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
a
n
d
C
o
n
t
ro
l
,
v
o
l
.
7
4
,
p
.
1
0
3
4
8
5
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
2
2
.
1
0
3
4
8
5
.
[
2
5
]
Y
.
N
a
n
,
J.
Ju
,
Q
.
H
u
a
,
H
.
Z
h
a
n
g
,
a
n
d
B
.
W
a
n
g
,
“
A
-
M
o
b
i
l
e
N
e
t
:
a
n
a
p
p
r
o
a
c
h
o
f
f
a
c
i
a
l
e
x
p
r
e
ss
i
o
n
r
e
c
o
g
n
i
t
i
o
n
,
”
A
l
e
x
a
n
d
ri
a
En
g
i
n
e
e
ri
n
g
J
o
u
rn
a
l
,
v
o
l
.
6
1
,
n
o
.
6
,
p
p
.
4
4
3
5
–
4
4
4
4
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
1
.
0
9
.
0
6
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
J
a
n
a
n
e
e
J
is
wo
r
k
i
n
g
a
s
As
sista
n
t
P
r
o
fe
ss
o
r
i
n
Bi
o
m
e
d
ica
l
En
g
i
n
e
e
rin
g
De
p
a
rtme
n
t,
Ra
ji
v
G
a
n
d
h
i
I
n
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Ba
n
g
a
lo
re
,
I
n
d
ia.
S
h
e
h
a
s
c
o
m
p
lete
d
1
3
y
e
a
rs
o
f
tea
c
h
i
n
g
o
n
b
o
t
h
g
ra
d
u
a
te
a
n
d
p
o
st
g
ra
d
u
a
te
le
v
e
l.
He
r
a
r
e
a
o
f
i
n
tere
st
in
c
l
u
d
e
s
b
ra
i
n
c
o
m
p
u
ter
in
terfa
c
e
,
EE
G
,
a
rti
ficia
l
n
e
u
ra
l
n
e
two
rk
s,
re
h
a
b
il
it
a
ti
o
n
e
n
g
i
n
e
e
rin
g
,
m
a
c
h
i
n
e
lea
rn
in
g
,
a
rti
ficia
l
in
tell
ig
e
n
c
e
a
n
d
n
e
u
ro
lo
g
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
jan
a
n
e
e
7
3
0
j@o
u
tl
o
o
k
.
c
o
m
.
Em
e
r
so
n
S
o
lo
m
o
n
F
is
wo
rk
i
n
g
a
s
P
ro
fe
ss
o
r
i
n
Bi
o
m
e
d
ica
l
En
g
in
e
e
ri
n
g
De
p
a
rtme
n
t
,
Bh
a
ra
th
In
stit
u
te
o
f
Hig
h
e
r
Ed
u
c
a
ti
o
n
a
n
d
Re
se
a
rc
h
,
Ch
e
n
n
a
i
,
In
d
ia.
He
h
a
s
c
o
m
p
lete
d
3
5
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
b
o
th
tea
c
h
in
g
a
n
d
in
d
u
str
y
.
His
a
re
a
o
f
i
n
tere
st
is
tu
m
o
r
tran
sp
lan
tati
o
n
,
fl
u
o
re
sc
e
n
ts
tec
h
n
i
q
u
e
,
c
h
r
o
m
o
so
m
e
p
re
p
a
ra
ti
o
n
s,
c
e
ll
c
y
c
le
a
n
a
ly
se
s,
a
n
d
c
h
ro
m
a
to
g
ra
p
h
ic t
e
c
h
n
iq
u
e
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
e
rso
n
so
l
o
m
o
n
4
1
f0
@
o
u
tl
o
o
k
.
c
o
m
.
Su
nd
a
r
Ra
j
M
c
u
rre
n
t
ly
w
o
rk
in
g
i
n
P
P
G
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
C
o
imb
a
to
re
,
Tam
il
Na
d
u
.
P
ro
fe
ss
o
r
a
n
d
H
e
a
d
,
De
p
a
rtme
n
t
of
B
io
m
e
d
ica
l
E
n
g
i
n
e
e
rin
g
.
He
p
u
b
li
s
h
e
d
m
o
r
e
th
a
n
2
0
re
se
a
rc
h
p
a
p
e
rs
re
late
d
to
b
io
m
e
d
ica
l
e
n
g
in
e
e
rin
g
i
n
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
jo
u
r
n
a
ls.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
s
u
n
d
a
rra
j
0
5
4
m
@o
u
t
lo
o
k
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.