I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
8
,
No
.
5
,
Octo
b
e
r
2
0
1
8
,
p
p
.
4
0
0
4
~4
0
1
4
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v8
i
5
.
p
p
4
0
0
4
-
401
4
4004
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
G
a
lv
a
nic S
k
in
Re
spo
nse Da
ta Cla
ss
ificatio
n f
o
r
E
m
o
tion
Dete
ctio
n
Dj
o
k
o
B
ud
iy
a
nto
Set
y
o
ha
di
1
,
Sri K
us
ro
h
m
a
nia
h
2
,
Se
ba
s
t
ia
n
B
a
g
y
a
G
un
a
w
a
n
3
,
P
ra
no
w
o
4
,
Ant
o
n Sa
t
ria
P
ra
bu
w
o
no
5
1,
3,
4
De
p
a
rtem
e
n
t
o
f
In
f
o
r
m
a
ti
c
s E
n
g
in
e
e
rin
g
.
Un
iv
e
rsitas
A
t
m
a
J
a
y
a
Yo
g
y
a
k
a
rta,
Yo
g
y
a
k
a
rta 5
5
2
8
1
,
In
d
o
n
e
sia
2
P
sy
c
h
o
lo
g
y
De
p
a
rt
m
e
n
t,
Un
iv
e
rsitas
Ga
jah
M
a
d
a
,
Yo
g
y
a
k
a
rta,
In
d
o
n
e
sia
5
F
a
c
u
lt
y
o
f
Co
m
p
u
ti
n
g
a
n
d
In
f
o
r
m
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
Kin
g
A
b
d
u
la
z
iz Un
iv
e
rsit
y
,
Ra
b
ig
h
2
1
9
1
1
,
S
a
u
d
i
A
ra
b
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
12
,
2
0
1
8
R
ev
i
s
ed
Ma
y
2
5
,
2
0
1
8
A
cc
ep
ted
J
u
l
2
,
2
0
1
8
Em
o
ti
o
n
d
e
tec
ti
o
n
is
a
v
e
ry
e
x
h
a
u
stin
g
j
o
b
a
n
d
n
e
e
d
s
a
c
o
m
p
li
c
a
ted
p
r
o
c
e
ss
;
m
o
re
o
v
e
r,
th
e
se
p
ro
c
e
ss
e
s
a
ls
o
re
q
u
ire
th
e
p
r
o
p
e
r
d
a
ta
tra
in
in
g
a
n
d
a
p
p
ro
p
riate
a
lg
o
rit
h
m
.
T
h
e
p
ro
c
e
ss
in
v
o
lv
e
s
th
e
e
x
p
e
rim
e
n
tal
re
se
a
rc
h
in
p
sy
c
h
o
lo
g
ica
l
e
x
p
e
ri
m
e
n
t
a
n
d
c
la
ss
if
ic
a
ti
o
n
m
e
th
o
d
s.
T
h
is
p
a
p
e
r
d
e
sc
rib
e
s
a
m
e
th
o
d
o
n
d
e
tec
ti
o
n
e
m
o
ti
o
n
u
si
n
g
G
a
l
v
a
n
ic
S
k
in
Re
sp
o
n
se
(G
S
R)
d
a
ta
.
W
e
u
se
d
th
e
P
o
siti
v
e
a
n
d
Ne
g
a
ti
v
e
Aff
e
c
t
S
c
h
e
d
u
le
(
P
A
NA
S
)
met
h
o
d
to
g
e
t
a
g
o
o
d
d
a
ta
train
i
n
g
.
F
u
rth
e
rm
o
re
,
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
a
n
d
a
c
o
rr
ec
t
p
re
p
ro
c
e
ss
in
g
a
re
p
e
rf
o
r
m
e
d
to
c
las
si
fy
th
e
G
S
R
d
a
ta.
T
o
v
a
li
d
a
te
th
e
p
ro
p
o
se
d
a
p
p
r
o
a
c
h
,
Re
c
e
iv
e
r
O
p
e
ra
ti
n
g
C
h
a
ra
c
teristic
(ROC)
c
u
r
v
e
,
a
n
d
a
c
c
u
r
a
c
y
m
e
a
su
re
m
e
n
t
a
re
u
se
d
.
O
u
r
m
e
th
o
d
s
h
o
w
s
th
a
t
th
e
a
c
c
u
ra
c
y
is
a
b
o
u
t
7
5
.
6
5
%
w
h
il
e
ROC
is
a
b
o
u
t
0
.
8
0
1
9
.
I
t
m
ea
n
s
th
at
t
h
e
e
m
o
ti
o
n
d
e
tec
ti
o
n
c
a
n
b
e
d
o
n
e
sa
ti
sf
a
c
to
ril
y
a
n
d
w
e
ll
p
e
rf
o
r
m
e
d
.
K
ey
w
o
r
d
:
C
las
s
i
f
icatio
n
E
m
o
tio
n
d
etec
tio
n
E
x
p
er
i
m
e
n
tal
r
esear
ch
Galv
a
n
ic
s
k
i
n
r
esp
o
n
s
e
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Dj
o
k
o
B
u
d
iy
a
n
to
Set
y
o
h
ad
i,
Ma
g
is
ter
T
ek
n
ik
I
n
f
o
r
m
a
tik
a,
Un
i
v
er
s
ita
s
A
t
m
a
J
a
y
a
Yo
g
y
a
k
ar
ta,
J
l.
B
ab
ar
s
ar
i 4
3
Y
o
g
y
ak
ar
ta
5
5
2
8
1
,
I
n
d
o
n
esia
.
E
m
ail: d
j
o
k
o
.
b
d
y
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
C
u
r
r
en
tl
y
,
h
u
m
a
n
e
m
o
tio
n
is
an
i
m
p
o
r
tan
t
t
h
i
n
g
a
n
d
h
as
b
ec
o
m
e
a
co
n
ce
r
n
i
n
v
ar
io
u
s
f
ield
s
o
f
r
esear
ch
,
in
cl
u
d
in
g
co
m
p
u
ter
s
cien
ce
[
1
]
.
T
h
is
p
h
en
o
m
e
n
o
n
is
r
ea
l,
co
n
s
id
er
in
g
t
h
at
e
m
o
tio
n
as
a
h
u
m
an
ex
p
r
ess
io
n
i
m
p
lie
s
ac
tiv
ities
d
o
n
e
b
y
h
u
m
a
n
b
ein
g
s
a
n
d
th
eir
ex
cite
m
e
n
t
ca
n
b
e
d
etec
ted
b
ased
o
n
th
e
d
ata
m
ea
s
u
r
ed
f
r
o
m
th
e
m
:
v
o
ice,
f
ac
e,
b
o
d
y
,
an
d
p
h
y
s
io
lo
g
y
[
2
]
,
[
3
]
.
Dete
ctio
n
o
f
h
u
m
a
n
e
m
o
tio
n
is
p
o
ten
tial
to
r
en
d
er
th
e
d
e
v
elo
p
m
e
n
t
o
f
d
i
v
er
s
e
a
s
p
ec
ts
o
f
li
f
e
s
u
c
h
a
s
en
ter
tai
n
m
e
n
t,
lear
n
i
n
g
,
an
d
o
th
er
ele
m
en
t
s
[
2
]
,
[
4
]
-
[
6
]
.
T
h
e
d
etec
tio
n
is
p
ar
t
o
f
a
d
ata
m
i
n
in
g
p
r
o
ce
s
s
,
n
a
m
el
y
clas
s
if
icatio
n
,
a
n
d
clu
s
ter
in
g
.
U
n
til
to
d
a
y
,
th
er
e
h
av
e
b
ee
n
at
leas
t
t
e
n
m
ac
h
in
e
lear
n
i
n
g
al
g
o
r
ith
m
s
w
h
ic
h
ca
n
b
e
u
s
ed
f
o
r
b
o
th
class
if
ica
tio
n
a
n
d
clu
s
ter
i
n
g
[
7
]
.
T
h
e
f
o
llo
w
i
n
g
m
et
h
o
d
s
ar
e
ex
a
m
p
les
o
f
t
h
e
d
etec
tio
n
alg
o
r
ith
m
b
ased
o
n
class
i
f
icatio
n
a
n
d
clu
s
ter
i
n
g
,
w
h
ic
h
m
ea
n
s
c
lass
i
f
y
in
g
lik
e
S
u
p
p
o
r
t V
ec
to
r
Ma
ch
in
e
(
SVM)
,
Naïv
e
B
a
y
es,
K
-
Nea
r
est
Nei
g
h
b
o
r
s
(
KNN)
,
Dec
is
io
n
T
r
ee
an
d
m
an
y
o
th
er
s
.
T
h
ey
r
ep
o
r
ted
th
at
t
h
e
p
er
f
o
r
m
an
ce
o
f
clas
s
if
ica
tio
n
co
u
ld
b
e
en
h
a
n
ce
d
w
h
e
n
t
h
e
y
c
u
s
to
m
iz
e
th
e
p
ar
a
m
eter
w
it
h
in
t
h
e
al
g
o
r
ith
m
to
g
a
in
a
m
ax
i
m
u
m
r
es
u
lt [
7
]
.
SVM
is
o
n
e
o
f
t
h
e
p
o
p
u
lar
alg
o
r
ith
m
s
d
u
e
to
its
s
u
f
f
icie
n
t
ca
p
ab
ilit
y
i
n
n
o
n
li
n
ea
r
clas
s
if
ica
tio
n
,
r
eg
r
ess
io
n
an
d
o
u
tlier
d
etec
tio
n
e
v
en
b
e
f
o
r
e
th
e
alg
o
r
it
h
m
b
ec
a
m
e
p
o
p
u
lar
[
7
]
.
A
l
th
o
u
g
h
th
e
u
s
e
o
f
S
VM
i
s
m
o
r
e
s
tr
ai
g
h
tf
o
r
w
ar
d
t
h
an
o
th
er
alg
o
r
ith
m
s
,
to
o
b
tain
an
o
p
ti
m
al
r
esu
lt
,
a
n
ap
p
r
o
p
r
iate
ap
p
r
o
ac
h
is
r
eq
u
ir
ed
.
So
m
e
m
et
h
o
d
s
t
h
at
h
a
v
e
b
ee
n
co
m
m
o
n
l
y
ap
p
lied
i
n
cl
u
d
e
tr
an
s
f
o
r
m
atio
n
,
f
ea
t
u
r
e
s
ca
li
n
g
,
ch
o
o
s
i
n
g
t
h
e
r
i
g
h
t
k
er
n
el
an
d
f
i
n
d
in
g
th
e
r
ig
h
t
C
an
d
γ
[
8
]
.
SVM
w
o
r
k
s
b
y
d
ete
ctin
g
t
h
e
h
y
p
er
p
lan
e
t
h
at
h
as
t
h
e
m
o
s
t
s
i
g
n
if
ica
n
t
m
ar
g
i
n
w
h
e
n
a
d
i
m
e
n
s
io
n
is
m
o
r
e
th
a
n
t
w
o
(
2
)
,
s
o
d
ata
ca
n
b
e
e
f
f
ec
t
iv
el
y
s
ep
ar
ated
in
a
lin
ea
r
m
a
n
n
er
(
t
h
i
s
p
r
o
j
ec
tio
n
is
ca
r
r
ied
o
u
t
i
n
k
e
r
n
el
tech
n
iq
u
e)
.
T
h
er
e
ar
e
f
o
u
r
p
r
im
ar
y
k
er
n
els
in
SVM,
n
a
m
el
y
li
n
ea
r
,
r
ad
ial
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Ga
lva
n
ic
S
kin
R
esp
o
n
s
e
Da
ta
C
la
s
s
i
fica
tio
n
fo
r
E
mo
tio
n
De
tectio
n
(
Djo
ko
B
u
d
iya
n
t
o
S
ety
o
h
a
d
i)
4005
b
asis
f
u
n
ctio
n
(
R
B
F),
s
ig
m
o
i
d
,
an
d
p
o
ly
-
n
o
m
i
n
al.
A
m
o
n
g
th
e
f
o
u
r
k
er
n
els,
t
h
e
R
B
F
i
s
w
o
r
th
co
n
s
id
er
i
n
g
to
b
e
u
s
ed
d
u
e
to
its
ca
p
ab
ilit
y
i
n
s
ep
ar
atin
g
n
o
n
li
n
ea
r
d
ata
[
9
]
,
[
1
0
]
.
W
ith
th
e
ca
p
ac
it
y
,
t
h
e
u
s
e
o
f
S
VM
ca
n
b
e
e
m
p
lo
y
ed
as a
p
r
o
m
is
i
n
g
alter
n
ati
v
e
f
o
r
e
m
o
tio
n
d
etec
tio
n
.
E
m
o
tio
n
d
etec
tio
n
u
s
i
n
g
b
io
s
en
s
o
r
h
a
s
b
ec
o
m
e
p
o
p
u
lar
r
e
ce
n
tl
y
.
B
esid
es
it
s
f
r
eq
u
en
t
u
s
e
in
m
a
n
y
ap
p
licatio
n
s
,
b
io
ce
n
s
o
r
also
p
o
s
s
ess
es
th
e
b
e
s
t
p
er
f
o
r
m
a
n
ce
in
d
ir
ec
tl
y
m
ea
s
u
r
i
n
g
p
ar
am
eter
s
i
n
t
h
e
h
u
m
a
n
b
o
d
y
,
w
h
o
s
e
v
alu
e
is
in
f
l
u
en
c
ed
b
y
h
u
m
an
e
m
o
tio
n
s
ta
tu
s
.
T
h
ese
s
en
s
o
r
s
ca
n
m
ea
s
u
r
e
g
e
n
er
ated
-
s
ig
n
als
f
r
o
m
h
u
m
a
n
b
o
d
y
s
u
c
h
as
h
ea
r
t
r
ate,
b
lo
o
d
p
r
ess
u
r
e,
tem
p
er
at
u
r
e,
s
k
i
n
co
n
d
u
cta
n
ce
,
etc.
Ma
n
y
s
c
h
o
lar
s
r
ep
o
r
ted
th
at
t
h
e
v
ar
iet
y
o
f
m
ea
s
u
r
e
m
en
t
o
f
g
en
er
ated
-
s
i
g
n
a
ls
co
u
l
d
b
e
u
s
ed
as
a
f
o
u
n
d
atio
n
o
f
e
m
o
tio
n
d
etec
tio
n
.
[
1
1
]
-
[
1
4
]
,
an
d
o
n
e
o
f
th
e
f
a
v
o
r
ite
b
io
ce
n
s
o
r
n
o
w
ad
a
y
s
i
s
Gal
v
an
ic
Sk
i
n
R
esp
o
n
s
e
(
G
SR
)
.
Galv
a
n
ic
S
k
i
n
R
e
s
p
o
n
s
e
(
G
S
R
)
is
a
to
o
l
w
h
ic
h
ce
n
s
o
r
s
h
u
m
an
p
s
y
c
h
o
lo
g
ical
s
y
m
p
to
m
.
I
t
m
ea
s
u
r
es
s
ig
n
al
s
s
e
n
t
b
y
t
h
e
h
u
m
a
n
s
k
i
n
w
h
ic
h
is
co
n
s
id
er
ed
as
a
r
e
f
lectio
n
o
f
p
h
y
s
io
lo
g
ica
l
ch
a
n
g
es
[
1
5
]
,
[
1
6
]
.
T
h
e
u
s
e
o
f
G
SR
f
o
r
p
h
y
s
io
lo
g
ical
p
u
r
p
o
s
es
is
f
ir
s
tl
y
i
m
p
le
m
e
n
ted
b
y
Vi
g
o
u
r
o
u
x
.
Mo
r
eo
v
er
,
m
an
y
r
esear
ch
er
s
r
ep
o
r
ted
th
e
u
s
e
o
f
G
SR
f
o
r
p
h
y
s
io
lo
g
ical
p
h
e
n
o
m
e
n
a
[
1
5
]
,
[1
7
]
.
GSR
s
ig
n
al
in
d
icate
s
elec
tr
ical
ch
an
g
es
m
ea
s
u
r
ed
at
th
e
s
u
r
f
ac
e
o
f
t
h
e
h
u
m
a
n
s
k
i
n
th
a
t
v
ar
ie
s
w
it
h
t
h
e
ch
a
n
g
es
i
n
s
k
i
n
m
o
i
s
t
u
r
e
lev
el
(
s
w
ea
ti
n
g
)
an
d
r
ef
lects
th
e
d
if
f
er
en
ce
s
i
n
t
h
eir
s
y
m
p
at
h
etic
n
er
v
o
u
s
s
y
s
t
e
m
[
1
5
]
.
T
h
e
GSR
s
ig
n
al
s
ar
e
f
o
r
m
ed
b
y
th
e
ch
an
g
i
n
g
b
o
d
y
r
esis
ta
n
ce
d
u
e
to
th
e
c
h
an
g
i
n
g
b
o
d
y
co
n
d
u
cti
v
it
y
ca
u
s
ed
b
y
t
h
e
p
r
o
d
u
ct
io
n
o
f
s
w
ea
t.
T
h
i
s
to
o
l
h
as
b
ee
n
q
u
ite
f
a
v
o
r
ite
as
it
is
ad
eq
u
atel
y
s
e
n
s
iti
v
e
an
d
in
e
x
p
en
s
iv
e.
I
n
its
d
ev
elo
p
m
en
t,
th
e
u
s
e
o
f
GS
R
to
d
etec
t
em
o
tio
n
ca
n
b
e
ca
r
r
ied
o
u
t
d
u
e
to
th
e
s
p
o
n
tan
eo
u
s
r
ea
ctio
n
w
h
ic
h
ca
n
n
o
t
b
e
co
n
tr
o
lled
b
y
th
e
u
s
er
.
Fu
r
t
h
er
m
o
r
e,
it
i
s
co
n
s
id
er
ed
as
o
n
e
o
f
t
h
e
s
tr
o
n
g
e
s
t
s
i
g
n
al
s
th
at
ca
n
b
e
u
s
ed
f
o
r
e
m
o
tio
n
d
etec
tio
n
[
1
8
]
,
[
1
9
]
.
R
el
y
in
g
o
n
t
h
e
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
o
f
S
VM
in
t
h
e
p
r
ev
io
u
s
r
esear
c
h
p
ar
ticu
lar
l
y
w
h
e
n
SVM
s
h
o
u
l
d
d
ea
l
w
it
h
th
e
te
m
p
o
r
al
d
ata
class
i
f
icatio
n
,
SVM
w
a
s
tak
e
n
as
th
e
SVM
alg
o
r
it
h
m
to
d
etec
t
em
o
tio
n
b
ased
o
n
GSR
d
ata
.
W
ith
in
t
h
i
s
d
ec
ad
e,
a
lo
t o
f
r
esear
ch
er
s
o
n
e
m
o
t
io
n
d
etec
tio
n
h
a
v
e
b
ee
n
co
n
d
u
cted
.
T
h
e
alg
o
r
ith
m
o
f
v
ar
io
u
s
d
etec
tio
n
to
o
ls
s
u
ch
a
s
GSR
,
e
lectr
o
en
ce
p
h
alo
g
r
a
m
(
EEG
)
an
d
o
th
er
d
ev
ice
s
h
av
e
b
ee
n
m
ad
e
[
3
]
,
[
4
]
,
[
1
2
]
.
Fo
r
ex
am
p
le,
E
E
G
is
u
s
ed
f
o
r
m
ea
s
u
r
i
n
g
t
h
e
c
h
an
g
e
o
f
p
o
s
iti
v
e
a
n
d
n
e
g
ati
v
e
e
m
o
tio
n
o
f
th
e
s
u
b
j
ec
t
w
h
o
i
s
i
n
d
u
ce
d
th
r
o
u
g
h
a
n
I
D
F
A
o
r
q
DF
A
v
id
eo
.
I
t
w
as
r
ep
o
r
ted
th
at
t
h
e
ac
c
u
r
ac
y
r
ea
ch
ed
7
4
.
3
%
w
h
ile
th
e
ac
cu
r
ac
y
o
f
t
h
e
q
DF
A
m
o
d
el
r
ea
ch
ed
6
9
.
4
%.
I
t w
a
s
also
s
aid
th
at
i
f
it
w
as a
p
p
lied
to
d
etec
t p
er
s
o
n
al
e
m
o
tio
n
,
th
e
ac
cu
r
ac
y
co
u
ld
r
ea
ch
9
4
.
5
%
[
2
0
]
.
T
h
e
co
m
b
in
atio
n
o
f
E
E
G
w
it
h
h
u
m
a
n
p
h
y
s
io
lo
g
ica
l
ch
an
g
e
ca
lled
E
y
e
Mo
v
e
m
e
n
t
Si
g
n
als
w
a
s
also
d
o
n
e
[
2
1
]
.
T
h
ey
r
ep
o
r
ted
th
at
w
h
en
t
h
e
co
m
b
i
n
atio
n
s
o
f
t
h
e
t
w
o
f
ac
to
r
s
ar
e
p
air
ed
f
u
zz
y
in
teg
r
al
f
u
s
io
n
a
lg
o
r
ith
m
clas
s
i
f
icatio
n
co
u
ld
in
cr
ea
s
e
th
e
p
er
f
o
r
m
a
n
ce
u
p
to
1
0
%
s
o
th
at
th
e
s
y
s
te
m
ac
c
u
r
a
cy
b
ec
a
m
e
8
7
.
5
9
.
E
E
G
d
ata
is
i
n
ter
esti
n
g
to
p
r
o
ce
s
s
a
n
d
te
n
d
to
h
av
e
h
i
g
h
ac
cu
r
ac
y
in
t
h
e
co
n
tex
t
o
f
e
m
o
tio
n
d
etec
tio
n
p
r
o
b
lem
s
.
Ho
w
e
v
er
,
E
E
G
h
as
s
ev
er
al
cr
u
c
ial
is
s
u
e
s
,
w
h
ich
ar
e
(
1
)
ex
p
en
s
iv
e
an
d
(
2
)
h
ig
h
n
o
is
e
o
f
d
ata
r
e
s
u
lted
b
y
it
s
s
e
n
s
o
r
.
T
h
is
p
h
en
o
m
e
n
o
n
h
as
m
ad
e
r
esear
ch
er
s
atte
m
p
t
to
f
i
n
d
alter
n
ati
v
es
t
h
at
ar
e
m
o
r
e
ap
p
r
o
p
r
iate,
an
d
GSR
is
o
n
e
o
f
t
h
e
o
th
er
o
p
tio
n
s
to
ch
o
o
s
e.
G
SR
i
s
an
al
ter
n
ati
v
e
th
at
h
a
s
b
ee
n
d
ev
elo
p
ed
s
i
n
ce
it
i
s
c
h
ea
p
a
n
d
ad
eq
u
atel
y
s
e
n
s
it
iv
e.
T
h
e
t
w
o
r
ea
s
o
n
s
a
t
le
ast
w
er
e
r
elate
d
to
th
e
m
ai
n
r
ea
s
o
n
w
h
y
GS
R
is
ap
p
lied
to
d
etec
t
p
s
y
c
h
o
lo
g
i
ca
l
co
n
d
itio
n
u
s
i
n
g
v
ar
io
u
s
m
et
h
o
d
s
.
T
h
er
e
a
r
e
s
ev
er
al
s
tu
d
ie
s
w
h
ich
p
r
o
p
o
s
e
d
if
f
er
e
n
t
m
et
h
o
d
s
o
f
d
etec
t
in
g
s
tr
es
s
le
v
els
b
y
m
ea
s
u
r
in
g
s
k
i
n
co
n
d
u
c
tan
c
e
[
1
4
]
,
[
2
2
]
.
A
n
e
x
a
m
p
le
o
f
t
h
i
s
r
esear
ch
w
as
th
e
o
n
e
co
n
d
u
ct
ed
b
y
Vi
llar
ej
o
.
T
h
ey
atte
m
p
t
ed
to
class
i
f
y
s
tr
es
s
s
u
f
f
er
ed
b
y
a
p
er
s
o
n
u
s
in
g
G
S
R
b
y
p
r
o
v
id
i
n
g
s
tr
es
s
i
n
d
u
ct
io
n
i
n
a
m
at
h
e
m
atica
l
ca
lc
u
lat
io
n
.
T
h
e
r
esu
lt
w
a
s
a
m
o
d
el
t
h
at
w
a
s
f
o
r
m
ed
b
y
u
s
i
n
g
GS
R
d
ata
co
u
ld
clas
s
i
f
y
s
tr
es
s
w
it
h
an
ac
c
u
r
ac
y
t
h
at
r
ea
ch
ed
u
p
to
7
6
.
5
6
% [
2
2
]
.
T
h
e
s
tu
d
y
d
escr
ib
ed
in
[
2
3
]
h
as
th
e
o
b
j
ec
tiv
e
o
f
d
etec
t
in
g
s
w
ea
t
lev
el
s
f
o
r
th
e
d
iag
n
o
s
is
o
f
s
u
d
o
m
o
to
r
d
y
s
f
u
n
ctio
n
,
s
o
m
eth
i
n
g
t
h
at
ca
n
h
elp
in
t
h
e
d
iag
n
o
s
i
s
o
f
d
iab
etes.
T
h
er
e
ar
e
o
th
er
m
ed
ical
ap
p
licatio
n
s
b
ased
o
n
s
k
in
co
n
d
u
cta
n
ce
,
s
u
c
h
as
ep
ilep
s
y
c
o
n
tr
o
l:
s
w
ea
t
y
h
a
n
d
s
m
a
y
b
e
a
w
ar
n
i
n
g
s
ig
n
al
o
f
an
ep
ilep
tic
attac
k
,
as
s
u
p
p
o
r
t
o
f
th
e
d
ia
g
n
o
s
is
a
n
d
tr
ea
t
m
en
t
o
f
b
ip
o
lar
d
is
o
r
d
er
p
atien
ts
[
2
4
]
.
B
y
co
m
b
in
i
n
g
th
e
s
w
ea
t
o
f
t
h
e
h
an
d
s
w
it
h
t
h
e
te
m
p
er
atu
r
e
o
f
th
e
s
k
in
,
it
is
p
o
s
s
ib
le
to
d
ev
elo
p
a
tr
u
th
m
eter
[
1
8
]
;
as
w
h
e
n
th
e
p
er
s
o
n
i
s
l
y
i
n
g
,
h
i
s
h
a
n
d
s
ar
e
co
ld
er
,
an
d
s
k
i
n
r
esi
s
ta
n
ce
is
lo
w
er
.
I
n
t
h
is
ca
s
e,
it
is
n
o
t
n
ec
es
s
ar
y
to
in
cl
u
d
e
an
ADC
b
ec
a
u
s
e
t
h
e
v
ar
iatio
n
o
f
s
k
i
n
r
esi
s
tan
ce
h
a
p
p
en
s
at
o
d
d
ti
m
es
s
o
,
w
it
h
d
if
f
er
en
t
r
es
is
ta
n
ce
s
an
d
tr
an
s
is
to
r
s
,
it
is
p
o
s
s
ib
le
t
o
b
u
ild
a
lie
d
etec
to
r
.
A
tr
u
t
h
m
eter
is
p
o
s
s
ib
l
y
e
s
tab
lis
h
ed
b
ased
o
n
th
e
h
a
n
d
s
s
w
ea
t
an
d
s
k
in
te
m
p
er
atu
r
e.
P
er
s
o
n
'
s
h
a
n
d
s
ar
e
co
ld
er
,
an
d
h
e
h
as
l
o
w
er
s
k
i
n
r
esis
ta
n
ce
w
h
e
n
h
e
is
telli
n
g
a
lie.
A
tte
m
p
ti
n
g
to
d
o
th
e
s
a
m
e
t
h
i
n
g
d
o
n
e
b
y
Villar
ej
o
,
Ku
r
n
ia
wan
clas
s
i
f
ied
s
tr
e
s
s
u
s
i
n
g
G
SR
an
d
n
o
i
s
e
s
ig
n
al
s
[
1
4
]
,
[
2
2
]
.
C
lass
if
icati
o
n
b
y
n
o
is
e
s
i
g
n
als
g
e
n
er
ated
th
e
b
est
r
es
u
lt,
w
h
ic
h
w
as
9
2
%
th
r
o
u
g
h
S
VM
alg
o
r
ith
m
.
W
h
en
t
h
e
GSR
d
a
ta
w
as
u
s
ed
,
h
o
w
e
v
er
,
th
e
ac
cu
r
ac
y
o
b
tain
ed
w
a
s
o
n
l
y
7
0
%
th
r
o
u
g
h
t
h
e
s
a
m
e
alg
o
r
ith
m
.
T
h
er
e
w
as
a
n
o
p
in
i
o
n
th
at
w
h
e
n
w
e
at
te
m
p
ted
to
class
i
f
y
a
p
er
s
o
n
'
s
s
tr
es
s
u
s
i
n
g
an
o
t
h
er
p
er
s
o
n
'
s
d
ata,
th
e
g
en
er
ated
ac
cu
r
ac
y
w
o
u
ld
d
ec
r
ea
s
e
[
1
4
]
.
R
esear
ch
er
s
co
m
m
o
n
l
y
u
s
e
GS
R
to
class
i
f
y
th
e
h
u
m
a
n
s
tr
ess
le
v
el.
I
n
a
d
i
f
f
er
en
t
ap
p
r
o
ac
h
,
L
iu
at
te
m
p
ted
to
clas
s
if
y
e
m
o
tio
n
al
s
tat
u
s
i
n
to
h
a
p
p
in
ess
,
g
r
ief
,
f
ea
r
,
an
g
er
,
an
d
ca
l
m
u
s
i
n
g
G
SR
d
ata.
T
h
e
b
est
ac
cu
r
ac
y
lev
el
o
b
tain
ed
b
y
L
i
u
w
as
6
6
.
6
7
%
th
r
o
u
g
h
S
VM
alg
o
r
ith
m
w
it
h
k
er
n
el
r
ad
ial
b
ased
f
u
n
ct
io
n
(
R
B
F)
[
1
2
]
.
R
ec
en
tl
y
,
t
h
e
Sli
d
in
g
W
in
d
o
w
tech
n
iq
u
e
h
a
s
o
f
ten
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
5
,
Octo
b
er
2
0
1
8
:
4
0
0
4
–
4
0
1
4
4006
b
ee
n
u
s
ed
in
p
h
y
s
io
lo
g
ical
d
ata
class
if
ica
tio
n
.
I
n
t
h
e
r
ese
ar
ch
,
th
e
s
tr
es
s
ca
n
b
e
ap
p
r
o
p
r
iatel
y
clas
s
i
f
ied
,
w
h
er
e
th
e
ac
cu
r
ac
y
o
f
cla
s
s
i
f
icatio
n
is
u
p
to
9
8
%
b
y
co
m
b
in
i
n
g
HR
V
d
ata
w
ith
E
C
G
d
ata
w
h
ic
h
w
er
e
p
r
o
ce
s
s
ed
b
y
Sli
d
i
n
g
W
i
n
d
o
w
s
u
s
in
g
w
id
t
h
s
2
4
p
o
in
ts
,
an
d
it
w
a
s
clas
s
i
f
ied
u
s
i
n
g
SV
M
w
it
h
li
n
ea
r
k
er
n
e
l
[
2
5
]
.
A
d
if
f
er
en
t
m
et
h
o
d
w
as
ca
r
r
ied
o
u
t
b
y
W
ei,
w
h
o
att
e
m
p
ted
to
cla
s
s
i
f
y
e
m
o
tio
n
i
n
to
a
n
g
er
,
f
ea
r
,
j
o
y
,
s
o
r
r
o
w
,
ac
ce
p
tan
ce
,
r
ej
ec
tio
n
,
s
u
r
p
r
is
e
an
d
ex
p
ec
tan
c
y
.
T
h
e
r
esear
ch
o
b
tain
ed
a
r
esu
lt
w
it
h
r
ea
s
o
n
ab
le
ac
cu
r
ac
y
as
m
u
c
h
as
8
0
%
u
s
i
n
g
S
VM
alg
o
r
ith
m
w
h
ic
h
w
a
s
p
r
o
ce
s
s
ed
b
y
Sli
d
in
g
W
in
d
o
w
s
tec
h
n
iq
u
e
[
1
2
]
.
Usi
n
g
d
if
f
er
e
n
t
ap
p
r
o
ac
h
,
Gu
o
also
tr
ied
to
class
if
y
h
u
m
a
n
e
m
o
tio
n
in
to
a
m
u
s
e
m
en
t,
f
ea
r
,
r
elax
atio
n
,
an
d
s
ad
n
es
s
u
s
i
n
g
Sli
d
in
g
W
i
n
d
o
w
s
tech
n
iq
u
e
w
it
h
t
h
e
lag
as
m
u
c
h
a
s
2
0
p
o
in
ts
.
T
h
e
r
esear
ch
also
o
b
tain
ed
a
g
o
o
d
r
esu
lt
w
it
h
ac
cu
r
ac
y
th
at
r
ea
ch
ed
7
9
.
4
5
% [
1
8
]
.
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
S
VM
)
w
as
f
ir
s
t
in
tr
o
d
u
ce
d
b
y
Vlad
i
m
ir
Vap
n
i
k
i
n
1
9
9
5
an
d
u
s
ed
f
o
r
b
in
ar
y
clas
s
i
f
icatio
n
p
u
r
p
o
s
e
[
2
6
]
.
W
h
en
SVM
p
er
f
o
r
m
s
,
it
w
il
l c
r
ea
te
h
y
p
er
p
la
n
e
w
h
ic
h
i
s
ai
m
ed
as a
d
iv
id
er
o
f
ea
ch
clas
s
.
T
h
e
b
asic c
o
n
ce
p
t
w
as lo
o
k
in
g
f
o
r
th
e
h
y
p
er
p
lan
e
w
h
ich
s
ep
ar
ated
d
-
d
i
m
en
s
io
n
al
d
ata
co
r
r
ec
tly
in
to
t
w
o
cla
s
s
e
s
.
T
h
e
h
y
p
er
p
lan
e
h
ad
th
e
b
i
g
g
e
s
t
m
ar
g
i
n
.
Fo
r
f
u
r
t
h
er
ex
p
la
n
atio
n
s
ee
Fig
u
r
e
1
.
(
a)
(
b
)
Fig
u
r
e
1
.
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
a)
an
d
a
n
ex
a
m
p
le
o
f
k
er
n
el
s
o
lv
i
n
g
(
b
)
T
h
e
f
o
llo
w
i
n
g
f
o
r
m
u
la
i
s
to
ca
lcu
late
t
h
e
h
y
p
er
p
lan
e
in
t
h
e
S
VM
:
i
i
i
b
w
x
y
1
(
1
)
in
w
h
ich
y
i
i
s
lab
el,
x
i
is
i
n
p
u
t,
w
is
w
ei
g
h
t a
n
d
b
is
b
ias.
A
lt
h
o
u
g
h
th
e
SVM
h
as
p
r
o
v
ed
to
b
ec
o
m
e
a
h
ig
h
l
y
e
f
f
ec
ti
v
e
lear
n
i
n
g
al
g
o
r
ith
m
in
t
h
e
r
ea
l
w
o
r
ld
d
ata,
it
h
as
n
o
t
f
r
eq
u
e
n
tl
y
b
ee
n
u
s
ed
.
I
t
is
ca
u
s
ed
b
y
s
e
v
er
al
p
r
o
b
lem
s
f
o
u
n
d
i
n
t
h
e
S
VM
,
s
u
ch
as
t
h
e
f
ac
t
t
h
at
th
e
i
m
p
le
m
e
n
tatio
n
o
f
t
h
e
S
VM
w
h
ic
h
is
n
o
t
ea
s
y
.
B
esid
es,
th
e
u
s
e
o
f
t
h
e
w
r
o
n
g
p
ar
a
m
eter
m
a
y
i
n
cr
ea
s
e
d
if
f
ic
u
lt
y
le
v
el
i
n
t
h
e
co
m
p
u
t
atio
n
p
r
o
ce
s
s
.
I
n
itiall
y
,
t
h
e
S
VM
w
a
s
cr
ea
ted
w
ith
a
m
et
h
o
d
o
f
lin
ea
r
p
r
o
b
lem
-
s
o
lv
i
n
g
.
Ho
w
e
v
er
,
th
er
e
h
av
e
b
ee
n
d
ata
th
at
ar
e
n
o
t
lin
ea
r
.
T
h
er
ef
o
r
e,
k
er
n
els
th
at
co
u
ld
b
e
ab
l
e
t
o
m
ap
th
e
d
ata
in
th
e
d
i
m
en
s
io
n
al
s
p
ac
e
w
h
ic
h
is
u
s
u
all
y
b
i
g
g
er
(
f
ea
t
u
r
e
s
p
ac
e)
w
er
e
cr
ea
ted
.
A
cc
o
r
d
in
g
l
y
,
n
o
n
li
n
ea
r
p
r
o
b
lem
s
t
h
at
co
u
ld
p
r
ev
io
u
s
l
y
n
o
t
b
e
ad
eq
u
atel
y
s
o
l
v
ed
co
u
ld
ev
e
n
tu
a
ll
y
b
e
s
o
l
v
ed
.
T
h
er
e
h
av
e
b
ee
n
k
er
n
el
s
th
at
f
r
eq
u
en
t
l
y
u
s
ed
in
S
VM
s
u
c
h
as
r
ad
ial
b
asis
f
u
n
ctio
n
(
R
B
F)
o
r
Gau
s
s
ia
n
,
p
o
l
y
n
o
m
ia
l
an
d
s
ig
m
o
id
.
T
h
e
f
i
g
u
r
e
s
h
o
w
s
t
w
o
an
ex
a
m
p
le
o
f
p
r
o
b
le
m
-
s
o
l
v
i
n
g
u
s
i
n
g
k
er
n
els.
Ho
w
ev
er
,
t
h
e
u
s
e
o
f
k
er
n
els
h
a
s
p
ar
tic
u
lar
w
ea
k
n
ess
e
s
.
W
r
o
n
g
m
ea
s
u
r
i
n
g
p
ar
a
m
eter
s
i
n
k
er
n
els
ca
n
c
au
s
e
t
h
e
m
o
d
el
to
b
ec
o
m
e
o
v
er
lif
t
o
r
u
n
d
er
f
it.
A
l
s
o
,
th
e
u
s
e
o
f
k
er
n
el
s
ca
n
i
n
cr
e
m
e
n
t
t
h
e
co
m
p
u
tatio
n
lo
ad
s
o
th
at
it
ca
u
s
es
t
h
e
p
r
o
ce
s
s
to
s
lo
w
d
o
w
n
.
R
B
F
is
o
n
e
o
f
th
e
k
er
n
els,
w
h
ich
h
as
f
r
eq
u
en
t
l
y
b
ee
n
u
s
ed
s
i
n
ce
it
h
a
s
a
g
o
o
d
p
er
f
o
r
m
a
n
ce
a
n
d
test
ed
.
R
B
F
m
ap
s
n
o
n
li
n
ea
r
d
a
ta
in
to
a
b
ig
g
er
d
i
m
e
n
s
io
n
.
T
h
e
h
y
p
er
p
lan
e
i
n
t
h
e
n
o
n
li
n
ea
r
d
ata
ca
n
b
e
s
o
u
g
h
t.
T
h
e
f
o
r
m
u
la
o
f
R
B
F k
er
n
e
ls
d
ata
m
ap
p
in
g
i
s
as f
o
llo
w
s
:
2
2
2
||
||
e
x
p
)
,
(
xb
xa
x
x
K
b
a
(
2
)
in
w
h
ich
ca
n
b
e
ch
an
g
ed
ac
co
r
d
in
g
to
th
e
n
ee
d
s
[
2
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Ga
lva
n
ic
S
kin
R
esp
o
n
s
e
Da
ta
C
la
s
s
i
fica
tio
n
fo
r
E
mo
tio
n
De
tectio
n
(
Djo
ko
B
u
d
iya
n
t
o
S
ety
o
h
a
d
i)
4007
2.
P
RO
P
O
SE
D
M
E
T
H
O
DO
L
O
G
Y
T
h
e
r
esear
ch
m
eth
o
d
o
lo
g
y
o
f
th
e
d
ata
co
llectio
n
w
as
d
iv
id
ed
in
to
t
w
o
p
ar
ts
.
On
e
w
a
s
d
esig
n
ed
f
o
r
th
e
r
esp
o
n
d
en
t
s
,
an
d
th
e
o
th
e
r
w
as
i
n
ten
d
ed
f
o
r
th
e
s
y
s
te
m
.
T
h
e
d
esig
n
f
o
r
th
e
r
esp
o
n
d
en
ts
u
s
ed
th
e
w
it
h
-
s
u
b
j
ec
t d
esig
n
s
,
an
d
t
h
e
s
y
s
te
m
d
esi
g
n
w
a
s
d
ev
elo
p
ed
b
y
co
m
b
in
i
n
g
s
e
v
er
al
m
e
th
o
d
o
lo
g
ie
s
th
at
co
r
r
esp
o
n
d
ed
to
e
m
o
tio
n
al
d
etec
tio
n
u
s
i
n
g
au
d
io
-
v
is
u
al
i
n
d
u
c
tio
n
.
I
n
t
h
i
s
s
t
u
d
y
,
as
m
a
n
y
as
3
9
r
esp
o
n
d
en
t
s
w
er
e
c
h
o
s
e
n
r
an
d
o
m
l
y
f
r
o
m
t
h
e
P
s
y
c
h
o
l
o
g
y
Fac
u
lt
y
o
f
Gad
j
ah
Ma
d
a
Un
i
v
er
s
it
y
,
Yo
g
y
ak
ar
ta
a
n
d
th
e
I
n
d
u
s
tr
ial
T
ec
h
n
o
lo
g
y
Fac
u
lt
y
o
f
At
m
a
J
a
y
a
U
n
iv
er
s
it
y
,
Yo
g
y
a
k
ar
ta,
all
o
f
w
h
o
m
w
er
e
s
till
ac
ti
v
e
s
t
u
d
en
t
s
.
Me
th
o
d
o
lo
g
y
,
a
s
an
o
v
er
all
p
r
o
ce
s
s
,
is
ill
u
s
tr
ated
i
n
Fi
g
u
r
e
2
.
W
h
ile
th
e
d
ata
co
llectio
n
p
r
o
ce
s
s
w
as
d
o
n
e
in
an
is
o
latio
n
r
o
o
m
a
n
d
th
e
to
o
l in
s
ta
llatio
n
i
s
co
n
f
i
g
u
r
ed
in
F
i
g
u
r
e
3
.
P
A
N
A
S
s
c
a
l
e
m
e
a
s
u
r
e
m
e
n
t
D
a
t
a
C
o
l
l
e
c
t
i
o
n
P
r
e
p
r
o
c
e
s
s
i
n
g
T
e
s
t
i
n
g
a
n
d
v
a
l
i
d
a
t
i
o
n
P
a
r
a
m
e
t
e
r
S
e
l
e
c
t
i
o
n
a
n
d
M
o
d
e
l
T
r
a
i
n
i
n
g
Fig
u
r
e
2
.
R
esear
ch
m
et
h
o
d
o
lo
g
y
Fig
u
r
e
3
.
T
h
e
G
SR
in
s
tallatio
n
2
.
1
.
P
ANAS
s
ca
le
m
ea
s
ure
m
ent
P
A
N
A
S
S
C
AL
E
w
as
g
iv
e
n
at
th
e
b
eg
in
n
i
n
g
o
f
th
e
ex
p
er
i
m
en
t
to
o
b
tain
b
o
th
p
o
s
itiv
e
an
d
n
eg
ati
v
e
af
f
ec
tio
n
b
aseli
n
es.
T
h
e
b
aseli
n
e
o
f
p
h
y
s
io
lo
g
ical
s
e
n
s
o
r
d
ata
w
as
r
ec
o
r
d
ed
f
o
r
th
r
ee
m
i
n
u
tes
af
ter
t
h
e
s
u
b
j
ec
t
h
ad
f
i
n
is
h
ed
w
o
r
k
in
g
o
n
t
h
e
P
A
N
A
S
s
ca
le.
Du
r
i
n
g
t
h
e
t
h
r
ee
m
in
u
te
s
,
th
e
r
esp
o
n
d
en
ts
wer
e
r
eq
u
ir
ed
to
w
ait
f
o
r
th
e
n
ex
t
in
s
tr
u
c
tio
n
.
Af
t
er
th
r
ee
m
i
n
u
tes,
a
n
i
n
s
tr
u
ct
io
n
w
o
u
ld
ap
p
ea
r
o
n
th
e
s
u
b
j
ec
t
to
m
e
m
o
r
ize
u
n
r
elate
d
p
air
s
o
f
w
o
r
d
s
f
o
ll
o
w
ed
b
y
t
h
e
ac
t
u
al
ta
s
k
g
i
v
e
n
to
th
e
m
,
w
h
ic
h
w
a
s
to
r
e
m
e
m
b
er
th
e
p
air
s
o
f
w
o
r
d
s
th
at
h
ad
b
ee
n
m
e
m
o
r
iz
ed
u
s
in
g
th
e
cu
ed
r
ec
all
m
et
h
o
d
.
P
A
N
A
S
Scale
is
a
s
elf
-
r
e
p
o
r
t
q
u
esti
o
n
n
air
e
co
n
s
is
tin
g
o
f
2
0
ite
m
s
w
i
th
a
n
s
w
er
s
ch
o
ices
i
n
th
e
L
i
k
er
t
s
c
ale
f
o
r
m
o
f
5
an
s
w
er
ch
o
ice
s
u
s
ed
to
m
ea
s
u
r
e
th
e
lev
el
o
f
af
f
ec
tio
n
[
2
8
]
.
W
e
h
ad
p
r
e
p
ar
ed
a
s
ch
ed
u
le
o
f
d
ata
co
llectio
n
w
h
ic
h
w
as
co
n
d
u
cted
f
o
r
s
ix
d
a
y
s
,
s
tar
tin
g
f
r
o
m
0
8
.
3
0
to
1
6
:3
0
w
it
h
3
0
m
i
n
u
te
s
b
et
w
ee
n
s
e
s
s
io
n
s
.
Su
b
j
ec
t
g
r
o
u
p
i
n
g
in
th
e
ex
p
er
i
m
e
n
tal
a
n
d
co
n
tr
o
l
g
r
o
u
p
s
w
a
s
ca
r
r
ied
o
u
t
r
an
d
o
m
l
y
,
a
n
d
s
o
w
er
e
th
e
p
r
esen
tatio
n
o
f
s
ti
m
u
li
a
n
d
li
s
t
s
o
f
w
o
r
d
s
t
o
r
e
m
e
m
b
er
.
B
ef
o
r
e
d
ata
co
llectio
n
,
ea
ch
s
u
b
j
ec
t
w
a
s
r
eq
u
ir
ed
to
f
ill
i
n
th
e
i
n
f
o
r
m
ed
co
n
s
en
t
co
n
tai
n
in
g
t
h
e
r
esear
ch
p
r
o
ce
d
u
r
es
to
b
e
f
o
l
lo
w
ed
,
th
e
co
n
s
eq
u
e
n
ce
s
t
h
at
m
ig
h
t
o
cc
u
r
,
as
w
ell
as
t
h
e
in
ce
n
tiv
e
s
th
a
t
th
e
s
u
b
j
ec
ts
w
o
u
ld
r
ec
ei
v
e.
I
f
t
h
e
y
ag
r
ee
d
,
t
h
e
y
w
er
e
as
k
e
d
to
s
ig
n
t
h
e
in
f
o
r
m
ed
co
n
s
en
t.
Af
ter
t
h
at,
t
h
e
ex
p
er
i
m
e
n
ter
s
g
av
e
a
n
ad
d
itio
n
al
ex
p
la
n
atio
n
to
en
s
u
r
e
th
at
t
h
e
s
u
b
j
ec
ts
co
m
p
lete
l
y
u
n
d
er
s
to
o
d
th
e
ex
p
er
i
m
e
n
t p
r
o
ce
d
u
r
e.
2
.
2
.
Da
t
a
c
o
llect
io
n
Data
co
llectio
n
w
a
s
d
o
n
e
in
a
r
o
o
m
w
h
ic
h
co
m
p
lied
w
it
h
th
e
ex
p
er
i
m
e
n
tal
p
r
o
to
co
l.
T
h
e
s
etti
n
g
s
h
er
e
in
c
lu
d
ed
t
h
e
te
m
p
er
at
u
r
e,
lig
h
t
a
n
d
n
o
is
e
s
et.
T
h
e
tr
ea
t
m
e
n
t
o
f
th
e
co
n
d
itio
n
a
n
d
eq
u
ip
m
e
n
t
w
a
s
t
h
e
s
a
m
e
f
o
r
all
r
esp
o
n
d
en
ts
,
w
h
i
ch
in
cl
u
d
ed
r
o
o
m
,
co
m
p
u
ter
,
s
cr
ee
n
,
s
p
ea
k
er
s
,
G
SR
s
e
n
s
o
r
,
k
e
y
b
o
ar
d
,
m
o
u
s
e,
tab
le,
an
d
ch
air
.
2
.
3
.
P
re
-
pro
ce
s
s
ing
P
r
e
-
p
r
o
ce
s
s
in
g
w
as
d
i
v
id
ed
i
n
to
s
e
v
er
al
s
tag
e
s
,
n
a
m
el
y
d
a
ta
ca
teg
o
r
izatio
n
,
d
ata
ag
g
r
eg
atio
n
,
d
ata
n
o
r
m
aliza
t
io
n
,
an
d
d
ata
lag
g
i
n
g
.
T
h
e
d
ata
o
b
tain
ed
w
er
e
th
e
n
ca
teg
o
r
ized
in
to
th
r
ee
co
lu
m
n
s
b
y
t
h
e
tr
ea
t
m
e
n
t
g
iv
e
n
at
th
e
ti
m
e
o
f
t
h
e
ex
p
er
i
m
e
n
t
(
p
o
s
itiv
e,
n
e
u
tr
al,
n
e
g
at
iv
e)
.
T
h
is
d
ata
ca
teg
o
r
izatio
n
w
o
u
ld
b
e
u
s
ef
u
l
in
d
ata
lab
elin
g
.
T
h
e
n
ex
t
p
r
o
ce
s
s
w
as
to
a
g
g
r
eg
ate
t
h
e
d
ata
to
co
n
v
er
t
t
h
e
ti
m
e
u
n
it
i
n
to
s
ec
o
n
d
s
b
y
a
v
er
ag
i
n
g
th
e
d
ata
ac
co
r
d
in
g
to
th
e
GS
R
f
r
eq
u
en
c
y
at
th
e
ti
m
e
o
f
d
ata
co
llectio
n
.
I
n
th
i
s
ca
s
e
,
th
e
d
at
a
w
as
a
v
er
ag
ed
o
n
ev
er
y
1
0
3
d
ata.
T
h
e
n
ex
t
t
h
in
g
to
d
o
w
a
s
n
o
r
m
a
lizatio
n
o
r
f
ea
tu
r
e
s
ca
li
n
g
w
h
ic
h
w
as
u
s
e
f
u
l
f
o
r
s
ta
n
d
ar
d
izin
g
th
e
d
is
tan
ce
o
r
r
an
g
e
o
f
v
ar
iab
les
o
r
f
ea
t
u
r
es
in
t
h
e
d
ata
s
o
th
at
th
e
m
a
x
i
m
u
m
a
n
d
m
in
i
m
u
m
v
alu
e
b
ec
a
m
e
1
an
d
0
.
Fin
all
y
,
th
e
d
ata
w
a
s
f
o
r
m
ed
b
y
t
h
e
n
u
m
b
er
o
f
n
lag
an
d
w
a
s
ad
d
ed
w
it
h
a
p
o
s
itiv
e,
n
e
u
tr
al
o
r
n
eg
at
iv
e
lab
el.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
5
,
Octo
b
er
2
0
1
8
:
4
0
0
4
–
4
0
1
4
4008
)
m
i
n
(
)
m
a
x
(
)
m
i
n
(
x
x
x
x
x
(
3
)
2
.
4
.
P
a
ra
m
et
er
s
elec
t
io
n a
nd
m
o
delin
g
t
ra
ini
ng
I
n
th
i
s
r
esear
ch
,
t
h
e
m
o
d
el
was
tr
ain
ed
to
u
s
e
SVM
alg
o
r
i
th
m
.
T
h
e
n
u
m
b
er
o
f
la
g
s
th
at
w
a
s
u
s
ed
s
tar
ted
f
r
o
m
5
to
4
0
lag
s
SVM
p
ar
am
eter
tu
n
ed
au
to
m
atica
ll
y
w
it
h
th
e
co
s
t
s
tar
ti
n
g
f
r
o
m
2
^1
to
2
^8
u
s
in
g
th
e
lin
ea
r
k
er
n
el,
p
o
l
y
n
o
m
ial,
r
ad
ial
b
ased
f
u
n
ctio
n
a
n
d
s
i
g
m
o
id
.
2
.
5
.
M
o
del t
esting
a
nd
v
a
lid
a
t
io
n
Af
ter
t
h
e
p
ar
a
m
eter
r
eq
u
ir
ed
b
y
SVM
m
o
d
el
w
as
s
et,
t
h
e
r
e
s
u
lt
w
as
v
a
lid
ated
to
ap
p
r
o
v
e
th
e
q
u
alit
y
o
f
th
e
cla
s
s
i
f
icatio
n
m
o
d
el.
T
h
e
ac
cu
r
ac
y
a
n
d
R
ec
ei
v
er
Op
er
atin
g
C
u
r
v
e
w
er
e
o
b
tain
ed
b
y
u
s
in
g
t
h
e
f
o
llo
w
in
g
f
o
r
m
u
la:
FN
FP
TN
TP
TN
TP
A
c
c
u
ra
c
y
/
(
4
)
w
h
er
e:
T
P
is
tr
u
e
p
o
s
itive
,
T
N
is
tr
u
e
n
eg
a
tive
,
an
d
FP
is
fa
l
s
e
p
o
s
itive
an
d
FN is
fa
l
s
e
n
eg
a
tive
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
I
n
th
i
s
s
ec
tio
n
,
it
is
e
x
p
lai
n
ed
th
e
r
esu
lts
o
f
r
esear
ch
an
d
at
th
e
s
a
m
e
ti
m
e
is
g
iv
e
n
t
h
e
co
m
p
r
e
h
en
s
iv
e
d
is
c
u
s
s
io
n
.
R
e
s
u
lt
s
ca
n
b
e
p
r
ese
n
ted
i
n
f
i
g
u
r
es,
g
r
ap
h
s
,
tab
le
s
a
n
d
o
th
er
s
t
h
at
m
a
k
e
t
h
e
r
ea
d
er
u
n
d
er
s
ta
n
d
ea
s
il
y
[
2
]
,
[
5
]
,
[
2
9
]
.
T
h
e
d
is
cu
s
s
io
n
ca
n
b
e
m
ad
e
i
n
s
e
v
er
al
s
u
b
-
c
h
ap
ter
s
.
3
.
1
.
Da
t
a
s
et
v
a
lid
a
t
io
n ba
s
ed
o
n P
ANAS
s
ca
le
Ma
n
ip
u
la
tio
n
v
a
lid
atio
n
w
as
d
o
n
e
b
y
r
u
n
n
in
g
R
ep
ea
ted
Me
asu
r
es
A
N
OV
A
o
n
t
h
e
P
A
N
AS
s
ca
le.
Ma
n
ip
u
la
tio
n
ca
n
b
e
d
ec
lar
ed
s
u
cc
e
s
s
f
u
l
if
th
er
e
is
a
d
i
f
f
er
en
t
s
co
r
e
o
f
P
A
N
A
S
i
n
a
co
n
d
i
tio
n
th
a
t
is
r
elati
v
e
to
th
e
b
asel
in
e
an
d
al
s
o
a
d
i
f
f
e
r
en
ce
in
ea
ch
co
n
d
itio
n
o
f
tr
ea
t
m
e
n
t.
T
h
e
d
escr
ip
tiv
e
d
ata
o
f
th
e
t
w
o
s
u
b
-
s
ca
le
s
o
f
P
A
N
AS
ca
n
b
e
s
ee
n
in
T
ab
le
1
.
Sp
h
er
icit
y
v
a
lid
atio
n
o
f
p
o
s
iti
v
e
a
n
d
n
e
g
ati
v
e
a
f
f
e
ctio
n
s
u
b
s
ca
le
o
f
P
A
N
A
S
s
ca
le
b
o
th
s
u
g
g
e
s
te
d
co
ef
f
icie
n
t
p
<0
.
0
0
1
.
C
o
r
r
ec
tio
n
o
n
s
p
h
er
ici
t
y
w
as
d
o
n
e
b
y
e
m
p
lo
y
in
g
Gr
ee
n
h
o
u
s
e
-
Gei
s
s
er
(
s
i
n
ce
th
e
ep
s
ilo
n
w
as a
b
o
v
e
0
.
7
)
.
T
ab
le
1
. S
tatis
tical
Descr
ip
tio
n
o
f
P
A
N
AS Sca
le
o
f
P
o
s
itiv
e
an
d
Neg
ati
v
e
A
f
f
ec
t
io
n
s
P
o
si
t
i
v
e
A
f
f
e
c
t
i
o
n
N
e
g
a
t
i
v
e
A
f
f
e
c
t
i
o
n
Me
a
n
SD
M
i
n
M
a
x
Me
a
n
SD
M
i
n
M
a
x
B
a
se
l
i
n
e
3
.
5
6
6
0
.
4
8
2
8
2
.
3
4
.
3
2
.
1
7
1
0
.
6
1
8
2
1
.
2
4
N
e
u
t
r
a
l
C
o
n
d
i
t
i
o
n
3
.
2
2
9
0
.
6
0
4
9
1
.
5
4
.
4
2
.
0
2
1
0
.
7
4
8
1
4
.
1
P
o
si
t
i
v
e
C
o
n
d
i
t
i
o
n
3
.
2
8
4
0
.
5
6
5
9
1
.
8
4
.
2
1
.
9
9
2
0
.
7
5
8
5
1
4
.
4
N
e
g
a
t
i
v
e
C
o
n
d
i
t
i
o
n
3
.
2
3
9
0
.
6
2
6
2
1
.
4
4
,
2
2
.
3
3
9
0
.
7
3
8
7
1
.
1
4
.
1
I
t
is
s
ee
n
i
n
T
ab
le
2
th
at
t
h
e
r
es
u
lt
o
f
R
ep
ea
ted
m
ea
s
u
r
es
A
N
OV
A
w
it
h
Gr
ee
n
h
o
u
s
e
-
Gei
s
s
er
co
r
r
ec
tio
n
r
esu
lted
f
r
o
m
co
e
f
f
icien
t
p
<0
.
0
0
1
in
th
e
s
u
b
-
s
ca
l
e
o
f
p
o
s
iti
v
e
a
f
f
ec
t
io
n
a
n
d
p
=0
.
0
0
2
(
p
<0
.
0
1
)
in
th
e
s
u
b
-
s
ca
le
o
f
n
e
g
ati
v
e
af
f
e
ct,
w
h
ich
m
ea
n
t
th
at
t
h
er
e
wer
e
s
ig
n
if
ica
n
t
d
i
f
f
er
e
n
ce
s
b
et
w
ee
n
th
e
t
w
o
i
n
at
least
o
n
e
o
f
t
h
e
co
n
d
it
io
n
s
.
Valid
atio
n
t
h
at
i
s
m
o
r
e
d
eta
iled
w
a
s
d
o
n
e
b
y
ca
r
r
y
i
n
g
o
u
t
p
o
s
t
h
o
c
u
s
i
n
g
B
o
n
f
er
r
o
n
i
m
et
h
o
d
,
o
f
w
h
ic
h
r
esu
lt c
a
n
b
e
s
ee
n
i
n
T
ab
le
3
.
T
ab
le
2
.
R
esu
lt o
f
R
ep
ea
ted
Me
asu
r
es
A
N
OV
A
w
it
h
Sp
h
er
icit
y
C
o
r
r
ec
tio
n
;
*
*
p
<0
,
0
0
1
S
u
b
-
s
c
a
l
e
S
p
h
e
r
i
c
i
t
y
C
o
r
r
e
c
t
i
o
n
ε
df
p
P
o
si
t
i
v
e
A
f
f
e
c
t
i
o
n
G
r
e
e
n
h
o
u
se
-
G
e
i
sser
0
.
7
0
5
2
.
1
1
4
<
0
.
0
0
1
*
*
N
e
g
a
t
i
v
e
A
f
f
e
c
t
i
o
n
G
r
e
e
n
h
o
u
se
-
G
e
i
sser
0
.
7
6
3
2
.
2
9
0
0
.
0
0
2
*
*
T
ab
le
3
.
P
o
s
t H
o
c
B
o
n
f
er
r
o
n
i
Valid
atio
n
o
f
P
AN
A
S S
ca
le
;
*
p
<0
.
0
5
; *
*
p
<0
.
0
1
P
o
si
t
i
v
e
A
f
f
e
c
t
i
o
n
N
e
g
a
t
i
v
e
A
f
f
e
c
t
i
o
n
M
e
a
n
d
i
f
f
e
r
e
n
c
e
p
b
o
n
f
M
e
a
n
D
i
f
f
e
r
e
n
c
e
p
b
o
n
f
Ba
se
l
i
n
e
N
e
u
t
r
a
l
0
.
3
3
7
0
.
0
1
1
*
0
.
1
5
0
0
.
6
8
8
P
o
si
t
i
v
e
C
o
n
d
i
t
i
o
n
0
.
2
8
2
0
.
0
3
7
*
0
.
1
7
9
0
.
3
3
2
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Ga
lva
n
ic
S
kin
R
esp
o
n
s
e
Da
ta
C
la
s
s
i
fica
tio
n
fo
r
E
mo
tio
n
De
tectio
n
(
Djo
ko
B
u
d
iya
n
t
o
S
ety
o
h
a
d
i)
4009
P
o
si
t
i
v
e
A
f
f
e
c
t
i
o
n
N
e
g
a
t
i
v
e
A
f
f
e
c
t
i
o
n
M
e
a
n
d
i
f
f
e
r
e
n
c
e
p
b
o
n
f
M
e
a
n
D
i
f
f
e
r
e
n
c
e
p
b
o
n
f
N
e
g
a
t
i
v
e
C
o
n
d
i
t
i
o
n
0
.
3
2
6
0
.
0
1
1
*
-
0
.
1
6
8
0
.
8
4
8
N
e
u
t
r
a
l
C
o
n
d
i
t
i
o
n
P
o
si
t
i
v
e
C
o
n
d
i
t
i
o
n
-
0
.
0
5
5
1
.
0
0
0
0
.
0
2
9
1
.
0
0
0
N
e
g
a
t
i
v
e
C
o
n
d
i
t
i
o
n
-
0
.
0
1
1
1
.
0
0
0
-
0
.
3
1
8
0
.
0
0
2
*
*
P
o
si
t
i
v
e
c
o
n
d
i
t
i
o
n
N
e
g
a
t
i
v
e
C
o
n
d
i
t
i
o
n
0
.
0
4
5
1
.
0
0
0
-
0
.
3
4
7
0
.
0
0
4
*
*
I
n
th
e
P
A
N
AS
s
u
b
-
s
ca
le
o
f
p
o
s
itiv
e
a
f
f
ec
tio
n
,
s
ig
n
i
f
ica
n
t
d
if
f
er
e
n
ce
(
p
<
0
.
0
5
)
o
cc
u
r
r
ed
in
th
e
b
aselin
e
co
n
d
itio
n
r
ath
er
th
a
n
in
n
e
u
tr
al
co
n
d
itio
n
(
p
=
0
.
0
1
1
)
,
p
o
s
itiv
e
co
n
d
itio
n
(
p
=
0
.
0
3
7
)
,
an
d
n
e
g
ati
v
e
co
n
d
itio
n
.
I
t
m
ea
n
t
th
at
p
r
o
v
i
d
in
g
t
h
e
tr
ea
t
m
e
n
t
h
ad
s
u
cc
es
s
f
u
ll
y
c
h
a
n
g
ed
t
h
e
co
n
d
itio
n
o
f
th
e
s
u
b
j
ec
t
f
r
o
m
th
e
b
asel
in
e
co
n
d
itio
n
b
ased
o
n
t
h
e
r
es
u
lt
o
f
th
e
P
AN
AS
s
ca
le.
Descr
ip
ti
v
el
y
,
th
e
c
o
n
d
itio
n
o
f
p
o
s
iti
v
e
af
f
ec
tio
n
tr
ea
t
m
e
n
t
s
h
o
w
ed
h
ig
h
er
m
ea
n
(
3
.
2
8
4
)
th
an
t
h
at
in
th
e
n
e
u
tr
al
co
n
d
itio
n
(
m
ea
n
=
3
.
2
2
9
)
an
d
n
eg
at
iv
e
co
n
d
itio
n
(
m
ea
n
=
3
.
2
3
9
)
.
T
h
e
d
if
f
er
e
n
ce
w
as
n
o
t
s
tatis
ticall
y
s
i
g
n
i
f
ican
t
(
p
>
0
.
0
5
)
,
w
h
ic
h
m
ea
n
t
th
at
g
i
v
i
n
g
t
h
e
tr
ea
t
m
e
n
t
w
as
i
n
ad
eq
u
atel
y
e
f
f
ec
ti
v
e
in
in
d
u
c
in
g
t
h
e
v
ale
n
ce
o
f
d
if
f
er
en
t
k
i
n
d
s
o
f
af
f
ec
tio
n
.
O
n
th
e
P
A
N
AS
s
u
b
-
s
ca
le
o
f
n
eg
ati
v
e
a
f
f
ec
t
io
n
,
s
i
g
n
if
ican
t
d
i
f
f
er
en
ce
s
o
cc
u
r
r
ed
in
n
eg
a
tiv
e
co
n
d
itio
n
s
r
ath
e
r
th
an
i
n
p
o
s
iti
v
e
co
n
d
itio
n
(
p
=
0
.
0
0
4
;
p
<
0
.
0
1
)
an
d
n
eu
tr
al
co
n
d
itio
n
(
p
=
0
.
0
0
2
;
p
<0
.
0
1
)
.
I
t
in
d
icate
d
th
at
b
ased
o
n
th
e
P
A
N
A
S
s
ca
le,
t
h
e
p
r
o
v
is
io
n
o
f
n
eg
at
iv
e
a
f
f
ec
tio
n
tr
ea
t
m
e
n
t
h
ad
s
u
cc
es
s
f
u
ll
y
i
n
d
u
ce
d
n
eg
ati
v
e
af
f
ec
tio
n
,
r
elativ
e
to
th
e
o
th
er
t
w
o
co
n
d
itio
n
s
.
Ne
g
ati
v
e
tr
ea
t
m
e
n
t
co
n
d
itio
n
d
escr
ip
tiv
el
y
in
cr
ea
s
ed
n
e
g
ativ
e
af
f
ec
tio
n
r
at
h
er
t
h
an
th
e
b
as
elin
e
co
n
d
it
io
n
(
m
ea
n
d
if
f
er
en
ce
=
-
0
.
2
2
2
)
alth
o
u
g
h
it
w
a
s
n
o
t
s
tati
s
ticall
y
si
g
n
i
f
ica
n
t.
T
h
e
r
esear
ch
er
s
c
o
n
clu
d
ed
th
a
t
th
e
p
r
o
v
is
io
n
o
f
af
f
ec
tio
n
i
n
d
u
ctio
n
h
ad
s
u
cc
e
s
s
f
u
l
l
y
c
h
a
n
g
ed
t
h
e
p
o
s
itiv
e
a
f
f
ec
t
io
n
co
n
d
itio
n
f
r
o
m
th
e
b
asel
in
e
al
th
o
u
g
h
it
was
n
o
t
y
e
t
af
f
ec
ti
v
e
to
d
if
f
er
e
n
tiate
it
f
r
o
m
o
t
h
er
tr
ea
t
m
e
n
t
co
n
d
it
io
n
.
Me
a
n
wh
ile,
t
h
e
r
e
s
u
l
t
o
f
t
h
e
n
e
g
at
iv
e
a
f
f
ec
tio
n
s
u
b
-
s
ca
le
s
u
g
g
ested
th
a
t
n
eg
a
tiv
e
tr
ea
t
m
e
n
t
co
n
d
itio
n
co
u
ld
i
n
d
u
ce
n
e
g
ati
v
e
af
f
ec
tio
n
r
elat
iv
e
to
o
th
er
tr
ea
t
m
e
n
t
co
n
d
i
tio
n
s
.
T
h
er
e
w
er
e
p
o
s
s
ib
le
m
ea
s
u
r
e
m
e
n
t
er
r
o
r
s
ca
u
s
ed
b
y
t
h
e
p
o
s
itiv
e
a
f
f
ec
ti
o
n
s
u
b
-
s
ca
le
o
f
P
A
N
A
S
s
ca
l
e
s
in
ce
s
o
m
e
ite
m
s
h
ad
a
r
elativ
e
l
y
lo
w
in
ter
-
co
r
r
elatio
n
a
m
o
n
g
th
e
m
.
Fu
r
t
h
er
m
o
r
e,
t
h
e
p
r
o
ce
s
s
o
f
clas
s
i
f
y
i
n
g
th
e
GS
R
d
ata
to
s
ee
th
e
e
m
o
tio
n
al
s
tatu
s
o
f
t
h
e
r
esp
o
n
d
en
ts
w
ill b
e
d
is
c
u
s
s
ed
in
th
e
n
ex
t c
h
ap
ter
.
3
.
2
.
Cla
s
s
if
ica
t
io
n o
f
G
RS d
a
t
a
T
h
e
d
ata
r
esu
lted
b
y
th
e
G
S
R
w
er
e
ca
teg
o
r
ized
in
to
th
r
e
e,
n
a
m
el
y
p
o
s
iti
v
e,
n
e
u
tr
al
an
d
n
eg
at
iv
e
ac
co
r
d
in
g
to
th
e
co
n
d
itio
n
in
ti
m
e
o
f
d
ata
co
llectio
n
.
T
h
e
r
esu
lt
o
f
th
e
d
ata
ca
te
g
o
r
y
w
as
s
till
i
n
th
e
f
o
r
m
o
f
ti
m
e
s
er
ie
s
.
Fo
r
th
e
s
ak
e
o
f
SVM
alg
o
r
it
h
m
tr
ai
n
i
n
g
,
t
h
e
d
ata
w
o
u
ld
b
e
s
ep
ar
ated
b
y
class
o
r
cu
t
b
y
th
e
ca
teg
o
r
y
.
E
x
a
m
p
les o
f
t
h
e
d
at
a
ca
teg
o
r
izatio
n
ca
n
b
e
s
ee
n
in
Fig
u
r
e
4
,
Fig
u
r
e
5
an
d
Fi
g
u
r
e
6
.
T
i
m
e
(
F
r
e
q
u
e
n
c
y
)
S
k
i
n
r
e
s
i
s
t
a
n
c
e
Fig
u
r
e
4
.
E
x
a
m
p
le
o
f
p
o
s
iti
v
e
d
ata
S
k
i
n
r
e
s
i
s
t
a
n
c
e
T
i
m
e
(
F
r
e
q
u
e
n
c
y
)
Fig
u
r
e
5
. E
x
a
m
p
le
o
f
n
eu
tr
al
d
ata
T
i
m
e
(
F
r
e
q
u
e
n
c
y
)
S
k
i
n
r
e
s
i
s
t
a
n
c
e
Fig
u
r
e
6
.
E
x
a
m
p
le
o
f
n
eg
a
tiv
e
d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
5
,
Octo
b
er
2
0
1
8
:
4
0
0
4
–
4
0
1
4
4010
3
.
3
.
P
re
pro
ce
s
s
ing
T
h
er
e
ar
e
th
r
ee
d
ata
p
r
ep
r
o
ce
s
s
in
g
p
er
f
o
r
m
ed
in
th
is
r
esear
ch
,
i.e
.
,
Ag
g
r
eg
atio
n
,
No
r
m
a
lizatio
n
/Feat
u
r
e
Scali
n
g
,
L
a
g
g
i
n
g
,
a
n
d
L
ab
ell
in
g
.
D
ata
ag
g
r
eg
atio
n
w
as
d
o
n
e
b
y
ch
an
g
i
n
g
th
e
ti
m
e
u
n
i
t
f
r
o
m
f
r
eq
u
en
c
y
i
n
to
s
ec
o
n
d
.
I
n
d
ata
m
in
i
n
g
,
ag
g
r
eg
ate
d
ata
is
u
s
e
f
u
l
a
n
d
is
ai
m
ed
to
in
cr
ea
s
e
t
h
e
s
ig
n
al/
n
o
is
e
r
atio
co
m
m
o
n
l
y
,
esp
ec
iall
y
o
n
th
e
te
m
p
o
r
al
d
ata
p
r
o
ce
s
s
in
g
.
T
h
e
r
esu
lt
o
f
th
e
d
ata
a
g
g
r
eg
at
io
n
ca
n
b
e
s
ee
n
in
Fi
g
u
r
e
7
.
T
h
e
r
esu
lt
s
h
o
w
ed
t
h
at
t
h
e
d
ata
s
t
ill
h
a
v
e
t
h
e
s
a
m
e
p
atter
n
s
w
i
t
h
t
h
o
s
e
b
ef
o
r
e
th
e
ag
g
r
e
g
atio
n
.
No
r
m
al
izatio
n
is
a
r
escalin
g
o
f
th
e
d
ata
f
r
o
m
t
h
e
o
r
ig
in
al
r
a
n
g
e
s
o
th
at
all
v
alu
es
ar
e
w
ith
in
t
h
e
r
an
g
e
o
f
0
an
d
1
.
No
r
m
a
lizatio
n
ca
n
b
e
u
s
ef
u
l a
n
d
ev
e
n
r
eq
u
ir
ed
i
n
s
o
m
e
m
ac
h
in
e
lear
n
i
n
g
al
g
o
r
ith
m
s
w
h
en
y
o
u
r
t
i
m
e
s
er
ies
d
ata
h
as
in
p
u
t
v
alu
e
s
w
it
h
d
i
f
f
er
in
g
s
ca
les.
I
t
m
a
y
b
e
n
ee
d
ed
f
o
r
an
y
cla
s
s
i
f
icat
i
o
n
alg
o
r
it
h
m
s
w
h
ic
h
u
s
e
d
is
tan
ce
a
s
a
f
o
u
n
d
atio
n
o
f
d
ata
p
r
o
ce
s
s
i
n
g
.
T
h
e
r
es
u
lt
o
f
d
ata
n
o
r
m
a
lizatio
n
in
th
e
r
esear
ch
ca
n
b
e
s
ee
n
in
Fi
g
u
r
e
8
.
T
h
e
last
p
r
ep
r
o
c
ess
i
n
g
i
s
L
ag
g
i
n
g
a
n
d
L
ab
ell
in
g
.
L
a
g
g
in
g
o
n
d
ata
f
u
n
ctio
n
s
i
s
p
r
ep
ar
in
g
an
d
f
r
a
m
i
n
g
th
e
t
i
m
e
s
er
ies d
ata.
E
x
a
m
p
le
o
f
lag
g
i
n
g
a
n
d
lab
elin
g
o
n
d
ata
w
ith
f
i
v
e
la
g
s
ca
n
b
e
s
ee
n
i
n
T
ab
le
4
.
T
ab
le
4
.
E
x
am
p
le
5
r
o
w
s
o
f
D
ata
L
a
g
g
i
n
g
an
d
L
ab
elin
g
l
a
g
.
1
l
a
g
.
2
l
a
g
.
3
l
a
g
.
4
l
a
g
.
5
l
a
b
e
l
0
.
1
0
9
8
2
7
0
.
2
1
6
1
4
9
0
.
3
3
4
7
3
8
0
.
5
3
9
2
0
3
0
.
6
1
3
3
9
5
p
o
si
t
i
v
e
0
.
2
1
6
1
4
9
0
.
3
3
4
7
3
8
0
.
5
3
9
2
0
3
0
.
6
1
3
3
9
5
0
.
9
2
9
3
1
4
p
o
si
t
i
v
e
0
.
3
3
4
7
3
8
0
.
5
3
9
2
0
3
0
.
6
1
3
3
9
5
0
.
9
2
9
3
1
4
1
p
o
si
t
i
v
e
0
.
5
3
9
2
0
3
0
.
6
1
3
3
9
5
0
.
9
2
9
3
1
4
1
0
.
8
1
2
8
8
9
p
o
si
t
i
v
e
0
.
6
1
3
3
9
5
0
.
9
2
9
3
1
4
1
0
.
8
1
2
8
8
9
0
.
7
1
7
2
5
4
p
o
si
t
i
v
e
3
.
4
.
M
o
del a
nd
v
a
lid
a
t
io
n
I
n
t
h
is
r
e
s
ea
r
ch
,
t
h
e
p
r
o
ce
s
s
ed
d
ata
w
er
e
clas
s
i
f
ied
w
it
h
d
i
f
f
er
en
t
k
in
d
s
o
f
lag
s
a
n
d
k
er
n
els
to
s
ee
t
h
e
co
m
p
ar
is
o
n
o
f
ac
c
u
r
ac
y
r
ate
b
et
w
ee
n
th
e
k
er
n
e
ls
a
n
d
d
if
f
e
r
en
t
n
u
m
b
er
s
o
f
la
g
s
.
T
h
e
d
ata
w
er
e
clas
s
i
f
ied
b
y
u
s
i
n
g
a
lib
r
ar
y
"
e1
0
7
1
"
in
lan
g
u
a
g
e
R
.
Fo
r
th
e
tr
ai
n
in
g
,
r
an
d
o
m
s
a
m
p
li
n
g
a
s
m
u
ch
a
s
7
0
%
w
a
s
u
s
ed
an
d
th
e
v
alid
atio
n
u
s
ed
t
h
e
r
est
3
0
%
o
f
th
e
d
ata.
T
h
e
class
if
icati
o
n
s
tar
ted
w
i
th
t
h
e
5
to
4
1
lag
s
.
T
h
e
r
esu
lt
o
f
ac
cu
r
ac
y
co
m
p
ar
is
o
n
in
t
h
e
cl
ass
i
f
icatio
n
m
o
d
el
ca
n
b
e
s
ee
n
in
Fi
g
u
r
e
9
.
N
e
g
a
t
i
v
e
P
o
s
i
t
i
v
e
N
e
u
t
r
a
l
Fig
u
r
e
9
.
R
OC
g
r
ap
h
T
i
m
e
(
s
e
c
o
n
d
s
)
S
k
i
n
r
e
s
i
s
t
a
n
c
e
Fig
u
r
e
7
.
E
x
a
m
p
le
o
f
p
o
s
iti
v
e
ag
g
r
e
g
atio
n
T
i
m
e
(
s
e
c
o
n
d
s
)
S
k
i
n
r
e
s
i
s
t
a
n
c
e
Fig
u
r
e
8
.
E
x
a
m
p
le
o
f
n
o
r
m
ali
za
tio
n
o
f
p
o
s
iti
v
e
d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Ga
lva
n
ic
S
kin
R
esp
o
n
s
e
Da
ta
C
la
s
s
i
fica
tio
n
fo
r
E
mo
tio
n
De
tectio
n
(
Djo
ko
B
u
d
iya
n
t
o
S
ety
o
h
a
d
i)
4011
I
t
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
9
t
h
at
th
e
ac
c
u
r
ac
y
lev
e
l
te
n
d
s
to
i
n
cr
ea
s
e
alo
n
g
w
it
h
t
h
e
i
n
cr
ea
s
i
n
g
n
u
m
b
e
r
o
f
lag
s
.
I
t
is
also
n
o
ticed
t
h
at
th
e
R
B
F
k
er
n
el
s
s
u
g
g
e
s
ted
th
e
b
est
p
er
f
o
r
m
a
n
ce
co
m
p
ar
e
d
to
th
e
k
er
n
el
s
an
d
alg
o
r
ith
m
s
o
f
o
th
er
class
i
f
icati
o
n
s
.
A
d
etaile
d
r
esu
l
t
o
f
th
i
s
p
r
o
ce
s
s
is
s
h
o
w
n
in
T
ab
le
5
.
T
h
is
tab
le
s
h
o
w
s
t
h
at
SVM
m
o
d
el
u
s
i
n
g
R
B
F
k
er
n
e
ls
i
s
t
h
e
b
est,
w
h
ic
h
w
as
7
5
.
6
5
%.
T
h
e
g
r
ap
h
o
f
R
OC
cu
r
v
e
w
as
v
i
s
u
al
ized
th
e
class
i
f
icatio
n
r
es
u
lt
w
it
h
t
h
e
h
ig
h
e
s
t
ac
cu
r
ac
y
,
w
h
ich
w
as
7
5
.
6
5
%,
an
d
it
ca
n
b
e
s
ee
n
i
n
Fig
u
r
e
9
.
Fig
u
r
e
9
s
h
o
w
s
th
e
m
ea
n
o
f
t
h
e
A
U
C
i
s
0
.
8
0
1
9
.
I
t in
d
icate
d
th
at
th
e
r
esu
lt
o
f
t
h
e
e
m
o
tio
n
clas
s
i
f
icat
io
n
w
as
q
u
ite
g
o
o
d
as th
e
m
ea
n
o
f
th
e
A
U
C
w
a
s
clo
s
e
to
1
.
T
ab
le
5
.
T
h
e
P
e
r
ce
n
tag
e
A
cc
u
r
ac
y
C
o
m
p
ar
is
o
n
L
a
g
RBF
L
i
n
e
a
r
N
a
ï
v
e
B
a
y
e
s
K
N
N
24
0
.
5
2
2
0
0
.
4
3
8
9
0
.
4
6
2
7
0
.
4
9
1
5
25
0
.
5
5
8
9
0
.
4
2
8
5
0
.
4
6
6
0
0
.
4
8
7
5
26
0
.
5
9
3
2
0
.
4
5
0
0
0
.
4
8
5
8
0
.
5
1
2
2
27
0
.
6
0
6
8
0
.
4
3
7
1
0
.
4
7
3
0
0
.
5
3
2
9
28
0
.
6
1
5
7
0
.
4
1
6
1
0
.
4
2
8
8
0
.
5
2
6
5
29
0
.
5
8
9
6
0
.
4
2
8
5
0
.
4
4
2
1
0
.
5
3
2
8
30
0
.
6
2
6
2
0
.
4
1
0
1
0
.
4
9
2
7
0
.
5
0
7
2
31
0
.
6
0
7
3
0
.
3
7
9
5
0
.
4
7
9
0
0
.
5
4
1
8
32
0
.
6
0
8
0
0
.
4
0
0
5
0
.
4
3
7
5
0
.
5
0
5
6
33
0
.
6
2
2
3
0
.
4
0
5
5
0
.
4
9
5
3
0
.
5
2
9
4
34
0
.
5
9
3
9
0
.
4
0
9
5
0
.
4
3
6
8
0
.
5
8
0
2
35
0
.
7
1
1
0
0
.
3
8
7
8
0
.
4
4
1
0
0
.
4
7
9
0
36
0
.
6
5
3
8
0
.
3
8
0
3
0
.
4
5
2
9
0
.
5
2
1
3
37
0
.
6
5
2
0
0
.
4
3
6
2
0
.
4
8
5
2
0
.
5
3
4
3
38
0
.
6
3
2
2
0
.
2
8
1
6
0
.
4
3
1
0
0
.
4
7
1
2
39
0
.
7
0
8
3
0
.
4
5
8
3
0
.
4
9
3
0
0
.
5
0
6
9
40
0
.
7
5
6
5
0
.
4
2
6
0
0
.
5
4
7
8
0
.
5
3
9
1
41
0
.
7
5
2
9
0
.
3
4
1
1
0
.
4
9
4
1
0
.
5
7
6
4
4.
DIS
CU
SS
I
O
N
Fro
m
th
e
r
es
u
lt
s
o
b
tain
ed
,
it
ap
p
ea
r
ed
th
at
th
e
h
ig
h
er
th
e
l
ag
w
as,
th
e
h
i
g
h
er
t
h
e
ac
cu
r
a
c
y
w
o
u
ld
ten
d
to
b
e
in
th
e
R
B
F
k
er
n
el
an
d
it
w
a
s
li
n
ea
r
.
I
t
w
as
k
n
o
w
n
in
t
h
e
R
B
F
k
er
n
el
t
h
at
to
p
er
f
o
r
m
th
e
class
i
f
icatio
n
o
f
h
u
m
a
n
e
m
o
ti
o
n
al
s
tat
u
s
,
a
lar
g
e
GSR
p
atte
r
n
w
as
r
eq
u
ir
ed
,
w
h
ic
h
w
as
4
0
lag
s
o
r
4
0
s
ec
o
n
d
s
(
1
lag
co
n
s
is
t
s
o
f
1
-
s
ec
o
n
d
d
ata)
s
o
th
a
t
t
h
e
e
m
o
tio
n
al
s
tat
u
s
co
u
ld
b
e
w
ell
clas
s
i
f
ied
.
S
i
m
ilar
r
e
s
u
lt
s
w
er
e
also
en
co
u
n
ter
ed
b
y
Gr
i
m
es
a
n
d
L
i
in
th
eir
p
r
ev
io
u
s
s
t
u
d
ies
.
T
h
ey
o
b
tai
n
ed
ac
cu
r
ac
y
th
at
ten
d
ed
to
in
cr
ea
s
e
alo
n
g
w
i
th
th
e
in
cr
ea
s
in
g
n
u
m
b
er
o
f
th
e
la
g
s
th
at
w
er
e
u
s
ed
.
Ho
w
e
v
er
,
L
i
ex
p
er
ie
n
ce
d
a
d
ec
r
ea
s
e
in
ac
c
u
r
ac
y
an
d
ar
g
u
ed
t
h
at
th
e
u
s
e
o
f
lar
g
e
la
g
w
o
u
ld
ca
u
s
e
th
e
co
m
p
u
tin
g
p
r
o
ce
s
s
to
b
ec
o
m
e
lar
g
er
an
d
n
o
t
all
d
ata
s
ets
w
o
u
ld
b
en
e
f
it
a
s
t
h
e
n
u
m
b
er
o
f
lag
s
u
s
ed
[
3
0
]
,
[
3
1
]
.
I
n
h
is
r
esear
ch
,
W
id
o
d
o
ar
g
u
ed
t
h
at
d
eter
m
i
n
in
g
t
h
e
n
u
m
b
er
o
f
lag
w
a
s
an
es
s
en
t
i
al
is
s
u
e
s
i
n
ce
to
o
lar
g
e
lag
s
c
o
u
ld
ca
r
r
y
ir
r
elev
a
n
t
i
n
f
o
r
m
at
io
n
w
h
ile
t
o
o
s
m
all
lag
s
m
i
g
h
t
d
is
ca
r
d
r
elev
a
n
t
in
f
o
r
m
atio
n
[
3
2
]
,
[
3
3
]
.
I
t
w
as
al
s
o
m
en
t
io
n
ed
b
y
L
i
u
in
h
er
/h
i
s
r
esear
ch
.
Sh
e/H
e
s
aid
th
at
t
h
e
u
s
e
o
f
to
o
lar
g
e
l
ag
s
co
u
ld
d
is
r
u
p
t
th
e
clas
s
if
ic
atio
n
p
r
o
ce
s
s
b
ec
au
s
e
it
m
ad
e
th
e
d
ata
ir
r
elev
a
n
t
[
2
5
]
.
W
id
o
d
o
'
s
an
d
L
iu
's
o
p
in
io
n
ca
n
b
e
u
s
ed
to
ex
p
lain
t
h
e
in
cid
e
n
ce
ex
p
er
ien
ce
d
b
y
L
i,
w
h
er
e
ac
cu
r
ac
y
w
o
u
ld
i
n
cr
ea
s
e
alo
n
g
w
it
h
i
n
c
r
ea
s
in
g
t
h
e
n
u
m
b
er
o
f
la
g
s
b
u
t
w
o
u
ld
d
ec
r
ea
s
e
a
f
ter
p
ass
i
n
g
a
ce
r
tai
n
n
u
m
b
er
o
f
lag
s
.
T
h
is
co
n
d
itio
n
i
s
d
if
f
e
r
en
t
f
r
o
m
th
e
o
p
in
io
n
g
iv
e
n
b
y
Gr
i
m
es
a
n
d
So
lo
v
e
y
.
T
h
e
y
ar
g
u
ed
t
h
at
lag
w
as
n
o
tab
le
w
h
e
n
th
e
cla
s
s
i
f
icatio
n
w
o
u
ld
b
e
o
p
er
ated
in
r
ea
l
-
tim
e
[
30
]
,
[3
4
]
.
T
h
u
s
,
th
e
lag
r
eq
u
ir
ed
to
f
o
r
m
t
h
e
r
elev
an
t d
ata
i
n
cla
s
s
i
f
y
in
g
h
u
m
an
e
m
o
tio
n
al
s
ta
tu
s
w
as 4
0
s
in
ce
it c
o
u
ld
g
e
n
er
ate
th
e
h
i
g
h
est ac
cu
r
ac
y
in
th
i
s
class
i
f
icatio
n
,
w
h
ic
h
w
as 7
5
.
6
5
%.
No
r
m
a
liz
atio
n
u
s
i
n
g
f
ea
t
u
r
e
s
ca
lin
g
m
et
h
o
d
also
d
ir
ec
tl
y
af
f
ec
ted
t
h
e
r
es
u
lt
s
o
f
clas
s
if
ica
tio
n
.
C
las
s
i
f
icatio
n
w
i
th
o
u
t
g
o
i
n
g
th
r
o
u
g
h
t
h
e
f
ea
tu
r
e
s
ca
li
n
g
p
r
o
ce
s
s
co
u
ld
o
n
l
y
ac
h
iev
e
ac
cu
r
ac
y
as
m
u
ch
a
s
6
0
.
8
7
%,
b
u
t
w
it
h
t
h
e
u
s
e
o
f
s
ca
li
n
g
f
ea
tu
r
e
t
h
e
ac
c
u
r
ac
y
co
u
ld
r
ea
ch
u
p
to
1
5
%
in
cr
ea
s
e,
a
m
o
u
n
tin
g
t
o
7
5
.
6
5
%
b
ec
au
s
e
th
e
p
r
o
ce
s
s
o
f
s
ca
li
n
g
f
ea
tu
r
e
m
ad
e
t
h
e
d
ata
o
n
ea
ch
r
esp
o
n
d
en
t
eq
u
iv
ale
n
t.
A
cc
o
r
d
in
g
l
y
,
th
e
class
i
f
icatio
n
p
r
o
ce
s
s
w
a
s
n
o
t
d
is
tu
r
b
ed
b
y
th
e
d
ata
r
an
g
e
t
h
at
w
as
to
o
lar
g
e
o
r
to
o
s
m
all
.
T
h
is
o
p
in
io
n
w
as
s
u
p
p
o
r
ted
b
y
Hs
u
w
h
o
s
tate
d
th
at
p
er
f
o
r
m
i
n
g
f
ea
tu
r
e
s
c
alin
g
b
ef
o
r
e
cla
s
s
i
f
icat
io
n
u
s
in
g
t
h
e
S
VM
w
a
s
ess
e
n
tial
a
s
d
ata
w
it
h
to
o
lar
g
e
r
an
g
e
co
u
ld
d
o
m
i
n
ate
d
ata
w
it
h
a
s
m
aller
r
an
g
e.
Als
o
,
f
e
atu
r
e
s
ca
li
n
g
p
r
o
ce
s
s
also
f
ac
ilit
ated
t
h
e
co
m
p
u
tat
io
n
p
r
o
ce
s
s
[
1
0
]
.
B
er
g
s
p
ec
if
icall
y
co
n
d
u
cted
a
s
t
u
d
y
o
n
co
m
p
ar
in
g
th
e
i
m
p
ac
t
s
o
f
v
ar
io
u
s
k
i
n
d
s
o
f
p
r
e
-
p
r
o
ce
s
s
in
g
o
n
b
io
lo
g
ical
d
ata.
Fro
m
th
e
r
esear
ch
,
it
co
u
ld
b
e
co
n
clu
d
ed
th
at
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
h
ad
b
ig
i
m
p
licatio
n
s
o
n
b
io
l
o
g
ical
d
ata,
esp
ec
ial
l
y
au
to
s
ca
lin
g
a
n
d
f
ea
t
u
r
e
s
ca
lin
g
.
P
r
ev
o
iu
s
r
es
u
lt
also
s
aid
th
at
t
h
e
f
ea
t
u
r
e
s
ca
l
i
n
g
p
r
o
ce
s
s
w
a
s
r
elate
d
to
b
io
lo
g
ical
d
ata
[
3
5
]
,
[
3
6
]
.
C
o
m
p
a
r
is
o
n
o
f
t
h
e
i
m
p
ac
t
s
o
f
n
o
r
m
aliz
a
tio
n
o
n
t
h
e
r
es
u
lts
o
f
th
e
clas
s
i
f
icatio
n
o
f
h
u
m
an
e
m
o
tio
n
al
s
tatu
s
ca
n
b
e
s
ee
n
i
n
T
ab
le
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
5
,
Octo
b
er
2
0
1
8
:
4
0
0
4
–
4
0
1
4
4012
T
ab
le
6.
E
f
f
ec
t o
f
N
o
r
m
aliz
at
i
o
n
to
an
A
cc
u
r
ac
y
N
o
r
mal
i
z
a
t
i
o
n
A
c
c
u
r
a
c
y
W
i
t
h
7
5
.
6
5
W
i
t
h
o
u
t
6
0
.
8
7
I
n
ad
d
itio
n
to
d
ata
p
r
o
ce
s
s
in
g
,
th
e
u
s
e
o
f
t
h
e
k
er
n
el
o
n
S
VM
also
g
e
n
er
ated
d
if
f
er
en
t
r
esu
lt
s
.
I
n
co
m
p
ar
is
o
n
,
th
e
R
B
F k
er
n
el
c
o
u
ld
p
r
o
v
id
e
class
if
icatio
n
r
es
u
lts
w
i
th
a
n
ac
cu
r
ac
y
o
f
7
5
.
6
5
%,
w
h
ile
t
h
e
r
es
u
lts
o
f
ac
cu
r
ac
y
b
y
u
s
i
n
g
o
th
er
k
er
n
els
s
u
c
h
as
lin
ea
r
,
p
o
l
y
n
o
m
ial
a
n
d
s
ig
m
o
id
w
a
s
u
n
d
er
th
e
ac
cu
r
ac
y
le
v
e
l
w
h
ic
h
t
h
e
R
B
F
k
er
n
el
g
e
n
er
ated
.
C
o
m
p
ar
is
o
n
o
f
k
er
n
el
u
s
a
g
e
to
ac
c
u
r
ac
y
r
es
u
lt
o
f
t
h
e
c
l
ass
i
f
icatio
n
ca
n
b
e
s
ee
n
i
n
T
ab
le
7
.
C
lass
if
icat
io
n
r
esu
lt
b
y
u
s
i
n
g
R
B
F
w
as
al
s
o
v
alid
ated
b
y
u
s
in
g
k
Fo
ld
C
r
o
s
s
V
alid
atio
n
b
y
u
s
i
n
g
k
as
m
u
c
h
as
1
0
.
A
f
ter
d
o
in
g
te
n
ti
m
es
o
f
v
a
lid
atio
n
u
s
in
g
th
e
m
et
h
o
d
,
th
e
ac
cu
r
ac
y
v
alu
e
o
b
tai
n
ed
w
as
7
3
%
at
th
e
m
i
n
i
m
u
m
an
d
7
8
%
at
th
e
m
a
x
i
m
u
m
.
T
h
e
r
esu
lt
s
h
o
w
ed
th
at
t
h
e
d
ata
u
s
ed
i
n
th
e
cla
s
s
i
f
icatio
n
p
r
o
ce
s
s
w
as
n
o
t
lin
ea
r
an
d
th
e
R
B
F
k
er
n
el
w
a
s
ab
le
to
g
e
n
er
ate
th
e
b
est
ac
cu
r
ac
y
i
n
th
e
cl
ass
i
f
icatio
n
o
f
ti
m
e
s
er
ies
d
ata
u
s
i
n
g
s
lid
in
g
w
i
n
d
o
w
s
tec
h
n
iq
u
e.
T
h
is
r
esu
lt
i
s
in
lin
e
w
it
h
t
h
e
o
p
in
io
n
s
tat
ed
b
y
H
s
u
,
w
h
ich
s
aid
th
at
t
h
e
R
B
F k
er
n
el
h
ad
o
f
ten
b
ee
n
u
s
ed
to
class
if
y
n
o
n
li
n
ea
r
d
ata
in
a
b
ig
g
er
d
i
m
e
n
s
io
n
al
s
p
ac
e
[
1
0
]
.
T
ab
le
7.
C
o
m
p
ar
is
o
n
o
f
Data
A
cc
u
r
ac
y
to
d
if
f
er
en
t K
er
n
el
s
K
e
r
n
e
l
A
c
c
u
r
a
c
y
RBF
7
5
.
6
5
P
o
l
y
n
o
mi
a
l
5
3
.
0
4
L
i
n
e
a
r
4
1
.
7
4
S
i
g
mo
i
d
2
8
.
7
5.
CO
NCLU
SI
O
N
W
e
h
av
e
d
ev
elo
p
ed
a
m
o
d
el
o
f
a
s
y
s
te
m
f
o
r
d
etec
tin
g
e
m
o
ti
o
n
f
r
o
m
g
al
v
an
ic
s
k
in
r
e
s
p
o
n
d
d
ata.
Ou
r
r
esear
ch
ai
m
ed
to
d
ev
elo
p
a
m
o
d
el
w
h
ic
h
ca
n
u
s
e
s
e
n
s
o
r
in
f
o
r
m
atio
n
to
d
etec
t
th
e
e
m
o
tio
n
s
tatu
s
o
f
th
e
r
esp
o
n
d
en
ts
.
P
A
N
AS
s
ca
le
i
s
ap
p
lied
to
v
alid
ate
th
e
d
ata
s
et
f
o
r
th
e
tr
ain
i
n
g
p
r
o
ce
s
s
.
On
ce
v
er
if
ied
,
a
d
ataset
is
u
s
ed
f
o
r
tr
ain
in
g
S
VM
.
T
h
e
ex
p
er
i
m
en
ts
o
n
e
m
o
tio
n
d
eter
m
i
n
atio
n
f
r
o
m
au
d
io
-
v
is
u
al
i
n
d
u
ct
io
n
to
e
m
o
tio
n
al
d
etec
tio
n
s
h
o
w
ed
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
s
y
s
te
m
.
T
h
e
r
es
u
lt
i
n
d
icate
s
th
at
th
e
m
o
d
el
i
s
w
el
l
p
er
f
o
r
m
ed
s
i
n
ce
t
h
e
ac
cu
r
ac
y
is
ab
o
u
t
7
5
.
6
5
%
af
ter
s
o
m
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
i
s
ap
p
lied
.
Mo
r
e
ex
p
lo
r
atio
n
is
also
r
eq
u
ir
ed
to
d
eter
m
in
e
t
h
e
la
g
o
f
th
e
d
ata
d
u
e
to
th
e
v
ar
iab
ilit
y
in
t
h
e
r
esp
o
n
d
en
t
s
.
ACK
NO
WL
E
D
G
M
E
NT
S
I
w
o
u
ld
li
k
e
to
th
a
n
k
Un
i
v
er
s
itas
A
t
m
a
J
a
y
a
Yo
g
y
ak
ar
ta,
I
n
d
o
n
esia
f
o
r
th
e
f
in
a
n
cial
s
u
p
p
o
r
t
to
o
u
r
r
esear
ch
p
r
o
j
ec
t.
I
w
o
u
ld
als
o
lik
e
to
ex
p
r
ess
m
y
g
r
atit
u
d
e
to
all
m
e
m
b
er
s
o
f
C
o
g
n
i
tiv
e
an
d
A
f
f
ec
ti
v
e
Neu
r
o
s
cie
n
ce
R
esear
c
h
Gr
o
u
p
,
P
s
y
ch
o
lo
g
y
Dep
ar
t
m
en
t,
Gad
j
ah
Ma
d
a
Un
iv
er
s
it
y
f
o
r
p
r
o
v
id
in
g
ti
m
e
to
co
n
d
u
ct
an
e
x
p
er
i
m
e
n
tal
p
r
o
ce
s
s
o
f
o
u
r
r
esear
ch
.
RE
F
E
R
E
NC
E
S
[1
]
N.
S
e
b
e
,
e
t
a
l.
,
“
M
u
l
ti
m
o
d
a
l
E
m
o
ti
o
n
Re
c
o
g
n
it
i
o
n
”
,
H
a
n
d
b
o
o
k
o
f
P
a
tt
e
rn
Rec
o
g
n
it
i
o
n
a
n
d
C
o
mp
u
ter
Vi
si
o
n
,
v
o
l.
4
,
p
p
.
3
8
7
-
4
1
9
,
2
0
0
5
.
[2
]
B.
M
e
u
lem
a
n
a
n
d
K.
R.
S
c
h
e
re
r,
“O
n
li
n
e
a
r
a
p
p
ra
isa
l
m
o
d
e
li
n
g
:
An
a
p
p
li
c
a
ti
o
n
o
f
m
a
c
h
in
e
lea
rn
in
g
to
th
e
stu
d
y
o
f
e
m
o
ti
o
n
p
ro
d
u
c
ti
o
n
”
,
IEE
E
T
ra
n
sa
c
ti
o
n
s o
n
Af
fec
ti
v
e
Co
m
p
u
ti
n
g
,
v
o
l
.
4
,
n
o
.
4
,
p
p
.
3
9
8
-
4
1
1
,
2
0
1
3
.
[3
]
E.
H.
Ja
n
g
,
e
t
a
l
.
,
“
Em
o
ti
o
n
C
la
ss
if
ic
a
ti
o
n
b
a
se
d
o
n
Bi
o
-
sig
n
a
ls
Em
o
ti
o
n
Re
c
o
g
n
it
i
o
n
u
si
n
g
M
a
c
h
in
e
L
e
a
rn
in
g
A
l
g
o
rit
h
m
s
”
,
v
o
l.
3
,
p
p
.
1
3
7
3
-
1
3
7
6
,
2
0
1
4
.
[4
]
K.
A
n
sa
ri
-
A
sl,
e
t
a
l.
,
“
Ch
a
n
n
e
l
S
e
lec
ti
o
n
M
e
th
o
d
f
o
r
Eeg
Cl
a
ss
if
i
c
a
ti
o
n
i
n
Em
o
ti
o
n
A
ss
e
ss
m
e
n
t
b
a
se
d
o
n
S
y
n
c
h
ro
n
iza
ti
o
n
L
ik
e
li
h
o
o
d
”
,
Eu
r
o
p
e
a
n
S
ig
n
a
l
Pro
c
e
ss
in
g
C
o
n
fer
e
n
c
e
(
EUS
IPCO)
,
2
0
0
7
.
[5
]
Y
.
L
iu
,
e
t
a
l.
,
“
Re
a
l
-
ti
m
e
EE
G
-
b
a
se
d
Hu
m
a
n
E
m
o
ti
o
n
Re
c
o
g
n
it
i
o
n
a
n
d
V
isu
a
li
z
a
ti
o
n
”
,
CW
'
1
0
Pro
c
e
e
d
in
g
s
o
f
th
e
2
0
1
0
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Cy
b
e
rwo
rld
s
,
p
p
.
2
6
2
-
2
6
9
,
2
0
1
0
.
[6
]
F
.
Rin
g
e
v
a
l,
e
t
a
l.
,
“
P
re
d
icti
o
n
o
f
A
s
y
n
c
h
ro
n
o
u
s Dim
e
n
sio
n
a
l
Em
o
ti
o
n
Ra
ti
n
g
s f
ro
m
A
u
d
io
v
isu
a
l
a
n
d
P
h
y
sio
lo
g
ica
l
Da
ta”
,
Pa
tt
e
rn
Rec
o
g
n
it
i
o
n
L
e
tt
e
r
s
,
v
o
l.
6
6
,
p
p
.
2
2
-
3
0
,
2
0
1
5
.
[7
]
X
.
W
u
,
e
t
a
l
.
,
“
T
o
p
1
0
a
lg
o
rit
h
m
s
in
d
a
ta
m
in
in
g
”
,
Kn
o
wled
g
e
a
n
d
in
f
o
rm
a
ti
o
n
sy
ste
ms
,
v
o
l
.
1
4
,
n
o
.
1
,
p
p
.
1
-
37
,
2
0
0
8
.
[8
]
H.
Y.
Hu
a
n
g
a
n
d
C.
J.
L
in
,
“
L
in
e
a
r
a
n
d
Ke
rn
e
l
Clas
si
f
ica
ti
o
n
:
W
h
e
n
to
u
se
w
h
ich
?
”
,
Pro
c
e
e
d
in
g
s o
f
th
e
2
0
1
6
S
IAM
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
D
a
ta
M
in
in
g
,
S
o
c
iety
fo
r
In
d
u
stria
l
a
n
d
Ap
p
li
e
d
M
a
th
e
ma
ti
c
,
p
p
.
2
1
6
-
2
2
4
,
2
0
1
6
.
[9
]
C.
Co
rtes
a
n
d
V
.
V
a
p
n
ik
,
“
S
u
p
p
o
rt
-
V
e
c
to
r
Ne
tw
o
rk
s,
M
a
c
h
in
e
Lea
rn
in
g
”
,
Klu
w
e
r
A
c
a
d
e
m
ic
P
u
b
l
ish
e
rs,
Bo
sto
n
,
p
p
.
2
7
3
-
2
9
7
,
1
9
9
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Ga
lva
n
ic
S
kin
R
esp
o
n
s
e
Da
ta
C
la
s
s
i
fica
tio
n
fo
r
E
mo
tio
n
De
tectio
n
(
Djo
ko
B
u
d
iya
n
t
o
S
ety
o
h
a
d
i)
4013
[1
0
]
C.
W
.
Hs
u
,
e
t
a
l.
,
“
A
P
ra
c
ti
c
a
l
G
u
id
e
t
o
S
u
p
p
o
rt
V
e
c
to
r
C
las
sif
ica
ti
o
n
”
,
2
0
1
6
.
[1
1
]
S
h
imm
e
r,
“
M
e
a
su
rin
g
E
m
o
ti
o
n
:
Re
a
c
ti
o
n
s
t
o
M
e
d
ia
”
,
Du
b
li
n
,
Ire
l
a
n
d
,
2
0
1
5
.
[1
2
]
M.
L
iu
,
e
t
a
l
.,
“
Hu
m
a
n
E
m
o
t
io
n
Re
c
o
g
n
it
io
n
b
a
se
d
o
n
G
a
lv
a
n
ic
S
k
in
Re
sp
o
n
se
S
ig
n
a
l
F
e
a
tu
re
S
e
lec
ti
o
n
a
n
d
S
V
M
”
,
S
ma
rt
Cit
y
a
n
d
S
y
ste
ms
E
n
g
i
n
e
e
rin
g
(
ICS
CS
E)
,
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
,
p
p
.
1
5
7
-
1
6
0
,
2
0
1
6
.
[1
3
]
K.
H.
Kim
,
e
t
a
l.
.
,
“
Em
o
ti
o
n
Re
c
o
g
n
it
io
n
S
y
ste
m
u
sin
g
sh
o
rt
-
term
M
o
n
i
to
r
in
g
o
f
P
h
y
sio
lo
g
ica
l
S
ig
n
a
ls
”
,
M
e
d
ica
l
a
n
d
Bi
o
lo
g
ica
l
En
g
in
e
e
rin
g
a
n
d
C
o
mp
u
t
in
g
,
v
o
l
.
4
2
,
n
o
.
3
,
p
p
.
4
1
9
-
4
2
7
,
2
0
0
4
.
[1
4
]
H.
Ku
rn
iaw
a
n
,
e
t
a
l
.,
“
S
tres
s
De
tec
ti
o
n
f
ro
m
S
p
e
e
c
h
a
n
d
G
a
l
v
a
n
ic
sk
in
re
sp
o
n
s
e
S
ig
n
a
ls
”
,
Co
mp
u
ter
-
B
a
se
d
M
e
d
ica
l
S
y
ste
ms
(
CBM
S
),
IEE
E
2
6
th
I
n
ter
n
a
ti
o
n
a
l
S
y
mp
o
siu
m
on
,
p
p
.
2
0
9
-
214
,
2
0
1
3
.
[1
5
]
N.
No
u
r
b
a
k
h
sh
,
e
t
a
l
.,
“
Us
in
g
G
a
l
v
a
n
ic
S
k
in
Re
sp
o
n
se
f
o
r
Co
g
n
it
iv
e
L
o
a
d
M
e
a
su
re
m
e
n
t
in
A
rit
h
m
e
ti
c
a
n
d
Re
a
d
in
g
T
a
s
k
s
”
,
2
4
th
Au
stra
li
a
n
Co
mp
u
ter
H
u
ma
n
In
ter
a
c
ti
o
n
Co
n
fer
e
n
c
e
,
p
p
.
4
2
0
-
4
2
3
,
2
0
1
2
.
[1
6
]
P.
S
h
a
n
g
g
u
a
n
,
e
t
a
l
.,
“
T
h
e
Em
o
ti
o
n
Re
c
o
g
n
it
i
o
n
Ba
se
d
o
n
G
S
R
S
ig
n
a
l
b
y
Cu
rv
e
F
it
ti
n
g
”
,
J
.
In
fo
rm
a
ti
o
n
a
n
d
Co
mp
u
t
a
ti
o
n
a
l
S
c
ien
c
e
,
v
o
l
.
11
,
n
o
.
8
,
p
p
.
2
6
3
5
-
2
6
4
6
,
2
0
1
4
.
[1
7
]
C.
S
e
tz,
e
t
a
l
.,
“
Disc
rim
in
a
ti
n
g
S
tres
s
f
ro
m
Co
g
n
it
iv
e
lo
a
d
u
sin
g
a
W
e
a
r
a
b
le
ED
A
De
v
ice
”
,
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
In
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
y
i
n
Bi
o
me
d
icin
e
,
v
o
l
.
1
4
,
n
o
.
2
,
p
p
.
4
1
0
-
4
1
7
,
2
0
1
0
.
[1
8
]
R.
G
u
o
,
e
t
a
l.
,
“
P
e
rv
a
siv
e
a
n
d
Un
o
b
t
ru
siv
e
Em
o
ti
o
n
S
e
n
sin
g
f
o
r
Hu
m
a
n
M
e
n
tal
He
a
lt
h
”
,
Per
v
a
siv
e
He
a
lt
h
'
1
3
Pro
c
e
e
d
in
g
s
o
f
th
e
7
t
h
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Per
v
a
si
v
e
Co
mp
u
ti
n
g
T
e
c
h
n
o
lo
g
ies
fo
r
He
a
lt
h
c
a
re
,
p
p
.
4
3
6
-
4
3
9
,
2
0
1
3
.
[1
9
]
A
.
Na
k
a
so
n
e
,
e
t
a
l
.
,
“
Em
o
ti
o
n
Re
c
o
g
n
it
io
n
f
ro
m
E
lec
tr
o
m
y
o
g
r
a
p
h
y
a
n
d
S
k
in
C
o
n
d
u
c
tan
c
e
”
,
P
ro
c
.
o
f
th
e
5
t
h
In
ter
n
a
t
io
n
a
l
W
o
rk
sh
o
p
o
n
Bi
o
sig
n
a
l
I
n
ter
p
re
ta
t
io
n
,
p
p
.
2
1
9
-
2
2
2
,
2
0
0
5
.
[2
0
]
M
.
S
ti
k
ic,
e
t
a
l
.
,
“
EEG
-
b
a
se
d
Clas
sif
ic
a
ti
o
n
o
f
P
o
siti
v
e
a
n
d
N
e
g
a
ti
v
e
Aff
e
c
ti
v
e
S
tate
s
”
,
Bra
in
-
Co
m
p
u
ter
In
ter
fa
c
e
s
,
v
o
l
.
1
,
n
o
.
2
,
p
p
.
9
9
-
1
1
2
,
2
0
1
4
.
[2
1
]
Y.
L
u
,
e
t
a
l.
,
“
Co
m
b
in
i
n
g
Ey
e
M
o
v
e
m
e
n
ts
a
n
d
EE
G
to
En
h
a
n
c
e
Em
o
ti
o
n
Re
c
o
g
n
it
io
n
”
,
Pro
c
e
e
d
i
n
g
s o
f
th
e
T
we
n
ty
-
Fo
u
rt
h
In
ter
n
a
ti
o
n
a
l
J
o
in
t
Co
n
fer
e
n
c
e
o
n
Arti
fi
c
ia
l
In
telli
g
e
n
c
e
(
IJ
CAI
),
2
0
1
5
.
[2
2
]
M
.
V
.
V
il
lare
jo
,
e
t
a
l
.,
“
A
S
tres
s
S
e
n
so
r
b
a
se
d
o
n
G
a
lv
a
n
ic
S
k
in
R
e
sp
o
n
se
(G
S
R)
C
o
n
tro
ll
e
d
b
y
Zi
g
Be
e
”
,
S
e
n
so
rs
,
v
o
l
.
1
2
,
n
o
.
5
,
p
p
.
6
0
7
5
-
6
1
0
1
,
2
0
1
2
.
[2
3
]
K.
Kh
a
lf
a
ll
a
h
,
e
t
a
l.
,
“
No
n
i
n
v
a
siv
e
Ga
lv
a
n
ic
S
k
in
S
e
n
so
r
f
o
r
Earl
y
Dia
g
n
o
sis
o
f
S
u
d
o
m
o
to
r
D
y
s
f
u
n
c
ti
o
n
:
A
p
p
li
c
a
ti
o
n
t
o
Dia
b
e
tes
”
,
IEE
E
S
e
n
so
r J.
,
v
o
l.
1
2
,
pp.
4
5
6
-
4
6
3
,
2
0
1
0
.
[2
4
]
K
.
S
e
tz,
e
t
a
l.
,
“
T
o
w
a
rd
s
L
o
n
g
T
e
r
m
M
o
n
it
o
ri
n
g
o
f
El
e
c
t
ro
d
e
r
m
a
l
Ac
ti
v
it
y
in
Da
il
y
L
i
f
e
”
,
Pr
o
c
e
e
d
in
g
s
o
f
5
t
h
In
ter
n
a
t
io
n
a
l
W
o
rk
sh
o
p
o
n
Ub
i
q
u
it
o
u
s He
a
lt
h
a
n
d
W
e
ll
n
e
ss
,
C
o
p
e
n
h
a
g
e
n
,
De
n
m
a
rk
,
2
0
1
0
.
[2
5
]
D.
L
iu
a
n
d
M
.
Ulrich
,
“
L
isten
to
Yo
u
r
He
a
rt:
S
tres
s
P
re
d
ictio
n
u
s
in
g
Co
n
su
m
e
r
He
a
rt
Ra
t
e
S
e
n
so
rs
”
,
CS
2
2
9
M
a
c
h
in
e
L
e
a
rn
in
g
,
A
u
tu
m
n
2
0
1
3
.
[2
6
]
V
.
N.
V
a
p
n
ik
,
“
T
h
e
Na
tu
re
o
f
S
ta
ti
s
ti
c
a
l
L
e
a
rn
in
g
T
h
e
o
r
y
”
,
S
p
rin
g
e
r
-
V
e
rlag
Ne
w
Yo
rk
,
In
c
.
,
1
9
9
5
.
[2
7
]
C.
Ca
m
p
b
e
ll
a
n
d
Y.
Yi
n
g
,
“
L
e
a
rn
i
n
g
w
it
h
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
s
”
,
M
o
rg
a
n
&
Clay
p
o
o
l
P
u
b
l
ish
e
r
s
,
2
0
1
1
.
[2
8
]
J.
R.
Cra
wf
o
rd
a
n
d
J
.
D.
He
n
r
y
,
“
T
h
e
P
o
siti
v
e
a
n
d
Ne
g
a
ti
v
e
Aff
e
c
t
S
c
h
e
d
u
le
(
P
A
NA
S
):
Co
n
stru
c
t
v
a
li
d
it
y
,
m
e
a
su
re
m
e
n
t
p
ro
p
e
rti
e
s
a
n
d
n
o
r
m
a
ti
v
e
d
a
ta
in
a
lar
g
e
n
o
n
‐
c
li
n
ica
l
sa
m
p
le
”
,
Brit
ish
J
o
u
rn
a
l
o
f
C
li
n
ica
l
Psy
c
h
o
l
o
g
y
,
v
o
l
.
4
3
,
n
o
.
3
,
p
p
.
2
4
5
-
2
6
5
,
2
0
0
4
.
[2
9
]
S
.
B
.
G
u
n
a
w
a
n
,
“
De
te
k
si
S
tatu
s
Em
o
si
M
a
n
u
sia
De
n
g
a
n
A
l
g
o
rit
m
a
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
M
e
n
g
g
u
n
a
k
a
n
Da
ta
G
a
l
v
a
n
ic S
k
in
Re
sp
o
n
se
”
,
T
h
e
se
s,
Un
iv
e
rsitas
A
t
m
a
Ja
y
a
Yo
g
y
a
k
a
rta
,
2
0
1
7
.
[3
0
]
D.
G
ri
m
e
s,
e
t
a
l.
,
“
F
e
a
sib
il
it
y
a
n
d
P
ra
g
m
a
ti
c
s
o
f
Clas
sify
in
g
”
,
CHI
2
0
0
8
Pro
c
e
e
d
i
n
g
s:
C
o
g
n
it
i
o
n
,
Per
c
e
p
ti
o
n
,
a
n
d
M
e
mo
ry
,
2
0
0
8
.
[3
1
]
X
.
L
i
a
n
d
B.
M
a
rli
n
,
“
Clas
sif
ic
a
ti
o
n
o
f
S
p
a
rse
a
n
d
Irre
g
u
larl
y
S
a
m
p
led
T
i
m
e
S
e
ries
w
it
h
”
,
Pro
c
e
e
d
in
g
UAI
'
1
5
P
ro
c
e
e
d
in
g
s
o
f
t
h
e
T
h
irty
-
Fi
rs
t
C
o
n
fer
e
n
c
e
o
n
Un
c
e
rta
i
n
ty i
n
Arti
fi
c
ia
l
In
tell
ig
e
n
c
e
,
p
p
.
4
8
4
-
4
9
3
,
2
0
1
5
.
[3
2
]
I.
B.
W
id
o
d
o
a
n
d
B.
W
id
jaja
,
“
A
u
to
m
a
ti
c
L
a
g
S
e
le
c
ti
o
n
in
ti
m
e
s
e
ries
F
o
re
c
a
stin
g
u
sin
g
M
u
lt
i
p
le
Ke
rn
e
l
L
e
a
rn
in
g
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
M
a
c
h
i
n
e
L
e
a
r
n
in
g
a
n
d
Cy
b
e
rn
e
ti
c
s
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
9
5
-
1
1
0
,
2
0
1
6
.
[3
3
]
E.
T
.
S
o
lo
v
e
y
,
e
t
a
l.
,
“
Clas
si
fy
in
g
Driv
e
r
W
o
rk
lo
a
d
u
sin
g
P
h
y
sio
lo
g
ica
l
a
n
d
Driv
in
g
P
e
rf
o
r
m
a
n
c
e
Da
ta:
Tw
o
F
ield
S
tu
d
ies
”
,
Pro
c
e
e
d
in
g
CHI
'
1
4
Pr
o
c
e
e
d
in
g
s
o
f
th
e
S
IGCH
I
Co
n
fer
e
n
c
e
o
n
Hu
ma
n
Fa
c
to
rs
i
n
Co
m
p
u
ti
n
g
S
y
ste
ms
,
p
p
.
4
0
5
7
-
4
0
6
6
,
2
0
1
4
.
[3
4
]
A
.
Am
b
a
r
w
a
ri,
e
t
a
l.
,
“
Bio
m
e
tri
c
A
n
a
l
y
si
s
o
f
L
e
a
f
V
e
n
a
ti
o
n
De
n
sit
y
Ba
s
e
d
o
n
Dig
it
a
l
I
m
a
g
e
”
,
T
e
lec
o
mm
u
n
ic
a
ti
o
n
Co
mp
u
t
in
g
El
e
c
tro
n
ics
a
n
d
C
o
n
tr
o
l
,
v
ol
.
16
,
n
o
.
4
,
2
0
1
8
.
[3
5
]
R.
A
.
v
.
d
.
Be
rg
,
e
t
a
l.
,
“
Ce
n
terin
g
,
S
c
a
li
n
g
,
a
n
d
T
ra
n
sf
o
r
m
a
ti
o
n
s:
Im
p
ro
v
in
g
th
e
Bio
lo
g
ica
l
In
f
o
rm
a
ti
o
n
C
o
n
te
n
t
o
f
M
e
tab
o
l
o
m
ics
Da
ta
”
,
BM
C
G
e
n
o
m
ic
s
,
2
0
0
6
.
[3
6
]
K.
Da
i
m
i
a
n
d
S
.
Ba
n
it
a
a
n
,
“
Us
in
g
Da
ta
M
in
in
g
to
P
re
d
ict
P
o
ss
ib
l
e
f
u
tu
re
D
e
p
re
ss
io
n
c
a
s
e
s
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
P
u
b
li
c
He
a
lt
h
S
c
ien
c
e
(
IJ
PHS
)
,
v
o
l
.
3
,
n
o
.
4
,
p
p
.
2
3
1
-
2
4
0
,
2
0
1
4
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Djo
k
o
B
u
d
iy
a
n
to
S
e
ty
o
h
a
d
i
re
c
e
iv
e
d
th
e
B.
E.
d
e
g
re
e
in
E
lec
tri
c
a
l
En
g
in
e
e
rin
g
f
ro
m
Un
iv
e
r
sita
s
G
a
d
jah
M
a
d
a
,
Yo
g
y
a
k
a
rta,
In
d
o
n
e
sia
in
1
9
9
0
,
th
e
M
.
En
g
.
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
,
In
f
o
rm
a
ti
o
n
M
a
n
a
g
e
m
e
n
t
f
ro
m
th
e
A
sia
n
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
Ba
n
g
k
o
k
,
T
h
a
il
a
n
d
,
i
n
1
9
9
8
a
n
d
th
e
P
h
.
D
.
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
Un
iv
e
rsit
y
K
e
b
a
n
g
sa
a
n
M
a
la
y
sia
.
He
is
a
n
A
ss
o
c
ia
te
P
r
o
f
e
ss
o
r
o
f
In
f
o
rm
a
ti
c
s E
n
g
in
e
e
rin
g
a
t
th
e
F
a
c
u
lt
y
o
f
In
d
u
strial
En
g
in
e
e
rin
g
,
Un
iv
e
rsitas
A
t
m
a
Ja
y
a
Yo
g
y
a
k
a
rta.
His
c
u
rre
n
t
re
se
a
rc
h
i
n
tere
sts
in
c
lu
d
e
I
n
f
o
rm
a
ti
o
n
S
y
ste
m
,
Hu
m
a
n
Co
m
p
u
ter
I
n
terf
a
c
e
a
n
d
Da
ta
En
g
in
e
e
rin
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.