I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
14
,
No
.
6
,
Dec
em
b
er
2
0
2
5
,
p
p
.
4
9
3
3
~
4
9
4
2
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
6
.
p
p
4
9
3
3
-
4
9
4
2
4933
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Cla
ss
ifying
clas
sica
l music’s
thera
peutic
effects
usin
g
deep
lea
rning
:
a
revie
w
Ang
elin,
Sa
m
uel A
dy
Sa
nja
y
a
,
Dina
r
Aj
eng
K
ristiy
a
nti
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
m
a
t
i
o
n
S
y
st
e
ms,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
r
mat
i
c
s,
U
n
i
v
e
r
s
i
t
a
s
M
u
l
t
i
me
d
i
a
N
u
sa
n
t
a
r
a
,
Ta
n
g
e
r
a
n
g
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
21
,
2
0
2
4
R
ev
is
ed
Au
g
6
,
2
0
2
5
Acc
ep
ted
Sep
7
,
2
0
2
5
M
e
n
tal
h
e
a
lt
h
issu
e
s
a
re
th
e
lea
d
i
n
g
c
a
u
se
o
f
g
lo
b
a
l
d
isa
b
il
i
ty
,
i
n
c
re
a
sin
g
t
h
e
n
e
e
d
fo
r
trea
tme
n
t
o
p
ti
o
n
s.
Wh
i
l
e
th
e
re
is
m
u
c
h
re
se
a
r
c
h
o
n
th
e
e
m
o
ti
o
n
a
l
re
c
o
g
n
it
i
o
n
o
f
m
u
sic
in
g
e
n
e
ra
l,
t
h
e
re
is
a
g
a
p
in
stu
d
ies
t
h
a
t
d
irec
tl
y
c
o
n
n
e
c
t
m
u
sic
a
l
fe
a
tu
re
s
with
th
e
ir
th
e
r
a
p
e
u
ti
c
e
ffe
c
ts
u
sin
g
d
e
e
p
lea
rn
in
g
.
Th
is
sy
ste
m
a
ti
c
li
tera
tu
re
re
v
iew
e
x
p
l
o
re
s
th
e
u
se
o
f
d
e
e
p
lea
rn
in
g
i
n
c
las
sify
in
g
th
e
th
e
ra
p
e
u
ti
c
e
ffe
c
ts
o
f
c
las
sic
a
l
m
u
sic
fo
r
m
e
n
tal
h
e
a
lt
h
.
F
o
ll
o
win
g
t
h
e
p
re
fe
rre
d
re
p
o
rti
n
g
it
e
m
s
fo
r
sy
ste
m
a
ti
c
re
v
iew
s
a
n
d
m
e
t
a
-
a
n
a
ly
se
s
(
P
RIS
M
A
)
f
ra
m
e
wo
rk
,
a
to
tal
o
f
1
5
p
a
p
e
rs
we
re
re
v
iew
e
d
.
T
h
is
re
v
iew
sy
n
th
e
siz
e
d
st
u
d
ies
o
n
t
h
e
ro
le
o
f
m
u
sic
a
l
e
lem
e
n
ts
th
a
t
a
ffe
c
t
m
e
n
tal
sta
tes
.
Diffe
re
n
t
fe
a
tu
re
e
x
trac
ti
o
n
m
e
th
o
d
s,
i
n
c
lu
d
in
g
mel
-
fre
q
u
e
n
c
y
c
e
p
stra
l
c
o
e
fficie
n
ts
(M
F
CCs
),
s
p
e
c
tral
c
o
n
tras
t,
a
n
d
c
h
r
o
m
a
fe
a
tu
re
s,
a
re
d
isc
u
ss
e
d
fo
r
t
h
e
ir
r
o
les
i
n
c
las
sify
i
n
g
th
e
se
th
e
ra
p
e
u
ti
c
e
ffe
c
ts.
T
h
is
re
v
iew
a
lso
lo
o
k
s
a
t
d
e
e
p
lea
rn
i
n
g
a
lg
o
rit
h
m
s
li
k
e
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
r
k
(C
NN
),
d
e
e
p
n
e
u
ra
l
n
e
tw
o
rk
(DN
N),
lo
n
g
sh
o
rt
-
term
m
e
m
o
ry
(
LS
TM
)
n
e
t
wo
rk
,
a
n
d
c
o
m
b
in
e
d
m
o
d
e
ls
to
a
ss
e
ss
th
e
ir
e
ffe
c
ti
v
e
n
e
ss
.
Co
m
m
o
n
e
v
a
lu
a
ti
o
n
m
e
th
o
d
s
a
re
a
lso
a
ss
e
ss
e
d
to
m
e
a
su
re
th
e
p
e
rfo
rm
a
n
c
e
o
f
th
e
se
m
o
d
e
ls
in
a
u
d
i
o
c
las
sifica
ti
o
n
.
Th
is
re
v
iew
h
i
g
h
li
g
h
ts
th
e
p
o
ten
ti
a
l
o
f
c
o
m
b
i
n
in
g
d
e
e
p
lea
rn
in
g
wit
h
c
las
sic
a
l
m
u
sic
fo
r
m
e
n
tal
h
e
a
lt
h
s
u
p
p
o
rt,
a
n
d
to
fu
t
u
re
p
o
ss
ib
i
li
ti
e
s fo
r
a
p
p
ly
i
n
g
th
e
se
m
e
th
o
d
s
in
t
h
e
re
a
l
wo
rl
d
.
K
ey
w
o
r
d
s
:
Dee
p
lear
n
in
g
Featu
r
e
s
elec
tio
n
Me
n
tal
h
ea
lth
Mu
s
ic
class
if
icat
io
n
Mu
s
ic
elem
en
ts
Mu
s
ic
th
er
ap
eu
tic
ef
f
ec
ts
Mu
s
ic
th
er
ap
y
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Sam
u
el
Ad
y
San
jay
a
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
Sy
s
tem
s
,
Facu
lty
o
f
E
n
g
in
ee
r
in
g
an
d
I
n
f
o
r
m
atics
Un
iv
er
s
itas
Mu
ltime
d
ia
Nu
s
an
tar
a
T
an
g
er
an
g
,
I
n
d
o
n
esia
E
m
ail: sam
u
el.
ad
y
@
u
m
n
.
ac
.
i
d
1.
I
NT
RO
D
UCT
I
O
N
Me
n
tal
d
is
o
r
d
er
s
h
av
e
b
ee
n
id
en
tifie
d
as
th
e
lead
in
g
ca
u
s
e
o
f
g
lo
b
al
d
is
ab
ilit
y
[
1
]
–
[
3
]
.
Me
n
tal
h
ea
lth
is
b
ec
o
m
in
g
an
in
cr
ea
s
in
g
ly
im
p
o
r
tan
t
is
s
u
e
wo
r
ld
wid
e,
with
m
o
r
e
an
d
m
o
r
e
p
e
o
p
le
ex
p
er
ien
cin
g
an
x
iety
,
d
ep
r
ess
io
n
,
an
d
o
t
h
er
em
o
tio
n
al
o
r
p
s
y
ch
o
l
o
g
ical
ch
allen
g
es.
As
a
r
esu
lt,
th
er
e
is
a
g
r
o
win
g
in
ter
est
in
f
in
d
in
g
ef
f
ec
tiv
e
tr
ea
tm
en
ts
th
at
ca
n
h
elp
im
p
r
o
v
e
m
en
tal
h
ea
lth
[
4
]
.
Am
o
n
g
th
e
v
ar
i
o
u
s
m
eth
o
d
s
ex
p
lo
r
ed
,
m
u
s
ic
th
er
ap
y
h
as
attr
ac
ted
s
ig
n
if
ican
t
in
te
r
est
[
5
]
.
Fo
r
m
a
n
y
y
ea
r
s
,
m
u
s
ic
h
as
b
ee
n
u
s
e
d
an
d
r
esear
ch
e
d
to
h
elp
m
en
tal
h
ea
lth
,
f
r
o
m
b
o
o
s
tin
g
m
o
o
d
an
d
r
ed
u
ci
n
g
s
tr
ess
,
to
tr
ea
tin
g
clin
ical
co
n
d
itio
n
s
[
6
]
–
[
8
]
.
I
n
p
ar
ticu
lar
,
t
h
e
u
s
e
o
f
class
ical
m
u
s
ic.
Stu
d
ies
h
a
v
e
s
h
o
wn
th
at
class
ical
m
u
s
ic
ca
n
d
o
m
o
r
e
th
an
ju
s
t
en
ter
tain
,
it
ca
n
r
ed
u
ce
s
tr
ess
,
en
h
an
ce
m
o
o
d
,
an
d
e
v
en
p
o
s
itiv
ely
af
f
ec
t
co
g
n
itiv
e
f
u
n
ctio
n
s
lik
e
m
em
o
r
y
a
n
d
atten
tio
n
[
9
]
.
C
lass
ical
m
u
s
ic
s
tan
d
s
o
u
t
in
m
en
tal
h
ea
lth
th
e
r
ap
y
b
ec
au
s
e
o
f
its
em
o
tio
n
al
d
ep
th
an
d
s
tr
u
ctu
r
ed
co
m
p
o
s
itio
n
s
.
I
t’
s
also
b
ee
n
f
o
u
n
d
to
lo
wer
h
ea
r
t
r
ates
an
d
r
ed
u
ce
b
lo
o
d
p
r
ess
u
r
e,
wh
ic
h
m
ak
es
it
a
to
o
l
f
o
r
im
p
r
o
v
in
g
b
o
th
m
e
n
tal
an
d
p
h
y
s
ical
h
ea
lth
[
1
0
]
.
B
ec
au
s
e
it
af
f
ec
ts
b
o
th
m
in
d
an
d
b
o
d
y
,
class
ica
l
m
u
s
ic
i
s
in
cr
ea
s
in
g
ly
s
ee
n
as
a
v
alu
ab
l
e
to
o
l
f
o
r
m
e
n
tal
h
ea
lth
tr
ea
t
m
en
ts
[
1
1
]
.
R
ec
en
t
s
tu
d
ies
h
a
v
e
f
o
cu
s
ed
o
n
h
o
w
m
u
s
ic's em
o
tio
n
al
an
d
p
s
y
ch
o
l
o
g
ical
ef
f
ec
ts
ca
n
b
e
class
if
ied
u
s
in
g
ad
v
a
n
ce
d
c
o
m
p
u
tatio
n
a
l te
ch
n
iq
u
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
er
20
25
:
4
9
3
3
-
4
9
4
2
4934
Stu
d
ies
h
av
e
s
h
o
wn
th
at
d
if
f
er
en
t
m
u
s
ical
f
ea
tu
r
es,
s
u
ch
as
tem
p
o
,
h
ar
m
o
n
y
,
an
d
r
h
y
th
m
,
ca
n
elicit
v
ar
io
u
s
em
o
tio
n
al
r
esp
o
n
s
es
[
1
2
]
.
Ho
wev
e
r
,
co
n
n
ec
tin
g
th
ese
m
u
s
ical
f
ea
tu
r
es
with
th
e
r
ap
eu
tic
o
u
tco
m
es
r
em
ain
s
u
n
d
e
r
ex
p
l
o
r
ed
[
1
3
]
–
[
1
5
]
,
esp
ec
ially
w
h
en
aim
in
g
to
au
to
m
ate
t
h
is
p
r
o
ce
s
s
th
r
o
u
g
h
d
ee
p
lear
n
in
g
.
Sev
er
al
s
tu
d
ies
h
av
e
u
tili
ze
d
m
ac
h
in
e
lear
n
in
g
a
n
d
d
ee
p
lear
n
in
g
al
g
o
r
ith
m
s
to
ex
p
l
o
r
e
an
d
p
r
e
d
ict
th
e
th
er
ap
eu
tic
ef
f
ec
ts
o
f
m
u
s
ic
[
1
5
]
.
Acc
o
r
d
in
g
to
M
o
d
r
a
n
et
a
l
.
[
1
6
]
,
d
ee
p
lear
n
in
g
was
em
p
lo
y
ed
to
id
e
n
tify
th
e
em
o
tio
n
al
ef
f
ec
ts
o
f
m
u
s
ic
b
y
tr
ain
in
g
a
n
eu
r
al
n
etwo
r
k
to
ca
teg
o
r
ize
m
u
s
ic
in
to
em
o
tio
n
s
lik
e
h
ap
p
y
,
s
ad
,
ca
lm
,
a
n
d
en
er
g
etic.
T
h
e
r
esear
ch
er
u
s
ed
m
el
-
f
r
e
q
u
en
cy
ce
p
s
tr
al
c
o
ef
f
icien
ts
(
MFC
C
s
)
,
wh
ich
ca
p
tu
r
e
th
e
s
p
ec
tr
al
p
r
o
p
er
ties
o
f
th
e
au
d
io
,
to
p
r
ed
ict
th
e
th
er
ap
e
u
t
ic
ef
f
ec
t
o
f
th
e
m
u
s
ic.
T
h
at
s
tu
d
y
h
ig
h
lig
h
ted
th
e
im
p
o
r
tan
ce
o
f
c
o
n
n
ec
tin
g
au
d
io
f
ea
tu
r
es
with
e
m
o
tio
n
al
f
ee
lin
g
s
.
Ho
wev
er
,
it
f
o
cu
s
e
d
o
n
v
ar
io
u
s
m
u
s
ic
g
en
r
es
with
o
u
t
th
o
r
o
u
g
h
ly
e
x
p
lo
r
in
g
class
ical
m
u
s
ic'
s
th
er
ap
eu
tic
p
o
ten
tial.
Similar
ly
,
Du
tta
an
d
C
h
an
d
a
[
1
7
]
em
p
lo
y
ed
a
h
y
b
r
i
d
co
n
v
o
lu
t
io
n
al
n
eu
r
al
n
etwo
r
k
-
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
C
NN
-
L
STM
)
d
ee
p
n
eu
r
al
n
etwo
r
k
(
DNN)
to
class
if
y
m
u
s
ic
em
o
tio
n
s
,
s
h
o
win
g
h
ig
h
ac
cu
r
ac
y
wh
en
ap
p
lied
to
a
d
ataset
o
f
Ass
am
es
e
s
o
n
g
s
an
d
th
e
R
y
er
s
o
n
au
d
i
o
-
v
is
u
al
d
atab
ase
o
f
em
o
tio
n
al
s
p
ee
ch
an
d
s
o
n
g
(
R
AVDE
SS
)
em
o
tio
n
al
s
o
n
g
d
atab
ase.
B
u
t
lik
e
m
an
y
p
r
ev
io
u
s
s
tu
d
ies,
it
is
f
o
cu
s
ed
o
n
em
o
tio
n
r
ec
o
g
n
itio
n
r
ath
e
r
t
h
an
th
e
th
e
r
ap
eu
tic
o
u
tco
m
es.
Desp
ite
th
ese
s
tu
d
ies,
a
s
ig
n
if
ican
t
g
ap
r
em
ai
n
s
in
co
n
n
ec
tin
g
m
u
s
ical
f
e
atu
r
es
d
ir
ec
tly
with
th
er
ap
eu
tic
o
u
tco
m
es,
p
ar
ticu
lar
ly
f
o
r
class
ical
m
u
s
ic.
C
u
r
r
en
t
r
esear
ch
o
f
ten
em
p
h
asizes
g
en
er
al
em
o
tio
n
class
if
icatio
n
o
r
m
u
s
ic
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
,
n
o
t
th
e
s
p
ec
if
ic
th
er
ap
e
u
tic
ef
f
ec
ts
,
s
u
ch
as
s
tr
ess
r
ed
u
ctio
n
o
r
m
o
o
d
en
h
a
n
ce
m
en
t.
T
h
is
g
ap
o
p
e
n
s
an
o
p
p
o
r
tu
n
ity
f
o
r
e
x
p
lo
r
in
g
a
m
o
r
e
tar
g
eted
ap
p
r
o
ac
h
th
at
co
m
b
i
n
es
d
ee
p
lear
n
in
g
with
f
ea
tu
r
e
e
x
tr
ac
tio
n
tech
n
iq
u
es
to
class
i
f
y
th
e
th
er
ap
e
u
tic
im
p
ac
ts
o
f
class
ical
m
u
s
ic
o
n
m
en
tal
h
ea
lth
,
th
e
r
ef
o
r
e
ad
d
r
e
s
s
in
g
th
e
th
er
ap
eu
tic
asp
ec
ts
.
T
h
i
s
s
y
s
t
e
m
a
t
i
c
l
it
e
r
a
t
u
r
e
r
e
v
ie
w
u
s
es
t
h
e
p
r
e
f
e
r
r
e
d
r
e
p
o
r
t
i
n
g
i
t
e
m
s
f
o
r
s
y
s
t
e
m
a
ti
c
r
e
v
i
ew
s
a
n
d
m
e
t
a
-
a
n
a
l
y
s
es
(
P
R
I
S
MA
)
f
r
a
m
e
w
o
r
k
t
o
e
v
a
l
u
a
t
e
t
h
e
u
s
e
o
f
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
m
e
t
h
o
d
s
,
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
,
m
o
d
e
l
e
v
a
l
u
a
t
i
o
n
,
a
n
d
m
u
s
i
c
a
l
e
l
e
m
e
n
t
s
i
n
c
la
s
s
i
f
y
i
n
g
a
u
d
i
o
.
A
u
d
i
o
s
i
g
n
a
l
p
r
o
c
e
s
s
i
n
g
c
o
m
m
o
n
l
y
u
s
e
s
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
t
e
c
h
n
i
q
u
es
t
o
c
a
p
t
u
r
e
k
e
y
c
h
a
r
a
c
t
e
r
is
t
i
cs
l
i
k
e
t
i
m
b
r
e
,
p
i
t
c
h
,
a
m
p
l
i
t
u
d
e
,
a
n
d
r
h
y
t
h
m
[
1
8
]
.
T
h
e
s
e
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
m
et
h
o
d
s
c
a
n
m
a
k
e
r
a
w
a
u
d
i
o
d
a
ta
i
n
t
o
a
s
t
r
u
c
t
u
r
e
d
f
o
r
m
a
t
s
o
t
h
a
t
i
t
c
a
n
b
e
a
n
al
y
ze
d
c
o
m
p
u
t
a
t
i
o
n
a
ll
y
[
1
9
]
,
[
2
0
]
.
C
o
m
m
o
n
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s
i
n
c
l
u
d
e
M
FC
C
s
,
c
h
r
o
m
a
f
e
a
t
u
r
es
,
s
p
e
c
t
r
al
c
o
n
t
r
a
s
t
,
a
n
d
ze
r
o
-
c
r
o
s
s
i
n
g
r
a
te
[
2
1
]
–
[
2
3
]
.
M
u
s
i
c
a
l
f
e
a
t
u
r
es
a
r
e
a
ls
o
e
s
s
e
n
ti
a
l
i
n
u
n
d
e
r
s
t
a
n
d
i
n
g
h
o
w
m
u
s
i
ca
l
c
o
m
p
o
s
i
ti
o
n
s
c
an
i
m
p
a
c
t
s
o
m
e
o
n
e
a
n
d
t
h
e
i
r
m
en
t
a
l
s
ta
t
e
[
2
4
]
,
[
2
5
]
.
T
h
e
r
e
s
e
ar
c
h
e
r
a
i
m
s
t
o
i
d
e
n
ti
f
y
w
h
i
c
h
s
p
e
c
i
f
i
c
e
l
e
m
e
n
t
s
o
f
m
u
s
i
c
p
la
y
a
s
i
g
n
i
f
i
ca
n
t
r
o
l
e
in
c
o
n
t
r
i
b
u
t
i
n
g
t
o
i
ts
e
f
f
e
c
ts
o
n
m
e
n
t
a
l
s
t
at
e
.
T
h
is
r
e
v
i
e
w
a
l
s
o
c
o
m
p
a
r
e
s
f
e
at
u
r
e
e
x
t
r
a
c
t
i
o
n
t
e
c
h
n
i
q
u
es
t
o
d
e
te
r
m
i
n
e
t
h
e
m
o
s
t
c
o
m
m
o
n
a
n
d
e
f
f
e
c
t
i
v
e
m
e
t
h
o
d
s
f
o
r
e
x
t
r
ac
t
i
n
g
m
u
s
i
c
a
l
f
ea
t
u
r
e
s
.
Dee
p
lear
n
in
g
o
f
f
er
s
an
ef
f
ici
en
t
ap
p
r
o
ac
h
f
o
r
h
a
n
d
lin
g
th
e
co
m
p
lex
d
ata
p
r
o
d
u
ce
d
b
y
t
h
e
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
[
2
6
]
.
Mo
d
e
ls
s
u
ch
as
C
NN
s
an
d
L
STM
n
etwo
r
k
s
ar
e
p
ar
ticu
la
r
ly
s
u
ited
f
o
r
class
if
y
in
g
a
n
d
an
aly
zin
g
tim
e
-
s
er
ies
d
ata,
lik
e
m
u
s
ic
[
2
7
]
,
[
2
8
]
.
Mo
r
eo
v
er
,
th
is
r
ev
iew
p
r
o
v
id
es
an
o
r
ig
i
n
al
co
n
tr
i
b
u
tio
n
b
y
s
y
s
tem
atica
lly
s
y
n
th
esizin
g
an
d
cr
itically
an
aly
zi
n
g
e
x
is
tin
g
s
tu
d
ies
o
n
th
e
u
s
e
o
f
f
ea
t
u
r
e
ex
tr
ac
tio
n
m
et
h
o
d
s
an
d
d
e
ep
lear
n
in
g
alg
o
r
ith
m
s
i
n
class
if
y
in
g
th
e
th
er
a
p
eu
tic
e
f
f
ec
ts
o
f
m
u
s
ic
o
n
m
e
n
tal
h
ea
l
th
,
with
a
f
o
c
u
s
o
n
class
ical
m
u
s
ic.
B
y
f
o
llo
win
g
th
e
PR
I
SMA
g
u
id
elin
es
an
d
well
-
d
ef
in
ed
in
cl
u
s
io
n
cr
ite
r
ia,
th
is
s
y
s
tem
atic
liter
atu
r
e
r
ev
iew
e
n
s
u
r
es
a
r
ig
o
r
o
u
s
a
n
d
t
r
an
s
p
ar
en
t
ap
p
r
o
ac
h
.
T
h
is
r
ev
iew
also
aim
s
to
b
e
a
u
s
ef
u
l
r
ef
e
r
en
ce
f
o
r
f
u
tu
r
e
r
esear
c
h
,
em
p
h
asizin
g
th
e
m
et
h
o
d
s
th
at
ca
n
b
e
u
til
ized
in
th
is
ar
ea
.
2.
M
E
T
H
O
D
T
h
e
PR
I
SMA
f
r
am
ewo
r
k
is
ap
p
lied
in
th
is
s
y
s
tem
atic
r
ev
iew
to
g
u
id
e
th
e
co
m
p
r
eh
e
n
s
iv
e
an
d
tr
an
s
p
ar
en
t
id
e
n
tific
atio
n
a
n
d
ass
ess
m
en
t
o
f
r
elev
an
t
liter
a
tu
r
e.
T
h
e
u
s
e
o
f
PR
I
SMA
als
o
h
elp
s
r
e
d
u
ce
t
h
e
lik
elih
o
o
d
o
f
r
e
p
o
r
tin
g
in
ac
cu
r
ac
ies
in
s
y
s
tem
atic
r
ev
iews
an
d
en
h
a
n
ce
s
th
e
clar
ity
a
n
d
tr
an
s
p
ar
en
cy
o
f
th
e
r
ev
iew
p
r
o
ce
s
s
[
2
9
]
,
[
3
0
]
.
T
h
e
r
esear
ch
er
u
s
es
th
e
PR
I
S
MA
f
r
am
ewo
r
k
clo
s
ely
t
o
e
n
s
u
r
e
a
s
y
s
tem
atic,
tr
an
s
p
ar
en
t,
a
n
d
co
n
s
is
ten
t
s
e
lectio
n
p
r
o
ce
s
s
,
wh
ich
s
tr
en
g
th
en
s
th
e
r
eliab
ilit
y
an
d
v
ali
d
ity
o
f
th
e
f
in
d
in
g
s
p
r
esen
ted
in
th
is
r
ev
iew.
T
h
e
aim
is
to
also
ef
f
ec
tiv
ely
in
v
esti
g
ate
th
e
p
ap
er
s
r
eg
a
r
d
in
g
th
e
th
eo
r
y
,
to
o
ls
,
m
eth
o
d
s
,
alg
o
r
ith
m
s
,
an
d
ev
al
u
atio
n
th
at
ar
e
u
s
ed
to
class
if
y
au
d
io
-
b
ased
d
atasets
.
2
.
1
.
Resea
rc
h ques
t
io
ns
T
o
g
i
v
e
t
h
is
r
e
v
ie
w
a
c
le
a
r
f
o
c
u
s
,
t
h
e
r
e
s
e
a
r
c
h
q
u
e
s
ti
o
n
s
w
e
r
e
c
h
o
s
e
n
b
a
s
e
d
o
n
r
e
s
e
a
r
ch
g
a
p
s
a
n
d
l
i
m
i
t
at
i
o
n
s
t
h
a
t
w
e
r
e
f
o
u
n
d
i
n
p
r
e
v
i
o
u
s
s
t
u
d
ie
s
.
W
h
il
e
m
a
n
y
s
t
u
d
i
es
e
x
p
l
o
r
e
t
h
e
e
m
o
t
i
o
n
a
l
e
f
f
e
c
t
s
o
f
m
u
s
i
c
o
n
t
h
e
m
e
n
t
a
l
s
t
at
e
,
t
h
e
r
e
i
s
s
ti
l
l a
l
a
c
k
o
f
r
e
s
e
a
r
c
h
t
h
a
t
d
i
r
ec
t
l
y
co
n
n
e
c
t
s
s
p
ec
i
f
i
c
m
u
s
i
ca
l
e
le
m
en
t
s
wi
t
h
m
e
as
u
r
a
b
l
e
t
h
e
r
a
p
e
u
t
i
c
o
u
t
c
o
m
es
.
T
h
is
g
a
p
l
e
d
t
o
t
h
es
e
r
es
e
a
r
c
h
q
u
es
ti
o
n
s
f
o
r
t
h
i
s
s
y
s
t
e
m
a
ti
c
li
t
e
r
at
u
r
e
r
ev
i
e
w
,
w
h
ic
h
a
i
m
t
o
e
x
p
l
o
r
e
t
h
e
l
e
s
s
e
x
p
l
o
r
e
d
a
r
e
as
.
M
a
n
y
p
r
e
v
i
o
u
s
s
t
u
d
i
es
h
a
v
e
a
l
s
o
f
o
c
u
s
e
d
o
n
c
la
s
s
i
f
y
i
n
g
g
e
n
e
r
a
l
e
m
o
t
i
o
n
s
o
r
m
u
s
i
c
r
e
c
o
m
m
e
n
d
a
ti
o
n
s
y
s
t
em
s
,
r
a
t
h
e
r
t
h
a
n
cl
as
s
i
f
y
i
n
g
t
h
e
s
p
e
c
i
f
i
c
t
h
e
r
a
p
e
u
ti
c
e
f
f
e
ct
s
o
f
t
h
e
m
u
s
i
c
.
T
h
e
l
i
m
i
t
at
i
o
n
s
h
e
l
p
e
d
t
o
g
u
i
d
e
th
e
r
e
s
e
a
r
c
h
q
u
e
s
t
i
o
n
s
t
o
f
o
c
u
s
o
n
w
h
i
c
h
m
u
s
i
c
a
l
e
le
m
e
n
ts
,
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
m
e
t
h
o
d
s
,
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
al
g
o
r
i
t
h
m
s
t
h
a
t
a
r
e
c
o
m
m
o
n
l
y
u
s
e
d
a
n
d
e
f
f
e
ct
i
v
e
i
n
c
la
s
s
i
f
y
in
g
t
h
e
t
h
e
r
a
p
e
u
ti
c
e
f
f
e
c
t
s
o
f
m
u
s
i
c
.
T
o
m
a
k
e
s
u
r
e
t
h
a
t
t
h
e
c
la
s
s
i
f
ic
a
t
i
o
n
p
e
r
f
o
r
m
s
w
e
ll
,
t
h
e
r
es
e
a
r
c
h
q
u
e
s
t
i
o
n
a
ls
o
a
i
m
s
t
o
e
v
a
l
u
a
te
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
la
s
s
i
fyin
g
cla
s
s
ica
l m
u
s
ic’
s
t
h
era
p
eu
tic
effec
ts
u
s
in
g
d
ee
p
l
ea
r
n
in
g
:
a
r
ev
iew
(
A
n
g
elin
)
4935
h
o
w
w
e
l
l
v
a
r
i
o
u
s
e
v
a
l
u
a
t
i
o
n
m
e
t
h
o
d
s
a
r
e
u
s
e
d
t
o
ass
e
s
s
t
h
e
p
er
f
o
r
m
a
n
c
e
o
f
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
i
n
a
u
d
i
o
-
b
a
s
e
d
c
l
a
s
s
i
f
ic
a
t
i
o
n
.
T
a
b
le
1
s
h
o
ws
t
h
e
r
e
s
e
a
r
c
h
q
u
e
s
t
i
o
n
s
f
o
r
t
h
i
s
s
y
s
t
e
m
at
i
c
li
t
e
r
at
u
r
e
r
e
v
i
e
w
.
T
ab
le
1
.
R
esear
ch
q
u
esti
o
n
s
I
n
d
e
x
R
e
se
a
r
c
h
q
u
e
st
i
o
n
s
R
Q
1
W
h
i
c
h
e
l
e
me
n
t
s
o
f
m
u
si
c
a
r
e
u
su
a
l
l
y
u
se
d
t
o
d
e
t
e
r
mi
n
e
t
h
e
e
f
f
e
c
t
s
o
n
me
n
t
a
l
s
t
a
t
e
?
R
Q
2
W
h
a
t
a
r
e
t
h
e
m
o
st
c
o
mm
o
n
a
n
d
e
f
f
e
c
t
i
v
e
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
me
t
h
o
d
s
f
o
r
c
l
a
ssi
f
y
i
n
g
t
h
e
i
m
p
a
c
t
o
f
c
l
a
ssi
c
a
l
m
u
si
c
o
n
men
t
a
l
h
e
a
l
t
h
?
R
Q
3
W
h
a
t
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
a
r
e
m
o
st
e
f
f
e
c
t
i
v
e
f
o
r
c
l
a
ssi
f
y
i
n
g
t
h
e
t
h
e
r
a
p
e
u
t
i
c
e
f
f
e
c
t
s
o
f
c
l
a
ssi
c
a
l
m
u
si
c
?
R
Q
4
W
h
a
t
m
e
t
h
o
d
s
a
r
e
e
m
p
l
o
y
e
d
f
o
r
e
v
a
l
u
a
t
i
n
g
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
i
n
a
u
d
i
o
-
b
a
se
d
c
l
a
ssi
f
i
c
a
t
i
o
n
?
2
.
2
.
Sea
rc
h str
a
t
eg
y
Pu
b
lis
h
o
r
p
er
is
h
(
Po
P)
is
a
w
id
ely
u
s
ed
to
o
l
f
o
r
ac
ad
em
ics
an
d
r
esear
ch
er
s
to
co
n
d
u
ct
an
d
r
etr
iev
e
ac
ad
em
ic
p
ap
er
s
f
r
o
m
v
a
r
io
u
s
o
n
lin
e
d
atab
ases
[
3
1
]
.
I
t
s
im
p
lifie
s
th
e
p
r
o
ce
s
s
o
f
g
ath
e
r
in
g
an
d
an
aly
zin
g
r
esear
ch
p
a
p
er
s
b
y
co
llectin
g
r
esu
lts
f
r
o
m
s
o
u
r
ce
s
s
u
ch
as
Go
o
g
le
Sch
o
lar
,
Sco
p
u
s
,
an
d
I
E
E
E
Xp
lo
r
e,
p
r
o
v
id
i
n
g
citatio
n
m
etr
ics
lik
e
th
e
h
-
in
d
e
x
,
g
-
in
d
e
x
,
an
d
to
ta
l
citatio
n
s
f
o
r
s
elec
ted
p
ap
er
s
[
3
2
]
.
T
h
u
s
,
f
o
r
th
is
s
y
s
tem
atic
liter
atu
r
e
r
ev
iew,
th
e
r
esear
c
h
er
id
e
n
tifie
d
r
elev
an
t
liter
atu
r
e
u
s
in
g
Po
P
s
o
f
twar
e
to
co
n
d
u
ct
s
y
s
tem
atic
s
ea
r
ch
es
ac
r
o
s
s
elec
tr
o
n
ic
d
atab
ases
,
in
cl
u
d
in
g
Go
o
g
le
Sch
o
lar
,
Sco
p
u
s
,
an
d
I
E
E
E
Xp
lo
r
e
.
Fig
u
r
e
1
s
h
o
ws
th
e
PR
I
SMA
f
r
am
ewo
r
k
f
lo
w
d
iag
r
am
,
illu
s
tr
atin
g
f
r
o
m
t
h
e
in
itial
id
en
tific
atio
n
o
f
p
a
p
er
s
co
llected
,
to
th
e
r
elev
an
t stu
d
i
es th
at
ar
e
in
clu
d
ed
in
th
is
r
ev
i
ew.
Fig
u
r
e
1
.
PR
I
SMA
f
r
am
ewo
r
k
f
lo
w
d
iag
r
a
m
T
h
e
s
ea
r
ch
ter
m
s
in
clu
d
ed
k
e
y
wo
r
d
s
s
u
ch
as
“c
lass
ical
m
u
s
ic”
AND
“m
en
tal
h
ea
lth
”,
“
m
u
s
ic
f
o
r
m
en
tal
h
ea
lth
”
,
“d
ee
p
lear
n
i
n
g
”
AND
“m
u
s
ic”,
“m
u
s
ic”
AND
“c
la
s
s
if
icat
io
n
”,
“
s
o
u
n
d
class
if
icatio
n
”,
“a
u
d
io
c
lass
if
icatio
n
”,
“f
ea
tu
r
e
ex
tr
ac
tio
n
”
AND
“th
er
ap
eu
tic
ef
f
ec
ts
”,
“f
ea
tu
r
e
ex
tr
ac
tio
n
”,
“m
u
s
ic
th
er
ap
y
”,
“m
u
s
ic
em
o
tio
n
class
if
icatio
n
”
AND
“d
ee
p
lear
n
in
g
”.
T
h
e
s
ea
r
ch
es
f
o
cu
s
ed
o
n
j
o
u
r
n
al
a
r
ticles
p
u
b
lis
h
ed
in
E
n
g
lis
h
with
in
th
e
last
5
y
ea
r
s
.
T
h
e
s
ea
r
c
h
r
esu
lts
ar
e
r
ev
ie
wed
u
s
in
g
th
e
PR
I
SMA
m
eth
o
d
,
w
h
ich
i
n
v
o
lv
es
s
ev
er
al
s
tep
s
[
3
3
]
.
I
t
s
tar
ts
b
y
id
en
tify
i
n
g
all
r
elev
an
t
p
a
p
er
s
,
an
d
th
en
n
ar
r
o
win
g
t
h
e
m
d
o
wn
b
ased
o
n
s
p
ec
if
ic
cr
iter
ia
to
s
elec
t th
e
s
tu
d
ies th
at
ar
e
m
o
s
t u
s
ef
u
l
f
o
r
t
h
is
r
ev
iew.
T
h
e
i
n
c
l
u
s
i
o
n
c
r
it
e
r
i
a
f
o
r
t
h
is
s
y
s
te
m
a
t
i
c
l
i
te
r
a
t
u
r
e
r
e
v
i
ew
a
r
e
d
e
s
i
g
n
e
d
t
o
p
r
i
o
r
i
ti
z
e
t
h
e
s
el
e
c
t
i
o
n
o
f
p
u
b
l
i
c
a
t
i
o
n
s
t
h
a
t
a
r
e
b
o
t
h
r
e
ce
n
t
a
n
d
r
e
le
v
a
n
t
.
T
h
e
r
e
v
i
e
w
f
o
c
u
s
e
s
o
n
p
e
e
r
-
r
e
v
i
e
w
e
d
a
r
t
ic
l
e
s
,
o
r
c
o
n
f
e
r
e
n
c
e
p
a
p
e
r
s
p
u
b
l
i
s
h
e
d
i
n
E
n
g
li
s
h
f
r
o
m
2
0
1
9
o
n
w
a
r
d
s
,
t
o
m
a
k
e
s
u
r
e
t
h
e
r
e
s
e
a
r
c
h
i
s
r
e
ce
n
t
.
St
u
d
i
e
s
m
u
s
t
f
o
c
u
s
o
n
t
o
p
i
c
s
s
u
c
h
as
t
h
e
e
f
f
e
ct
s
o
f
m
u
s
i
c
o
n
m
e
n
t
al
s
t
a
t
e
,
o
r
h
o
w
d
e
e
p
l
e
a
r
n
i
n
g
is
u
s
e
d
i
n
m
u
s
i
c
a
n
al
y
s
is
,
a
n
d
o
r
f
e
a
t
u
r
e
e
x
t
r
a
c
ti
o
n
m
e
t
h
o
d
s
li
k
e
M
FC
C
f
o
r
u
n
d
e
r
s
t
a
n
d
i
n
g
m
u
s
ic
’
s
e
m
o
t
i
o
n
al
o
r
t
h
e
r
a
p
e
u
t
i
c
e
f
f
e
c
t
s
.
T
h
es
e
c
r
i
t
e
r
ia
h
e
l
p
t
o
m
a
k
e
s
u
r
e
t
h
at
t
h
e
s
e
l
e
ct
e
d
s
t
u
d
i
es
a
r
e
d
i
r
ec
t
l
y
r
e
la
t
e
d
to
t
h
e
r
e
v
i
e
w
’
s
a
i
m
a
n
d
r
e
s
e
a
r
ch
q
u
e
s
t
i
o
n
s
.
Af
ter
th
e
s
ea
r
ch
es
o
r
id
en
tific
atio
n
,
titl
es
an
d
ab
s
tr
ac
ts
w
ill
b
e
s
cr
ee
n
ed
f
o
r
r
elev
an
ce
to
th
e
r
esear
ch
q
u
esti
o
n
s
,
an
d
a
f
u
ll
-
te
x
t
r
ev
i
ew
will
b
e
co
n
d
u
cted
f
o
r
p
ap
er
s
m
ee
tin
g
th
e
i
n
clu
s
io
n
cr
it
er
ia.
T
h
e
last
s
tag
e
in
v
o
lv
es
an
al
y
zin
g
an
d
s
y
n
t
h
esizin
g
to
a
n
s
wer
th
e
r
esear
ch
q
u
esti
o
n
s
.
A
n
a
r
r
ativ
e
s
y
n
th
esis
is
u
s
ed
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
er
20
25
:
4
9
3
3
-
4
9
4
2
4936
co
m
p
ar
e
th
e
f
in
d
i
n
g
s
o
f
th
e
r
ev
iewe
d
s
tu
d
ies.
T
h
e
r
esu
lts
o
f
th
e
r
ev
iew
ar
e
s
tr
u
ctu
r
ed
,
s
u
m
m
ar
izin
g
k
e
y
f
in
d
in
g
s
an
d
h
ig
h
lig
h
tin
g
g
ap
s
in
cu
r
r
en
t
r
esear
ch
.
T
h
e
li
m
itatio
n
s
o
f
th
e
r
ev
iewe
d
s
tu
d
ies
ar
e
d
is
cu
s
s
ed
,
alo
n
g
with
r
ec
o
m
m
en
d
atio
n
s
f
o
r
f
u
tu
r
e
r
esear
ch
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
r
esear
ch
er
co
n
d
u
cted
a
s
cr
ee
n
in
g
an
d
s
elec
tio
n
p
r
o
ce
s
s
o
n
8
0
0
p
ap
er
s
to
f
in
ally
in
clu
d
e
o
n
l
y
1
5
p
ap
er
s
th
at
m
et
th
e
in
clu
s
io
n
cr
iter
ia.
B
y
an
aly
zin
g
s
p
e
cif
ic
p
ar
ts
o
f
th
e
s
elec
ted
p
ap
er
s
,
th
e
r
esear
ch
er
aim
s
to
an
s
wer
th
e
(
R
Q1
,
R
Q2
,
R
Q3
,
an
d
R
Q4
)
q
u
esti
o
n
s
.
T
h
e
an
aly
s
is
lo
o
k
s
at
th
e
d
ata
o
f
m
u
s
ical
elem
en
ts
s
u
ch
as
m
elo
d
y
,
tem
p
o
,
an
d
r
h
y
th
m
,
th
at
ca
n
af
f
ec
t
th
e
m
en
tal
s
tate.
Als
o
,
th
e
m
u
s
ical
f
ea
tu
r
es
ca
n
b
e
p
r
o
d
u
ce
d
f
r
o
m
r
aw
a
u
d
io
u
s
in
g
d
if
f
er
en
t
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
s
t
o
d
o
th
is
p
r
o
ce
s
s
in
g
.
T
h
e
r
ev
iew
als
o
an
aly
ze
s
th
e
s
p
ec
if
ic
d
ee
p
lea
r
n
in
g
m
o
d
els
u
s
ed
(
e
.
g
.
,
C
NN
,
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
s
(
R
NNs)
)
to
class
if
y
m
u
s
ic.
L
astl
y
,
th
is
r
e
v
iew
also
ex
am
i
n
es
ev
alu
atio
n
m
etr
ic
s
lik
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all,
ev
alu
atin
g
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
o
d
els.
T
ab
le
2
p
r
o
v
id
es
a
s
u
m
m
ar
y
o
f
s
ix
s
elec
ted
r
esear
c
h
p
a
p
er
s
th
at
ex
p
l
o
r
e
t
h
e
r
elatio
n
s
h
ip
b
etwe
en
s
p
ec
if
ic
m
u
s
ical
f
ea
tu
r
es
an
d
t
h
eir
t
h
er
ap
eu
tic
ef
f
ec
ts
.
T
ab
le
2
p
r
esen
ts
th
e
f
ea
tu
r
es
ex
tr
ac
ted
f
r
o
m
th
e
m
u
s
ic,
th
e
m
en
tal
o
r
em
o
tio
n
al
b
en
ef
i
ts
r
ep
o
r
ted
(
s
u
ch
as
r
elax
atio
n
,
f
o
cu
s
,
o
r
s
tr
ess
r
ed
u
ctio
n
)
,
a
n
d
t
h
e
c
o
r
r
esp
o
n
d
in
g
f
in
d
in
g
s
an
d
class
if
icatio
n
r
esu
lts
.
T
h
is
o
v
e
r
v
iew
h
elp
s
h
ig
h
lig
h
t
wh
ich
f
ea
tu
r
es
ar
e
m
o
s
t
co
m
m
o
n
l
y
ass
o
ciate
d
with
ce
r
tain
em
o
ti
o
n
al
o
r
th
er
ap
e
u
tic
o
u
tco
m
es
an
d
h
o
w
ef
f
ec
tiv
e
d
if
f
er
en
t m
o
d
els h
av
e
b
ee
n
i
n
r
ec
o
g
n
izin
g
th
em
.
T
ab
le
2
.
R
esear
ch
p
a
p
er
s
u
m
m
ar
ies o
f
k
ey
m
u
s
ical
f
ea
tu
r
es
an
d
th
eir
c
o
r
r
esp
o
n
d
in
g
th
er
a
p
eu
tic
ef
f
ec
ts
o
n
m
en
tal
s
tates
R
e
f
e
r
e
n
c
e
F
e
a
t
u
r
e
s
o
f
m
u
s
i
c
Th
e
r
a
p
e
u
t
i
c
e
f
f
e
c
t
s
R
e
s
u
l
t
[
1
6
]
i)
To
n
e
c
l
a
ss
p
r
o
f
i
l
e
ii)
C
l
a
r
i
t
y
o
f
t
h
e
k
e
y
iii)
H
a
r
mo
n
i
c
c
h
a
n
g
e
i
v
)
M
u
s
i
c
a
l
mo
d
u
l
e
v)
B
e
a
t
h
i
s
t
o
g
r
a
m
v
i
)
M
e
d
i
u
m
t
e
m
p
o
C
a
l
m,
h
a
p
p
y
,
e
n
e
r
g
e
t
i
c
,
a
n
d
s
a
d
Th
e
r
e
s
e
a
r
c
h
e
r
c
a
n
c
l
a
ssi
f
y
c
a
l
m,
h
a
p
p
y
,
a
n
d
e
n
e
r
g
e
t
i
c
s
o
n
g
s
w
i
t
h
9
4
%
a
c
c
u
r
a
c
y
,
b
u
t
t
h
e
a
c
c
u
r
a
c
y
f
o
r
sa
d
s
o
n
g
s
i
s
a
b
i
t
l
o
w
e
r
a
t
8
5
%.
[
3
4
]
i)
Te
mp
o
ii)
Ti
m
b
r
e
iii)
A
mp
l
i
t
u
d
e
R
e
l
a
x
i
n
g
Th
e
r
e
sea
r
c
h
e
r
f
o
u
n
d
t
h
a
t
c
h
a
n
g
i
n
g
o
n
e
p
a
r
t
o
f
t
h
e
m
u
s
i
c
a
l
e
l
e
m
e
n
t
f
r
o
m
‘
r
e
l
a
x
i
n
g
’
m
u
si
c
a
f
f
e
c
t
e
d
p
e
o
p
l
e
’
s
h
e
a
r
t
r
a
t
e
,
b
r
e
a
t
h
i
n
g
,
a
n
d
e
v
e
n
s
k
i
n
r
e
a
c
t
i
o
n
s.
[
3
5
]
B
e
a
t
s
R
e
l
a
x
i
n
g
Th
e
r
e
s
e
a
r
c
h
e
r
f
o
u
n
d
t
h
a
t
so
n
g
s
c
a
n
b
e
a
n
e
f
f
e
c
t
i
v
e
t
o
o
l
f
o
r
r
e
d
u
c
i
n
g
a
c
u
t
e
st
r
e
ss.
[
3
6
]
i)
Te
mp
o
ii)
B
e
a
t
s
H
a
p
p
y
,
r
e
l
a
x
,
s
a
d
Th
e
r
e
sea
r
c
h
e
r
su
c
c
e
ssf
u
l
l
y
c
l
a
ss
i
f
i
e
d
‘
h
a
p
p
y
’
a
n
d
‘
s
a
d
’
w
i
t
h
a
n
a
c
c
u
r
a
c
y
o
f
8
0
%
-
9
0
%,
b
u
t
f
o
r
‘
r
e
l
a
x
’
,
t
h
e
a
c
c
u
r
a
c
y
i
s
l
o
w
e
r
,
a
r
o
u
n
d
6
0
%
-
7
0
%,
s
o
i
t
i
s s
t
i
l
l
i
n
t
h
e
p
o
o
r
c
a
t
e
g
o
r
y
.
[
3
7
]
i)
Te
mp
o
ii)
Ti
m
b
r
e
F
o
c
u
si
n
g
A
l
t
h
o
u
g
h
f
e
a
t
u
r
e
s
l
i
k
e
t
e
m
p
o
a
n
d
t
i
mb
r
e
o
f
t
h
e
mu
s
i
c
c
a
n
i
n
f
l
u
e
n
c
e
f
o
c
u
s,
t
h
e
f
a
mi
l
i
a
r
i
t
y
o
f
t
h
e
so
n
g
h
a
s
a
s
i
g
n
i
f
i
c
a
n
t
l
y
g
r
e
a
t
e
r
i
m
p
a
c
t
o
n
e
n
h
a
n
c
i
n
g
a
t
t
e
n
t
i
o
n
a
n
d
mai
n
t
a
i
n
i
n
g
f
o
c
u
s.
[
3
8
]
Te
mp
o
S
t
r
e
ss
r
e
d
u
c
t
i
o
n
,
mo
t
i
v
a
t
i
n
g
S
l
o
w
b
a
c
k
g
r
o
u
n
d
mu
s
i
c
s
u
c
c
e
ssf
u
l
l
y
r
e
d
u
c
e
d
t
h
e
st
r
e
ss
e
x
p
e
r
i
e
n
c
e
d
b
y
st
u
d
e
n
t
s
d
u
r
i
n
g
t
o
u
g
h
d
e
n
t
a
l
t
r
a
i
n
i
n
g
.
I
t
i
s
a
l
so
f
o
u
n
d
t
o
i
n
c
r
e
a
s
e
t
h
e
i
r
mo
t
i
v
a
t
i
o
n
t
o
l
e
a
r
n
a
n
d
p
r
a
c
t
i
c
e
.
3
.
1
.
RQ
1
:
w
hich ele
m
ent
s
o
f
m
us
ic
a
re
us
ua
lly
us
ed
t
o
de
t
er
m
ine t
he
ef
f
ec
t
s
o
n
m
ent
a
l st
a
t
e?
T
h
e
r
esear
ch
p
ap
er
s
u
m
m
ar
ie
s
r
ev
ea
l
s
ev
er
al
m
u
s
ical
f
ea
tu
r
es
th
at
s
ig
n
if
ican
tly
in
f
lu
en
ce
em
o
tio
n
s
an
d
co
g
n
itiv
e
r
esp
o
n
s
es.
T
a
b
le
3
s
h
o
ws
th
e
o
v
er
all
c
o
m
p
ar
i
s
o
n
o
f
th
e
k
ey
m
u
s
ical
f
ea
tu
r
e
s
an
d
th
e
ef
f
ec
ts
o
n
m
en
tal
s
tates.
T
em
p
o
is
a
v
e
r
s
atile
elem
en
t,
f
aster
tem
p
o
s
ten
d
to
en
h
a
n
ce
m
o
tiv
atio
n
an
d
aler
tn
ess
,
m
ak
i
n
g
lis
ten
er
s
f
ee
l
m
o
r
e
ac
tiv
e,
w
h
ile
s
lo
wer
tem
p
o
s
ar
e
ass
o
c
iated
with
r
elax
atio
n
a
n
d
s
tr
ess
r
ed
u
ctio
n
[
3
9
]
.
Similar
ly
,
tim
b
r
e,
o
r
th
e
u
n
iq
u
e
to
n
al
q
u
ality
o
f
a
n
in
s
tr
u
m
e
n
t
o
r
v
o
ice,
a
f
f
ec
ts
h
o
w
en
g
a
g
in
g
o
r
s
o
o
th
i
n
g
th
e
m
u
s
ic
f
ee
ls
.
So
f
ter
tim
b
r
es
ar
e
o
f
ten
ass
o
ciate
d
with
r
elax
a
tio
n
,
wh
er
ea
s
b
r
ig
h
ter
,
s
h
ar
p
e
r
tim
b
r
es
ca
n
h
elp
m
ain
tain
atten
tio
n
an
d
f
o
cu
s
.
Am
p
litu
d
e
in
f
l
u
en
ce
s
th
e
v
o
l
u
m
e
o
r
in
ten
s
ity
o
f
m
u
s
ic,
wh
i
ch
d
ir
ec
tly
im
p
ac
ts
p
h
y
s
io
lo
g
ical
r
esp
o
n
s
es
lik
e
h
ea
r
t
r
ate
a
n
d
s
tr
ess
lev
els.
So
f
ter
v
o
l
u
m
es
ar
e
o
f
ten
ass
o
ciate
d
with
a
ca
lm
in
g
ef
f
ec
t.
A
s
tead
y
b
ea
t
ca
n
af
f
e
ct
th
e
s
en
s
e
o
f
s
tab
ilit
y
th
at
c
an
h
elp
to
r
elax
a
n
d
ea
s
e
ac
u
t
e
s
tr
ess
[
4
0
]
.
Als
o
,
ce
r
tain
h
ar
m
o
n
ic
p
atter
n
s
ca
n
ev
o
k
e
ca
lm
n
ess
,
s
ad
n
ess
,
to
n
o
s
talg
ia.
I
t
is
f
o
u
n
d
th
at
th
e
ef
f
ec
ts
o
n
th
e
m
en
tal
s
tate
d
o
n
o
t
ju
s
t
co
m
e
f
r
o
m
o
n
e
elem
en
t
o
f
m
u
s
i
c.
R
ath
er
,
th
e
co
m
b
in
atio
n
o
f
tem
p
o
,
tim
b
r
e,
am
p
litu
d
e,
b
ea
ts
,
an
d
h
a
r
m
o
n
ic
s
tr
u
ctu
r
es
cr
ea
tes
th
e
ef
f
ec
ts
o
n
th
e
m
en
tal
s
tate.
Fo
r
ex
am
p
le,
th
e
m
ix
o
f
tem
p
o
an
d
tim
b
r
e
ca
n
r
ea
lly
af
f
ec
t
h
o
w
p
eo
p
le
f
ee
l.
Stu
d
i
es
h
av
e
s
h
o
wn
th
at
f
aster
tem
p
o
s
co
m
b
in
ed
with
s
o
f
ter
s
o
u
n
d
s
ca
n
a
f
f
ec
t
s
o
m
eo
n
e’
s
m
o
ti
v
atio
n
a
n
d
h
a
p
p
in
ess
,
wh
ile
s
lo
wer
tem
p
o
s
co
m
b
i
n
ed
with
s
h
ar
p
er
s
o
u
n
d
s
ca
n
im
p
r
o
v
e
f
o
cu
s
an
d
clar
ity
[
3
4
]
,
[
3
6
]
–
[
3
8
]
.
An
aly
zin
g
th
ese
co
m
b
in
atio
n
s
o
f
m
u
s
ical
f
ea
tu
r
es
h
elp
s
r
esear
ch
er
s
u
n
d
e
r
s
tan
d
h
o
w
m
u
s
ic
af
f
ec
ts
th
e
m
in
d
.
T
h
is
m
ak
es
th
e
p
r
o
ce
s
s
o
f
m
o
d
elin
g
o
r
class
if
y
in
g
th
e
em
o
tio
n
al
im
p
ac
t
o
f
m
u
s
ic
ea
s
ier
.
T
ab
le
4
s
u
m
m
ar
izes
v
ar
io
u
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
la
s
s
i
fyin
g
cla
s
s
ica
l m
u
s
ic’
s
t
h
era
p
eu
tic
effec
ts
u
s
in
g
d
ee
p
l
ea
r
n
in
g
:
a
r
ev
iew
(
A
n
g
elin
)
4937
r
esear
ch
p
ap
er
s
th
at
u
tili
ze
f
ea
tu
r
e
ex
tr
ac
tio
n
tech
n
i
q
u
es
an
d
class
if
icatio
n
alg
o
r
ith
m
s
to
an
aly
ze
a
n
au
d
io
-
b
ased
d
ataset.
T
h
is
tab
le
in
clu
d
es
in
f
o
r
m
atio
n
o
n
t
h
e
ty
p
es
o
f
m
ac
h
in
e
lea
r
n
in
g
o
r
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
u
s
ed
,
to
o
ls
an
d
m
eth
o
d
s
f
o
r
f
ea
t
u
r
e
ex
tr
ac
tio
n
s
u
ch
as
MFC
C
,
an
d
ev
alu
atio
n
m
etr
ics
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e.
T
ab
le
3
.
C
o
m
p
a
r
is
o
n
o
f
k
ey
f
e
atu
r
es a
n
d
th
e
e
f
f
ec
ts
M
u
s
i
c
a
l
f
e
a
t
u
r
e
I
n
d
i
c
a
t
o
r
s a
n
d
t
h
e
e
f
f
e
c
t
o
n
m
e
n
t
a
l
st
a
t
e
S
t
u
d
i
e
s s
u
p
p
o
r
t
i
n
g
Te
mp
o
F
a
st
e
r
t
e
m
p
o
s
e
n
h
a
n
c
e
m
o
t
i
v
a
t
i
o
n
a
n
d
f
o
c
u
s,
a
n
d
s
l
o
w
e
r
t
e
m
p
o
s
e
n
h
a
n
c
e
r
e
l
a
x
a
t
i
o
n
[
1
6
]
,
[
3
4
]
,
[
3
6
]
–
[
3
8
]
Ti
m
b
r
e
S
o
f
t
e
r
t
o
n
e
s
p
r
o
m
o
t
e
r
e
l
a
x
a
t
i
o
n
a
n
d
s
h
a
r
p
e
r
t
o
n
e
s
p
r
o
m
o
t
e
f
o
c
u
s
[
3
4
]
,
[
3
7
]
A
mp
l
i
t
u
d
e
Lo
w
e
r
v
o
l
u
mes
c
a
l
m
a
n
d
r
e
d
u
c
e
s
t
r
e
s
s
[
3
4
]
B
e
a
t
s
S
t
e
a
d
y
r
h
y
t
h
ms
r
e
d
u
c
e
a
c
u
t
e
s
t
r
e
ss
[
3
5
]
H
a
r
mo
n
i
c
p
a
t
t
e
r
n
s
Ev
o
k
e
s e
mo
t
i
o
n
s s
u
c
h
a
s c
a
l
m
n
e
ss
,
n
o
st
a
l
g
i
a
,
o
r
s
a
d
n
e
ss
[
1
6
]
T
ab
le
4
.
R
esear
ch
p
a
p
er
s
u
m
m
ar
ies o
f
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
class
if
icatio
n
tech
n
iq
u
es
R
e
f
e
r
e
n
c
e
A
l
g
o
r
i
t
h
m
To
o
l
s
a
n
d
me
t
h
o
d
s
Ev
a
l
u
a
t
i
o
n
R
e
s
u
l
t
s
[
1
6
]
DNN
Li
b
r
o
sa
,
M
F
C
C
C
o
n
f
u
s
i
o
n
mat
r
i
x
A
n
o
v
e
r
a
l
l
a
c
c
u
r
a
c
y
o
f
m
o
r
e
t
h
a
n
9
4
%
w
a
s
a
c
h
i
e
v
e
d
b
y
t
h
e
m
o
d
e
l
[
4
1
]
C
N
N
,
g
a
t
e
d
l
i
n
e
a
r
u
n
i
t
s
(
G
LU
)
,
r
e
c
u
r
r
e
n
t
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
(
R
C
N
N
)
,
r
e
si
d
u
a
l
g
a
t
e
d
l
i
n
e
a
r
u
n
i
t
s (
R
G
LU
)
Li
b
r
o
sa
,
M
F
C
C
A
c
c
u
r
a
c
y
(
%),
C
o
n
f
u
s
i
o
n
mat
r
i
x
Th
e
h
i
g
h
e
st
m
o
d
e
l
a
c
c
u
r
a
c
y
a
c
h
i
e
v
e
d
w
a
s
8
7
%.
[
1
7
]
D
e
c
i
s
i
o
n
t
r
e
e
,
r
a
n
d
o
m
f
o
r
e
s
t
,
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s,
m
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
(
M
LP)
,
LST
M
n
e
u
r
a
l
n
e
t
w
o
r
k
,
C
N
N
s,
a
n
d
C
N
N
-
LSTM
h
y
b
r
i
d
M
F
C
C
,
M
e
l
S
p
e
c
t
r
o
g
r
a
m
,
C
h
r
o
ma
f
e
a
t
u
r
e
s
A
c
c
u
r
a
c
y
(
%)
U
si
n
g
M
F
C
C
,
M
e
l
s
p
e
c
t
r
o
g
r
a
m
,
a
n
d
c
h
r
o
ma
f
e
a
t
u
r
e
s
w
i
t
h
d
e
c
i
s
i
o
n
t
r
e
e
,
r
a
n
d
o
m
f
o
r
e
st
,
M
LP,
a
n
d
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s,
t
h
e
mo
d
e
l
a
c
c
u
r
a
c
y
i
s
8
9
.
6
6
%
.
W
i
t
h
LST
M
,
C
N
N
,
a
n
d
C
N
N
-
LSTM
mo
d
e
l
s
,
i
t
a
c
h
i
e
v
e
s
8
5
%
a
c
c
u
r
a
c
y
.
[
1
8
]
M
LP,
s
e
q
u
e
n
t
i
a
l
m
i
n
i
ma
l
o
p
t
i
m
i
z
a
t
i
o
n
(
S
M
O
)
f
o
r
S
V
M
,
r
a
n
d
o
m
f
o
r
e
s
t
,
D
N
N
M
F
C
C
,
Li
b
r
o
s
a
C
o
n
f
u
s
i
o
n
mat
r
i
x
,
a
c
c
u
r
a
c
y
,
A
U
C
,
F1
-
sc
o
r
e
,
p
r
e
c
i
si
o
n
,
r
e
c
a
l
l
Th
e
S
M
O
mo
d
e
l
a
c
h
i
e
v
e
d
a
n
A
U
C
o
f
0
.
9
6
9
,
a
n
a
c
c
u
r
a
c
y
o
f
0
.
8
6
0
,
a
n
F
1
-
s
c
o
r
e
o
f
0
.
8
6
1
,
a
p
r
e
c
i
si
o
n
o
f
0
.
8
6
5
,
a
n
d
a
r
e
c
a
l
l
o
f
0
.
8
6
0
.
T
h
e
r
a
n
d
o
m
f
o
r
e
st
m
o
d
e
l
h
a
d
a
n
A
U
C
o
f
0
.
9
8
7
,
a
n
a
c
c
u
r
a
c
y
o
f
0
.
8
5
5
,
a
n
F
1
-
sco
r
e
o
f
0
.
8
4
9
,
a
p
r
e
c
i
si
o
n
o
f
0
.
8
6
3
,
a
n
d
a
r
e
c
a
l
l
o
f
0
.
8
5
5
.
T
h
e
n
e
u
r
a
l
n
e
t
w
o
r
k
mo
d
e
l
p
e
r
f
o
r
m
e
d
t
h
e
b
e
s
t
,
w
i
t
h
a
n
A
U
C
o
f
0
.
9
8
9
,
a
n
a
c
c
u
r
a
c
y
o
f
0
.
8
8
9
,
a
n
F
1
-
sco
r
e
o
f
0
.
8
8
9
,
a
p
r
e
c
i
si
o
n
o
f
0
.
8
9
1
,
a
n
d
a
r
e
c
a
l
l
o
f
0
.
8
8
9
.
[
4
2
]
C
N
N
-
LSTM
M
F
C
C
A
c
c
u
r
a
c
y
U
si
n
g
t
h
e
M
i
l
l
i
o
n
S
o
n
g
D
a
t
a
se
t
,
t
h
e
c
o
m
b
i
n
e
d
a
u
d
i
o
f
e
a
t
u
r
e
s
n
e
t
w
o
r
k
c
l
a
ssi
f
i
e
r
a
c
h
i
e
v
e
s
a
n
a
u
d
i
o
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
y
o
f
6
8
%,
a
l
y
r
i
c
s
c
l
a
ssi
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
y
o
f
7
4
%,
a
n
d
a
n
a
v
e
r
a
g
e
m
u
l
t
i
mo
d
a
l
a
c
c
u
r
a
c
y
o
f
7
8
%,
w
h
i
c
h
i
s
b
e
t
t
e
r
t
h
a
n
u
si
n
g
a
si
n
g
l
e
mo
d
e
.
[
4
3
]
C
N
N
,
R
N
N
M
F
C
C
C
o
n
f
u
s
i
o
n
mat
r
i
x
,
p
r
e
c
i
si
o
n
,
r
e
c
a
l
l
,
F
1
-
sc
o
r
e
Th
e
m
o
d
e
l
a
c
h
i
e
v
e
s
a
n
a
c
c
u
r
a
c
y
o
f
8
5
.
3
6
%
o
n
a
1
0
-
g
e
n
r
e
c
l
a
ssi
f
i
c
a
t
i
o
n
t
a
s
k
.
W
h
e
n
t
r
a
i
n
e
d
a
n
d
t
e
s
t
e
d
o
n
t
h
e
M
a
g
n
a
T
a
g
A
Tu
n
e
d
a
t
a
se
t
w
i
t
h
1
8
,
4
7
6
2
9
-
se
c
o
n
d
c
l
i
p
s
,
i
t
a
c
h
i
e
v
e
s
a
n
a
c
c
u
r
a
c
y
o
f
8
6
.
0
6
%.
[
4
4
]
C
N
N
M
u
s
i
c
e
m
o
t
i
o
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
sy
st
e
m (
M
EC
S
)
sp
e
c
t
r
o
g
r
a
m
A
c
c
u
r
a
c
y
(
%),
l
o
ss
T
h
e
M
E
C
S
m
o
d
e
l
s
h
a
v
e
v
a
r
y
i
n
g
r
e
s
u
l
t
s
:
M
E
C
S
1
h
a
s
b
e
t
t
e
r
a
c
c
u
r
a
c
y
a
n
d
l
o
w
e
r
l
o
s
s
t
h
a
n
M
E
C
S
2
,
w
h
i
l
e
M
E
C
S
3
h
a
s
a
c
c
u
r
a
c
y
r
e
s
u
l
t
s
o
f
8
2
.
3
%
,
8
2
%
,
a
n
d
8
1
.
6
%
a
c
r
o
s
s
t
h
r
e
e
t
e
s
t
s
.
[
2
7
]
LSTM
-
DNN
M
F
C
C
A
c
c
u
r
a
c
y
,
p
r
e
c
i
si
o
n
,
r
e
c
a
l
l
,
F
-
mea
s
u
r
e
Th
e
o
v
e
r
a
l
l
a
c
c
u
r
a
c
y
i
s
9
9
.
1
9
%,
u
si
n
g
10
-
f
o
l
d
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
.
[
4
5
]
C
N
N
M
F
C
C
A
c
c
u
r
a
c
y
,
l
o
s
s
Th
e
r
e
se
a
r
c
h
e
r
f
o
u
n
d
t
h
a
t
t
h
e
r
e
c
o
g
n
i
t
i
o
n
a
c
c
u
r
a
c
y
o
f
t
h
e
p
r
o
p
o
se
d
m
e
t
h
o
d
i
s
9
2
.
0
6
%.
T
a
b
les
2
a
n
d
3
s
h
o
w
t
h
e
o
v
e
r
all
c
o
m
p
ar
is
o
n
o
f
th
e
r
ese
ar
c
h
p
a
p
e
r
s
a
n
d
p
r
o
v
id
e
a
n
a
n
a
l
y
s
is
o
f
t
h
e
v
a
r
i
o
u
s
t
ec
h
n
i
q
u
es
u
s
e
d
t
o
cla
s
s
if
y
m
u
s
ic
o
r
a
u
d
io
-
b
as
ed
c
la
s
s
if
i
ca
t
io
n
.
O
n
e
o
f
t
h
e
f
o
cu
s
es
o
f
th
ese
s
t
u
d
ies
is
o
n
t
h
e
m
et
h
o
d
s
o
f
f
ea
tu
r
e
e
x
t
r
ac
ti
o
n
,
wi
th
MFC
C
s
h
o
w
in
g
a
s
o
n
e
o
f
t
h
e
m
o
s
t
c
o
m
m
o
n
l
y
u
s
ed
te
c
h
n
iq
u
es
.
D
u
e
to
t
h
eir
a
b
ili
ty
t
o
r
ep
r
ese
n
t
a
u
d
i
o
i
n
a
wa
y
t
h
a
t
al
ig
n
s
w
it
h
h
u
m
an
p
e
r
ce
p
ti
o
n
o
f
s
o
u
n
d
,
MFC
C
s
ar
e
wi
d
e
ly
ap
p
li
e
d
i
n
a
u
d
io
s
ig
n
al
p
r
o
c
es
s
in
g
[
4
6
]
.
I
n
a
u
d
io
p
r
o
ce
s
s
in
g
,
t
h
is
m
et
h
o
d
is
c
r
u
ci
al
f
o
r
t
r
a
n
s
f
o
r
m
i
n
g
r
a
w
a
u
d
i
o
in
t
o
a
f
o
r
m
t
h
at
is
s
u
i
ta
b
l
e
f
o
r
class
i
f
y
i
n
g
em
o
t
io
n
al
r
es
p
o
n
s
e
s
.
B
esi
d
es
MFC
C
,
p
r
e
v
i
o
u
s
r
e
s
ea
r
c
h
e
r
s
h
a
v
e
a
ls
o
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
er
20
25
:
4
9
3
3
-
4
9
4
2
4938
u
s
e
d
m
et
h
o
d
s
li
k
e
t
h
e
Me
l
s
p
ec
t
r
o
g
r
a
m
a
n
d
ch
r
o
m
a
f
ea
t
u
r
e
s
t
o
ex
p
lo
r
e
t
h
e
f
r
e
q
u
e
n
c
y
a
n
d
h
ar
m
o
n
y
o
f
m
u
s
i
c
m
o
r
e
c
lo
s
el
y
.
T
h
es
e
tec
h
n
i
q
u
es
h
el
p
t
h
e
m
t
o
u
n
d
e
r
s
ta
n
d
th
e
m
u
s
i
ca
l
e
le
m
e
n
ts
t
h
at
a
f
f
ec
t
em
o
t
i
o
n
s
,
h
e
lp
in
g
th
e
m
t
o
class
if
y
u
s
in
g
m
ac
h
i
n
e
l
ea
r
n
i
n
g
o
r
d
e
ep
l
ea
r
n
i
n
g
a
l
g
o
r
i
th
m
s
.
T
o
b
e
tte
r
ill
u
s
t
r
a
te
t
h
es
e
r
e
lat
io
n
s
h
i
p
s
,
Fig
u
r
e
2
p
r
ese
n
ts
a
r
esea
r
c
h
m
in
d
m
ap
t
h
at
s
u
m
m
a
r
iz
es th
e
c
o
n
n
ec
t
io
n
s
b
et
wee
n
f
ea
tu
r
e
ex
tr
a
cti
o
n
te
ch
n
i
q
u
es
,
class
i
f
i
ca
t
io
n
m
o
d
els
,
a
n
d
e
v
alu
ati
o
n
m
et
h
o
d
s
.
T
h
is
v
is
u
al
izat
io
n
p
r
o
v
i
d
es
a
cle
ar
er
u
n
d
e
r
s
t
an
d
i
n
g
o
f
h
o
w
d
i
f
f
er
e
n
t
c
o
m
p
o
n
e
n
ts
wo
r
k
to
g
eth
e
r
i
n
m
u
s
i
c
-
b
ase
d
em
o
t
io
n
class
i
f
i
ca
t
io
n
.
I
n
s
u
m
m
ar
ized
s
tu
d
ies,
class
if
icatio
n
m
eth
o
d
s
o
f
ten
u
s
e
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
,
with
C
NNs
b
ein
g
th
e
m
o
s
t
co
m
m
o
n
ch
o
ice.
C
NNs
ar
e
g
o
o
d
at
ca
p
tu
r
in
g
s
p
atial
f
ea
tu
r
es,
wh
ich
m
ak
es
th
em
ef
f
ec
tiv
e
f
o
r
an
aly
zin
g
co
m
p
lex
p
atter
n
s
in
m
u
s
ic
d
ata
[
4
7
]
.
B
ec
au
s
e
m
u
s
ic
h
ap
p
en
s
o
v
er
tim
e,
it
o
f
ten
n
ee
d
s
m
o
d
els
th
at
ca
n
wo
r
k
with
th
is
k
in
d
o
f
d
ata.
As
a
r
esu
lt,
C
NNs
ar
e
o
f
te
n
co
m
b
i
n
ed
with
L
STM
n
etwo
r
k
s
to
cr
ea
te
h
y
b
r
id
m
o
d
els,
lik
e
C
NN
-
L
STM
,
wh
ich
ca
n
b
etter
u
n
d
e
r
s
tan
d
p
ar
t
s
o
f
m
u
s
ic
[
4
8
]
.
Oth
er
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
,
lik
e
DNN
,
ar
e
also
o
f
ten
u
s
ed
f
o
r
th
eir
a
b
ilit
y
to
ca
p
tu
r
e
p
atter
n
s
with
in
lar
g
e
d
atas
ets
b
y
p
ass
in
g
d
ata
th
r
o
u
g
h
m
u
ltip
le
la
y
er
s
o
f
n
eu
r
o
n
s
.
Fo
r
th
e
s
am
e
r
ea
s
o
n
th
at
C
NN
is
co
m
b
in
ed
with
L
STM
,
DNN
is
f
r
eq
u
e
n
tly
co
m
b
in
ed
with
L
S
T
M
to
h
an
d
le
th
e
tem
p
o
r
al
p
ar
ts
o
f
th
e
m
u
s
ic.
R
NNs
ar
e
also
u
s
ed
f
o
r
t
h
eir
s
tr
en
g
th
in
p
r
o
ce
s
s
in
g
s
eq
u
en
c
es.
Mo
r
e
ad
v
an
ce
d
m
o
d
els
lik
e
GL
U,
R
C
NN,
an
d
R
GL
U
ar
e
al
s
o
d
esig
n
ed
to
ca
p
tu
r
e
b
o
th
s
p
atial
an
d
tem
p
o
r
al
f
ea
tu
r
es,
m
ak
in
g
th
em
v
er
s
atile
f
o
r
d
etailed
m
u
s
ic
class
if
icatio
n
task
s
[
4
9
]
.
Me
an
wh
ile,
ML
P
is
u
s
ed
as
a
s
im
p
ler
,
f
u
lly
co
n
n
e
cted
n
eu
r
al
n
etwo
r
k
,
an
d
alth
o
u
g
h
th
ey
d
o
n
’
t
s
p
ec
ialize
in
s
eq
u
en
tial
d
ata,
th
ey
ar
e
s
till
ap
p
lied
f
o
r
ce
r
tain
ty
p
es
o
f
m
u
s
ic
class
if
icatio
n
to
a
n
aly
ze
th
e
d
ata
[
5
0
]
.
T
h
ese
m
o
d
els
ar
e
ev
al
u
ate
d
u
s
in
g
d
if
f
er
en
t
m
ea
s
u
r
es,
li
k
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
th
e
F1
-
s
co
r
e,
to
en
s
u
r
e
th
at
th
e
class
if
icatio
n
is
r
eliab
le.
So
m
e
s
tu
d
ies
also
ta
k
e
a
m
u
lti
-
m
o
d
al
ap
p
r
o
ac
h
b
y
co
m
b
in
in
g
au
d
io
an
d
ly
r
ics,
wh
ich
h
elp
s
to
g
iv
e
m
o
r
e
u
n
d
er
s
tan
d
in
g
o
f
h
o
w
d
if
f
er
en
t a
s
p
ec
ts
o
f
m
u
s
ic
in
f
lu
e
n
ce
em
o
tio
n
.
Fig
u
r
e
2
.
R
esear
ch
m
in
d
m
ap
3
.
2
.
RQ
2
:
w
ha
t
a
re
t
he
mo
s
t
co
m
mo
n
a
nd
ef
f
ec
t
iv
e
f
ea
t
ure
ex
t
ra
ct
io
n
m
e
t
ho
ds
f
o
r
cla
s
s
if
y
ing
t
he
im
pa
ct
o
f
cla
s
s
ica
l m
us
ic
o
n m
ent
a
l hea
lt
h?
B
ased
o
n
t
h
e
r
es
ea
r
c
h
s
u
m
m
ar
ies
in
T
a
b
le
3
,
it
is
e
v
i
d
e
n
t
t
h
a
t
t
h
e
m
o
s
t
c
o
m
m
o
n
a
n
d
e
f
f
e
cti
v
e
f
ea
tu
r
e
ex
t
r
ac
ti
o
n
m
et
h
o
d
u
s
e
d
f
o
r
c
lass
i
f
y
in
g
a
u
d
i
o
is
MFC
C
s
.
I
n
a
lm
o
s
t
a
ll
o
f
t
h
e
s
t
u
d
ies
,
MFC
C
is
u
s
e
d
as
th
e
f
e
at
u
r
e
ex
tr
ac
t
io
n
m
et
h
o
d
.
MFC
C
s
ca
n
ef
f
ec
t
iv
el
y
ex
tr
a
ct
au
d
i
o
f
ea
tu
r
es
l
ik
e
tim
b
r
e
,
p
it
ch
,
a
n
d
r
h
y
th
m
[
1
9
]
,
[
2
0
]
.
I
ts
ef
f
e
cti
v
en
ess
is
also
d
e
m
o
n
s
tr
at
ed
i
n
n
u
m
er
o
u
s
s
t
u
d
ies
,
w
h
e
r
e
m
o
d
els
u
s
in
g
MFC
C
c
o
n
s
is
t
en
tl
y
ac
h
ie
v
e
h
ig
h
ac
cu
r
a
c
y
.
F
o
r
e
x
a
m
p
le
,
i
n
t
h
e
s
t
u
d
y
t
h
at
u
s
es
L
S
T
M
-
DNN
f
o
r
m
u
s
i
c
e
m
o
ti
o
n
r
ec
o
g
n
i
ti
o
n
,
M
FC
C
h
el
p
ed
t
h
e
m
o
d
el
t
o
r
ea
c
h
a
n
ac
c
u
r
a
cy
o
f
9
9
.
1
9
%
.
B
esi
d
es
MFC
C
,
o
t
h
e
r
f
e
at
u
r
e
ex
tr
ac
t
io
n
m
et
h
o
d
s
,
s
u
ch
as
th
e
M
el
s
p
e
ct
r
o
g
r
a
m
an
d
c
h
r
o
m
a
f
e
at
u
r
es
,
a
r
e
als
o
u
s
e
d
,
b
u
t
l
ess
f
r
e
q
u
en
tl
y
.
Me
l
s
p
e
ct
r
o
g
r
a
m
an
d
c
h
r
o
m
a
f
e
at
u
r
es
a
r
e
als
o
u
s
e
d
i
n
s
t
u
d
i
es,
co
m
b
i
n
i
n
g
t
h
e
m
wit
h
ad
v
a
n
c
ed
d
ee
p
l
ea
r
n
in
g
m
o
d
els
l
ik
e
C
NN
a
n
d
C
NN
-
L
STM
.
T
h
e
M
el
s
p
ec
tr
o
g
r
a
m
e
m
p
h
asiz
es
c
h
a
n
g
e
o
v
er
t
im
e,
w
h
ic
h
is
u
s
e
f
u
l
f
o
r
m
u
s
ic
class
i
f
i
ca
t
io
n
,
wh
ile
ch
r
o
m
a
c
ap
tu
r
es
t
h
e
p
it
c
h
a
n
d
th
e
h
ar
m
o
n
ic
co
n
t
e
n
t
[
5
1
]
.
T
h
ese
m
et
h
o
d
s
p
r
o
v
i
d
e
ad
d
i
ti
o
n
a
l
r
e
p
r
es
en
tat
io
n
s
o
f
th
e
au
d
i
o
’
s
f
r
e
q
u
e
n
c
y
a
n
d
h
a
r
m
o
n
i
c
s
tr
u
ct
u
r
e,
f
u
r
t
h
e
r
e
n
h
a
n
cin
g
t
h
e
c
lass
i
f
i
ca
t
io
n
p
r
o
c
ess
.
T
h
e
c
o
m
b
i
n
ati
o
n
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
la
s
s
i
fyin
g
cla
s
s
ica
l m
u
s
ic’
s
t
h
era
p
eu
tic
effec
ts
u
s
in
g
d
ee
p
l
ea
r
n
in
g
:
a
r
ev
iew
(
A
n
g
elin
)
4939
th
es
e
f
e
at
u
r
es
w
it
h
d
e
ep
le
a
r
n
in
g
al
g
o
r
it
h
m
s
s
i
g
n
i
f
i
ca
n
tl
y
e
n
h
a
n
c
es
t
h
e
a
cc
u
r
ac
y
a
n
d
e
f
f
e
cti
v
e
n
ess
o
f
m
o
d
els
aim
ed
a
t
ass
ess
i
n
g
th
e
em
o
t
io
n
al
an
d
t
h
e
r
a
p
e
u
t
ic
e
f
f
ec
ts
o
f
cl
ass
ic
al
m
u
s
ic
.
3
.
3
.
RQ
3
:
w
ha
t
deep
lea
rning
a
lg
o
rit
hm
s
a
re
m
o
s
t
ef
f
e
ct
iv
e
f
o
r
cla
s
s
if
y
ing
t
he
t
her
a
peutic
ef
f
ec
t
s
o
f
cla
s
s
ica
l m
us
ic?
T
a
b
l
e
5
s
h
o
ws
t
h
a
t
t
h
e
s
t
u
d
i
e
s
u
s
e
s
e
v
e
r
al
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
,
b
u
t
C
NN
a
r
e
s
h
o
w
n
a
s
o
n
e
o
f
t
h
e
m
o
s
t
c
o
m
m
o
n
l
y
u
s
e
d
f
o
r
m
u
s
ic
c
l
as
s
i
f
i
c
at
i
o
n
.
C
N
Ns
,
w
h
i
c
h
a
r
e
u
s
u
a
ll
y
u
s
e
d
f
o
r
i
m
a
g
e
a
n
d
p
a
t
t
e
r
n
r
e
c
o
g
n
it
i
o
n
t
a
s
k
s
[
5
2
]
,
a
d
a
p
t
w
e
l
l
t
o
m
u
s
i
c
c
l
as
s
i
f
i
c
a
ti
o
n
b
y
i
d
e
n
t
i
f
y
i
n
g
c
o
m
p
l
e
x
,
h
i
e
r
a
r
c
h
i
c
a
l
p
a
t
t
e
r
n
s
w
i
t
h
i
n
t
h
e
a
u
d
io
f
e
a
t
u
r
e
s
e
x
t
r
a
c
t
e
d
f
r
o
m
t
h
e
m
u
s
i
c
[
5
3
]
.
I
n
s
e
v
e
r
a
l
s
t
u
d
ie
s
,
C
NN
s
h
a
v
e
b
ee
n
u
s
e
d
b
o
t
h
a
s
s
tan
d
a
l
o
n
e
m
o
d
e
l
s
a
n
d
i
n
c
o
m
b
i
n
a
t
i
o
n
w
i
t
h
o
t
h
e
r
a
r
c
h
i
t
e
c
t
u
r
es
s
u
c
h
as
L
S
T
M
n
e
t
w
o
r
k
s
,
w
h
i
c
h
a
r
e
p
a
r
t
i
c
u
l
a
r
l
y
g
o
o
d
a
t
h
a
n
d
l
i
n
g
t
i
m
e
-
s
e
q
u
e
n
c
e
d
d
a
t
a
[
5
4
]
.
Al
t
h
o
u
g
h
C
N
Ns
a
r
e
t
h
e
m
o
s
t
c
o
m
m
o
n
l
y
u
s
e
d
,
i
t
i
s
s
h
o
w
n
t
h
at
C
NN
,
a
s
a
s
ta
n
d
a
l
o
n
e
m
o
d
e
l
,
o
n
l
y
r
e
a
c
h
es
9
2
.
0
6
%
a
c
c
u
r
a
c
y
.
T
h
e
h
y
b
r
i
d
m
o
d
e
l
C
N
N
-
L
S
T
M
a
p
p
r
o
a
c
h
h
a
s
b
ee
n
s
h
o
w
n
t
o
a
c
h
i
e
v
e
r
e
s
u
l
ts
w
i
t
h
a
n
o
v
e
r
a
l
l
a
c
c
u
r
ac
y
o
f
8
5
%
,
n
o
t
a
s
h
i
g
h
a
s
L
S
T
M
-
D
NN
,
w
h
i
c
h
r
e
a
c
h
es
a
n
a
c
c
u
r
a
c
y
o
f
u
p
t
o
9
9
.
1
9
%
.
O
t
h
e
r
d
e
e
p
l
ea
r
n
i
n
g
a
lg
o
r
i
t
h
m
s
,
s
u
c
h
as
ML
P
a
n
d
R
N
N
,
a
ls
o
d
e
m
o
n
s
t
r
a
t
e
g
o
o
d
p
e
r
f
o
r
m
a
n
c
e
,
b
u
t
C
NN
a
n
d
D
N
N
-
b
a
s
e
d
a
l
g
o
r
i
t
h
m
s
g
e
n
e
r
a
l
l
y
a
c
h
i
e
v
e
h
i
g
h
e
r
a
c
c
u
r
a
c
y
,
m
a
k
i
n
g
t
h
e
m
t
h
e
p
r
e
f
e
r
r
e
d
c
h
o
i
c
e
f
o
r
m
u
s
i
c
c
l
a
s
s
i
f
ic
a
t
i
o
n
ta
s
k
s
.
I
t
c
o
n
c
l
u
d
e
s
t
h
a
t
C
N
N
-
L
S
T
M
m
o
d
e
ls
a
r
e
u
s
u
a
l
l
y
u
s
e
d
f
o
r
a
u
d
i
o
-
b
a
s
e
d
c
l
a
s
s
i
f
ic
a
t
i
o
n
,
e
v
e
n
t
h
o
u
g
h
t
h
e
i
r
a
c
c
u
r
a
c
y
v
a
r
i
e
s
a
cr
o
s
s
s
t
u
d
i
es
,
b
u
t
L
S
T
M
-
D
NN
h
a
s
p
r
o
v
e
n
t
o
h
a
v
e
t
h
e
h
i
g
h
e
s
t
a
c
c
u
r
a
c
y
.
T
ab
le
5
.
C
o
m
p
a
r
is
o
n
o
f
d
ee
p
l
ea
r
n
in
g
ac
c
u
r
ac
y
al
g
o
r
ith
m
s
A
l
g
o
r
i
t
h
ms
u
s
e
d
A
c
c
u
r
a
c
y
(
%)
S
t
u
d
i
e
s
r
e
f
e
r
e
n
c
e
DNN
94
[
1
6
]
C
N
N
,
G
LU
,
R
C
N
N
,
R
G
LU
87
[
4
1
]
M
LP,
LST
M
n
e
u
r
a
l
n
e
t
w
o
r
k
,
C
N
N
s,
a
n
d
C
N
N
-
LSTM
h
y
b
r
i
d
8
9
.
6
6
,
8
5
[
1
7
]
M
LP,
D
N
N
8
8
.
9
[
1
8
]
C
N
N
-
LSTM
68
[
4
2
]
C
N
N
,
R
N
N
8
6
.
0
6
[
4
3
]
C
N
N
8
2
.
3
[
4
4
]
LSTM
-
DNN
9
9
.
1
9
[
2
7
]
C
N
N
9
2
.
0
6
[
4
5
]
3
.
4
.
RQ
4
:
w
ha
t
m
e
t
ho
ds
a
re
em
plo
y
ed
f
o
r
ev
a
lua
t
ing
t
he
perf
o
rm
a
nce
o
f
deep
lea
rning
m
o
dels
in
a
ud
io
-
ba
s
ed
cla
s
s
if
ica
t
io
n?
R
e
s
ea
r
ch
er
s
co
m
m
o
n
ly
u
s
e
a
cc
u
r
ac
y
m
e
tr
ic
s
alo
n
g
s
i
d
e
o
th
er
ev
a
lu
a
tio
n
t
ec
h
n
iq
u
e
s
to
co
m
p
r
eh
en
s
iv
el
y
a
s
s
e
s
s
th
e
p
er
f
o
r
m
an
c
e
o
f
d
e
ep
l
ea
r
n
in
g
m
o
d
el
s
in
au
d
io
-
b
a
s
ed
c
la
s
s
i
f
ic
at
io
n
.
Acc
u
r
a
cy
(
%)
i
s
th
e
m
o
s
t
f
r
eq
u
en
tly
u
s
ed
m
e
tr
ic,
in
d
ic
at
in
g
h
o
w
a
cc
u
r
a
te
ly
th
e
m
o
d
el
's
p
r
ed
ic
t
i
o
n
s
m
a
tch
th
e
tr
u
e
cla
s
s
if
i
ca
tio
n
o
u
tco
m
e
s
[
5
5
]
.
Ho
w
ev
er
,
m
o
d
el
s
ar
e
o
f
ten
f
u
r
th
er
ev
alu
at
ed
u
s
in
g
a
co
n
f
u
s
i
o
n
m
atr
ix
,
wh
ich
p
r
o
v
id
e
s
in
s
ig
h
t
in
to
s
p
ec
if
ic
p
r
ed
i
ct
io
n
er
r
o
r
s
ac
r
o
s
s
d
i
f
f
er
en
t
c
la
s
s
e
s
.
B
e
s
id
e
s
a
cc
u
r
ac
y
,
o
th
er
m
e
tr
ic
s
l
ik
e
p
r
ec
is
io
n
,
r
e
ca
ll,
F1
-
s
co
r
e
,
an
d
ar
e
a
u
n
d
er
th
e
cu
r
v
e
(
AU
C
)
ar
e
o
f
ten
u
s
ed
to
ev
alu
at
e
h
o
w
w
el
l
a
m
o
d
e
l
c
an
cla
s
s
if
y
[
5
6
]
.
Pr
ec
i
s
io
n
m
ea
s
u
r
e
s
th
e
ac
c
u
r
a
cy
o
f
p
o
s
i
tiv
e
p
r
ed
ic
tio
n
s
,
wh
i
le
r
ec
al
l
a
s
s
e
s
s
e
s
th
e
m
o
d
el
's
ef
f
e
ct
iv
en
e
s
s
in
d
e
tec
t
in
g
a
ll
o
f
th
e
tr
u
e
p
o
s
it
iv
e
ca
s
e
s
.
T
h
e
F1
-
s
c
o
r
e
co
m
b
in
e
s
p
r
ec
i
s
io
n
an
d
r
e
ca
ll
in
to
o
n
e
v
alu
e,
wh
ic
h
m
ak
e
s
i
t
u
s
ef
u
l
wh
en
th
er
e
i
s
an
u
n
ev
en
n
u
m
b
er
o
f
c
la
s
s
e
s
.
A
U
C
,
o
n
th
e
o
t
h
er
h
an
d
,
m
e
as
u
r
e
s
h
o
w
we
l
l
th
e
m
o
d
el
s
e
p
ar
a
te
s
th
e
cl
a
s
s
e
s
at
d
if
f
e
r
en
t
th
r
e
s
h
o
ld
s
,
w
it
h
h
ig
h
e
r
A
U
C
m
e
an
i
n
g
b
et
te
r
p
er
f
o
r
m
an
c
e
[
5
7
]
.
On
e
o
f
th
e
r
ev
i
ew
ed
s
tu
d
ie
s
e
m
p
lo
y
s
cr
o
s
s
-
v
a
l
id
a
tio
n
te
ch
n
i
q
u
e
s
,
s
u
c
h
as
1
0
-
f
o
l
d
cr
o
s
s
-
v
al
id
a
tio
n
,
to
en
s
u
r
e
th
a
t
th
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
i
s
n
o
t b
i
as
ed
b
y
an
y
p
ar
t
ic
u
l
ar
s
u
b
s
e
t
o
f
th
e
d
a
ta
[
5
8
]
.
I
t
i
s
f
o
u
n
d
t
h
a
t
n
o
t
a
l
l
e
v
a
l
u
a
t
i
o
n
m
e
t
h
o
d
s
w
o
r
k
e
f
f
e
c
t
i
v
e
l
y
i
n
a
l
l
c
o
n
t
e
x
t
s
.
E
v
e
n
t
h
o
u
g
h
a
c
c
u
r
a
c
y
i
s
c
o
m
m
o
n
l
y
u
s
e
d
,
i
t
c
a
n
b
e
m
i
s
l
e
a
d
i
n
g
w
i
t
h
i
m
b
a
l
a
n
c
e
d
d
a
t
a
,
w
h
e
r
e
o
n
e
c
l
a
s
s
i
s
m
u
c
h
m
o
r
e
c
o
m
m
o
n
t
h
a
n
t
h
e
o
t
h
e
r
.
I
n
t
h
a
t
c
a
s
e
,
a
m
o
d
e
l
m
i
g
h
t
s
e
e
m
a
c
c
u
r
a
t
e
w
h
i
l
e
m
i
s
s
i
n
g
i
m
p
o
r
t
a
n
t
p
r
e
d
i
c
t
i
o
n
s
f
o
r
s
m
a
l
l
e
r
c
l
a
s
s
e
s
.
T
h
i
s
i
s
w
h
e
n
p
r
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
a
n
d
F
-
m
e
a
s
u
r
e
c
a
n
b
e
u
s
e
d
e
f
f
e
c
t
i
v
e
l
y
b
e
c
a
u
s
e
t
h
e
F
-
m
e
a
s
u
r
e
b
a
l
a
n
c
e
s
p
r
e
c
i
s
i
o
n
a
n
d
r
e
c
a
l
l
.
Fro
m
a
ll
o
f
t
h
e
f
i
n
d
i
n
g
s
,
i
t
is
c
o
n
cl
u
d
e
d
t
h
at
C
N
N,
D
NN,
an
d
L
S
T
M
a
lg
o
r
it
h
m
s
ca
n
r
e
all
y
b
e
u
s
e
d
t
o
class
i
f
y
th
e
th
er
a
p
e
u
ti
c
ef
f
ec
ts
o
f
cl
ass
ic
al
m
u
s
i
c
o
n
m
e
n
t
al
h
e
alt
h
e
f
f
ec
t
iv
el
y
.
T
h
ese
m
o
d
els
ca
n
b
e
d
es
ig
n
ed
to
a
n
a
ly
ze
a
u
d
i
o
d
ata
t
o
r
ev
ea
l
h
o
w
d
i
f
f
e
r
e
n
t
m
u
s
i
ca
l
ele
m
e
n
ts
i
n
f
lu
e
n
ce
e
m
o
ti
o
n
s
a
n
d
m
en
t
al
s
ta
tes
.
C
N
Ns
ar
e
g
o
o
d
at
r
ec
o
g
n
izi
n
g
p
att
er
n
s
li
k
e
r
h
y
t
h
m
a
n
d
t
o
n
e
,
wh
ile
t
h
e
c
o
m
b
i
n
a
ti
o
n
o
f
C
NNs
a
n
d
L
S
T
M
all
o
ws
f
o
r
a
d
e
ep
er
u
n
d
er
s
ta
n
d
in
g
o
f
h
o
w
m
u
s
ic
is
o
v
e
r
tim
e.
DN
Ns ca
n
d
is
c
o
v
e
r
c
o
m
p
l
ex
p
at
te
r
n
s
i
n
l
ar
g
e
d
at
asets
.
Usi
n
g
MFC
C
s
as
a
f
ea
t
u
r
e
ex
tr
ac
t
io
n
m
et
h
o
d
is
b
en
ef
ici
al
,
i
n
c
o
r
p
o
r
ati
n
g
f
e
at
u
r
es
li
k
e
c
h
r
o
m
a
o
r
s
p
e
ct
r
al
co
n
t
r
as
t
ca
n
en
h
a
n
ce
t
h
e
m
o
d
el'
s
ab
ilit
y
t
o
u
n
d
e
r
s
t
an
d
i
m
p
o
r
t
an
t
as
p
e
c
ts
o
f
m
u
s
ic
,
s
u
c
h
as
h
a
r
m
o
n
y
a
n
d
to
n
alit
y
.
T
h
e
r
es
u
lts
f
r
o
m
v
a
r
i
o
u
s
s
t
u
d
i
es
s
u
p
p
o
r
t
t
h
e
id
ea
t
h
at
t
h
es
e
m
e
th
o
d
s
ca
n
e
f
f
ec
ti
v
el
y
c
lass
i
f
y
t
h
e
im
p
a
ct
o
f
class
ica
l
m
u
s
ic
o
r
its
t
h
e
r
a
p
eu
tic
ef
f
e
c
ts
o
n
m
en
tal
h
ea
lt
h
.
B
y
n
o
t
o
n
l
y
f
o
c
u
s
i
n
g
o
n
ac
c
u
r
a
cy
b
u
t
a
ls
o
c
o
n
s
id
er
in
g
m
et
r
i
cs
l
ik
e
F
1
-
s
c
o
r
e
,
a
cc
u
r
a
cy
,
an
d
r
ec
ei
v
e
r
o
p
e
r
at
in
g
c
h
ar
ac
t
er
is
tic
(
R
OC
)
-
AUC
,
r
es
e
ar
ch
er
s
c
an
c
r
e
ate
m
o
r
e
r
el
ia
b
le
m
o
d
els
th
at
a
cc
u
r
at
el
y
ass
ess
t
h
e
m
e
n
tal
h
e
alt
h
b
e
n
e
f
i
ts
o
f
class
i
ca
l
m
u
s
ic
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
er
20
25
:
4
9
3
3
-
4
9
4
2
4940
4.
CO
NCLU
SI
O
N
T
h
is
s
y
s
tem
atic
liter
atu
r
e
r
ev
i
ew
h
ig
h
lig
h
ts
k
ey
elem
en
ts
an
d
m
eth
o
d
s
u
s
ed
in
class
if
y
in
g
th
e
ef
f
ec
ts
o
f
m
u
s
ic,
p
a
r
ticu
lar
ly
class
ical
m
u
s
ic,
o
n
m
e
n
tal
h
ea
lth
.
M
u
s
ical
f
ea
tu
r
es
s
u
ch
as
tem
p
o
,
tim
b
r
e,
am
p
litu
d
e,
an
d
h
a
r
m
o
n
ic
p
atter
n
s
s
ig
n
if
ic
an
tly
in
f
lu
e
n
ce
em
o
tio
n
al
an
d
co
g
n
itiv
e
s
tates,
with
f
aster
t
em
p
o
s
an
d
b
r
ig
h
ter
tim
b
r
es
b
o
o
s
tin
g
aler
t
n
ess
,
wh
ile
s
lo
wer
tem
p
o
s
an
d
s
o
f
te
r
to
n
es
af
f
ec
t
r
elax
atio
n
.
Fo
r
f
ea
tu
r
e
ex
tr
ac
tio
n
,
MFC
C
is
th
e
m
o
s
t
co
m
m
o
n
l
y
em
p
lo
y
ed
an
d
ef
f
ec
tiv
e
m
e
th
o
d
.
C
NN
an
d
h
y
b
r
id
DNN
-
L
STM
m
o
d
els
ar
e
id
en
tifie
d
as
th
e
m
o
s
t
ef
f
ec
tiv
e
f
o
r
class
if
y
in
g
m
u
s
ic’
s
th
er
a
p
eu
tic
ef
f
ec
ts
,
ac
h
iev
in
g
h
ig
h
ac
cu
r
ac
y
.
T
o
ass
ess
th
ese
m
o
d
els,
ev
alu
atio
n
m
eth
o
d
s
lik
e
ac
cu
r
ac
y
,
co
n
f
u
s
io
n
m
atr
ices,
an
d
m
etr
ics
s
u
ch
a
s
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
an
d
AUC
ar
e
u
s
ed
with
cr
o
s
s
-
v
alid
atio
n
.
T
h
ese
f
in
d
in
g
s
p
o
in
t
to
th
e
im
p
o
r
ta
n
ce
o
f
b
o
th
m
u
s
ical
f
ea
tu
r
es
an
d
a
d
v
an
ce
d
d
ee
p
lear
n
in
g
m
eth
o
d
s
in
s
tu
d
y
in
g
m
u
s
ic'
s
im
p
ac
t
o
n
m
en
tal
h
ea
lth
.
T
h
is
r
ev
iew
h
ig
h
lig
h
ts
u
s
ef
u
l
a
p
p
r
o
ac
h
es,
b
u
t
th
er
e
a
r
e
s
o
m
e
lim
itatio
n
s
.
Dee
p
lear
n
in
g
m
o
d
els
o
f
ten
n
ee
d
a
lo
t
o
f
d
ata,
b
u
t f
in
d
in
g
en
o
u
g
h
r
esear
ch
p
ap
er
s
o
n
class
ical
m
u
s
ic’
s
th
er
ap
eu
tic
ef
f
ec
ts
is
ch
allen
g
in
g
.
Als
o
,
m
an
y
s
tu
d
ies
f
o
cu
s
o
n
g
en
er
al
m
u
s
ic
f
ea
tu
r
es
an
d
m
ig
h
t
m
is
s
th
e
s
p
ec
if
ic
th
er
ap
eu
tic
q
u
alities
o
f
class
ical
m
u
s
ic.
Fu
tu
r
e
r
esear
ch
co
u
ld
h
elp
b
y
r
ev
ie
win
g
m
o
r
e
p
ap
e
r
s
th
at
ex
p
lo
r
e
th
ese
u
n
iq
u
e
th
er
ap
e
u
tic
f
ea
tu
r
es.
I
t
co
u
ld
also
lo
o
k
in
to
u
s
in
g
th
ese
m
o
d
els in
r
ea
l
-
tim
e,
esp
ec
ially
in
clin
i
ca
l settin
g
s
wh
er
e
q
u
ick
r
esp
o
n
s
es a
r
e
n
ee
d
ed
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
an
k
s
to
th
e
B
ig
Data
L
ab
f
o
r
p
r
o
v
id
in
g
t
h
e
ess
en
tial r
eso
u
r
ce
s
an
d
in
f
r
astru
ctu
r
e.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
is
s
u
p
p
o
r
ted
b
y
th
e
R
esear
ch
,
I
n
n
o
v
atio
n
,
a
n
d
Su
s
tain
ab
ilit
y
Div
is
io
n
o
f
Un
iv
er
s
itas
Mu
ltime
d
ia
Nu
s
an
tar
a.
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
An
g
elin
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Sam
u
el
Ad
y
San
jay
a
✓
✓
✓
✓
✓
✓
✓
✓
Din
ar
Aj
e
n
g
K
r
is
t
iy
a
n
ti
✓
✓
✓
✓
✓
✓
✓
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
th
o
r
s
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
co
n
f
licts
o
f
in
ter
est r
e
lated
to
th
is
wo
r
k
.
DATA AV
AI
L
AB
I
L
I
T
Y
D
a
t
a
a
v
a
il
a
b
i
li
t
y
is
n
o
t
a
p
p
l
i
ca
b
l
e
t
o
t
h
is
p
a
p
e
r
a
s
n
o
n
e
w
d
at
a
w
e
r
e
c
r
e
a
t
e
d
o
r
a
n
al
y
z
e
d
i
n
t
h
is
s
t
u
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
T.
L.
G
o
l
d
e
n
e
t
a
l
.
,
“
Th
e
u
s
e
o
f
mu
s
i
c
i
n
t
h
e
t
r
e
a
t
me
n
t
a
n
d
ma
n
a
g
e
m
e
n
t
o
f
seri
o
u
s
me
n
t
a
l
i
l
l
n
e
ss
:
a
g
l
o
b
a
l
sc
o
p
i
n
g
r
e
v
i
e
w
o
f
t
h
e
l
i
t
e
r
a
t
u
r
e
,
”
Fro
n
t
i
e
rs i
n
Psy
c
h
o
l
o
g
y
,
v
o
l
.
1
2
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
sy
g
.
2
0
2
1
.
6
4
9
8
4
0
.
[
2
]
A
.
F
o
n
sec
a
a
n
d
J.
O
sma,
“
U
si
n
g
i
n
f
o
r
mat
i
o
n
a
n
d
c
o
mm
u
n
i
c
a
t
i
o
n
t
e
c
h
n
o
l
o
g
i
e
s
(
I
C
T)
f
o
r
me
n
t
a
l
h
e
a
l
t
h
p
r
e
v
e
n
t
i
o
n
a
n
d
t
r
e
a
t
me
n
t
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
n
v
i
ro
n
m
e
n
t
a
l
Re
s
e
a
r
c
h
a
n
d
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
1
8
,
n
o
.
2
,
Ja
n
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
e
r
p
h
1
8
0
2
0
4
6
1
.
[
3
]
B
.
W
i
e
s
,
C
.
La
n
d
e
r
s,
a
n
d
M
.
I
e
n
c
a
,
“
D
i
g
i
t
a
l
m
e
n
t
a
l
h
e
a
l
t
h
f
o
r
y
o
u
n
g
p
e
o
p
l
e
:
a
sc
o
p
i
n
g
r
e
v
i
e
w
o
f
e
t
h
i
c
a
l
p
r
o
mi
s
e
s
a
n
d
c
h
a
l
l
e
n
g
e
s,”
Fr
o
n
t
i
e
rs
i
n
D
i
g
i
t
a
l
H
e
a
l
t
h
,
v
o
l
.
3
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
8
9
/
f
d
g
t
h
.
2
0
2
1
.
6
9
7
0
7
2
.
[
4
]
N
.
R
.
P
r
o
v
e
n
z
a
e
t
a
l
.
,
“
T
h
e
c
a
s
e
f
o
r
a
d
a
p
t
i
v
e
n
e
u
r
o
mo
d
u
l
a
t
i
o
n
t
o
t
r
e
a
t
se
v
e
r
e
i
n
t
r
a
c
t
a
b
l
e
me
n
t
a
l
d
i
s
o
r
d
e
r
s,”
Fr
o
n
t
i
e
rs
i
n
N
e
u
ro
s
c
i
e
n
c
e
,
v
o
l
.
1
3
,
F
e
b
.
2
0
1
9
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
i
n
s.
2
0
1
9
.
0
0
1
5
2
.
[
5
]
B
.
F
o
st
e
r
,
S
.
P
e
a
r
so
n
,
A
.
B
e
r
e
n
d
s,
a
n
d
C
.
M
a
c
k
i
n
n
o
n
,
“
T
h
e
e
x
p
a
n
d
i
n
g
sc
o
p
e
,
i
n
c
l
u
s
i
v
i
t
y
,
a
n
d
i
n
t
e
g
r
a
t
i
o
n
o
f
m
u
si
c
i
n
h
e
a
l
t
h
c
a
r
e
:
r
e
c
e
n
t
d
e
v
e
l
o
p
me
n
t
s
,
r
e
s
e
a
r
c
h
i
l
l
u
s
t
r
a
t
i
o
n
,
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
,
”
H
e
a
l
t
h
c
a
r
e
,
v
o
l
.
9
,
n
o
.
1
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
h
e
a
l
t
h
c
a
r
e
9
0
1
0
0
9
9
.
[
6
]
D
.
L
.
B
o
w
l
i
n
g
,
“
B
i
o
l
o
g
i
c
a
l
p
r
i
n
c
i
p
l
e
s
f
o
r
m
u
s
i
c
a
n
d
me
n
t
a
l
h
e
a
l
t
h
,
”
T
ra
n
s
l
a
t
i
o
n
a
l
Ps
y
c
h
i
a
t
r
y
,
v
o
l
.
1
3
,
n
o
.
1
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
3
9
8
-
023
-
0
2
6
7
1
-
4.
[
7
]
E.
L
i
e
b
ma
n
a
n
d
P
.
S
t
o
n
e
,
“
U
t
i
l
i
z
i
n
g
mo
o
d
-
i
n
d
u
c
i
n
g
b
a
c
k
g
r
o
u
n
d
mu
s
i
c
i
n
h
u
m
a
n
-
r
o
b
o
t
i
n
t
e
r
a
c
t
i
o
n
,
”
a
rXi
v
:
2
3
0
8
.
1
4
2
6
9
,
2
0
2
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
la
s
s
i
fyin
g
cla
s
s
ica
l m
u
s
ic’
s
t
h
era
p
eu
tic
effec
ts
u
s
in
g
d
ee
p
l
ea
r
n
in
g
:
a
r
ev
iew
(
A
n
g
elin
)
4941
[
8
]
J.
H
u
a
n
g
a
n
d
X
.
L
i
,
“
Ef
f
e
c
t
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
o
f
mu
s
i
c
t
h
e
r
a
p
y
o
n
p
s
y
c
h
o
l
o
g
i
c
a
l
h
e
a
l
t
h
:
a
r
e
v
i
e
w
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
2
1
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
P
u
b
l
i
c
A
rt
a
n
d
H
u
m
a
n
D
e
v
e
l
o
p
m
e
n
t
,
2
0
2
2
.
d
o
i
:
1
0
.
2
9
9
1
/
a
sse
h
r
.
k
.
2
2
0
1
1
0
.
1
8
6
.
[
9
]
L.
D
u
,
“
C
l
a
ss
i
c
a
l
mu
s
i
c
st
y
l
e
s
a
n
d
p
i
a
n
o
t
h
e
r
a
p
y
f
o
r
p
a
t
i
e
n
t
s
w
i
t
h
d
e
p
r
e
ssi
v
e
d
i
s
o
r
d
e
r
s,”
Re
v
i
s
t
a
M
ú
s
i
c
a
H
o
d
i
e
,
v
o
l
.
2
1
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
5
2
1
6
/
mh
.
v
2
1
.
6
6
5
1
9
.
[
1
0
]
O
.
T
a
n
r
i
v
e
r
d
i
,
T
.
K
a
r
a
o
g
l
u
,
a
n
d
F
.
N
.
A
y
d
e
m
i
r
,
“
C
a
n
m
u
s
i
c
a
n
d
m
e
d
i
c
i
n
e
b
e
e
f
f
e
c
t
i
v
e
o
n
a
n
x
i
e
t
y
,
d
e
p
r
e
s
s
i
o
n
,
a
n
d
c
h
e
m
o
t
h
e
r
a
p
y
-
r
e
l
a
t
e
d
n
a
u
s
e
a
a
n
d
v
o
m
i
t
i
n
g
?
(
P
E
G
A
S
U
S
s
t
u
d
y
)
,
”
I
n
d
i
a
n
J
o
u
r
n
a
l
o
f
C
a
n
c
e
r
,
v
o
l
.
6
0
,
n
o
.
2
,
p
p
.
2
8
2
–
2
9
1
,
2
0
2
3
,
d
o
i
:
1
0
.
4
1
0
3
/
i
j
c
.
I
J
C
_
3
8
7
_
2
0
.
[
1
1
]
K
.
D
e
v
e
n
d
r
a
n
,
S
.
K
.
Th
a
n
g
a
r
a
su
,
P
.
K
e
e
r
t
h
i
k
a
,
R
.
M
.
D
e
v
i
,
a
n
d
B
.
K
.
P
o
n
n
a
r
a
se
e
,
“
Ef
f
e
c
t
i
v
e
p
r
e
d
i
c
t
i
o
n
o
n
m
u
si
c
t
h
e
r
a
p
y
u
s
i
n
g
h
y
b
r
i
d
S
V
M
-
A
N
N
a
p
p
r
o
a
c
h
,
”
I
T
M
W
e
b
o
f
C
o
n
f
e
re
n
c
e
s
,
v
o
l
.
3
7
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
5
1
/
i
t
m
c
o
n
f
/
2
0
2
1
3
7
0
1
0
1
4
.
[
1
2
]
T.
T
h
e
o
r
e
l
l
a
n
d
E
.
B
.
H
o
r
w
i
t
z
,
“
E
m
o
t
i
o
n
a
l
e
f
f
e
c
t
s
o
f
l
i
v
e
a
n
d
r
e
c
o
r
d
e
d
mu
si
c
i
n
v
a
r
i
o
u
s
a
u
d
i
e
n
c
e
s
a
n
d
l
i
s
t
e
n
i
n
g
si
t
u
a
t
i
o
n
s,
”
Me
d
i
c
i
n
e
s
,
v
o
l
.
6
,
n
o
.
1
,
Ja
n
.
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
m
e
d
i
c
i
n
e
s6
0
1
0
0
1
6
.
[
1
3
]
Y
.
D
i
n
g
e
t
a
l
.
,
“
U
n
c
o
v
e
r
i
n
g
p
o
t
e
n
t
i
a
l
d
i
st
i
n
c
t
i
v
e
a
c
o
u
s
t
i
c
f
e
a
t
u
r
e
s
o
f
h
e
a
l
i
n
g
m
u
si
c
,
”
G
e
n
e
r
a
l
Ps
y
c
h
i
a
t
r
y
,
v
o
l
.
3
6
,
n
o
.
6
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
3
6
/
g
p
s
y
c
h
-
2
0
2
3
-
1
0
1
1
4
5
.
[
1
4
]
M
.
H
a
r
t
m
a
n
n
e
t
a
l
.
,
“
M
u
si
c
a
l
i
n
t
e
r
a
c
t
i
o
n
i
n
m
u
si
c
t
h
e
r
a
p
y
f
o
r
d
e
p
r
e
ssi
o
n
t
r
e
a
t
m
e
n
t
,
”
Psy
c
h
o
l
o
g
y
o
f
M
u
s
i
c
,
v
o
l
.
5
1
,
n
o
.
1
,
p
p
.
3
3
–
5
0
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
7
7
/
0
3
0
5
7
3
5
6
2
2
1
0
8
4
3
6
8
.
[
1
5
]
A
.
R
a
g
l
i
o
e
t
a
l
.
,
“
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
t
o
p
r
e
d
i
c
t
t
h
e
e
f
f
e
c
t
i
v
e
n
e
ss
o
f
m
u
s
i
c
t
h
e
r
a
p
y
:
a
r
a
n
d
o
mi
z
e
d
c
o
n
t
r
o
l
l
e
d
t
r
i
a
l
,
”
C
o
m
p
u
t
e
r
M
e
t
h
o
d
s
a
n
d
Pr
o
g
r
a
m
s
i
n
Bi
o
m
e
d
i
c
i
n
e
,
v
o
l
.
1
8
5
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
m
p
b
.
2
0
1
9
.
1
0
5
1
6
0
.
[
1
6
]
H
.
A
.
M
o
d
r
a
n
,
T
.
C
h
a
m
u
n
o
r
w
a
,
D
.
U
r
su
ț
i
u
,
C
.
S
a
m
o
i
l
ă
,
a
n
d
H
.
H
e
d
e
ș
i
u
,
“
U
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
t
o
r
e
c
o
g
n
i
z
e
t
h
e
r
a
p
e
u
t
i
c
e
f
f
e
c
t
s
o
f
mu
si
c
b
a
s
e
d
o
n
e
mo
t
i
o
n
s
,
”
S
e
n
so
rs
,
v
o
l
.
2
3
,
n
o
.
2
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
0
2
0
9
8
6
.
[
1
7
]
J.
D
u
t
t
a
a
n
d
D
.
C
h
a
n
d
a
,
“
M
u
s
i
c
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
h
y
b
r
i
d
C
N
N
-
LSTM
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
Ba
n
g
l
a
d
e
sh
J
o
u
r
n
a
l
o
f
M
u
l
t
i
d
i
sc
i
p
l
i
n
a
ry
S
c
i
e
n
t
i
f
i
c
Re
s
e
a
rc
h
,
v
o
l
.
9
,
n
o
.
3
,
p
p
.
2
1
–
3
2
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
4
6
2
8
1
/
b
j
msr
.
v
9
i
3
.
2
2
3
0
.
[
1
8
]
U
.
A
y
v
a
z
,
H
.
G
ü
r
ü
l
e
r
,
F
.
K
h
a
n
,
N
.
A
h
me
d
,
T.
W
h
a
n
g
b
o
,
a
n
d
A
.
A
.
B
o
b
o
mi
r
z
a
e
v
i
c
h
,
“
A
u
t
o
mat
i
c
sp
e
a
k
e
r
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
M
e
l
-
f
r
e
q
u
e
n
c
y
c
e
p
s
t
r
a
l
c
o
e
f
f
i
c
i
e
n
t
s
t
h
r
o
u
g
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
C
o
m
p
u
t
e
rs,
Ma
t
e
r
i
a
l
s
&
C
o
n
t
i
n
u
a
,
v
o
l
.
7
1
,
n
o
.
3
,
p
p
.
5
5
1
1
–
5
5
2
1
,
2
0
2
2
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
mc
.
2
0
2
2
.
0
2
3
2
7
8
.
[
1
9
]
G
.
Y
o
o
,
S
.
H
o
n
g
,
a
n
d
H
.
K
i
m,
“
E
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
a
n
d
m
u
l
t
i
-
c
l
a
ss
c
l
a
ss
i
f
i
c
a
t
i
o
n
i
n
m
u
si
c
w
i
t
h
M
F
C
C
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
n
Ad
v
a
n
c
e
d
S
c
i
e
n
c
e
,
E
n
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
8
1
8
–
8
2
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
8
5
1
7
/
i
j
a
s
e
i
t
.
1
4
.
3
.
1
8
6
7
1
.
[
2
0
]
S
.
C
a
r
v
a
l
h
o
a
n
d
E.
F
.
G
o
mes
,
“
A
u
t
o
mat
i
c
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
b
i
r
d
so
u
n
d
s
:
u
si
n
g
M
F
C
C
a
n
d
M
e
l
s
p
e
c
t
r
o
g
r
a
m
f
e
a
t
u
r
e
s
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Vi
e
t
n
a
m
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
0
,
n
o
.
0
1
,
p
p
.
3
9
–
5
4
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
4
2
/
S
2
1
9
6
8
8
8
8
2
2
5
0
0
3
0
0
.
[
2
1
]
Z.
K
.
A
b
d
u
l
a
n
d
A
.
K
.
A
.
-
Ta
l
a
b
a
n
i
,
“
M
e
l
f
r
e
q
u
e
n
c
y
c
e
p
s
t
r
a
l
c
o
e
f
f
i
c
i
e
n
t
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
s:
a
r
e
v
i
e
w
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
1
2
2
1
3
6
–
1
2
2
1
5
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
2
2
3
4
4
4
.
[
2
2
]
A
.
K
o
d
u
r
u
,
H
.
B
.
V
a
l
i
v
e
t
i
,
a
n
d
A
.
K
.
B
u
d
a
t
i
,
“
F
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
l
g
o
r
i
t
h
ms
t
o
i
mp
r
o
v
e
t
h
e
s
p
e
e
c
h
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
r
a
t
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
p
e
e
c
h
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
3
,
n
o
.
1
,
p
p
.
4
5
–
5
5
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
7
7
2
-
020
-
0
9
6
7
2
-
4.
[
2
3
]
S
.
M
S
K
,
G
.
V
.
K
.
J
,
M
.
V
.
U
,
H
.
K
.
V
e
g
e
,
a
n
d
S
.
K
u
c
h
i
b
h
o
t
l
a
,
“
M
LP
m
o
d
e
l
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
a
c
o
u
st
i
c
f
e
a
t
u
r
e
s
,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Em
e
r
g
i
n
g
T
r
e
n
d
s
i
n
E
n
g
i
n
e
e
r
i
n
g
Re
se
a
r
c
h
,
v
o
l
.
8
,
n
o
.
5
,
2
0
2
0
,
d
o
i
:
1
0
.
3
0
5
3
4
/
i
j
e
t
e
r
/
2
0
2
0
/
3
4
8
5
2
0
2
0
.
[
2
4
]
B
.
X
i
e
,
J
.
C
.
K
i
m,
a
n
d
C
.
H
.
P
a
r
k
,
“
M
u
si
c
a
l
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
sp
e
c
t
r
a
l
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
b
a
s
e
d
o
n
a
s
i
n
u
s
o
i
d
a
l
mo
d
e
l
w
i
t
h
mo
d
e
l
-
b
a
s
e
d
a
n
d
d
e
e
p
-
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
0
,
n
o
.
3
,
J
a
n
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
0
0
3
0
9
0
2
.
[
2
5
]
J.
S
u
n
,
J.
Y
a
n
g
,
G
.
Zh
o
u
,
Y
.
J
i
n
,
a
n
d
J.
G
o
n
g
,
“
U
n
d
e
r
s
t
a
n
d
i
n
g
h
u
m
a
n
-
A
I
c
o
l
l
a
b
o
r
a
t
i
o
n
i
n
mu
s
i
c
t
h
e
r
a
p
y
t
h
r
o
u
g
h
c
o
-
d
e
s
i
g
n
w
i
t
h
t
h
e
r
a
p
i
st
s
,
”
i
n
C
H
I
C
o
n
f
e
r
e
n
c
e
o
n
H
u
m
a
n
Fa
c
t
o
rs
i
n
C
o
m
p
u
t
i
n
g
S
y
s
t
e
m
s
,
2
0
2
4
,
p
p
.
1
–
21
,
d
o
i
:
1
0
.
1
1
4
5
/
3
6
1
3
9
0
4
.
3
6
4
2
7
6
4
.
[
2
6
]
A
.
A
g
g
a
r
w
a
l
e
t
a
l
.
,
“
Tw
o
-
w
a
y
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
f
o
r
s
p
e
e
c
h
e
m
o
t
i
o
n
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
,
”
S
e
n
so
r
s
,
v
o
l
.
2
2
,
n
o
.
6
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
2
0
6
2
3
7
8
.
[
2
7
]
S
.
H
i
z
l
i
s
o
y
,
S
.
Y
i
l
d
i
r
i
m
,
a
n
d
Z
.
T
u
f
e
k
c
i
,
“
M
u
s
i
c
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
l
o
n
g
s
h
o
r
t
t
e
r
m
m
e
m
o
r
y
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
E
n
g
i
n
e
e
r
i
n
g
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
a
n
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
,
v
o
l
.
2
4
,
n
o
.
3
,
p
p
.
7
6
0
–
7
6
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
e
s
t
c
h
.
2
0
2
0
.
1
0
.
0
0
9
.
[
2
8
]
K
.
B
a
g
a
s
t
i
o
,
R
.
S
.
O
e
t
a
m
a
,
a
n
d
A
.
R
a
mad
h
a
n
,
“
D
e
v
e
l
o
p
m
e
n
t
o
f
st
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
s
y
st
e
m
u
si
n
g
F
l
a
sk
f
r
a
me
w
o
r
k
a
n
d
LS
TM
a
l
g
o
r
i
t
h
m,
”
J
o
u
rn
a
l
o
f
I
n
f
r
a
st
r
u
c
t
u
re,
Po
l
i
c
y
a
n
d
D
e
v
e
l
o
p
m
e
n
t
,
v
o
l
.
7
,
n
o
.
3
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
2
4
2
9
4
/
j
i
p
d
.
v
7
i
3
.
2
6
3
1
.
[
2
9
]
A
.
L
i
b
e
r
a
t
i
e
t
a
l
.
,
“
T
h
e
P
R
I
S
M
A
s
t
a
t
e
m
e
n
t
f
o
r
r
e
p
o
r
t
i
n
g
s
y
s
t
e
m
a
t
i
c
r
e
v
i
e
w
s
a
n
d
m
e
t
a
-
a
n
a
l
y
s
e
s
o
f
s
t
u
d
i
e
s
t
h
a
t
e
v
a
l
u
a
t
e
h
e
a
l
t
h
c
a
r
e
i
n
t
e
r
v
e
n
t
i
o
n
s
:
e
x
p
l
a
n
a
t
i
o
n
a
n
d
e
l
a
b
o
r
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
C
l
i
n
i
c
a
l
E
p
i
d
e
m
i
o
l
o
g
y
,
v
o
l
.
6
2
,
n
o
.
1
0
,
2
0
0
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
c
l
i
n
e
p
i
.
2
0
0
9
.
0
6
.
0
0
6
.
[
3
0
]
H
.
L
i
u
,
X
.
Z
h
o
u
,
G
.
Y
u
,
a
n
d
X
.
S
u
n
,
“
T
h
e
e
f
f
e
c
t
s
o
f
t
h
e
P
R
I
S
M
A
st
a
t
e
me
n
t
t
o
i
m
p
r
o
v
e
t
h
e
c
o
n
d
u
c
t
a
n
d
r
e
p
o
r
t
i
n
g
o
f
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
s
a
n
d
me
t
a
‐
a
n
a
l
y
s
e
s
o
f
n
u
r
si
n
g
i
n
t
e
r
v
e
n
t
i
o
n
s
f
o
r
p
a
t
i
e
n
t
s
w
i
t
h
h
e
a
r
t
f
a
i
l
u
r
e
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
N
u
rs
i
n
g
P
ra
c
t
i
c
e
,
v
o
l
.
2
5
,
n
o
.
3
,
Ju
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
1
1
/
i
j
n
.
1
2
7
2
9
.
[
3
1
]
N
.
C
.
P
.
S
u
s
a
n
t
o
,
S
.
J.
H
a
r
t
a
t
i
,
a
n
d
R
.
E.
S
t
a
n
d
s
y
a
h
,
“
S
y
st
e
ma
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
:
a
p
p
l
i
c
a
t
i
o
n
o
f
d
y
n
a
m
i
c
g
e
o
met
r
y
so
f
t
w
a
r
e
t
o
i
mp
r
o
v
e
ma
t
h
e
ma
t
i
c
a
l
p
r
o
b
l
e
m
-
s
o
l
v
i
n
g
sk
i
l
l
s
,
”
M
a
t
h
l
i
n
e
:
J
u
r
n
a
l
M
a
t
e
m
a
t
i
k
a
d
a
n
Pe
n
d
i
d
i
k
a
n
M
a
t
e
m
a
t
i
k
a
,
v
o
l
.
8
,
n
o
.
3
,
p
p
.
8
5
7
–
8
7
2
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
3
1
9
4
3
/
m
a
t
h
l
i
n
e
.
v
8
i
3
.
4
5
8
.
[
3
2
]
K
.
A
r
i
y
a
n
t
o
,
“
R
u
r
a
l
d
e
v
e
l
o
p
me
n
t
r
e
s
e
a
r
c
h
t
r
e
n
d
s:
b
i
b
l
i
o
met
r
i
c
a
n
a
l
y
si
s
u
si
n
g
p
u
b
l
i
s
h
o
r
P
e
r
i
sh
a
n
d
V
o
s
v
i
e
w
e
r
,
”
At
h
e
n
a
:
J
o
u
r
n
a
l
o
f
S
o
c
i
a
l
,
C
u
l
t
u
r
e
a
n
d
S
o
c
i
e
t
y
,
v
o
l
.
1
,
n
o
.
4
,
p
p
.
1
6
9
–
1
7
9
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
5
8
9
0
5
/
a
t
h
e
n
a
.
v
1
i
4
.
1
2
1
.
[
3
3
]
J.
G
u
e
r
r
e
r
o
a
n
d
I
.
A
l
sma
d
i
,
“
S
y
n
t
h
e
t
i
c
t
e
x
t
d
e
t
e
c
t
i
o
n
:
sy
s
t
e
m
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,”
a
rX
i
v
:
2
2
1
0
.
0
6
3
3
6
,
O
c
t
.
2
0
2
2
.
[
3
4
]
E.
H
.
-
R
u
i
z
,
B
.
J
a
mes
,
J
.
N
o
l
l
,
a
n
d
E.
G
.
C
h
r
y
si
k
o
u
,
“
W
h
a
t
ma
k
e
s
mu
s
i
c
r
e
l
a
x
i
n
g
?
a
n
i
n
v
e
st
i
g
a
t
i
o
n
i
n
t
o
m
u
si
c
a
l
e
l
e
m
e
n
t
s,
”
Psy
c
h
o
l
o
g
y
o
f
M
u
si
c
,
v
o
l
.
4
8
,
n
o
.
3
,
p
p
.
3
2
7
–
3
4
3
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
1
1
7
7
/
0
3
0
5
7
3
5
6
1
8
7
9
8
0
2
7
.
[
3
5
]
D
.
S
h
e
p
h
e
r
d
,
M
.
J.
H
a
u
t
u
s
,
E.
G
i
a
n
g
,
a
n
d
J.
La
n
d
o
n
,
“
‘
T
h
e
m
o
s
t
r
e
l
a
x
i
n
g
so
n
g
i
n
t
h
e
w
o
r
l
d
’
?
a
c
o
mp
a
r
a
t
i
v
e
s
t
u
d
y
,
”
Ps
y
c
h
o
l
o
g
y
o
f
Mu
s
i
c
,
v
o
l
.
5
1
,
n
o
.
1
,
p
p
.
3
–
1
5
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
7
7
/
0
3
0
5
7
3
5
6
2
2
1
0
8
1
1
6
9
.
[
3
6
]
T.
B
.
S
a
n
t
o
so
a
n
d
T
.
D
u
t
o
n
o
,
“
I
n
st
r
u
men
t
a
l
m
u
si
c
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
M
F
C
C
a
n
d
K
N
N
a
l
g
o
r
i
t
h
m
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
2
,
n
o
.
1
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
0
2
2
/
i
j
c
s.
v
1
2
i
1
.
3
1
5
2
.
[
3
7
]
L.
K
i
ss
a
n
d
K
.
J
.
L
i
n
n
e
l
l
,
“
Th
e
e
f
f
e
c
t
o
f
p
r
e
f
e
r
r
e
d
b
a
c
k
g
r
o
u
n
d
m
u
si
c
o
n
t
a
sk
-
f
o
c
u
s
i
n
s
u
s
t
a
i
n
e
d
a
t
t
e
n
t
i
o
n
,
”
Psy
c
h
o
l
o
g
i
c
a
l
Re
se
a
rc
h
,
v
o
l
.
8
5
,
n
o
.
6
,
p
p
.
2
3
1
3
–
2
3
2
5
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
4
2
6
-
0
2
0
-
0
1
4
0
0
-
6.
[
3
8
]
S
.
F
e
l
sz
e
g
h
y
e
t
a
l
.
,
“
I
n
f
l
u
e
n
c
e
o
f
b
a
c
k
g
r
o
u
n
d
mu
s
i
c
o
n
st
r
e
ss
r
e
d
u
c
t
i
o
n
a
n
d
i
m
p
a
c
t
o
n
p
e
r
f
o
r
ma
n
c
e
s
d
u
r
i
n
g
st
u
d
e
n
t
s’
si
m
u
l
a
t
i
o
n
e
x
e
r
c
i
s
e
s,”
J
o
u
rn
a
l
o
f
D
e
n
t
a
l
E
d
u
c
a
t
i
o
n
,
v
o
l
.
8
7
,
n
o
.
8
,
p
p
.
1
1
7
0
–
1
1
7
9
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
2
/
j
d
d
.
1
3
2
3
5
.
[
3
9
]
A
.
R
a
g
l
i
o
,
“
A
n
o
v
e
l
mu
s
i
c
-
b
a
se
d
t
h
e
r
a
p
e
u
t
i
c
a
p
p
r
o
a
c
h
:
t
h
e
t
h
e
r
a
p
e
u
t
i
c
mu
si
c
l
i
s
t
e
n
i
n
g
,
”
Fr
o
n
t
i
e
rs
i
n
H
u
m
a
n
N
e
u
ro
s
c
i
e
n
c
e
,
v
o
l
.
1
7
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
h
u
m.2
0
2
3
.
1
2
0
4
5
9
3
.
[
4
0
]
Q
.
D
i
n
g
,
“
E
v
a
l
u
a
t
i
o
n
o
f
t
h
e
e
f
f
i
c
a
c
y
o
f
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
-
b
a
s
e
d
m
u
si
c
t
h
e
r
a
p
y
f
o
r
d
e
p
r
e
ss
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
–
6
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
9
2
0
8
6
0
7
.
[
4
1
]
J.
Z
h
a
n
g
,
“
M
u
si
c
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
m
b
a
se
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
,
”
S
c
i
e
n
t
i
f
i
c
Pro
g
r
a
m
m
i
n
g
,
v
o
l
.
2
0
2
1
,
p
p
.
1
–
9
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
1
6
5
1
5
6
0
.
[
4
2
]
C
.
C
h
e
n
a
n
d
Q
.
Li
,
“
A
mu
l
t
i
m
o
d
a
l
mu
si
c
e
m
o
t
i
o
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
m
e
t
h
o
d
b
a
se
d
o
n
m
u
l
t
i
f
e
a
t
u
r
e
c
o
m
b
i
n
e
d
n
e
t
w
o
r
k
c
l
a
ss
i
f
i
e
r
,
”
Ma
t
h
e
m
a
t
i
c
a
l
Pr
o
b
l
e
m
s i
n
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
2
0
,
p
p
.
1
–
1
1
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
0
/
4
6
0
6
0
2
7
.
[
4
3
]
D
.
B
i
s
h
a
r
a
d
a
n
d
R
.
H
.
La
s
k
a
r
,
“
M
u
si
c
g
e
n
r
e
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
a
r
c
h
i
t
e
c
t
u
r
e
,
”
E
x
p
e
rt
S
y
s
t
e
m
s
,
v
o
l
.
3
6
,
n
o
.
4
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
1
1
/
e
x
s
y
.
1
2
4
2
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
er
20
25
:
4
9
3
3
-
4
9
4
2
4942
[
4
4
]
D
.
C
h
a
u
d
h
a
r
y
,
N
.
P
.
S
i
n
g
h
,
a
n
d
S
.
S
i
n
g
h
,
“
D
e
v
e
l
o
p
me
n
t
o
f
m
u
s
i
c
e
m
o
t
i
o
n
c
l
a
s
si
f
i
c
a
t
i
o
n
sy
s
t
e
m
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
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
S
p
e
e
c
h
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
4
,
n
o
.
3
,
p
p
.
5
7
1
–
5
8
0
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
7
7
2
-
0
2
0
-
0
9
7
8
1
-
0.
[
4
5
]
X
.
Ji
a
,
“
A
mu
s
i
c
e
mo
t
i
o
n
c
l
a
ssi
f
i
c
a
t
i
o
n
m
o
d
e
l
b
a
se
d
o
n
t
h
e
i
mp
r
o
v
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
,
”
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
1
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
6
7
4
9
6
2
2
.
[
4
6
]
K
.
M
.
R
e
z
a
u
l
e
t
a
l
.
,
“
E
n
h
a
n
c
i
n
g
a
u
d
i
o
c
l
a
s
s
i
f
i
c
a
t
i
o
n
t
h
r
o
u
g
h
M
F
C
C
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
d
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
w
i
t
h
C
N
N
a
n
d
R
N
N
m
o
d
e
l
s
,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
5
,
n
o
.
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
J
A
C
S
A
.
2
0
2
4
.
0
1
5
0
7
0
4
.
[
4
7
]
E.
K
.
G
y
a
si
a
n
d
S
.
P
u
r
u
s
h
o
t
h
a
m
,
“
S
o
i
l
-
M
o
b
i
N
e
t
:
a
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
m
o
d
e
l
b
a
s
e
so
i
l
c
l
a
ssi
f
i
c
a
t
i
o
n
t
o
d
e
t
e
r
mi
n
e
so
i
l
mo
r
p
h
o
l
o
g
y
a
n
d
i
t
s
g
e
o
sp
a
t
i
a
l
l
o
c
a
t
i
o
n
,
”
S
e
n
so
rs
,
v
o
l
.
2
3
,
n
o
.
1
5
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
3
1
5
6
7
0
9
.
[
4
8
]
M
.
C
o
n
n
e
r
,
L
.
G
r
a
l
,
K
.
A
d
a
m
s
,
D
.
H
u
n
g
e
r
,
R
.
S
t
r
e
l
o
w
,
a
n
d
A
.
N
e
u
w
i
r
t
h
,
“
M
u
s
i
c
g
e
n
e
r
a
t
i
o
n
u
s
i
n
g
a
n
L
S
T
M
,
”
a
r
X
i
v
:
2
2
0
3
.
1
2
1
0
5
,
2
0
2
2
.
[
4
9
]
S
.
A
l
l
a
m
y
a
n
d
A
.
L.
K
o
e
r
i
c
h
,
“
1
D
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
s
f
o
r
mu
s
i
c
g
e
n
r
e
c
l
a
s
si
f
i
c
a
t
i
o
n
,
”
a
rXi
v
:
2
1
0
5
.
0
7
3
0
2
,
M
a
y
2
0
2
1
.
[
5
0
]
R
.
R
e
f
i
a
n
t
i
a
n
d
F
.
M
a
h
a
r
d
i
,
“
C
o
m
p
a
r
i
so
n
o
f
mu
s
i
c
g
e
n
r
e
c
l
a
ssi
f
i
c
a
t
i
o
n
r
e
su
l
t
s
u
si
n
g
mu
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
w
i
t
h
c
h
r
o
ma
f
e
a
t
u
r
e
a
n
d
M
e
l
f
r
e
q
u
e
n
c
y
c
e
p
st
r
a
l
c
o
e
f
f
i
c
i
e
n
t
s
e
x
t
r
a
c
t
i
o
n
f
e
a
t
u
r
e
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
ri
n
g
,
S
c
i
e
n
c
e
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
3
,
n
o
.
2
,
p
p
.
5
3
–
5
9
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
5
2
0
8
8
/
i
j
e
st
y
.
v
3
i
2
.
4
4
4
.
[
5
1
]
J.
Li
,
L.
H
a
n
,
X
.
L
i
,
J.
Zh
u
,
B
.
Y
u
a
n
,
a
n
d
Z.
G
o
u
,
“
A
n
e
v
a
l
u
a
t
i
o
n
o
f
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
mo
d
e
l
s
f
o
r
m
u
s
i
c
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
sp
e
c
t
r
o
g
r
a
m
s,”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
1
,
n
o
.
4
,
p
p
.
4
6
2
1
–
4
6
4
7
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
2
0
-
1
0
4
6
5
-
9.
[
5
2
]
T.
A
.
H
a
r
t
a
n
t
o
a
n
d
S
.
H
a
n
s
u
n
,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s o
f
p
re
-
t
r
a
i
n
e
d
C
N
N
mo
d
e
l
s
o
n
r
e
t
i
n
a
l
d
i
sea
s
e
s c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
d
u
s
t
ri
a
l
E
n
g
i
n
e
e
r
i
n
g
&
Pro
d
u
c
t
i
o
n
Re
se
a
r
c
h
,
v
o
l
.
3
5
,
n
o
.
3
,
p
p
.
1
–
1
2
,
2
0
2
4
,
d
o
i
:
1
0
.
2
2
0
6
8
/
i
j
i
e
p
r
.
3
5
.
3
.
1
9
3
5
.
[
5
3
]
X
.
C
h
e
n
,
“
T
h
e
a
p
p
l
i
c
a
t
i
o
n
o
f
n
e
u
r
a
l
n
e
t
w
o
r
k
w
i
t
h
c
o
n
v
o
l
u
t
i
o
n
a
l
g
o
r
i
t
h
m
i
n
W
e
st
e
r
n
mu
s
i
c
r
e
c
o
mm
e
n
d
a
t
i
o
n
p
r
a
c
t
i
c
e
,
”
J
o
u
rn
a
l
o
f
Am
b
i
e
n
t
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
H
u
m
a
n
i
z
e
d
C
o
m
p
u
t
i
n
g
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
6
5
2
-
0
2
0
-
0
1
8
0
6
-
5.
[
5
4
]
Y
.
X
i
a
o
,
H
.
Y
i
n
,
Y
.
Z
h
a
n
g
,
H
.
Q
i
,
Y
.
Zh
a
n
g
,
a
n
d
Z
.
L
i
u
,
“
A
d
u
a
l
‐
s
t
a
g
e
a
t
t
e
n
t
i
o
n
‐
b
a
s
e
d
C
o
n
v
‐
LST
M
n
e
t
w
o
r
k
f
o
r
sp
a
t
i
o
‐
t
e
m
p
o
r
a
l
c
o
r
r
e
l
a
t
i
o
n
a
n
d
m
u
l
t
i
v
a
r
i
a
t
e
t
i
me
seri
e
s
p
r
e
d
i
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
,
v
o
l
.
3
6
,
n
o
.
5
,
p
p
.
2
0
3
6
–
2
0
5
7
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
2
/
i
n
t
.
2
2
3
7
0
.
[
5
5
]
J.
C
.
O
b
i
,
“
A
c
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
o
f
s
e
v
e
r
a
l
c
l
a
ssi
f
i
c
a
t
i
o
n
m
e
t
r
i
c
s
a
n
d
t
h
e
i
r
p
e
r
f
o
r
m
a
n
c
e
s
o
n
d
a
t
a
,
”
Wo
rl
d
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
En
g
i
n
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
y
a
n
d
S
c
i
e
n
c
e
s
,
v
o
l
.
8
,
n
o
.
1
,
p
p
.
3
0
8
–
3
1
4
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
0
5
7
4
/
w
j
a
e
t
s
.
2
0
2
3
.
8
.
1
.
0
0
5
4
.
[
5
6
]
A
.
M
.
C
a
r
r
i
n
g
t
o
n
e
t
a
l
.
,
“
D
e
e
p
R
O
C
a
n
a
l
y
si
s
a
n
d
A
U
C
a
s
b
a
l
a
n
c
e
d
a
v
e
r
a
g
e
a
c
c
u
r
a
c
y
,
f
o
r
i
m
p
r
o
v
e
d
c
l
a
ssi
f
i
e
r
s
e
l
e
c
t
i
o
n
,
a
u
d
i
t
a
n
d
e
x
p
l
a
n
a
t
i
o
n
,
”
I
EE
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
Pa
t
t
e
rn
A
n
a
l
y
s
i
s
a
n
d
M
a
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
4
5
,
n
o
.
1
,
p
p
.
3
2
9
–
3
4
1
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TPA
M
I
.
2
0
2
2
.
3
1
4
5
3
9
2
.
[
5
7
]
V
.
S
i
n
g
h
,
M
.
P
e
n
c
i
n
a
,
A
.
J.
Ei
n
s
t
e
i
n
,
J
.
X
.
L
i
a
n
g
,
D
.
S
.
B
e
r
ma
n
,
a
n
d
P
.
S
l
o
mk
a
,
“
I
mp
a
c
t
o
f
t
r
a
i
n
/
t
e
s
t
sa
mp
l
e
r
e
g
i
m
e
n
o
n
p
e
r
f
o
r
m
a
n
c
e
e
s
t
i
m
a
t
e
s
t
a
b
i
l
i
t
y
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
c
a
r
d
i
o
v
a
sc
u
l
a
r
i
m
a
g
i
n
g
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
1
,
n
o
.
1
,
J
u
l
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
021
-
9
3
6
5
1
-
5.
[
5
8
]
A
.
A
l
i
a
n
d
C
.
G
r
a
v
i
n
o
,
“
A
n
e
m
p
i
r
i
c
a
l
c
o
m
p
a
r
i
s
o
n
o
f
v
a
l
i
d
a
t
i
o
n
me
t
h
o
d
s
f
o
r
s
o
f
t
w
a
r
e
p
r
e
d
i
c
t
i
o
n
mo
d
e
l
s,
”
J
o
u
r
n
a
l
o
f
S
o
f
t
w
a
r
e
:
Ev
o
l
u
t
i
o
n
a
n
d
Pro
c
e
ss
,
v
o
l
.
3
3
,
n
o
.
8
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
2
/
smr
.
2
3
6
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ang
e
li
n
h
o
l
d
s
a
n
u
n
d
e
r
g
ra
d
u
a
te
Ba
c
h
e
lo
r
o
f
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
a
t
Un
iv
e
rsitas
M
u
lt
ime
d
ia
N
u
sa
n
tara
,
In
d
o
n
e
sia
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
b
ig
d
a
ta,
d
a
ta
a
n
a
ly
sis,
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
in
g
,
a
n
d
a
rt
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
g
e
li
n
@s
t
u
d
e
n
t
.
u
m
n
.
a
c
.
id
.
S
a
m
u
e
l
Ady
S
a
n
ja
y
a
h
o
l
d
s
a
M
a
ste
r
o
f
In
fo
rm
a
ti
c
s
d
e
g
re
e
fro
m
In
stit
u
t
Tek
n
o
lo
g
i
Ba
n
d
u
n
g
,
In
d
o
n
e
sia
,
i
n
2
0
1
9
.
He
a
ls
o
re
c
e
iv
e
d
h
is
Ba
c
h
e
lo
r
o
f
In
f
o
rm
a
ti
c
s
fro
m
Atm
a
Ja
y
a
Yo
g
y
a
k
a
rta
Un
iv
e
rsit
y
,
In
d
o
n
e
sia
,
in
2
0
1
6
,
re
sp
e
c
ti
v
e
l
y
.
He
is
c
u
rre
n
tl
y
a
l
e
c
tu
re
r
a
t
De
p
a
rtme
n
t
o
f
I
n
fo
rm
a
ti
o
n
S
y
ste
m
s,
F
a
c
u
lt
y
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
In
f
o
rm
a
ti
c
s,
Un
i
v
e
rsitas
M
u
lt
ime
d
ia
Nu
sa
n
tara
,
In
d
o
n
e
sia
.
His
re
se
a
rc
h
i
n
c
lu
d
e
s
d
a
ta
a
n
a
l
y
sis,
m
a
c
h
in
e
lea
rn
i
n
g
,
d
a
ta
m
in
in
g
,
a
n
d
so
c
ial
n
e
two
r
k
a
n
a
l
y
sis
.
He
h
a
s
p
u
b
li
s
h
e
d
o
v
e
r
5
p
a
p
e
rs
in
in
tern
a
t
io
n
a
l
j
o
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
m
u
e
l.
a
d
y
@u
m
n
.
a
c
.
id
.
Din
a
r
Aje
n
g
K
r
istiy
a
n
ti
re
c
e
i
v
e
d
h
e
r
M
a
ste
r'
s d
e
g
re
e
in
Co
m
p
u
ter S
c
ien
c
e
a
n
d
a
Ba
c
h
e
lo
r'
s
d
e
g
re
e
in
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
fro
m
N
u
sa
M
a
n
d
iri
Un
i
v
e
rsity
,
In
d
o
n
e
sia
.
Cu
rre
n
tl
y
,
sh
e
is
a
P
h
.
D
.
c
a
n
d
id
a
t
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
t
IP
B
U
n
iv
e
rsity
,
I
n
d
o
n
e
sia
.
S
h
e
is
a
lec
tu
re
r
a
t
De
p
a
rtme
n
t
o
f
I
n
fo
r
m
a
ti
o
n
S
y
ste
m
s,
F
a
c
u
lt
y
o
f
E
n
g
in
e
e
rin
g
a
n
d
I
n
fo
rm
a
ti
c
s,
Un
iv
e
rsitas
M
u
lt
ime
d
ia
Nu
sa
n
t
a
ra
,
In
d
o
n
e
sia
.
He
r
re
se
a
rc
h
i
n
tere
sts
in
c
lu
d
e
se
n
ti
m
e
n
t
a
n
a
ly
sis,
tex
t
m
in
i
n
g
,
fe
a
tu
re
se
lec
ti
o
n
,
o
p
ti
m
iza
ti
o
n
,
d
a
ta
sc
ien
c
e
,
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
S
h
e
h
a
s
p
u
b
l
ish
e
d
o
v
e
r
1
3
p
a
p
e
rs
in
i
n
tern
a
ti
o
n
a
l
jo
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
in
a
r.
k
risti
y
a
n
ti
@u
m
n
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.