I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Ro
bo
t
ics a
nd
Aut
o
m
a
t
io
n
(
I
J
RA)
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
,
p
p
.
257
~
2
6
6
I
SS
N:
2722
-
2
5
8
6
,
DOI
:
1
0
.
1
1
5
9
1
/i
jr
a
.
v
1
5
i
2
.
pp
2
5
7
-
266
257
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
a
.
ia
esco
r
e.
co
m
A comp
rehe
nsiv
e
revi
ew of sou
nd
s
o
urce loca
liza
tion
methods
for rob
o
tics
M
uh
a
m
m
a
d Ak
ma
l A
liff
1
,
E
m
er
s
o
n J
o
s
eph Ra
j
a
2
1
C
e
n
t
e
r
o
f
E
x
c
e
l
l
e
n
c
e
R
o
b
o
t
i
c
s
a
n
d
S
e
n
s
i
n
g
Te
c
h
n
o
l
o
g
y
,
TM
R
e
se
a
r
c
h
a
n
d
D
e
v
e
l
o
p
me
n
t
,
C
y
b
e
r
j
a
y
a
,
M
a
l
a
y
s
i
a
2
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
Te
c
h
n
o
l
o
g
y
,
M
u
l
t
i
me
d
i
a
U
n
i
v
e
r
s
i
t
y
,
M
e
l
a
k
a
,
M
a
l
a
y
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
2
3
,
2
0
2
4
R
ev
is
ed
Ma
r
1
0
,
2
0
2
6
Acc
ep
ted
Ap
r
1
,
2
0
2
6
S
o
u
n
d
so
u
rc
e
lo
c
a
li
z
a
ti
o
n
(S
S
L)
is
a
k
e
y
tec
h
n
o
lo
g
y
i
n
ro
b
o
ti
c
s
t
h
a
t
a
ll
o
ws
m
a
c
h
in
e
s
to
d
e
tec
t
a
n
d
l
o
c
a
te
a
u
d
it
o
ry
c
u
e
s
i
n
re
a
l
ti
m
e
.
Th
i
s
re
v
iew
p
ro
v
id
e
s
a
th
o
ro
u
g
h
e
x
a
m
in
a
ti
o
n
o
f
S
S
L
tec
h
n
iq
u
e
s
c
las
sified
in
t
o
c
las
sic
a
l,
a
rti
ficia
l
in
telli
g
e
n
c
e
(AI)
,
a
n
d
h
y
b
rid
m
e
th
o
d
s.
Clas
sic
a
l
m
e
th
o
d
s,
w
h
ich
a
c
c
o
u
n
t
fo
r
4
4
%
o
f
re
v
iew
e
d
stu
d
ies
,
e
x
c
e
l
in
c
o
m
p
u
tatio
n
a
l
e
fficie
n
c
y
a
n
d
re
li
a
b
il
it
y
u
n
d
e
r
c
o
n
tro
ll
e
d
c
o
n
d
it
io
n
s
b
u
t
h
a
v
e
li
m
it
a
ti
o
n
s
i
n
d
y
n
a
m
ic
e
n
v
iro
n
m
e
n
ts.
AI
m
e
th
o
d
s,
w
h
i
c
h
a
c
c
o
u
n
t
f
o
r
1
6
%
o
f
st
u
d
ies
,
u
se
d
e
e
p
lea
rn
in
g
to
a
d
a
p
t
t
o
c
o
m
p
lex
sc
e
n
a
rio
s,
b
u
t
t
h
e
y
re
q
u
ire
larg
e
d
a
t
a
se
ts
a
n
d
c
o
m
p
u
tati
o
n
a
l
re
so
u
rc
e
s.
Hy
b
r
id
m
e
th
o
d
s,
wh
ich
c
o
m
b
in
e
c
las
sic
a
l
sig
n
a
l
p
ro
c
e
ss
in
g
a
n
d
AI,
a
re
th
e
m
o
st
ro
b
u
st
a
n
d
a
c
c
u
ra
te,
with
a
n
a
v
e
ra
g
e
a
c
c
u
ra
c
y
o
f
9
7
.
4
5
%
.
T
h
e
re
v
iew
a
lso
l
o
o
k
s
a
t
th
e
ro
le
o
f
m
icro
p
h
o
n
e
a
rra
y
s
in
S
S
L
p
e
rf
o
rm
a
n
c
e
,
re
v
e
a
li
n
g
t
h
a
t
sy
ste
m
s
wit
h
ten
o
r
m
o
re
m
i
c
ro
p
h
o
n
e
s
a
c
h
iev
e
th
e
h
ig
h
e
st
a
c
c
u
ra
c
y
o
f
9
9
.
2
3
%
,
wh
il
e
sin
g
le
-
a
n
d
d
u
a
l
-
m
icro
p
h
o
n
e
sy
ste
m
s
stil
l
p
e
rfo
rm
c
o
m
p
e
ti
ti
v
e
ly
(
9
7
.
6
0
%
a
n
d
9
7
.
2
1
%
,
re
sp
e
c
ti
v
e
ly
).
Th
e
se
fin
d
in
g
s
su
g
g
e
st
th
a
t
h
y
b
rid
m
e
th
o
d
s
c
o
m
b
in
e
d
wi
th
lar
g
e
r
m
icro
p
h
o
n
e
a
rra
y
s
a
re
th
e
m
o
st
e
ffe
c
ti
v
e
S
S
L
so
lu
t
io
n
in
ro
b
o
t
ics
,
b
a
lan
c
in
g
p
re
c
isio
n
a
n
d
a
d
a
p
tab
il
it
y
.
T
h
is
p
a
p
e
r
d
isc
u
ss
e
s
c
u
rre
n
t
S
S
L
tren
d
s,
c
h
a
ll
e
n
g
e
s,
a
n
d
f
u
tu
re
re
se
a
rc
h
d
irec
ti
o
n
s,
p
r
o
v
i
d
in
g
in
si
g
h
t
s
fo
r
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
a
d
v
a
n
c
e
d
a
u
d
it
o
r
y
sy
ste
m
s
c
a
p
a
b
le
o
f
re
li
a
b
le
p
e
rfo
rm
a
n
c
e
in
d
y
n
a
m
ic,
re
a
l
-
wo
rl
d
e
n
v
iro
n
m
e
n
ts.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
C
las
s
ical
m
eth
o
d
Mic
r
o
p
h
o
n
es a
r
r
ay
R
o
b
o
tics
So
u
n
d
s
o
u
r
ce
lo
ca
lizatio
n
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
:
Mu
h
am
m
ad
A
k
m
al
Alif
f
C
en
ter
o
f
E
x
ce
llen
ce
R
o
b
o
tics
an
d
Sen
s
in
g
T
ec
h
n
o
l
o
g
y
,
T
M
R
ND
C
y
b
er
jay
a,
Selan
g
o
r
,
Ma
lay
s
ia
E
m
ail:
ak
m
alalif
f
@
tm
r
n
d
.
co
m
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
So
u
n
d
s
o
u
r
ce
lo
ca
lizatio
n
(
S
SL)
h
as
em
er
g
ed
as
a
p
iv
o
tal
tech
n
o
lo
g
y
in
th
e
d
o
m
ai
n
o
f
r
o
b
o
tics
,
en
ab
lin
g
m
ac
h
in
es
to
p
er
ce
iv
e
an
d
in
ter
ac
t
with
th
eir
au
d
ito
r
y
en
v
ir
o
n
m
en
t
[
1
]
.
T
h
is
ca
p
ab
ilit
y
is
p
ar
ticu
lar
ly
cr
u
cial
f
o
r
h
u
m
a
n
-
r
o
b
o
t
in
ter
ac
tio
n
(
HR
I
)
,
wh
er
e
th
e
ab
ilit
y
to
d
etec
t
an
d
lo
ca
te
s
o
u
n
d
s
o
u
r
ce
s
en
h
an
ce
s
a
r
o
b
o
t'
s
s
itu
atio
n
al
awa
r
en
ess
,
co
m
m
u
n
icatio
n
ab
ilit
ies,
an
d
d
ec
is
io
n
-
m
ak
in
g
[
2
]
.
SS
L
u
n
d
er
p
in
s
a
wid
e
ar
r
ay
o
f
ap
p
licatio
n
s
,
in
clu
d
in
g
g
u
id
in
g
v
is
u
ally
im
p
air
e
d
in
d
i
v
id
u
als,
en
h
an
cin
g
au
to
n
o
m
o
u
s
n
av
ig
atio
n
,
a
n
d
en
ab
lin
g
v
o
ice
-
co
m
m
an
d
-
b
ased
in
ter
f
ac
es e
v
en
in
n
o
is
y
en
v
i
r
o
n
m
en
ts
[
3
]
.
Ov
er
th
e
y
ea
r
s
,
ad
v
an
ce
m
e
n
t
s
in
s
en
s
o
r
tech
n
o
lo
g
y
,
s
ig
n
al
p
r
o
ce
s
s
in
g
,
an
d
m
ac
h
in
e
lear
n
in
g
h
av
e
s
ig
n
if
ican
tly
ev
o
lv
e
d
SS
L
tech
n
iq
u
es,
tr
an
s
itio
n
in
g
f
r
o
m
tr
a
d
itio
n
al
b
ea
m
f
o
r
m
in
g
[
4
]
a
n
d
tim
e
-
d
if
f
er
en
ce
-
of
-
ar
r
iv
al
(
T
DOA)
m
eth
o
d
s
[
5
]
t
o
m
o
d
er
n
d
ee
p
lear
n
i
n
g
an
d
h
y
b
r
id
ap
p
r
o
ac
h
es
[
6
]
.
Ho
wev
er
,
in
teg
r
atin
g
SS
L
in
to
r
o
b
o
tic
s
y
s
tem
s
p
r
esen
ts
u
n
iq
u
e
ch
allen
g
es:
en
s
u
r
in
g
r
ea
l
-
tim
e
p
r
o
ce
s
s
in
g
[
7
]
,
m
ain
t
ain
in
g
r
o
b
u
s
tn
ess
in
d
y
n
am
ic
a
n
d
n
o
is
y
en
v
ir
o
n
m
e
n
ts
,
an
d
ac
h
iev
in
g
s
ca
lab
ilit
y
f
o
r
m
u
lti
-
s
o
u
r
ce
lo
ca
lizatio
n
[
8
]
,
[
9
]
.
T
h
e
n
ee
d
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
:
257
-
2
6
6
258
b
alan
ce
co
m
p
u
tatio
n
al
co
m
p
lex
ity
,
h
ar
d
war
e
c
o
n
s
tr
ain
ts
,
an
d
s
y
s
tem
a
d
ap
tab
ilit
y
,
p
ar
ticu
lar
ly
in
co
s
t
-
s
en
s
itiv
e
an
d
r
eso
u
r
ce
-
lim
ited
r
o
b
o
tic
p
latf
o
r
m
s
,
am
p
lifie
s
th
ese
ch
allen
g
es
[
1
0
]
.
T
h
is
r
ev
iew
aim
s
to
ad
d
r
ess
th
ese
ch
allen
g
es
b
y
p
r
o
v
i
d
in
g
a
co
m
p
r
eh
en
s
iv
e
ex
am
in
atio
n
o
f
co
n
tem
p
o
r
ar
y
SS
L
m
eth
o
d
s
.
I
t
ca
teg
o
r
izes
th
e
tech
n
i
q
u
es
in
to
t
h
r
ee
p
r
im
ar
y
g
r
o
u
p
s
—
class
ical
m
eth
o
d
s
,
ar
tific
ial
in
tellig
en
ce
(
AI
)
m
eth
o
d
s
,
a
n
d
h
y
b
r
id
m
eth
o
d
s
—
an
aly
zin
g
th
eir
s
tr
en
g
th
s
,
lim
itatio
n
s
,
an
d
ap
p
licatio
n
s
in
r
o
b
o
tics
.
Ad
d
itio
n
ally
,
it
e
x
p
lo
r
es
t
h
e
r
o
le
o
f
m
icr
o
p
h
o
n
e
ar
r
ay
s
i
n
in
f
lu
e
n
cin
g
SS
L
p
er
f
o
r
m
an
ce
,
h
ig
h
lig
h
ti
n
g
tr
en
d
s
in
th
e
tr
a
d
e
-
o
f
f
s
b
etwe
en
ac
cu
r
ac
y
an
d
h
ar
d
wa
r
e
co
n
f
ig
u
r
atio
n
s
.
B
y
s
y
n
th
esizin
g
f
in
d
in
g
s
f
r
o
m
5
5
r
esear
ch
p
ap
er
s
,
th
is
wo
r
k
id
e
n
tifie
s
th
e
m
o
s
t
ef
f
ec
tiv
e
tech
n
i
q
u
es
an
d
co
n
f
ig
u
r
atio
n
s
f
o
r
m
o
d
er
n
r
o
b
o
tic
s
y
s
tem
s
.
T
h
e
r
e
v
iew
co
n
clu
d
es
with
in
s
ig
h
ts
in
to
em
er
g
in
g
r
esear
ch
d
ir
ec
tio
n
s
,
f
o
c
u
s
in
g
o
n
en
h
a
n
c
in
g
SS
L
ac
cu
r
ac
y
,
ef
f
icien
cy
,
an
d
ad
a
p
tab
ilit
y
f
o
r
r
ea
l
-
wo
r
ld
ap
p
licatio
n
s
.
2.
CL
AS
SI
F
I
CAT
I
O
N
M
E
T
H
O
D
T
h
is
s
ec
tio
n
p
r
esen
ts
a
co
m
p
r
eh
en
s
iv
e
an
aly
s
is
o
f
f
in
d
in
g
s
f
r
o
m
5
5
r
esear
c
h
p
ap
er
s
,
ex
a
m
in
in
g
th
e
d
is
tr
ib
u
tio
n
an
d
p
er
f
o
r
m
an
ce
o
f
v
ar
io
u
s
SS
L
m
eth
o
d
s
.
I
t
ca
teg
o
r
izes
th
ese
m
eth
o
d
s
in
to
c
lass
ical,
AI
-
d
r
iv
en
,
an
d
h
y
b
r
id
ap
p
r
o
ac
h
es,
h
ig
h
lig
h
tin
g
th
eir
r
esp
ec
tiv
e
s
tr
e
n
g
th
s
,
lim
itatio
n
s
,
an
d
r
ea
l
-
wo
r
ld
ap
p
licab
ilit
y
.
Fu
r
th
er
m
o
r
e
,
th
is
an
aly
s
is
p
r
o
v
id
es
in
s
ig
h
ts
in
to
em
er
g
in
g
tr
en
d
s
,
o
n
g
o
in
g
ch
allen
g
es,
an
d
p
o
ten
tial
f
u
tu
r
e
d
ir
ec
tio
n
s
in
SS
L
r
esear
ch
,
o
f
f
er
in
g
a
v
al
u
ab
le
r
ef
e
r
en
ce
f
o
r
b
o
th
ac
ad
e
m
ic
an
d
i
n
d
u
s
tr
ial
a
p
p
licatio
n
s
.
Fig
u
r
e
1
illu
s
tr
ates
th
e
d
is
tr
ib
u
tio
n
o
f
SS
L
m
eth
o
d
s
in
t
h
e
r
ev
iewe
d
s
tu
d
ies.
C
lass
ic
al
m
eth
o
d
s
ac
co
u
n
t
f
o
r
4
4
%
(
2
4
p
ap
e
r
s
)
,
AI
m
eth
o
d
s
f
o
r
1
6
%
(
9
p
ap
er
s
)
,
an
d
h
y
b
r
id
m
eth
o
d
s
f
o
r
4
0
%
(
2
2
p
ap
er
s
)
.
E
ac
h
ap
p
r
o
ac
h
d
em
o
n
s
tr
ates u
n
iq
u
e
s
tr
en
g
th
s
an
d
lim
itatio
n
s
:
a.
C
las
s
ical
m
eth
o
d
s
:
T
h
ese
tech
n
iq
u
es
r
ely
o
n
s
ig
n
al
p
r
o
ce
s
s
in
g
ap
p
r
o
ac
h
es
s
u
ch
as
b
ea
m
f
o
r
m
in
g
,
T
DOA,
an
d
p
h
ase
-
b
ased
m
eth
o
d
s
.
Kn
o
wn
f
o
r
th
eir
s
im
p
licity
an
d
e
f
f
icien
cy
,
class
ical
m
eth
o
d
s
a
r
e
id
ea
l
f
o
r
r
ea
l
-
tim
e
ap
p
licatio
n
s
b
u
t a
r
e
less
ef
f
ec
tiv
e
in
n
o
is
y
o
r
c
o
m
p
lex
en
v
ir
o
n
m
en
ts
.
b.
AI
m
eth
o
d
s
:
T
h
ese
u
tili
ze
d
ee
p
lear
n
i
n
g
a
n
d
o
th
er
d
ata
-
d
r
iv
en
tech
n
iq
u
es,
ex
ce
llin
g
in
d
y
n
am
ic
a
n
d
m
u
lti
-
s
o
u
r
ce
s
ce
n
a
r
io
s
.
Ho
we
v
er
,
t
h
eir
r
elian
ce
o
n
la
r
g
e
d
at
asets
an
d
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
lim
its
th
eir
s
ca
lab
ilit
y
f
o
r
r
ea
l
-
tim
e
an
d
r
e
s
o
u
r
ce
-
co
n
s
tr
ain
e
d
ap
p
licatio
n
s
.
c.
Hy
b
r
id
m
eth
o
d
s
:
B
y
co
m
b
in
i
n
g
class
ical
f
ea
tu
r
e
ex
tr
ac
tio
n
with
AI
-
d
r
iv
en
p
atter
n
r
ec
o
g
n
itio
n
,
h
y
b
r
i
d
m
eth
o
d
s
ac
h
iev
e
th
e
b
est
o
f
b
o
th
wo
r
ld
s
.
T
h
ey
ar
e
p
ar
ticu
la
r
ly
ef
f
ec
tiv
e
in
ad
d
r
ess
in
g
ch
a
llen
g
es
s
u
ch
as
n
o
is
e,
r
ev
er
b
er
atio
n
,
an
d
c
o
m
p
lex
s
o
u
r
ce
d
y
n
a
m
ics.
T
h
e
n
ex
t
s
ec
tio
n
p
r
o
v
id
es
a
d
etailed
o
v
er
v
iew
o
f
th
e
5
5
p
a
p
er
s
an
aly
ze
d
,
ca
teg
o
r
ized
in
to
th
r
ee
g
r
o
u
p
s
b
ased
o
n
th
e
m
eth
o
d
o
lo
g
y
em
p
lo
y
ed
:
class
ical
m
eth
o
d
s
,
AI
m
eth
o
d
s
,
an
d
h
y
b
r
id
m
eth
o
d
s
.
E
ac
h
ca
teg
o
r
y
is
ex
am
in
ed
in
ter
m
s
o
f
its
tech
n
iq
u
es,
ap
p
licatio
n
s
,
an
d
f
u
t
u
r
e
p
o
ten
tial.
Fig
u
r
e
1
.
Dif
f
e
r
en
t
m
eth
o
d
s
o
f
s
o
u
n
d
s
o
u
r
ce
lo
ca
lizatio
n
a
n
d
d
etec
tio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
A
co
mp
r
eh
en
s
ive
r
ev
iew
o
f so
u
n
d
s
o
u
r
ce
lo
c
a
liz
a
tio
n
meth
o
d
s
fo
r
r
o
b
o
tics
(
Mu
h
a
mma
d
A
kma
l A
liff
)
259
2.
1
.
Cla
s
s
ica
l
m
et
ho
ds
C
las
s
ical
m
eth
o
d
s
,
r
e
p
r
esen
ti
n
g
4
4
%
(
2
4
p
ap
e
r
s
)
o
f
th
e
r
e
v
iewe
d
s
tu
d
ies,
r
ely
o
n
estab
lis
h
ed
s
ig
n
al
p
r
o
ce
s
s
in
g
tech
n
iq
u
es su
ch
as T
DOA,
p
h
ase
-
b
ased
m
eth
o
d
s
,
an
d
b
ea
m
f
o
r
m
i
n
g
.
T
h
ese
m
eth
o
d
s
ar
e
v
al
u
ed
f
o
r
th
eir
m
ath
em
atica
l
s
im
p
licit
y
,
lo
w
co
m
p
u
tatio
n
al
d
e
m
a
n
d
s
,
an
d
r
ea
l
-
tim
e
ap
p
licab
i
lity
,
m
ak
in
g
th
em
f
o
u
n
d
atio
n
al
f
o
r
SS
L
.
W
h
ile
t
h
ey
f
ac
e
lim
itatio
n
s
in
co
m
p
l
ex
ac
o
u
s
tic
en
v
ir
o
n
m
en
ts
,
r
ef
i
n
em
en
ts
an
d
n
o
v
el
im
p
lem
en
tatio
n
s
h
av
e
s
ig
n
if
ic
an
tly
ex
p
a
n
d
ed
t
h
eir
u
tili
ty
.
C
las
s
ical
m
eth
o
d
s
ex
ce
l
in
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
an
d
em
b
ed
d
e
d
a
p
p
licatio
n
s
.
Fo
r
ex
am
p
le
,
J
am
alu
d
in
et
a
l.
[
1
1
]
im
p
le
m
e
n
ted
SS
L
u
s
in
g
T
DOA
o
n
f
ield
p
r
o
g
r
am
m
ab
le
g
ate
ar
r
ay
(
F
PGA)
tech
n
o
lo
g
y
,
ac
h
iev
in
g
im
p
r
o
v
ed
ac
cu
r
ac
y
an
d
p
r
o
ce
s
s
in
g
s
p
ee
d
.
L
in
et
a
l.
[
7
]
o
p
tim
ized
SS
L
o
n
an
FP
GA
So
C
p
latf
o
r
m
,
b
alan
cin
g
p
o
we
r
co
n
s
u
m
p
tio
n
an
d
p
r
o
ce
s
s
in
g
d
em
an
d
s
f
o
r
r
ea
l
-
tim
e
lo
ca
lizatio
n
.
Pam
u
n
g
k
as
an
d
R
ais
[
1
2
]
d
em
o
n
s
tr
ated
a
r
ea
l
-
tim
e
SS
L
s
y
s
tem
u
s
in
g
th
e
in
ter
au
r
al
tim
e
d
if
f
er
en
ce
(
I
T
D
)
m
eth
o
d
o
n
th
e
T
MS3
2
0
C
6
7
1
3
b
o
ar
d
,
wh
ile
Gr
o
n
d
in
et
a
l.
[
1
3
]
p
r
o
p
o
s
e
d
th
e
o
p
e
n
em
b
ed
d
e
d
a
u
d
iti
o
n
s
y
s
tem
(
ODAS)
f
r
am
ewo
r
k
,
in
te
g
r
atin
g
g
en
e
r
alize
d
cr
o
s
s
-
co
r
r
elatio
n
p
h
ase
tr
an
s
f
o
r
m
(
GC
C
-
PHAT
)
alg
o
r
ith
m
,
d
elay
-
a
n
d
-
s
u
m
b
ea
m
f
o
r
m
in
g
,
an
d
Kalm
a
n
f
ilter
in
g
f
o
r
r
o
b
u
s
t SSL
o
n
p
latf
o
r
m
s
lik
e
R
asp
b
er
r
y
Pi.
B
ea
m
f
o
r
m
in
g
in
n
o
v
ati
o
n
s
h
av
e
s
ig
n
if
ican
tly
im
p
r
o
v
e
d
lo
ca
lizatio
n
ac
cu
r
ac
y
an
d
ef
f
icien
cy
.
Gr
o
n
d
in
an
d
Mic
h
au
d
[
8
]
in
t
r
o
d
u
ce
d
th
e
s
teer
ed
r
esp
o
n
s
e
p
o
wer
p
h
ase
tr
a
n
s
f
o
r
m
with
h
ier
ar
ch
ical
s
ea
r
c
h
with
d
ir
ec
tiv
ity
(
SR
P
-
PHAT
-
HSDA)
alg
o
r
ith
m
,
o
p
tim
izin
g
h
ier
a
r
ch
ical
s
ea
r
ch
an
d
d
ir
ec
tiv
ity
m
o
d
els
f
o
r
r
ea
l
-
tim
e
r
o
b
o
tic
ap
p
licatio
n
s
.
Su
n
et
a
l.
[
4
]
d
ev
el
o
p
ed
c
o
m
p
r
ess
ed
b
ea
m
f
o
r
m
in
g
(
C
SB
-
I
I
)
with
iter
ativ
e
th
r
esh
o
ld
in
g
f
o
r
e
n
h
an
ce
d
s
p
atial
r
eso
lu
tio
n
.
Salv
ati
et
a
l.
[
1
4
]
r
ef
in
e
d
SR
P
-
PHAT
with
g
e
o
m
etr
ically
s
am
p
led
g
r
id
s
an
d
m
ax
-
p
o
o
lin
g
,
im
p
r
o
v
in
g
p
er
f
o
r
m
an
ce
in
n
o
is
y
en
v
ir
o
n
m
en
ts
.
Ad
d
itio
n
ally
,
Qin
et
a
l.
[
1
5
]
p
r
o
p
o
s
ed
a
co
m
p
r
ess
iv
e
s
en
s
in
g
-
b
ased
m
eth
o
d
th
at
r
ed
u
ce
d
d
ata
r
eq
u
ir
em
en
ts
wh
ile
m
ain
tain
in
g
ac
cu
r
ac
y
in
r
ev
er
b
er
a
n
t
co
n
d
itio
n
s
.
Go
m
b
o
ts
et
a
l.
[
1
6
]
f
u
r
t
h
er
e
x
ten
d
ed
b
ea
m
f
o
r
m
in
g
b
y
in
teg
r
atin
g
th
e
Helm
h
o
ltz
eq
u
atio
n
a
n
d
f
in
ite
elem
e
n
t m
eth
o
d
(
FEM
)
,
ac
h
iev
in
g
h
ig
h
-
r
eso
lu
tio
n
lo
ca
lizatio
n
in
c
o
m
p
lex
en
v
ir
o
n
m
en
ts
.
C
las
s
ical
m
eth
o
d
s
h
a
v
e
a
d
v
a
n
ce
d
T
DOA
tech
n
iq
u
es
to
im
p
r
o
v
e
lo
ca
lizatio
n
u
n
d
er
c
h
allen
g
in
g
co
n
d
itio
n
s
.
Z
h
ao
et
a
l.
[
1
7
]
en
h
an
ce
d
T
DOA
esti
m
atio
n
with
PHAT
-
GC
C
an
d
a
f
r
eq
u
e
n
cy
d
iv
id
er
,
ad
d
r
ess
in
g
lo
w
s
ig
n
al
-
to
-
n
o
is
e
r
atio
s
.
Hey
d
a
r
i
an
d
Ma
h
a
b
a
d
i
[
5
]
d
em
o
n
s
tr
ated
T
DOA
l
o
ca
lizatio
n
with
h
ig
h
ac
cu
r
ac
y
a
n
d
lo
w
co
m
p
u
tatio
n
al
co
m
p
le
x
ity
,
ac
h
ie
v
in
g
l
o
c
aliza
tio
n
in
ju
s
t
3
6
0
m
illi
s
ec
o
n
d
s
.
Still
et
a
l.
[
1
8
]
in
tr
o
d
u
ce
d
r
ea
l
-
tim
e
T
DOA
(
R
T
DOA)
u
s
in
g
Mo
n
te
C
ar
lo
s
im
u
latio
n
s
to
im
p
r
o
v
e
r
eliab
i
lity
.
L
ee
et
a
l.
[
1
9
]
in
co
r
p
o
r
ated
a
d
i
f
f
u
s
en
ess
m
ask
to
r
ef
in
e
GC
C
-
PHAT
in
r
ev
er
b
er
an
t
s
ettin
g
s
,
wh
ile
C
h
u
n
g
et
a
l.
[
2
0
]
co
m
b
in
ed
GC
C
-
PHAT
with
T
DOA
f
o
r
p
r
ec
is
e
lo
ca
lizatio
n
in
two
-
m
icr
o
p
h
o
n
e
s
y
s
tem
s
,
ac
h
iev
in
g
er
r
o
r
s
as
lo
w
as 2
.
3
cm
.
B
io
lo
g
ically
in
s
p
ir
ed
m
eth
o
d
s
h
av
e
b
r
o
ad
en
e
d
th
e
s
co
p
e
o
f
class
ical
tech
n
iq
u
es.
Yan
g
et
a
l.
[
2
1
]
m
o
d
eled
l
o
ca
lizatio
n
o
n
th
e
a
u
d
ito
r
y
s
y
s
tem
o
f
th
e
p
ar
asit
o
id
f
ly
Or
m
ia
o
ch
r
ac
ea
,
ac
h
ie
v
in
g
h
ig
h
ac
cu
r
ac
y
with
co
m
p
ac
t
s
en
s
o
r
ar
r
ay
s
.
An
et
a
l.
[
2
2
]
p
r
o
p
o
s
ed
a
d
if
f
r
ac
tio
n
-
an
d
r
ef
lectio
n
-
a
war
e
SS
L
m
eth
o
d
,
lev
er
ag
in
g
g
eo
m
etr
ic
ac
o
u
s
tic
m
o
d
elin
g
an
d
r
ay
tr
ac
in
g
to
esti
m
ate
th
e
p
o
s
itio
n
s
o
f
d
ir
e
ct
an
d
n
o
n
-
lin
e
-
of
-
s
ig
h
t (
NL
OS)
s
o
u
r
ce
s
.
C
las
s
ical
tech
n
iq
u
es
h
av
e
als
o
b
ee
n
r
ef
in
e
d
f
o
r
m
u
lti
-
s
o
u
r
ce
s
ce
n
ar
io
s
.
J
ia
et
a
l.
[
9
]
in
tr
o
d
u
ce
d
d
if
f
u
s
en
ess
esti
m
atio
n
to
is
o
late
s
in
g
le
-
s
o
u
r
ce
tim
e
-
f
r
e
q
u
e
n
cy
p
o
in
ts
,
s
im
p
lif
y
in
g
m
u
lti
-
s
o
u
r
ce
lo
ca
lizatio
n
.
So
n
g
an
d
Sh
in
[
2
3
]
co
m
b
i
n
e
d
in
ter
ch
an
n
el
p
h
ase
d
if
f
e
r
en
ce
s
(
I
PDs
)
with
s
p
ec
tr
al
m
as
k
s
an
d
p
r
o
b
ab
ilis
tic
v
o
tin
g
to
im
p
r
o
v
e
d
ir
ec
tio
n
o
f
ar
r
iv
al
(
Do
A)
esti
m
atio
n
.
Z
h
o
u
et
a
l.
[
2
4
]
u
tili
ze
d
p
h
a
s
e
co
n
s
is
ten
cy
an
d
o
u
tlier
r
em
o
v
al
f
o
r
r
o
b
u
s
t m
u
l
ti
-
s
o
u
r
ce
lo
ca
lizatio
n
in
r
ev
er
b
er
an
t e
n
v
ir
o
n
m
e
n
ts
.
C
las
s
ical
m
eth
o
d
s
ar
e
ef
f
ec
ti
v
e
in
d
iv
e
r
s
e
an
d
s
p
ec
ialized
s
ce
n
ar
io
s
.
H
o
s
an
g
ad
i
[
3
]
d
e
v
elo
p
ed
an
SS
L
m
eth
o
d
f
o
r
s
ea
r
ch
-
a
n
d
-
r
escu
e
r
o
b
o
ts
u
s
in
g
GC
C
-
PH
AT
an
d
d
elay
-
a
n
d
-
s
u
m
b
ea
m
f
o
r
m
in
g
,
ac
h
iev
in
g
h
ig
h
an
g
u
lar
r
eso
lu
tio
n
a
n
d
ef
f
icien
t
tr
ian
g
u
latio
n
.
Sier
ie
b
r
iak
o
v
et
a
l.
[
2
5
]
p
r
o
p
o
s
ed
a
m
eth
o
d
b
ased
o
n
s
o
u
n
d
in
te
n
s
ity
an
d
f
r
e
q
u
en
c
y
v
ar
iatio
n
f
o
r
lo
ca
lizatio
n
i
n
r
estricte
d
v
is
ib
ilit
y
en
v
ir
o
n
m
en
ts
.
W
an
g
an
d
Z
h
an
g
[
2
6
]
co
m
b
in
ed
T
DOA
with
Kalm
an
f
ilter
in
g
t
o
ac
h
ie
v
e
s
tab
le
in
d
o
o
r
tr
ac
k
in
g
,
d
em
o
n
s
tr
atin
g
av
e
r
ag
e
lo
ca
lizatio
n
er
r
o
r
s
as lo
w
as 1
0
cm
ac
r
o
s
s
1
0
m
eter
s
.
Ad
a
p
t
iv
e
f
il
te
r
i
n
g
a
n
d
r
ea
l
-
t
i
m
e
ca
p
a
b
i
liti
es
f
u
r
t
h
e
r
s
tr
en
g
t
h
e
n
class
i
ca
l
m
et
h
o
d
s
.
S
ewt
z
et
a
l
.
[
2
7
]
in
t
r
o
d
u
ce
d
t
h
e
m
o
t
io
n
m
o
d
el
e
n
h
a
n
c
ed
m
u
lt
ip
le
s
ig
n
al
class
i
f
ic
ati
o
n
(
MM
E
-
MU
S
I
C
)
al
g
o
r
ith
m
,
i
n
c
o
r
p
o
r
at
in
g
m
o
ti
o
n
m
o
d
el
in
g
a
n
d
n
o
is
e
-
awa
r
e
f
r
e
q
u
e
n
c
y
s
ele
cti
o
n
to
e
n
h
a
n
ce
D
o
A
esti
m
at
i
o
n
i
n
r
e
v
e
r
b
e
r
a
n
t
en
v
i
r
o
n
m
e
n
ts
.
G
al
a
a
n
d
S
u
n
[
2
8
]
c
o
m
b
i
n
e
d
th
e
e
x
t
e
n
d
e
d
K
alm
an
f
ilt
er
(
E
KF
)
wi
th
t
h
e
H
ilb
er
t
t
r
a
n
s
f
o
r
m
f
o
r
r
e
al
-
ti
m
e
SS
L
,
ac
h
i
ev
in
g
q
u
ic
k
c
o
n
v
e
r
g
e
n
c
e
a
n
d
i
m
p
r
o
v
e
d
a
cc
u
r
ac
y
.
Desp
ite
th
eir
s
tr
en
g
th
s
in
m
at
h
em
atica
l
s
im
p
licity
an
d
r
ea
l
-
tim
e
p
er
f
o
r
m
a
n
ce
,
class
ical
m
e
th
o
d
s
f
ac
e
lim
itatio
n
s
in
d
y
n
am
ic
an
d
n
o
is
y
en
v
ir
o
n
m
e
n
ts
,
wh
er
e
r
e
v
er
b
er
atio
n
,
m
u
lti
-
s
o
u
r
ce
in
ter
f
er
en
ce
,
an
d
c
o
m
p
le
x
ac
o
u
s
tic
p
h
en
o
m
en
a
d
eg
r
a
d
e
th
eir
ac
cu
r
ac
y
.
I
n
cr
e
m
en
tal
ad
v
an
ce
m
en
ts
,
s
u
ch
as
a
d
a
p
tiv
e
b
ea
m
f
o
r
m
in
g
,
b
io
lo
g
ically
in
s
p
ir
ed
d
esig
n
s
,
an
d
ad
v
a
n
ce
d
f
ilter
in
g
tech
n
i
q
u
es,
co
n
tin
u
e
to
ex
ten
d
th
eir
r
elev
an
ce
.
Ho
wev
er
,
th
eir
r
elian
ce
o
n
p
r
e
d
ef
in
ed
m
o
d
els
u
n
d
er
s
co
r
es
th
e
g
r
o
win
g
n
ee
d
f
o
r
in
teg
r
atio
n
with
d
ata
-
d
r
iv
en
tech
n
iq
u
es
to
ad
d
r
ess
ev
o
lv
i
n
g
SS
L
ch
all
en
g
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
:
257
-
2
6
6
260
2
.2
.
Art
if
ici
a
l
inte
llig
ence
met
ho
ds
AI
m
eth
o
d
s
,
ex
p
lo
r
ed
in
1
6
%
(
9
p
ap
er
s
)
o
f
th
e
r
e
v
iewe
d
s
tu
d
ies,
lev
er
ag
e
th
e
ca
p
ab
ilit
ies
o
f
m
ac
h
in
e
lear
n
in
g
an
d
d
ee
p
lea
r
n
in
g
to
a
d
d
r
ess
th
e
in
h
er
en
t
li
m
itatio
n
s
o
f
class
ical
ap
p
r
o
ac
h
es.
B
y
em
p
lo
y
in
g
d
ata
-
d
r
iv
e
n
alg
o
r
ith
m
s
s
u
ch
a
s
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
etwo
r
k
s
(
C
NNs),
r
ec
u
r
r
e
n
t
n
eu
r
al
n
etwo
r
k
s
(
R
NNs),
an
d
o
th
e
r
ad
v
a
n
ce
d
m
o
d
els,
AI
m
eth
o
d
s
ex
ce
l
in
l
o
ca
lizin
g
s
o
u
n
d
s
o
u
r
ce
s
in
c
o
m
p
le
x
an
d
c
h
allen
g
in
g
en
v
ir
o
n
m
en
ts
,
in
clu
d
in
g
m
u
lti
-
s
o
u
r
ce
,
n
o
is
y
,
a
n
d
r
ev
er
b
er
an
t
co
n
d
itio
n
s
,
wh
er
e
class
ical
tech
n
iq
u
es o
f
ten
f
all
s
h
o
r
t.
AI
m
eth
o
d
s
ar
e
i
n
cr
ea
s
in
g
ly
b
ein
g
u
s
ed
to
s
tu
d
y
an
d
m
o
d
el
co
m
p
lex
a
u
d
ito
r
y
m
ec
h
a
n
is
m
s
.
Fo
r
ex
am
p
le,
I
h
lef
eld
et
a
l.
[
2
9
]
ex
p
l
o
r
ed
p
o
p
u
latio
n
r
ate
-
co
d
in
g
in
h
u
m
an
s
o
u
n
d
l
o
ca
lizatio
n
,
u
s
in
g
p
s
y
ch
o
p
h
y
s
ical
ex
p
er
im
e
n
ts
an
d
co
m
p
u
tatio
n
al
n
eu
r
al
m
o
d
els
to
d
em
o
n
s
tr
ate
h
o
w
s
o
u
n
d
in
ten
s
ity
af
f
ec
ts
p
er
ce
iv
ed
later
ality
.
T
h
is
r
esear
ch
h
ig
h
lig
h
ted
th
e
p
o
ten
tial
o
f
AI
-
d
r
iv
e
n
n
eu
r
al
m
o
d
elin
g
to
d
ec
o
d
e
in
tr
icate
au
d
ito
r
y
p
r
o
ce
s
s
es a
n
d
ad
v
an
c
e
o
u
r
u
n
d
er
s
tan
d
in
g
o
f
s
o
u
n
d
l
o
ca
lizatio
n
d
y
n
am
ics.
Sev
er
al
s
tu
d
ies
h
av
e
f
o
cu
s
e
d
o
n
ap
p
ly
in
g
AI
tech
n
iq
u
e
s
to
en
h
an
ce
tr
ad
itio
n
al
s
o
u
n
d
s
o
u
r
ce
lo
ca
lizatio
n
task
s
.
Fo
r
in
s
tan
ce
,
T
an
et
a
l.
[
3
0
]
in
tr
o
d
u
ce
d
a
C
NN
-
r
eg
r
ess
io
n
m
o
d
el
(
C
NN
-
R
)
to
p
r
o
ce
s
s
in
ter
au
r
al
p
h
ase
d
if
f
er
en
ce
(
I
PD)
f
ea
tu
r
es
e
x
tr
ac
ted
th
r
o
u
g
h
s
h
o
r
t
-
tim
e
Fo
u
r
ier
tr
an
s
f
o
r
m
(
STFT
)
.
T
h
is
m
eth
o
d
ac
h
iev
e
d
h
ig
h
ac
cu
r
ac
y
f
o
r
an
g
le
an
d
d
is
tan
ce
esti
m
atio
n
,
d
em
o
n
s
tr
atin
g
s
u
p
e
r
io
r
r
o
b
u
s
tn
ess
to
n
o
is
e
in
b
o
th
s
im
u
lated
an
d
r
ea
l
-
wo
r
ld
co
n
d
itio
n
s
.
Similar
ly
,
Hu
an
g
et
a
l.
[
3
1
]
em
p
l
o
y
ed
a
b
ac
k
p
r
o
p
ag
atio
n
n
eu
r
al
n
etwo
r
k
(
B
PNN)
to
p
r
o
ce
s
s
tim
e
-
d
elay
d
if
f
er
e
n
ce
d
ata
f
r
o
m
ac
ce
ler
atio
n
s
en
s
o
r
s
,
ac
h
iev
in
g
lo
ca
lizatio
n
er
r
o
r
s
as lo
w
as 0
.
0
1
m
eter
s
a
n
d
d
em
o
n
s
tr
atin
g
r
o
b
u
s
t p
e
r
f
o
r
m
an
ce
in
s
tr
u
ctu
r
al
s
o
u
n
d
lo
c
aliza
tio
n
.
Z
h
o
u
et
a
l.
[
3
2
]
f
o
cu
s
ed
o
n
n
o
is
e
s
o
u
r
ce
lo
ca
lizatio
n
u
s
in
g
a
d
ee
p
lear
n
in
g
f
r
am
ewo
r
k
b
ased
o
n
C
NNs.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
ef
f
ec
tiv
ely
lo
ca
lizes
s
o
u
n
d
s
o
u
r
ce
s
b
y
lea
r
n
in
g
s
p
atial
p
atter
n
s
an
d
n
o
is
e
f
ea
tu
r
es
f
r
o
m
ac
o
u
s
tic
s
ig
n
als.
E
x
p
er
im
en
tal
r
esu
lts
s
h
o
wed
th
at
th
e
ap
p
r
o
ac
h
is
h
ig
h
ly
r
o
b
u
s
t
in
n
o
is
y
en
v
ir
o
n
m
en
ts
,
o
u
tp
e
r
f
o
r
m
in
g
tr
ad
itio
n
al
lo
ca
lizatio
n
m
e
th
o
d
s
b
y
im
p
r
o
v
in
g
d
etec
ti
o
n
ac
cu
r
ac
y
an
d
g
en
er
alizin
g
well
ac
r
o
s
s
v
ar
y
i
n
g
co
n
d
itio
n
s
.
Sak
av
ičiu
s
an
d
Ser
ac
k
is
[
3
3
]
f
o
cu
s
ed
o
n
3
D
l
o
ca
lizatio
n
task
s
,
em
p
lo
y
in
g
a
C
NN
to
esti
m
ate
az
im
u
th
an
d
elev
atio
n
u
s
in
g
a
2
D
Do
A
p
r
o
b
ab
ilit
y
h
ea
tm
ap
d
er
i
v
ed
f
r
o
m
STFT
p
h
ase
co
m
p
o
n
en
ts
.
T
h
is
m
eth
o
d
ac
h
iev
ed
r
em
a
r
k
ab
le
p
r
ec
is
io
n
ev
e
n
in
lo
w
s
ig
n
al
-
to
-
n
o
is
e
r
atio
(
SNR
)
co
n
d
itio
n
s
,
u
n
d
er
s
co
r
in
g
th
e
ef
f
ec
tiv
en
ess
o
f
AI
-
d
r
iv
en
ap
p
r
o
ac
h
es in
ad
d
r
ess
in
g
co
m
p
lex
s
p
atial
lo
ca
lizatio
n
ch
allen
g
es.
AI
m
et
h
o
d
s
h
a
v
e
als
o
p
r
o
v
en
ef
f
e
cti
v
e
i
n
m
u
lti
-
s
o
u
r
ce
an
d
p
i
x
e
l
-
wis
e
l
o
ca
liz
ati
o
n
.
L
ee
et
a
l
.
[
3
4
]
p
r
o
p
o
s
e
d
a
f
u
ll
y
co
n
v
o
l
u
ti
o
n
a
l
n
e
u
r
al
n
etw
o
r
k
(
FC
N)
wit
h
an
e
n
c
o
d
e
r
-
d
ec
o
d
e
r
s
t
r
u
ct
u
r
e
f
o
r
g
e
n
e
r
a
ti
n
g
h
i
g
h
-
r
es
o
l
u
ti
o
n
s
o
u
r
ce
m
a
p
s
w
it
h
o
u
t
p
r
e
-
d
e
f
i
n
i
n
g
t
h
e
n
u
m
b
er
o
f
s
o
u
r
ce
s
.
T
h
is
a
p
p
r
o
a
ch
o
u
t
p
er
f
o
r
m
e
d
c
o
n
v
e
n
t
io
n
al
d
e
co
n
v
o
l
u
ti
o
n
m
et
h
o
d
s
in
b
o
th
ac
c
u
r
ac
y
a
n
d
e
f
f
ic
ie
n
c
y
,
ac
h
ie
v
i
n
g
l
o
ca
li
za
ti
o
n
e
r
r
o
r
s
as
l
o
w
as
0
.
0
2
0
m
.
I
n
n
o
v
ativ
e
AI
ar
ch
itectu
r
es
h
av
e
b
ee
n
e
m
p
lo
y
e
d
to
h
a
n
d
le
s
p
ec
if
ic
ch
allen
g
es
in
s
o
u
n
d
s
o
u
r
ce
lo
ca
lizatio
n
.
Fo
r
e
x
am
p
le,
B
o
zk
u
r
tlar
et
a
l.
[
3
5
]
in
t
r
o
d
u
ce
d
th
e
v
o
n
-
Mises
R
esNet
(
v
M
-
B
R
esNet)
,
wh
ich
in
co
r
p
o
r
ates
a
n
o
v
el
v
o
n
-
Mi
s
es
co
n
v
o
lu
tio
n
al
lay
er
to
m
an
ag
e
p
er
io
d
ic
p
h
ase
in
f
o
r
m
atio
n
.
T
h
is
m
o
d
el
ac
h
iev
ed
r
ed
u
ce
d
p
r
ed
ictio
n
e
r
r
o
r
s
in
b
o
th
q
u
iet
an
d
n
o
is
y
en
v
ir
o
n
m
en
ts
,
o
u
tp
er
f
o
r
m
in
g
tr
ad
itio
n
al
R
esNet
-
b
ased
m
o
d
els.
Me
an
wh
ile,
Ko
et
a
l.
[
3
6
]
f
o
c
u
s
ed
o
n
r
ea
l
-
tim
e
ap
p
licatio
n
s
,
d
em
o
n
s
tr
atin
g
a
m
u
lti
-
s
tr
ea
m
C
NN
th
at
p
r
o
ce
s
s
es
r
aw
m
u
lti
-
ch
an
n
el
ac
o
u
s
tic
d
ata
with
h
ig
h
ac
cu
r
ac
y
,
tailo
r
ed
f
o
r
lo
w
-
p
o
wer
I
o
T
d
e
v
ices
s
u
ch
as th
e
R
asp
b
er
r
y
Pi.
Fin
ally
,
m
u
ltimo
d
al
ap
p
r
o
ac
h
es
ar
e
g
ain
in
g
tr
ac
tio
n
in
AI
-
d
r
iv
en
SS
L
.
Hu
an
g
et
a
l.
[
3
7
]
i
n
tr
o
d
u
ce
d
au
d
io
-
v
is
u
al
-
lan
g
u
ag
e
m
ap
s
(
AVL
Ma
p
s
)
,
wh
ich
co
m
b
in
e
a
u
d
io
,
v
is
u
al,
an
d
lan
g
u
a
g
e
f
ea
tu
r
es
in
to
a
u
n
if
ie
d
3
D
s
p
atial
m
ap
u
s
in
g
p
r
e
-
tr
a
in
ed
m
u
ltimo
d
al
m
o
d
els
lik
e
Au
d
io
C
L
I
P.
T
h
is
f
r
am
ewo
r
k
en
ab
les
ze
r
o
-
s
h
o
t
n
av
ig
atio
n
f
r
o
m
n
atu
r
al
lan
g
u
ag
e
d
escr
ip
tio
n
s
,
ac
h
iev
in
g
u
p
to
5
0
%
h
ig
h
er
r
ec
all
in
a
m
b
ig
u
o
u
s
s
ce
n
ar
io
s
.
Su
ch
in
n
o
v
atio
n
s
h
ig
h
lig
h
t th
e
tr
an
s
f
o
r
m
ativ
e
p
o
ten
tial o
f
AI
-
b
ased
m
u
ltimo
d
al
f
u
s
io
n
f
o
r
r
o
b
u
s
t SSL
in
r
ea
l
-
wo
r
ld
r
o
b
o
tics
ap
p
licatio
n
s
.
W
h
ile
AI
m
e
th
o
d
s
o
f
f
e
r
s
i
g
n
i
f
ic
a
n
t
a
d
v
a
n
c
em
en
ts
i
n
a
d
ap
t
a
b
ili
ty
a
n
d
ac
cu
r
a
c
y
,
t
h
ey
a
ls
o
f
a
ce
ch
all
en
g
es
s
u
ch
as
r
eli
a
n
ce
o
n
la
r
g
e
l
ab
el
ed
d
a
tas
ets,
h
i
g
h
c
o
m
p
u
ta
ti
o
n
al
r
e
q
u
i
r
e
m
e
n
ts
,
a
n
d
li
m
it
ed
g
e
n
e
r
a
liz
a
b
ili
ty
t
o
u
n
s
ee
n
en
v
i
r
o
n
m
e
n
ts
.
D
esp
ite
t
h
ese
h
u
r
d
les
,
A
I
-
d
r
i
v
en
a
p
p
r
o
a
c
h
es
c
o
n
ti
n
u
e
t
o
p
u
s
h
t
h
e
b
o
u
n
d
a
r
i
es
o
f
s
o
u
n
d
s
o
u
r
c
e
l
o
ca
li
za
t
i
o
n
,
a
d
d
r
ess
in
g
e
v
o
l
v
i
n
g
c
h
al
le
n
g
es
ac
r
o
s
s
d
i
v
er
s
e
an
d
co
m
p
le
x
s
ce
n
ar
i
o
s
.
2.
3
.
H
y
brid
m
et
ho
ds
Hy
b
r
id
m
eth
o
d
s
,
r
ep
r
esen
tin
g
4
0
%
(
2
2
p
a
p
er
s
)
o
f
th
e
r
e
v
i
ewe
d
s
tu
d
ies,
co
m
b
in
e
class
i
ca
l
s
ig
n
al
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
with
AI
m
o
d
els,
lev
er
ag
in
g
th
e
s
tr
en
g
th
s
o
f
b
o
th
d
o
m
ain
s
.
C
lass
ic
al
m
eth
o
d
s
ex
ce
l
in
r
eliab
le
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
p
r
ep
r
o
ce
s
s
in
g
,
wh
ile
AI
tech
n
iq
u
es
p
r
o
v
id
e
r
o
b
u
s
t
p
att
er
n
r
ec
o
g
n
itio
n
an
d
d
ec
is
io
n
-
m
ak
in
g
ca
p
ab
ilit
ies.
T
h
ese
in
teg
r
ated
ap
p
r
o
ac
h
es
h
av
e
s
h
o
wn
s
ig
n
if
ica
n
t
p
o
te
n
tial
in
ad
d
r
ess
in
g
co
m
p
lex
a
n
d
d
y
n
am
ic
c
h
allen
g
es in
SS
L
.
Hy
b
r
id
m
eth
o
d
s
h
av
e
d
em
o
n
s
tr
ated
ex
ce
p
tio
n
al
p
er
f
o
r
m
an
ce
in
s
o
u
n
d
ev
en
t
lo
ca
liz
atio
n
an
d
d
etec
tio
n
(
SEL
D)
.
Fo
r
in
s
tan
ce
,
C
ao
et
a
l.
[
3
8
]
p
r
o
p
o
s
ed
a
two
-
s
tag
e
SEL
D
m
eth
o
d
u
s
in
g
GC
C
-
PH
AT
f
ea
tu
r
es
with
a
co
n
v
o
l
u
tio
n
al
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
(
C
R
NN)
,
r
ed
u
cin
g
d
ir
ec
tio
n
al
an
g
le
er
r
o
r
s
to
9
.
8
5
°.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
A
co
mp
r
eh
en
s
ive
r
ev
iew
o
f so
u
n
d
s
o
u
r
ce
lo
c
a
liz
a
tio
n
meth
o
d
s
fo
r
r
o
b
o
tics
(
Mu
h
a
mma
d
A
kma
l A
liff
)
261
Similar
ly
,
Kr
au
s
e
et
a
l.
[
3
9
]
in
teg
r
ated
GC
C
-
PHAT
an
d
in
ter
ch
a
n
n
el
p
h
ase
d
if
f
er
e
n
ce
s
with
C
R
NNs
,
ac
h
iev
in
g
a
4
°
r
ed
u
ctio
n
in
l
o
ca
lizatio
n
er
r
o
r
an
d
im
p
r
o
v
ed
SEL
D
s
co
r
es.
Min
et
a
l.
[
4
0
]
e
x
ten
d
ed
th
is
ap
p
r
o
ac
h
b
y
co
m
b
in
in
g
GC
C
-
PHAT
with
p
r
in
cip
al
co
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
to
en
h
an
c
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
f
o
r
SEL
Dn
et
m
o
d
els,
r
ed
u
cin
g
DOA
er
r
o
r
s
to
1
8
.
5
° an
d
ac
h
i
ev
in
g
a
f
r
am
e
r
ec
all
r
ate
o
f
9
1
.
7
%.
T
h
e
in
teg
r
atio
n
o
f
m
u
ltip
le
d
a
ta
m
o
d
alities
is
an
o
th
er
h
allm
ar
k
o
f
h
y
b
r
i
d
m
eth
o
d
s
.
C
h
en
et
a
l.
[
4
1
]
co
m
b
in
ed
v
is
u
al
d
ata
an
d
ac
o
u
s
tic
s
ig
n
als
u
s
in
g
Fo
u
r
ier
-
b
a
s
ed
p
o
lar
h
is
to
g
r
am
o
f
o
r
ie
n
ted
g
r
ad
ien
ts
(
HOG)
d
escr
ip
to
r
s
an
d
h
id
d
e
n
Ma
r
k
o
v
m
o
d
els
(
HM
Ms)
,
ac
h
iev
in
g
en
h
a
n
ce
d
lo
ca
lizatio
n
ac
cu
r
ac
y
in
r
ev
er
b
er
an
t
en
v
ir
o
n
m
en
ts
.
Similar
ly
,
Gr
in
s
tein
et
a
l.
[
4
2
]
i
n
tr
o
d
u
ce
d
a
d
u
al
-
in
p
u
t
n
eu
r
al
n
etwo
r
k
(
DI
-
NN)
th
at
in
te
g
r
ates
class
ical
m
etad
ata
with
s
p
e
ctr
o
g
r
am
f
ea
tu
r
es,
r
ed
u
cin
g
lo
ca
lizatio
n
er
r
o
r
s
s
ig
n
if
ica
n
tly
ac
r
o
s
s
v
ar
io
u
s
ac
o
u
s
tic
co
n
d
itio
n
s
.
L
iu
et
a
l.
[
2
]
r
ev
iewe
d
h
y
b
r
id
a
p
p
r
o
ac
h
es
in
eld
er
l
y
s
er
v
ice
r
o
b
o
ts
,
em
p
h
asizin
g
th
e
u
s
e
o
f
SLAM
-
b
ased
3
D
r
ec
o
n
s
tr
u
ctio
n
an
d
m
u
ltimo
d
al
f
u
s
io
n
f
o
r
s
ea
m
less
h
u
m
an
-
r
o
b
o
t i
n
ter
ac
tio
n
.
C
las
s
ical
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
es
h
av
e
b
ee
n
ef
f
ec
tiv
el
y
in
teg
r
ated
with
AI
m
o
d
els
to
en
h
an
ce
s
p
atial
r
eso
lu
tio
n
an
d
r
o
b
u
s
tn
ess
.
B
o
ztas
[
1
]
em
p
lo
y
e
d
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
(
DW
T
)
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
,
f
ee
d
i
n
g
th
e
r
esu
lts
in
to
C
NNs
an
d
b
iLST
Ms,
ac
h
iev
in
g
an
R
²
o
f
0
.
9
7
.
Z
h
an
g
et
a
l.
[
4
3
]
co
m
b
in
ed
co
n
v
en
tio
n
al
b
ea
m
f
o
r
m
in
g
(
C
B
F)
with
a
d
en
s
ely
co
n
n
ec
ted
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
DC
FC
N)
,
wh
ich
en
h
an
ce
d
s
p
atial
r
eso
lu
tio
n
a
n
d
d
y
n
am
ic
r
an
g
e
f
o
r
p
r
ec
is
e
SS
L
.
Z
h
o
u
et
a
l.
[
4
4
]
p
r
o
p
o
s
ed
Aco
u
s
tic
-
Net,
wh
ich
u
s
es
STFT
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
in
te
g
r
ates
R
ep
VGG
-
B
0
with
m
u
lti
-
task
le
ar
n
in
g
f
o
r
r
ea
l
-
tim
e
lo
ca
lizatio
n
,
ac
h
iev
in
g
lo
ca
liz
atio
n
er
r
o
r
s
o
f
0
.
0
1
1
4
m
.
Sev
er
al
s
tu
d
ies
u
s
ed
T
DOA
an
d
GC
C
-
PHAT
f
ea
tu
r
es
alo
n
g
s
id
e
m
ac
h
in
e
lear
n
in
g
to
im
p
r
o
v
e
lo
ca
lizatio
n
.
J
ad
d
o
a
et
a
l.
[
4
5
]
co
m
b
in
ed
T
DOA
-
b
ased
G
C
C
f
ea
tu
r
es
with
R
estricte
d
B
o
ltzm
an
n
Ma
ch
in
e
(
R
B
M)
an
d
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
n
etwo
r
k
s
,
ac
h
i
ev
in
g
o
v
er
9
9
%
ac
cu
r
ac
y
in
n
o
is
y
en
v
ir
o
n
m
en
ts
.
W
an
g
et
a
l.
[
4
6
]
en
h
a
n
ce
d
GC
C
-
P
HAT
with
a
s
p
ee
ch
-
o
r
ien
ted
m
ask
in
g
tech
n
i
q
u
e,
i
n
teg
r
atin
g
m
ac
h
in
e
lear
n
in
g
class
if
ier
s
lik
e
ML
P
an
d
s
p
ik
in
g
n
eu
r
al
n
etwo
r
k
s
(
SNNs
)
.
T
an
g
et
a
l.
[
4
7
]
d
em
o
n
s
tr
ated
th
e
s
y
n
er
g
y
o
f
GC
C
an
d
b
r
o
a
d
lear
n
in
g
s
y
s
tem
s
(
B
L
S),
ac
h
iev
in
g
r
o
b
u
s
t p
er
f
o
r
m
an
ce
in
h
ig
h
-
r
ev
er
b
er
atio
n
an
d
lo
w
-
SNR
en
v
ir
o
n
m
en
ts
.
Li
et
a
l.
[
4
8
]
p
r
o
p
o
s
ed
GC
C
-
Sp
ea
k
er
,
wh
ich
u
s
es
s
p
ea
k
er
-
d
ep
en
d
e
n
t
weig
h
tin
g
f
u
n
ctio
n
s
d
er
iv
ed
f
r
o
m
Sp
ea
k
e
r
B
ea
m
,
im
p
r
o
v
in
g
lo
ca
lizatio
n
ac
cu
r
ac
y
in
m
u
lti
-
s
p
ea
k
er
s
ce
n
ar
i
o
s
.
L
iu
et
a
l.
[
4
9
]
in
tr
o
d
u
ce
d
a
h
y
b
r
id
a
p
p
r
o
ac
h
co
m
b
in
in
g
T
DOA
-
b
ased
g
e
n
er
alize
d
cr
o
s
s
-
co
r
r
elatio
n
(
G
C
C
)
with
m
ac
h
in
e
lear
n
in
g
class
if
ier
s
s
u
ch
as
SVM,
KNN,
an
d
Naiv
e
B
ay
es,
ac
h
iev
in
g
1
0
0
%
lo
ca
lizatio
n
ac
cu
r
ac
y
in
o
u
t
d
o
o
r
f
ield
ex
p
er
im
en
ts
with
o
u
t
r
e
q
u
ir
in
g
m
icr
o
p
h
o
n
e
ca
lib
r
atio
n
.
Z
h
an
g
et
a
l.
[
5
0
]
co
m
b
in
ed
T
DOA
with
n
eu
r
al
n
etwo
r
k
s
f
o
r
n
o
n
li
n
ea
r
f
itti
n
g
an
d
Kalm
an
f
ilter
in
g
to
i
n
teg
r
ate
in
er
tial
m
ea
s
u
r
em
e
n
t
u
n
it
(
I
MU
)
d
ata,
r
ed
u
cin
g
a
n
g
u
lar
r
eso
lu
tio
n
er
r
o
r
s
f
r
o
m
5
.
4
5
° to
1
.
1
°,
m
ak
in
g
it h
ig
h
ly
ef
f
ec
tiv
e
f
o
r
d
y
n
am
ic
ap
p
licatio
n
s
lik
e
s
m
ar
t c
ar
n
av
ig
atio
n
.
Hy
b
r
id
m
eth
o
d
s
h
av
e
also
d
r
awn
in
s
p
ir
atio
n
f
r
o
m
b
io
l
o
g
y
to
ad
d
r
ess
r
ea
l
-
wo
r
ld
c
h
allen
g
es.
Dav
ila
-
C
h
ac
o
n
et
a
l.
[
5
1
]
p
r
o
p
o
s
ed
a
b
io
m
im
etic
b
in
au
r
al
SS
L
s
y
s
tem
co
m
b
in
in
g
class
ical
in
ter
au
r
al
tim
e
an
d
lev
el
d
if
f
er
e
n
ce
s
(
I
T
D/I
L
D)
with
s
p
ik
in
g
n
eu
r
al
n
etwo
r
k
s
,
d
o
u
b
lin
g
s
en
ten
ce
r
ec
o
g
n
itio
n
r
ates
in
n
o
is
y
en
v
ir
o
n
m
en
ts
.
Similar
ly
,
Go
t
o
et
a
l.
[
5
2
]
co
m
b
in
ed
m
i
n
im
u
m
v
ar
ia
n
ce
d
is
to
r
tio
n
less
r
esp
o
n
s
e
(
MV
DR
)
b
ea
m
f
o
r
m
in
g
with
L
iDAR
-
g
en
er
ated
3
D
s
p
atial
d
ata
to
im
p
r
o
v
e
s
o
u
n
d
lo
ca
lizatio
n
an
d
v
is
u
aliza
tio
n
,
d
em
o
n
s
tr
atin
g
r
o
b
u
s
t p
er
f
o
r
m
an
ce
in
b
o
th
d
ir
ec
t a
n
d
r
e
f
lecte
d
s
o
u
n
d
s
ce
n
ar
io
s
.
Hy
b
r
id
m
et
h
o
d
s
c
o
n
t
in
u
e
t
o
p
u
s
h
t
h
e
b
o
u
n
d
a
r
i
es
w
it
h
i
n
n
o
v
ati
v
e
al
g
o
r
it
h
m
s
.
Hu
et
a
l
.
[
5
3
]
co
m
b
i
n
e
d
GC
C
-
PHA
T
wi
th
r
esi
d
u
al
n
e
t
wo
r
k
s
a
n
d
c
h
a
n
n
el
at
te
n
ti
o
n
m
o
d
u
l
es,
ac
h
i
ev
in
g
8
6
.
5
3
%
a
cc
u
r
ac
y
w
it
h
i
n
a
5
°
er
r
o
r
r
a
n
g
e
.
T
an
g
e
t
a
l.
[
1
0
]
u
s
e
d
GC
C
wit
h
t
h
e
i
n
c
r
e
m
e
n
ta
l
b
r
o
a
d
l
ea
r
n
in
g
s
y
s
t
em
(
E
n
h
a
n
ce
)
,
ac
h
i
ev
in
g
9
7
.
2
%
ac
c
u
r
a
cy
i
n
s
i
m
u
la
ti
o
n
s
u
n
d
e
r
h
i
g
h
-
r
e
v
e
r
b
e
r
a
ti
o
n
a
n
d
l
o
w
-
SNR
c
o
n
d
i
ti
o
n
s
.
F
e
n
g
et
a
l
.
[
5
4
]
co
m
b
i
n
e
d
im
p
r
o
v
e
d
GC
C
wit
h
C
NNs,
a
ch
i
e
v
i
n
g
r
o
o
t
m
ea
n
s
q
u
a
r
e
e
r
r
o
r
s
b
el
o
w
5
°
i
n
n
o
is
y
co
n
d
it
io
n
s
.
B
u
lu
t
e
t
a
l
.
[
5
5
]
co
m
b
i
n
e
d
w
av
ele
t
-
tr
a
n
s
f
o
r
m
e
d
a
c
o
u
s
tic
e
m
is
s
i
o
n
s
i
g
n
als
wi
th
C
N
Ns,
ac
h
i
ev
in
g
o
v
e
r
9
9
%
v
al
id
ati
o
n
ac
c
u
r
a
cy
in
s
t
r
u
ct
u
r
e
d
e
n
v
ir
o
n
m
e
n
ts
.
G
r
i
n
s
te
in
et
a
l.
[
6
]
i
n
t
r
o
d
u
c
e
d
Neu
r
a
l
-
SR
P
,
i
n
te
g
r
a
ti
n
g
s
t
ee
r
ed
r
es
p
o
n
s
e
p
o
w
er
(
SR
P)
wi
th
a
C
R
NN
,
r
e
d
u
c
in
g
l
o
ca
liz
ati
o
n
e
r
r
o
r
s
b
y
6
7
%
in
r
ev
er
b
e
r
an
t
en
v
i
r
o
n
m
e
n
ts
.
Hy
b
r
id
m
eth
o
d
s
h
av
e
em
e
r
g
e
d
as
a
tr
an
s
f
o
r
m
ativ
e
ap
p
r
o
ac
h
to
SS
L
,
ad
d
r
ess
in
g
co
m
p
le
x
ac
o
u
s
tic
ch
allen
g
es
with
u
n
p
a
r
alleled
ac
cu
r
ac
y
,
r
o
b
u
s
tn
ess
to
n
o
is
e,
an
d
co
m
p
u
tatio
n
al
e
f
f
icien
cy
.
B
y
b
alan
cin
g
t
h
e
s
im
p
licity
o
f
class
ical
tech
n
iq
u
es
with
th
e
ad
a
p
tab
ilit
y
o
f
A
I
,
th
ey
r
ep
r
esen
t
th
e
m
o
s
t
p
r
o
m
is
in
g
d
ir
ec
tio
n
f
o
r
ad
v
an
cin
g
SS
L
,
p
ar
ticu
la
r
ly
i
n
r
o
b
o
tics
an
d
r
ea
l
-
tim
e
ap
p
li
ca
tio
n
s
.
Ho
wev
er
,
ch
allen
g
es
s
u
ch
as
in
teg
r
atio
n
co
m
p
lex
ity
an
d
co
m
p
u
tatio
n
al
o
v
er
h
ea
d
r
em
ai
n
,
h
ig
h
lig
h
tin
g
th
e
n
ee
d
f
o
r
f
u
r
th
er
r
esear
ch
to
o
p
tim
ize
h
y
b
r
id
s
y
s
tem
s
f
o
r
p
r
ac
tical
d
ep
lo
y
m
en
t
3.
CO
M
P
ARA
T
I
V
E
ANA
L
YS
I
S
3
.
1
.
Acc
ura
cy
o
f
SS
L
m
et
ho
d
As s
h
o
wn
in
Fig
u
r
e
2
,
th
e
av
e
r
ag
e
ac
cu
r
ac
y
o
f
SS
L
m
eth
o
d
s
v
ar
ies ac
r
o
s
s
ca
teg
o
r
ies:
a.
H
y
b
r
i
d
m
e
t
h
o
d
s
a
c
h
i
e
v
e
t
h
e
h
i
g
h
e
s
t
a
c
c
u
r
a
c
y
,
a
v
e
r
a
g
i
n
g
9
7
.
4
5
%
.
T
h
e
i
r
a
b
i
li
t
y
t
o
i
n
t
e
g
r
a
t
e
cl
as
s
ic
a
l
p
r
e
p
r
o
c
e
s
s
i
n
g
te
c
h
n
i
q
u
e
s
(
e
.
g
.
,
T
D
O
A
,
G
C
C
-
P
H
A
T
)
w
i
t
h
a
d
ap
t
i
v
e
A
I
m
o
d
e
ls
a
ll
o
w
s
t
h
e
m
to
h
a
n
d
l
e
d
i
v
e
r
s
e
a
c
o
u
s
t
i
c
c
o
n
d
i
t
i
o
n
s
e
f
f
ec
t
i
v
el
y
.
T
h
i
s
m
a
k
es
t
h
e
m
w
el
l
-
s
u
i
t
e
d
f
o
r
c
o
m
p
l
e
x
,
r
e
a
l
-
w
o
r
l
d
r
o
b
o
t
i
c
a
p
p
l
i
c
a
t
i
o
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
:
257
-
2
6
6
262
b.
AI
m
eth
o
d
s
f
o
llo
w
with
a
n
av
er
ag
e
ac
cu
r
ac
y
o
f
9
6
.
5
2
%.
T
h
ese
m
eth
o
d
s
ex
ce
l
in
lear
n
in
g
c
o
m
p
lex
p
atter
n
s
an
d
ad
a
p
tin
g
to
ch
all
en
g
in
g
e
n
v
ir
o
n
m
en
ts
.
Ho
wev
er
,
th
eir
s
lig
h
tly
lo
wer
ac
cu
r
a
cy
co
m
p
ar
e
d
to
h
y
b
r
id
m
eth
o
d
s
m
ay
s
tem
f
r
o
m
ch
allen
g
es su
ch
as g
e
n
er
ali
za
tio
n
an
d
h
ig
h
c
o
m
p
u
tatio
n
al
d
em
an
d
s
.
c.
C
las
s
ical
m
eth
o
d
s
ex
h
ib
it
th
e
lo
west
av
er
ag
e
ac
cu
r
ac
y
,
at
9
5
.
3
9
%.
W
h
ile
th
eir
m
ath
em
atica
l
s
im
p
licity
an
d
co
m
p
u
tatio
n
al
e
f
f
icien
cy
m
ak
e
th
em
v
alu
ab
le,
t
h
ey
ar
e
m
o
r
e
s
u
s
ce
p
tib
le
to
p
er
f
o
r
m
a
n
ce
d
eg
r
ad
atio
n
in
n
o
is
y
o
r
r
ev
er
b
er
an
t c
o
n
d
iti
o
n
s
.
T
h
e
an
aly
s
is
h
ig
h
lig
h
ts
th
e
tr
en
d
th
at
w
h
ile
class
ical
m
eth
o
d
s
r
em
ain
co
m
p
etitiv
e,
h
y
b
r
i
d
m
eth
o
d
s
o
f
f
e
r
th
e
m
o
s
t r
o
b
u
s
t so
lu
tio
n
b
y
lev
er
a
g
in
g
th
e
s
tr
en
g
th
s
o
f
b
o
th
clas
s
ical
an
d
AI
ap
p
r
o
ac
h
es.
Fig
u
r
e
2
.
Av
e
r
ag
e
ac
c
u
r
ac
y
f
o
r
SS
L
m
eth
o
d
ac
c
o
r
d
in
g
to
its
class
if
icatio
n
3
.
2
.
I
m
pa
ct
o
f
m
icro
ph
o
ne
a
rr
a
y
s
ize
Fig
u
r
e
3
illu
s
tr
ates th
e
r
elatio
n
s
h
ip
b
etwe
en
th
e
n
u
m
b
e
r
o
f
m
icr
o
p
h
o
n
es a
n
d
SS
L
ac
cu
r
ac
y
:
a.
Sin
g
le
m
icr
o
p
h
o
n
e
s
y
s
tem
s
a
ch
iev
e
a
s
u
r
p
r
is
in
g
ly
h
i
g
h
ac
c
u
r
ac
y
o
f
9
7
.
6
0
%,
d
em
o
n
s
tr
atin
g
th
e
p
o
ten
tial
o
f
o
p
tim
ized
alg
o
r
ith
m
s
f
o
r
r
eso
u
r
ce
-
lim
ited
s
etu
p
s
.
T
h
ese
m
eth
o
d
s
ar
e
p
ar
ticu
lar
ly
s
u
itab
le
f
o
r
p
o
r
ta
b
le
o
r
lo
w
-
p
o
wer
d
e
v
ices.
b.
T
wo
m
icr
o
p
h
o
n
e
s
y
s
tem
s
ex
h
ib
it
s
lig
h
tly
lo
wer
ac
cu
r
ac
y
at
9
7
.
2
1
%,
in
d
icatin
g
p
o
ten
tial
ch
allen
g
es
with
p
h
ase
alig
n
m
en
t a
n
d
n
o
is
e
in
ter
f
er
en
ce
in
d
u
al
-
m
icr
o
p
h
o
n
e
co
n
f
ig
u
r
atio
n
s
.
c.
T
h
r
ee
to
ten
m
icr
o
p
h
o
n
e
s
y
s
te
m
s
s
h
o
w
a
f
u
r
th
er
d
r
o
p
in
ac
c
u
r
ac
y
to
9
5
.
9
0
%,
lik
ely
d
u
e
t
o
th
e
co
m
p
lex
ity
o
f
p
r
o
ce
s
s
in
g
m
u
lti
-
ch
an
n
el
s
ig
n
als an
d
en
v
ir
o
n
m
en
tal
f
ac
to
r
s
s
u
ch
as r
ev
er
b
e
r
atio
n
.
d.
Sy
s
tem
s
with
ten
o
r
m
o
r
e
m
icr
o
p
h
o
n
es
ac
h
ie
v
e
th
e
h
i
g
h
est
ac
cu
r
ac
y
o
f
9
9
.
2
3
%,
b
en
ef
itin
g
f
r
o
m
en
h
an
ce
d
s
p
atial
r
eso
lu
tio
n
an
d
r
o
b
u
s
tn
ess
to
n
o
is
e.
T
h
ese
co
n
f
ig
u
r
atio
n
s
ar
e
i
d
ea
l
f
o
r
ap
p
licatio
n
s
r
eq
u
ir
in
g
h
ig
h
p
r
ec
is
io
n
i
n
co
m
p
lex
en
v
ir
o
n
m
e
n
ts
.
T
h
e
r
esu
lts
in
d
icate
th
at
wh
il
e
lar
g
er
m
icr
o
p
h
o
n
e
ar
r
ay
s
p
r
o
v
id
e
s
ig
n
if
ican
t
ac
c
u
r
ac
y
im
p
r
o
v
em
e
n
ts
,
s
in
g
le
an
d
d
u
al
-
m
icr
o
p
h
o
n
e
s
y
s
tem
s
r
em
ain
v
iab
le
f
o
r
ap
p
licatio
n
s
with
h
ar
d
war
e
co
n
s
tr
ain
ts
,
p
r
o
v
id
ed
t
h
ey
a
r
e
p
air
ed
with
well
-
o
p
tim
ized
alg
o
r
ith
m
s
.
Fig
u
r
e
3
.
Av
e
r
ag
e
ac
c
u
r
ac
y
f
o
r
SS
L
m
eth
o
d
ac
c
o
r
d
in
g
to
its
n
u
m
b
er
o
f
m
icr
o
p
h
o
n
es u
s
ed
i
n
its
s
y
s
tem
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
A
co
mp
r
eh
en
s
ive
r
ev
iew
o
f so
u
n
d
s
o
u
r
ce
lo
c
a
liz
a
tio
n
meth
o
d
s
fo
r
r
o
b
o
tics
(
Mu
h
a
mma
d
A
kma
l A
liff
)
263
3
.
3
.
P
ra
ct
ica
l
im
pli
ca
t
io
ns
T
h
e
f
in
d
i
n
g
s
s
u
g
g
est s
ev
er
al
p
r
ac
tical
co
n
s
id
er
atio
n
s
f
o
r
SS
L
s
y
s
tem
d
esig
n
:
a.
Hy
b
r
id
m
eth
o
d
s
an
d
lar
g
e
ar
r
ay
s
f
o
r
h
ig
h
-
p
er
f
o
r
m
a
n
ce
ap
p
licatio
n
s
:
Hy
b
r
id
m
eth
o
d
s
,
co
m
b
in
ed
with
m
icr
o
p
h
o
n
e
ar
r
a
y
s
o
f
1
0
o
r
m
o
r
e
ch
an
n
els,
ar
e
th
e
m
o
s
t
ef
f
ec
tiv
e
f
o
r
ap
p
licatio
n
s
r
eq
u
ir
i
n
g
h
ig
h
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
,
s
u
ch
as a
u
to
n
o
m
o
u
s
n
a
v
ig
atio
n
a
n
d
h
u
m
an
-
r
o
b
o
t in
te
r
ac
tio
n
in
n
o
is
y
en
v
ir
o
n
m
en
ts
.
b.
C
o
s
t
-
ef
f
ec
tiv
e
s
o
lu
tio
n
s
f
o
r
r
eso
u
r
ce
-
co
n
s
tr
ain
e
d
s
y
s
tem
s
:
Sin
g
le
an
d
d
u
al
-
m
icr
o
p
h
o
n
e
s
y
s
tem
s
,
p
air
ed
with
class
ical
o
r
AI
m
eth
o
d
s
,
o
f
f
er
c
o
m
p
etitiv
e
ac
cu
r
ac
y
f
o
r
lo
w
-
c
o
s
t
an
d
p
o
r
tab
le
d
ev
ices,
s
u
ch
as
wea
r
ab
le
r
o
b
o
ts
o
r
I
o
T
s
y
s
tem
s
.
c.
T
r
ad
e
-
o
f
f
s
in
m
u
lti
-
m
icr
o
p
h
o
n
e
s
y
s
tem
s
:
Sy
s
tem
s
with
3
to
1
0
m
icr
o
p
h
o
n
es
r
eq
u
i
r
e
f
u
r
t
h
er
o
p
tim
izatio
n
to
m
an
ag
e
s
ig
n
al
co
m
p
lex
ity
an
d
co
m
p
u
tatio
n
al
lo
a
d
s
,
p
ar
ticu
lar
ly
f
o
r
r
ea
l
-
tim
e
ap
p
licatio
n
s
in
r
ev
er
b
er
a
n
t e
n
v
i
r
o
n
m
e
n
ts
.
3
.
4
.
Cha
lleng
es
a
nd
f
uture
d
irec
t
io
ns
Desp
ite
th
eir
ad
v
an
ce
m
e
n
ts
,
ea
ch
ca
teg
o
r
y
o
f
SS
L
m
eth
o
d
s
f
ac
es sp
ec
if
ic
ch
allen
g
es:
a.
C
las
s
ical
m
eth
o
d
s
:
−
Stru
g
g
le
in
d
y
n
am
ic
e
n
v
ir
o
n
m
en
ts
with
n
o
is
e
an
d
r
e
v
er
b
er
ati
o
n
.
−
Fu
tu
r
e
r
esear
ch
s
h
o
u
l
d
ex
p
l
o
r
e
ad
ap
tiv
e
f
ilter
in
g
tech
n
i
q
u
es
an
d
in
teg
r
ati
o
n
with
AI
m
o
d
els
to
en
h
an
ce
r
o
b
u
s
tn
ess
.
b.
AI
m
eth
o
d
s
:
−
Dep
en
d
en
ce
o
n
lar
g
e
d
atasets
an
d
h
ig
h
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
lim
its
s
ca
lab
ilit
y
.
−
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
f
o
cu
s
o
n
l
ig
h
tweig
h
t
AI
ar
c
h
itectu
r
es
an
d
s
em
i
-
s
u
p
er
v
is
ed
lear
n
in
g
to
r
ed
u
ce
d
ata
an
d
r
eso
u
r
ce
r
eq
u
ir
em
en
ts
.
c.
Hy
b
r
id
m
eth
o
d
s
:
−
I
n
teg
r
atio
n
co
m
p
le
x
ity
an
d
co
m
p
u
tatio
n
al
o
v
er
h
ea
d
r
em
ain
s
ig
n
if
ican
t h
u
r
d
les.
−
Op
tim
izatio
n
o
f
h
y
b
r
id
s
y
s
tem
s
f
o
r
r
ea
l
-
tim
e
p
r
o
ce
s
s
in
g
an
d
en
er
g
y
ef
f
icien
c
y
will
b
e
cr
u
cial
f
o
r
b
r
o
ad
e
r
ad
o
p
tio
n
.
I
n
ad
d
itio
n
,
th
e
ex
p
lo
r
atio
n
o
f
n
o
v
el
s
en
s
o
r
d
esig
n
s
,
s
u
c
h
as
b
io
lo
g
ically
in
s
p
ir
ed
s
y
s
tem
s
o
r
m
u
ltimo
d
al
ap
p
r
o
ac
h
es,
co
u
ld
f
u
r
t
h
er
en
h
an
ce
SS
L
ca
p
ab
ilit
ies in
r
o
b
o
ti
cs.
4.
CO
NCLU
SI
O
N
T
h
is
r
ev
iew
p
ap
er
p
r
esen
ts
a
co
m
p
r
eh
e
n
s
iv
e
an
aly
s
is
o
f
SS
L
m
eth
o
d
s
,
ca
teg
o
r
ized
in
to
class
ica
l
m
eth
o
d
s
,
AI
m
eth
o
d
s
,
an
d
h
y
b
r
id
m
eth
o
d
s
.
E
ac
h
ca
te
g
o
r
y
d
em
o
n
s
tr
ates
u
n
iq
u
e
s
tr
en
g
th
s
an
d
lim
itatio
n
s
.
C
las
s
ical
m
eth
o
d
s
ar
e
ef
f
icien
t
an
d
co
m
p
u
tatio
n
ally
lig
h
t
weig
h
t
b
u
t
s
tr
u
g
g
le
with
n
o
is
e
an
d
r
ev
er
b
er
atio
n
.
AI
-
b
ased
m
eth
o
d
s
ex
ce
l
in
h
a
n
d
lin
g
co
m
p
lex
,
d
y
n
am
ic
e
n
v
i
r
o
n
m
en
ts
b
u
t
f
ac
e
ch
allen
g
es with
s
ca
lab
ilit
y
an
d
co
m
p
u
tatio
n
al
in
te
n
s
ity
.
Hy
b
r
id
m
eth
o
d
s
,
in
teg
r
atin
g
class
ical
s
ig
n
al
p
r
o
ce
s
s
in
g
with
AI
-
d
r
iv
en
m
o
d
els,
em
er
g
e
as
th
e
m
o
s
t
ef
f
ec
tiv
e
ap
p
r
o
ac
h
,
ac
h
iev
i
n
g
th
e
h
ig
h
e
s
t
av
er
ag
e
ac
cu
r
ac
y
(
9
7
.
4
5
%).
T
h
eir
ad
ap
ta
b
ilit
y
an
d
r
o
b
u
s
tn
ess
m
ak
e
th
em
p
ar
ticu
lar
ly
s
u
itab
le
f
o
r
r
ea
l
-
wo
r
l
d
r
o
b
o
tic
ap
p
licatio
n
s
.
T
h
e
r
e
v
iew
also
ev
al
u
ates
th
e
im
p
ac
t
o
f
m
icr
o
p
h
o
n
e
co
n
f
ig
u
r
atio
n
s
o
n
SS
L
p
e
r
f
o
r
m
an
ce
.
Sy
s
tem
s
with
1
0
o
r
m
o
r
e
m
ic
r
o
p
h
o
n
es a
ch
iev
e
th
e
h
ig
h
est
ac
cu
r
ac
y
(
9
9
.
2
3
%),
b
en
e
f
itin
g
f
r
o
m
s
p
at
ial
r
ed
u
n
d
a
n
cy
a
n
d
r
o
b
u
s
t
s
ig
n
al
p
r
o
ce
s
s
in
g
.
H
o
wev
er
,
s
in
g
le
an
d
d
u
al
-
m
ic
r
o
p
h
o
n
e
s
y
s
tem
s
,
wh
en
p
air
ed
with
o
p
tim
ized
alg
o
r
ith
m
s
,
d
eliv
er
co
m
p
eti
tiv
e
ac
cu
r
ac
y
,
o
f
f
er
in
g
co
s
t
-
ef
f
ec
tiv
e
s
o
lu
tio
n
s
f
o
r
r
e
s
o
u
r
ce
-
co
n
s
tr
ain
e
d
ap
p
licatio
n
s
.
I
n
co
n
clu
s
io
n
,
h
y
b
r
id
m
et
h
o
d
s
co
m
b
in
ed
with
lar
g
e
r
m
icr
o
p
h
o
n
e
ar
r
a
y
s
o
f
f
e
r
th
e
m
o
s
t
r
eliab
le
an
d
p
r
ec
is
e
s
o
lu
tio
n
s
f
o
r
SS
L
in
r
o
b
o
tics
an
d
o
th
er
ad
v
a
n
ce
d
ap
p
licatio
n
s
.
Fu
tu
r
e
r
esear
ch
s
h
o
u
l
d
f
o
cu
s
o
n
o
p
tim
izin
g
h
y
b
r
id
a
p
p
r
o
ac
h
es
f
o
r
r
ea
l
-
tim
e
a
n
d
en
e
r
g
y
-
ef
f
i
cien
t
p
er
f
o
r
m
an
ce
,
e
n
ab
lin
g
t
h
eir
d
ep
lo
y
m
en
t
in
d
y
n
am
ic
a
n
d
n
o
is
y
e
n
v
ir
o
n
m
en
ts
.
Ad
d
itio
n
ally
,
ex
p
l
o
r
in
g
m
u
ltimo
d
al
h
y
b
r
id
s
y
s
tem
s
o
r
lig
h
tweig
h
t
AI
tech
n
iq
u
es
with
m
in
im
al
m
icr
o
p
h
o
n
es
co
u
ld
y
ield
co
s
t
-
ef
f
e
ctiv
e
s
o
lu
tio
n
s
f
o
r
a
wid
e
r
r
an
g
e
o
f
p
r
ac
tical
SS
L
ap
p
licatio
n
s
.
B
y
ad
d
r
ess
in
g
th
ese
ch
allen
g
es,
SS
L
te
ch
n
o
lo
g
ies
will
co
n
tin
u
e
t
o
ev
o
l
v
e,
d
r
iv
in
g
ad
v
an
ce
m
e
n
ts
in
r
o
b
o
tics
an
d
au
d
ito
r
y
s
y
s
tem
s
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
s
wo
u
ld
lik
e
to
ex
p
r
ess
th
eir
s
in
ce
r
e
g
r
atitu
d
e
to
th
e
C
en
ter
o
f
E
x
ce
llen
ce
(
C
o
E
)
R
o
b
o
tics
an
d
Sen
s
in
g
T
ec
h
n
o
lo
g
ies
team
o
f
T
MRND
f
o
r
th
eir
in
v
alu
ab
le
g
u
id
a
n
ce
an
d
s
u
p
p
o
r
t
th
r
o
u
g
h
o
u
t
th
e
d
ev
elo
p
m
e
n
t o
f
t
h
is
r
esear
ch
p
ap
er
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
:
257
-
2
6
6
264
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
f
u
n
d
ed
b
y
Pro
ject
SOLA
R
I
S
(
R
DT
C
2
4
1
1
2
9
)
,
a
co
llab
o
r
ativ
e
r
esear
ch
p
r
o
g
r
am
b
etwe
en
T
elek
o
m
Ma
lay
s
ia
R
esear
ch
&
Dev
elo
p
m
en
t
(
T
MRND)
an
d
Mu
ltime
d
ia
Un
iv
er
s
ity
(
MM
U)
,
Ma
lay
s
ia.
T
h
e
f
u
n
d
in
g
s
u
p
p
o
r
ted
th
e
d
esig
n
,
im
p
lem
en
tatio
n
,
an
d
an
aly
s
is
o
f
th
e
s
tu
d
y
.
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
Mu
h
am
m
ad
A
k
m
al
Alif
f
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
E
m
er
s
o
n
J
o
s
ep
h
R
aja
✓
✓
✓
✓
✓
✓
✓
✓
✓
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
r
e
ar
e
n
o
c
o
n
f
licts
o
f
in
ter
est r
e
g
ar
d
in
g
th
e
p
u
b
licatio
n
o
f
th
is
p
ap
er
.
DATA AV
AI
L
AB
I
L
I
T
Y
All
d
ata
u
s
ed
in
t
h
is
s
tu
d
y
ar
e
o
b
tain
e
d
f
r
o
m
p
u
b
licly
a
v
ailab
le
r
esear
ch
ar
ticles
cited
i
n
t
h
is
p
ap
er
.
T
h
e
p
r
o
ce
s
s
ed
d
ata,
in
clu
d
i
n
g
th
e
co
m
p
iled
d
ataset
o
f
r
ev
iewe
d
s
tu
d
ies
an
d
an
aly
s
is
r
e
s
u
lts
,
ar
e
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est
.
RE
F
E
R
E
NC
E
S
[
1
]
G
.
B
o
z
t
a
s
,
“
S
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
f
o
r
a
u
d
i
t
o
r
y
p
e
r
c
e
p
t
i
o
n
o
f
a
h
u
man
o
i
d
r
o
b
o
t
u
s
i
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
N
e
u
ra
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
5
,
n
o
.
9
,
p
p
.
6
8
0
1
–
6
8
1
1
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
2
2
-
0
8
0
4
7
-
x.
[
2
]
X
.
Li
u
,
C
.
H
u
a
n
g
,
H
.
Z
h
u
,
Z.
W
a
n
g
,
J.
Li
,
a
n
d
A
.
C
a
n
g
e
l
o
si
,
“
S
t
a
t
e
-
of
-
t
h
e
-
a
r
t
e
l
d
e
r
l
y
serv
i
c
e
r
o
b
o
t
:
e
n
v
i
r
o
n
m
e
n
t
a
l
p
e
r
c
e
p
t
i
o
n
,
c
o
m
p
l
i
a
n
c
e
c
o
n
t
r
o
l
,
i
n
t
e
n
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
,
a
n
d
r
e
se
a
r
c
h
c
h
a
l
l
e
n
g
e
s,
”
I
EE
E
S
y
s
t
e
m
s,
M
a
n
,
a
n
d
C
y
b
e
r
n
e
t
i
c
s
M
a
g
a
zi
n
e
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
2
–
1
6
,
Ja
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
M
S
M
C
.
2
0
2
3
.
3
2
3
8
8
5
5
.
[
3
]
R
.
H
o
s
a
n
g
a
d
i
,
“
A
p
r
o
p
o
se
d
m
e
t
h
o
d
f
o
r
a
c
o
u
st
i
c
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
i
n
sea
r
c
h
a
n
d
r
e
sc
u
e
r
o
b
o
t
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
5
t
h
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
Me
c
h
a
t
r
o
n
i
c
s
a
n
d
R
o
b
o
t
i
c
s E
n
g
i
n
e
e
ri
n
g
,
F
e
b
.
2
0
1
9
,
p
p
.
1
3
4
–
1
4
0
.
d
o
i
:
1
0
.
1
1
4
5
/
3
3
1
4
4
9
3
.
3
3
1
4
5
1
0
.
[
4
]
J.
S
u
n
,
P
.
L
i
,
Y
.
C
h
e
n
,
H
.
Lu
,
D
.
S
h
a
o
,
a
n
d
G
.
C
h
e
n
,
“
S
o
u
n
d
so
u
r
c
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
c
o
mp
r
e
sse
d
b
e
a
mf
o
r
mi
n
g
,
”
J
o
u
rn
a
l
o
f
Me
c
h
a
n
i
c
a
l
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
3
8
,
n
o
.
4
,
p
p
.
1
6
2
7
–
1
6
3
4
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
2
0
6
-
0
2
4
-
0
3
0
1
-
z.
[
5
]
Z.
H
e
y
d
a
r
i
a
n
d
A
.
M
a
h
a
b
a
d
i
,
“
S
c
a
l
a
b
l
e
r
e
a
l
-
t
i
m
e
s
o
u
n
d
so
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
me
t
h
o
d
b
a
se
d
o
n
TD
O
A
,
”
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
2
,
n
o
.
1
5
,
p
p
.
2
3
3
3
3
–
2
3
3
7
2
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
022
-
1
4
2
5
6
-
2.
[
6
]
E.
G
r
i
n
st
e
i
n
,
T
.
v
a
n
W
a
t
e
r
sc
h
o
o
t
,
M
.
B
r
o
o
k
e
s,
a
n
d
P
.
A
.
N
a
y
l
o
r
,
“
T
h
e
N
e
u
r
a
l
-
S
R
P
m
e
t
h
o
d
f
o
r
p
o
si
t
i
o
n
a
l
s
o
u
n
d
so
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
,
”
a
rX
i
v
:
2
4
0
3
.
0
9
4
5
5
,
2
0
2
4
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
2
4
0
3
.
0
9
4
5
5
.
[
7
]
Z.
L
i
n
,
K
.
I
t
o
y
a
ma,
K
.
N
a
k
a
d
a
i
,
a
n
d
H
.
A
ma
n
o
,
“
F
P
G
A
-
b
a
se
d
l
o
w
p
o
w
e
r
a
c
c
e
l
e
r
a
t
i
o
n
o
f
H
A
R
K
so
u
n
d
so
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
,
”
i
n
2
0
2
4
I
EEE
S
y
m
p
o
s
i
u
m
i
n
L
o
w
-
Po
w
e
r
a
n
d
H
i
g
h
-
S
p
e
e
d
C
h
i
p
s
(
C
O
O
L
C
H
I
PS
)
,
A
p
r
.
2
0
2
4
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
C
O
O
L
C
H
I
P
S
6
1
2
9
2
.
2
0
2
4
.
1
0
5
3
1
1
8
0
.
[
8
]
F
.
G
r
o
n
d
i
n
a
n
d
F
.
M
i
c
h
a
u
d
,
“
L
i
g
h
t
w
e
i
g
h
t
a
n
d
o
p
t
i
m
i
z
e
d
s
o
u
n
d
so
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
a
n
d
t
r
a
c
k
i
n
g
met
h
o
d
s
f
o
r
o
p
e
n
a
n
d
c
l
o
s
e
d
mi
c
r
o
p
h
o
n
e
a
r
r
a
y
c
o
n
f
i
g
u
r
a
t
i
o
n
s,
”
R
o
b
o
t
i
c
s
a
n
d
A
u
t
o
n
o
m
o
u
s
S
y
s
t
e
m
s
,
v
o
l
.
1
1
3
,
p
p
.
6
3
–
8
0
,
M
a
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
o
b
o
t
.
2
0
1
9
.
0
1
.
0
0
2
.
[
9
]
X
.
Ji
a
,
M
.
J
i
a
,
L.
Li
,
a
n
d
Y
.
Ji
a
,
“
M
u
l
t
i
p
l
e
s
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
b
y
u
s
i
n
g
d
i
f
f
u
s
e
n
e
ss
e
st
i
ma
t
i
o
n
,
”
i
n
2
0
2
0
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
a
n
d
C
o
n
t
r
o
l
En
g
i
n
e
e
r
i
n
g
(
I
C
I
S
C
E)
,
D
e
c
.
2
0
2
0
,
p
p
.
8
7
4
–
8
7
7
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
S
C
E5
0
9
6
8
.
2
0
2
0
.
0
0
1
8
1
.
[
1
0
]
R
.
T
a
n
g
,
Y
.
Zh
a
n
g
,
Y
.
Z
u
o
,
B
.
Li
n
,
a
n
d
M
.
Li
a
n
g
,
“
S
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
o
f
m
i
c
r
o
p
h
o
n
e
a
r
r
a
y
b
a
se
d
o
n
i
n
c
r
e
me
n
t
a
l
b
r
o
a
d
l
e
a
r
n
i
n
g
s
y
st
e
m,
”
C
i
rc
u
i
t
s,
S
y
st
e
m
s
,
a
n
d
S
i
g
n
a
l
Pro
c
e
s
si
n
g
,
v
o
l
.
4
3
,
n
o
.
3
,
p
p
.
1
5
4
9
–
1
5
7
1
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
0
3
4
-
0
2
3
-
0
2
5
2
1
-
0.
[
1
1
]
N
.
C
.
Jam
a
l
u
d
i
n
,
I
.
S
.
A
.
H
a
l
i
m
,
S
.
L.
M
.
H
a
ssa
n
,
a
n
d
W
.
F
.
H
.
A
b
d
u
l
l
a
h
,
“
R
e
a
l
-
t
i
me
F
P
G
A
-
b
a
se
d
s
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
,
”
i
n
2
0
2
4
I
EE
E
1
4
t
h
S
y
m
p
o
s
i
u
m
o
n
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s
&
a
m
p
;
I
n
d
u
s
t
ri
a
l
El
e
c
t
r
o
n
i
c
s
(
I
S
C
AI
E)
,
M
a
y
2
0
2
4
,
p
p
.
2
6
0
–
2
6
4
.
d
o
i
:
1
0
.
1
1
0
9
/
I
S
C
A
I
E6
1
3
0
8
.
2
0
2
4
.
1
0
5
7
6
6
0
8
.
[
1
2
]
Y
.
P
a
m
u
n
g
k
a
s
a
n
d
Y
.
R
a
i
s,
“
I
mp
l
e
m
e
n
t
a
t
i
o
n
o
f
r
e
a
l
-
t
i
me
s
o
u
n
d
so
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
u
si
n
g
TM
S
3
2
0
C
6
7
1
3
b
o
a
r
d
w
i
t
h
i
n
t
e
r
a
u
r
a
l
t
i
m
e
d
i
f
f
e
r
e
n
c
e
me
t
h
o
d
,
”
i
n
2
0
2
2
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
S
e
m
i
n
a
r
o
n
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
,
O
p
t
i
m
i
z
a
t
i
o
n
,
a
n
d
D
a
t
a
S
c
i
e
n
c
e
(
I
S
MOD
E)
,
D
e
c
.
2
0
2
2
,
p
p
.
2
6
9
–
2
7
4
.
d
o
i
:
1
0
.
1
1
0
9
/
I
S
M
O
D
E5
6
9
4
0
.
2
0
2
2
.
1
0
1
8
0
9
9
9
.
[
1
3
]
F
.
G
r
o
n
d
i
n
e
t
a
l
.
,
“
O
D
A
S
:
O
p
e
n
e
mb
e
d
d
e
D
a
u
d
i
t
i
o
n
s
y
st
e
m,”
Fr
o
n
t
i
e
rs
i
n
Ro
b
o
t
i
c
s
a
n
d
AI
,
v
o
l
.
9
,
M
a
y
2
0
2
2
,
d
o
i
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
A
co
mp
r
eh
en
s
ive
r
ev
iew
o
f so
u
n
d
s
o
u
r
ce
lo
c
a
liz
a
tio
n
meth
o
d
s
fo
r
r
o
b
o
tics
(
Mu
h
a
mma
d
A
kma
l A
liff
)
265
1
0
.
3
3
8
9
/
f
r
o
b
t
.
2
0
2
2
.
8
5
4
4
4
4
.
[
1
4
]
D
.
S
a
l
v
a
t
i
,
C
.
D
r
i
o
l
i
,
a
n
d
G
.
L.
F
o
r
e
s
t
i
,
“
A
c
o
u
st
i
c
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
u
si
n
g
a
g
e
o
me
t
r
i
c
a
l
l
y
s
a
mp
l
e
d
g
r
i
d
S
R
P
-
P
H
A
T
a
l
g
o
r
i
t
h
m
w
i
t
h
ma
x
-
p
o
o
l
i
n
g
o
p
e
r
a
t
i
o
n
,
”
I
EEE
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
L
e
t
t
e
rs
,
v
o
l
.
2
9
,
p
p
.
1
8
2
8
–
1
8
3
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
LSP
.
2
0
2
2
.
3
1
9
9
6
6
2
.
[
1
5
]
M
.
Q
i
n
,
D
.
H
u
,
Z.
C
h
e
n
,
a
n
d
F
.
Y
i
n
,
“
C
o
mp
r
e
ssi
v
e
se
n
si
n
g
-
b
a
se
d
s
o
u
n
d
so
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
f
o
r
mi
c
r
o
p
h
o
n
e
a
r
r
a
y
s,
”
C
i
rc
u
i
t
s,
S
y
s
t
e
m
s,
a
n
d
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
,
v
o
l
.
4
0
,
n
o
.
9
,
p
p
.
4
6
9
6
–
4
7
1
9
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
0
3
4
-
021
-
0
1
6
9
2
-
y.
[
1
6
]
S
.
G
o
m
b
o
t
s,
J.
N
o
w
a
k
,
a
n
d
M
.
K
a
l
t
e
n
b
a
c
h
e
r
,
“
S
o
u
n
d
so
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
–
s
t
a
t
e
o
f
t
h
e
a
r
t
a
n
d
n
e
w
i
n
v
e
r
se
sc
h
e
me
,
”
e
&
i
El
e
k
t
r
o
t
e
c
h
n
i
k
u
n
d
I
n
f
o
rm
a
t
i
o
n
s
t
e
c
h
n
i
k
,
v
o
l
.
1
3
8
,
n
o
.
3
,
p
p
.
2
2
9
–
2
4
3
,
J
u
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s0
0
5
0
2
-
0
2
1
-
0
0
8
8
1
-
6.
[
1
7
]
J.
Zh
a
o
e
t
a
l
.
,
“
A
s
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
m
e
t
h
o
d
b
a
s
e
d
o
n
f
r
e
q
u
e
n
c
y
d
i
v
i
d
e
r
a
n
d
t
i
me
d
i
f
f
e
r
e
n
c
e
o
f
a
r
r
i
v
a
l
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
1
0
,
p
.
6
1
8
3
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
1
0
6
1
8
3
.
[
1
8
]
L.
S
t
i
l
l
,
M
.
O
i
s
p
u
u
,
a
n
d
W
.
K
o
c
h
,
“
S
i
mu
l
t
a
n
e
o
u
s
se
n
so
r
a
n
d
s
o
u
n
d
so
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
i
n
u
r
b
a
n
e
n
v
i
r
o
n
m
e
n
t
s,”
i
n
2
0
2
3
2
6
t
h
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
I
n
f
o
rm
a
t
i
o
n
F
u
s
i
o
n
(
FU
S
I
O
N
)
,
Ju
n
.
2
0
2
3
,
p
p
.
1
–
8
.
d
o
i
:
1
0
.
2
3
9
1
9
/
F
U
S
I
O
N
5
2
2
6
0
.
2
0
2
3
.
1
0
2
2
4
2
3
0
.
[
1
9
]
R
.
Le
e
,
M
.
-
S
.
K
a
n
g
,
B
.
-
H
.
K
i
m,
K
.
-
H
.
P
a
r
k
,
S
.
Q
.
Le
e
,
a
n
d
H
.
-
M
.
P
a
r
k
,
“
S
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
b
a
s
e
d
o
n
G
C
C
-
P
H
A
T
w
i
t
h
d
i
f
f
u
s
e
n
e
ss
mas
k
i
n
n
o
i
sy
a
n
d
r
e
v
e
r
b
e
r
a
n
t
e
n
v
i
r
o
n
me
n
t
s
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
7
3
7
3
–
7
3
8
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
6
3
7
6
8
.
[
2
0
]
M.
-
A
.
C
h
u
n
g
,
H
.
-
C
.
C
h
o
u
,
a
n
d
C
.
-
W
.
Li
n
,
“
S
o
u
n
d
l
o
c
a
l
i
z
a
t
i
o
n
b
a
s
e
d
o
n
a
c
o
u
st
i
c
so
u
r
c
e
u
s
i
n
g
mu
l
t
i
p
l
e
mi
c
r
o
p
h
o
n
e
a
r
r
a
y
i
n
a
n
i
n
d
o
o
r
e
n
v
i
r
o
n
me
n
t
,
”
El
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
1
,
n
o
.
6
,
p
.
8
9
0
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
1
0
6
0
8
9
0
.
[
2
1
]
M
.
Y
a
n
g
,
X
.
Z
h
u
,
Y
.
Z
h
a
n
g
,
N
.
T
a
,
a
n
d
Z.
R
a
o
,
“
Est
i
m
a
t
i
o
n
o
f
so
u
n
d
s
o
u
r
c
e
d
i
r
e
c
t
i
o
n
s
u
s
i
n
g
a
b
i
o
l
o
g
i
c
a
l
c
o
u
p
l
e
d
se
n
s
o
r
a
r
r
a
y
w
i
t
h
a
mu
l
t
i
st
a
g
e
i
t
e
r
a
t
i
o
n
m
e
t
h
o
d
,
”
A
p
p
l
i
e
d
Ac
o
u
st
i
c
s
,
v
o
l
.
1
7
7
,
p
.
1
0
7
9
6
0
,
Ju
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
p
a
c
o
u
s
t
.
2
0
2
1
.
1
0
7
9
6
0
.
[
2
2
]
I
.
A
n
,
Y
.
K
w
o
n
,
a
n
d
S
.
Y
o
o
n
,
“
D
i
f
f
r
a
c
t
i
o
n
-
a
n
d
r
e
f
l
e
c
t
i
o
n
-
a
w
a
r
e
m
u
l
t
i
p
l
e
so
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
Ro
b
o
t
i
c
s
,
v
o
l
.
3
8
,
n
o
.
3
,
p
p
.
1
9
2
5
–
1
9
4
4
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
T
R
O
.
2
0
2
1
.
3
1
1
8
9
6
6
.
[
2
3
]
H
.
S
o
n
g
a
n
d
J.
W
.
S
h
i
n
,
“
M
u
l
t
i
p
l
e
so
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
b
a
se
d
o
n
i
n
t
e
r
c
h
a
n
n
e
l
p
h
a
se
d
i
f
f
e
r
e
n
c
e
s
i
n
a
l
l
f
r
e
q
u
e
n
c
i
e
s
w
i
t
h
sp
e
c
t
r
a
l
m
a
sk
s
,
”
i
n
I
n
t
e
rs
p
e
e
c
h
2
0
2
1
,
A
u
g
.
2
0
2
1
,
p
p
.
6
7
1
–
6
7
5
.
d
o
i
:
1
0
.
2
1
4
3
7
/
I
n
t
e
r
s
p
e
e
c
h
.
2
0
2
1
-
1
1
7
8
.
[
2
4
]
L.
Zh
o
u
,
M
.
J
i
a
,
L.
L
i
,
a
n
d
L.
T
a
o
,
“
S
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
b
y
c
o
mb
i
n
i
n
g
p
h
a
s
e
c
o
n
s
i
st
e
n
c
y
a
n
d
a
n
g
l
e
d
e
v
i
a
t
i
o
n
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
2
3
9
t
h
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
C
o
m
p
u
t
i
n
g
a
n
d
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
M
a
r
.
2
0
2
3
,
p
p
.
6
1
9
–
6
2
3
.
d
o
i
:
1
0
.
1
1
4
5
/
3
5
9
4
3
1
5
.
3
5
9
4
3
8
1
.
[
2
5
]
A
.
S
i
e
r
i
e
b
r
i
a
k
o
v
,
O
.
H
o
sp
o
d
a
r
c
h
u
k
,
D
.
La
k
h
t
y
r
,
V
.
S
i
ma
k
h
i
n
,
a
n
d
S
.
B
o
n
d
a
r
,
“
T
e
c
h
n
o
l
o
g
y
o
f
s
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
b
a
se
d
o
n
i
n
c
o
m
i
n
g
s
o
u
n
d
i
n
t
e
n
s
i
t
y
,
”
i
n
2
0
2
3
I
EEE
1
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
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
i
e
s
(
C
S
I
T
)
,
O
c
t
.
2
0
2
3
,
p
p
.
1
–
5
.
d
o
i
:
1
0
.
1
1
0
9
/
C
S
I
T6
1
5
7
6
.
2
0
2
3
.
1
0
3
2
4
2
2
9
.
[
2
6
]
K
.
W
a
n
g
a
n
d
M
.
Z
h
a
n
g
,
“
S
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
s
y
st
e
m
b
a
s
e
d
o
n
TD
O
A
a
l
g
o
r
i
t
h
m,
”
i
n
A
d
v
a
n
c
e
s
i
n
T
ra
n
s
d
i
sci
p
l
i
n
a
r
y
En
g
i
n
e
e
ri
n
g
,
I
O
S
Pre
ss BV
,
2
0
2
4
.
d
o
i
:
1
0
.
3
2
3
3
/
A
TD
E
2
3
1
2
0
7
.
[
2
7
]
M
.
S
e
w
t
z
,
T
.
B
o
d
e
n
mu
l
l
e
r
,
a
n
d
R
.
Tr
i
e
b
e
l
,
“
R
o
b
u
st
M
U
S
I
C
-
b
a
se
d
s
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
i
n
r
e
v
e
r
b
e
r
a
n
t
a
n
d
e
c
h
o
i
c
e
n
v
i
r
o
n
m
e
n
t
s,
”
i
n
2
0
2
0
I
EEE
/
R
S
J
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
Ro
b
o
t
s
a
n
d
S
y
s
t
e
m
s
(
I
RO
S
)
,
O
c
t
.
2
0
2
0
,
p
p
.
2
4
7
4
–
2
4
8
0
.
d
o
i
:
1
0
.
1
1
0
9
/
I
R
O
S
4
5
7
4
3
.
2
0
2
0
.
9
3
4
0
8
2
6
.
[
2
8
]
D
.
G
a
l
a
a
n
d
L
.
S
u
n
,
“
M
o
v
i
n
g
so
u
n
d
so
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
a
n
d
t
r
a
c
k
i
n
g
u
s
i
n
g
a
se
l
f
r
o
t
a
t
i
n
g
b
i
-
mi
c
r
o
p
h
o
n
e
a
r
r
a
y
,
”
i
n
AS
ME
2
0
1
9
D
y
n
a
m
i
c
S
y
s
t
e
m
s
a
n
d
C
o
n
t
r
o
l
C
o
n
f
e
re
n
c
e
,
D
S
C
C
2
0
1
9
,
Am
e
ri
c
a
n
S
o
c
i
e
t
y
o
f
M
e
c
h
a
n
i
c
a
l
E
n
g
i
n
e
e
rs
(
A
S
ME
)
,
2
0
1
9
.
d
o
i
:
1
0
.
1
1
1
5
/
D
S
C
C
2
0
1
9
-
9
0
2
4
.
[
2
9
]
A
.
I
h
l
e
f
e
l
d
,
N
.
A
l
a
ma
t
sa
z
,
a
n
d
R
.
M
.
S
h
a
p
l
e
y
,
“
P
o
p
u
l
a
t
i
o
n
r
a
t
e
-
c
o
d
i
n
g
p
r
e
d
i
c
t
s
c
o
r
r
e
c
t
l
y
t
h
a
t
h
u
m
a
n
s
o
u
n
d
l
o
c
a
l
i
z
a
t
i
o
n
d
e
p
e
n
d
s
o
n
so
u
n
d
i
n
t
e
n
s
i
t
y
,
”
e
L
i
f
e
,
v
o
l
.
8
,
O
c
t
.
2
0
1
9
,
d
o
i
:
1
0
.
7
5
5
4
/
e
Li
f
e
.
4
7
0
2
7
.
[
3
0
]
T.
-
H
.
Ta
n
,
Y
.
-
T
.
Li
n
,
Y
.
-
L.
C
h
a
n
g
,
a
n
d
M
.
A
l
k
h
a
l
e
e
f
a
h
,
“
S
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
u
si
n
g
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
a
n
d
r
e
g
r
e
ss
i
o
n
m
o
d
e
l
,
”
S
e
n
so
rs
,
v
o
l
.
2
1
,
n
o
.
2
3
,
p
.
8
0
3
1
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
1
2
3
8
0
3
1
.
[
3
1
]
X
.
H
u
a
n
g
,
R
.
X
u
,
W
.
Y
u
,
a
n
d
T.
P
e
n
g
,
“
R
e
s
e
a
r
c
h
o
n
st
r
u
c
t
u
r
a
l
s
o
u
n
d
so
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
me
t
h
o
d
b
y
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
EU
RA
S
I
P
J
o
u
rn
a
l
o
n
A
d
v
a
n
c
e
s
i
n
S
i
g
n
a
l
Pr
o
c
e
s
si
n
g
,
v
o
l
.
2
0
2
3
,
n
o
.
1
,
p
.
5
4
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
3
6
3
4
-
0
2
3
-
0
1
0
1
7
-
y.
[
3
2
]
J.
Z
h
o
u
e
t
a
l
.
,
“
N
o
i
se
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
G
e
o
p
h
y
s
i
c
a
l
J
o
u
r
n
a
l
I
n
t
e
r
n
a
t
i
o
n
a
l
,
v
o
l
.
2
3
8
,
n
o
.
1
,
p
p
.
5
1
3
–
5
3
6
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
0
9
3
/
g
j
i
/
g
g
a
e
1
7
1
.
[
3
3
]
S
.
S
a
k
a
v
i
č
i
u
s
a
n
d
A
.
S
e
r
a
c
k
i
s
,
“
Est
i
mat
i
o
n
o
f
A
z
i
m
u
t
h
a
n
d
El
e
v
a
t
i
o
n
f
o
r
mu
l
t
i
p
l
e
a
c
o
u
s
t
i
c
s
o
u
r
c
e
s
u
s
i
n
g
t
e
t
r
a
h
e
d
r
a
l
m
i
c
r
o
p
h
o
n
e
a
r
r
a
y
s
a
n
d
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
El
e
c
t
ro
n
i
c
s
,
v
o
l
.
1
0
,
n
o
.
2
1
,
p
.
2
5
8
5
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s1
0
2
1
2
5
8
5
.
[
3
4
]
S
.
Y
.
L
e
e
,
J.
C
h
a
n
g
,
a
n
d
S
.
Le
e
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
met
h
o
d
f
o
r
m
u
l
t
i
p
l
e
s
o
u
n
d
so
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
w
i
t
h
h
i
g
h
r
e
s
o
l
u
t
i
o
n
a
n
d
a
c
c
u
r
a
c
y
,
”
Me
c
h
a
n
i
c
a
l
S
y
st
e
m
s
a
n
d
S
i
g
n
a
l
Pro
c
e
ss
i
n
g
,
v
o
l
.
1
6
1
,
p
.
1
0
7
9
5
9
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
y
mss
p
.
2
0
2
1
.
1
0
7
9
5
9
.
[
3
5
]
M
.
B
o
z
k
u
r
t
l
a
r
,
B
.
Y
e
n
,
K
.
I
t
o
y
a
ma
,
a
n
d
K
.
N
a
k
a
d
a
i
,
“
R
e
a
l
t
i
me
s
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
u
si
n
g
v
o
n
-
M
i
ses
R
e
sN
e
t
,
”
i
n
2
0
2
4
I
EEE/
S
I
C
E
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
S
y
st
e
m
I
n
t
e
g
r
a
t
i
o
n
(
S
I
I
)
,
Ja
n
.
2
0
2
4
,
p
p
.
4
6
6
–
4
7
1
.
d
o
i
:
1
0
.
1
1
0
9
/
S
I
I
5
8
9
5
7
.
2
0
2
4
.
1
0
4
1
7
2
2
4
.
[
3
6
]
J.
K
o
,
H
.
K
i
m,
a
n
d
J.
K
i
m
,
“
R
e
a
l
-
t
i
me
so
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
f
o
r
l
o
w
-
p
o
w
e
r
I
o
T
d
e
v
i
c
e
s
b
a
se
d
o
n
M
u
l
t
i
-
S
t
r
e
a
m
C
N
N
,
”
S
e
n
so
rs
,
v
o
l
.
2
2
,
n
o
.
1
2
,
p
.
4
6
5
0
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
2
1
2
4
6
5
0
.
[
3
7
]
C
.
H
u
a
n
g
,
O
.
M
e
e
s,
A
.
Ze
n
g
,
a
n
d
W
.
B
u
r
g
a
r
d
,
“
A
u
d
i
o
v
i
su
a
l
l
a
n
g
u
a
g
e
map
s
f
o
r
r
o
b
o
t
n
a
v
i
g
a
t
i
o
n
,
”
i
n
E
x
p
e
ri
m
e
n
t
a
l
R
o
b
o
t
i
c
s
,
2
0
2
4
,
p
p
.
1
0
5
–
1
1
7
.
[
3
8
]
Y
.
C
a
o
,
Q
.
K
o
n
g
,
T.
I
q
b
a
l
,
F
.
A
n
,
W
.
W
a
n
g
,
a
n
d
M
.
P
l
u
m
b
l
e
y
,
“
P
o
l
y
p
h
o
n
i
c
s
o
u
n
d
e
v
e
n
t
d
e
t
e
c
t
i
o
n
a
n
d
l
o
c
a
l
i
z
a
t
i
o
n
u
si
n
g
a
t
w
o
-
st
a
g
e
st
r
a
t
e
g
y
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
D
e
t
e
c
t
i
o
n
a
n
d
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
A
c
o
u
st
i
c
S
c
e
n
e
s
a
n
d
Ev
e
n
t
s
2
0
1
9
W
o
rks
h
o
p
(
D
C
AS
E2
0
1
9
)
,
2
0
1
9
,
p
p
.
3
0
–
3
4
.
d
o
i
:
1
0
.
3
3
6
8
2
/
4
j
h
y
-
b
j
8
1
.
[
3
9
]
D
.
K
r
a
u
se,
A
.
P
o
l
i
t
i
s,
a
n
d
K
.
K
o
w
a
l
c
z
y
k
,
“
F
e
a
t
u
r
e
o
v
e
r
v
i
e
w
f
o
r
j
o
i
n
t
m
o
d
e
l
i
n
g
o
f
so
u
n
d
e
v
e
n
t
d
e
t
e
c
t
i
o
n
a
n
d
l
o
c
a
l
i
z
a
t
i
o
n
u
s
i
n
g
a
mi
c
r
o
p
h
o
n
e
a
r
r
a
y
,
”
i
n
2
0
2
0
2
8
t
h
E
u
ro
p
e
a
n
S
i
g
n
a
l
Pr
o
c
e
ss
i
n
g
C
o
n
f
e
re
n
c
e
(
EU
S
I
PC
O
)
,
Ja
n
.
2
0
2
1
,
p
p
.
3
1
–
3
5
.
d
o
i
:
1
0
.
2
3
9
1
9
/
Eu
s
i
p
c
o
4
7
9
6
8
.
2
0
2
0
.
9
2
8
7
3
7
4
.
[
4
0
]
Y
.
M
i
n
,
P
.
X
i
n
,
C
.
X
u
,
a
n
d
H
.
Li
u
,
“
D
e
t
e
c
t
i
o
n
a
n
d
l
o
c
a
l
i
z
a
t
i
o
n
o
f
s
o
u
n
d
e
v
e
n
t
s
b
a
se
d
o
n
p
r
i
n
c
i
p
a
l
c
o
m
p
o
n
e
n
t
s
a
n
a
l
y
si
s
,
”
i
n
2
0
2
2
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
n
su
m
e
r
El
e
c
t
ro
n
i
c
s
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
(
I
C
C
EC
E)
,
Ja
n
.
2
0
2
2
,
p
p
.
5
0
7
–
5
1
1
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
EC
E5
4
1
3
9
.
2
0
2
2
.
9
7
1
2
7
1
7
.
[
4
1
]
J.
C
h
e
n
e
t
a
l
.
,
“
M
u
l
t
i
mo
d
a
l
f
u
s
i
o
n
f
o
r
i
n
d
o
o
r
s
o
u
n
d
so
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
,
”
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
1
1
5
,
p
.
1
0
7
9
0
6
,
J
u
l
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
2
1
.
1
0
7
9
0
6
.
[
4
2
]
E.
G
r
i
n
s
t
e
i
n
,
V
.
W
.
N
e
o
,
a
n
d
P
.
A
.
N
a
y
l
o
r
,
“
D
u
a
l
i
n
p
u
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
p
o
si
t
i
o
n
a
l
s
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
,
”
EU
R
AS
I
P
J
o
u
rn
a
l
o
n
A
u
d
i
o
,
S
p
e
e
c
h
,
a
n
d
Mu
s
i
c
Pro
c
e
ssi
n
g
,
v
o
l
.
2
0
2
3
,
n
o
.
1
,
p
.
3
2
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
3
6
3
6
-
0
2
3
-
0
0
3
0
1
-
x.
[
4
3
]
G
.
Zh
a
n
g
,
L.
G
e
n
g
,
a
n
d
X
.
C
h
e
n
,
“
S
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
m
e
t
h
o
d
b
a
s
e
d
o
n
D
e
n
s
e
l
y
c
o
n
n
e
c
t
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
,
”
i
n
2
0
2
2
5
t
h
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
I
n
f
o
rm
a
t
i
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
(
I
C
I
C
S
P)
,
N
o
v
.
2
0
2
2
,
p
p
.
7
4
3
–
7
4
7
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
S
P
5
5
5
3
9
.
2
0
2
2
.
1
0
0
5
0
6
8
2
.
[
4
4
]
G
.
Z
h
o
u
,
H
.
Li
a
n
g
,
X
.
D
i
n
g
,
Y
.
H
u
a
n
g
,
X
.
T
u
,
a
n
d
S
.
A
b
b
a
s,
“
A
c
o
u
s
t
i
c
-
N
e
t
:
A
n
o
v
e
l
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
so
u
n
d
l
o
c
a
l
i
z
a
t
i
o
n
a
n
d
q
u
a
n
t
i
f
i
c
a
t
i
o
n
,
”
ArX
i
v
:
2
2
0
3
.
1
6
9
8
8
,
2
0
2
1
.
[
4
5
]
S
.
Ja
d
d
o
a
,
R
.
A
l
i
,
M
.
N
a
j
m
A
b
d
u
l
l
a
h
,
a
n
d
B
.
F
.
A
b
e
d
,
“
L
o
c
a
l
i
z
a
t
i
o
n
o
f
sp
e
a
k
e
r
u
si
n
g
f
u
si
o
n
t
e
c
h
n
i
q
u
e
s
a
n
d
n
e
u
r
a
l
n
e
t
w
o
r
k
a
l
g
o
r
i
t
h
ms,
”
W
a
s
i
t
J
o
u
r
n
a
l
f
o
r
P
u
re
s
c
i
e
n
c
e
s
,
v
o
l
.
3
,
n
o
.
2
,
p
p
.
1
7
2
–
1
8
4
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
3
1
1
8
5
/
w
j
p
s.
3
9
9
.
[
4
6
]
J.
W
a
n
g
,
X
.
Q
i
a
n
,
Z.
P
a
n
,
M
.
Z
h
a
n
g
,
a
n
d
H
.
Li
,
“
G
C
C
-
P
H
A
T
w
i
t
h
sp
e
e
c
h
-
o
r
i
e
n
t
e
d
a
t
t
e
n
t
i
o
n
f
o
r
r
o
b
o
t
i
c
s
o
u
n
d
s
o
u
r
c
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
:
257
-
2
6
6
266
l
o
c
a
l
i
z
a
t
i
o
n
,
”
i
n
2
0
2
1
I
EE
E
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Ro
b
o
t
i
c
s
a
n
d
Au
t
o
m
a
t
i
o
n
(
I
C
RA)
,
M
a
y
2
0
2
1
,
p
p
.
5
8
7
6
–
5
8
8
3
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
R
A
4
8
5
0
6
.
2
0
2
1
.
9
5
6
1
8
8
5
.
[
4
7
]
R
.
Ta
n
g
,
Y
.
Z
h
a
n
g
,
T.
L
u
,
a
n
d
M
.
H
e
,
“
S
o
u
n
d
so
u
r
c
e
l
o
c
a
t
i
o
n
p
r
e
d
i
c
t
i
o
n
me
t
h
o
d
b
a
s
e
d
o
n
b
r
o
a
d
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
3
1
1
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
:
I
o
T
a
n
d
S
m
a
rt
C
i
t
y
(
I
T
I
o
T
S
C
)
,
A
u
g
.
2
0
2
3
,
p
p
.
1
3
5
–
1
3
8
.
d
o
i
:
1
0
.
1
1
0
9
/
I
TI
o
TSC6
0
3
7
9
.
2
0
2
3
.
0
0
0
3
0
.
[
4
8
]
G
.
Li
,
W
.
X
u
e
,
W
.
Li
u
,
J.
Y
i
,
a
n
d
J.
T
a
o
,
“
G
C
C
-
S
p
e
a
k
e
r
:
t
a
r
g
e
t
s
p
e
a
k
e
r
l
o
c
a
l
i
z
a
t
i
o
n
w
i
t
h
o
p
t
i
m
a
l
sp
e
a
k
e
r
-
d
e
p
e
n
d
e
n
t
w
e
i
g
h
t
i
n
g
i
n
mu
l
t
i
-
s
p
e
a
k
e
r
sc
e
n
a
r
i
o
s,”
i
n
I
C
AS
S
P
2
0
2
3
-
2
0
2
3
I
E
EE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ac
o
u
st
i
c
s,
S
p
e
e
c
h
a
n
d
S
i
g
n
a
l
Pro
c
e
ss
i
n
g
(
I
C
AS
S
P)
,
Ju
n
.
2
0
2
3
,
p
p
.
1
–
5
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
S
S
P
4
9
3
5
7
.
2
0
2
3
.
1
0
0
9
5
5
5
1
.
[
4
9
]
S
.
Li
u
,
H
.
Li
,
Q
.
Y
u
,
Y
.
Zh
a
o
,
a
n
d
W
.
Zh
a
n
g
,
“
R
e
se
a
r
c
h
o
n
s
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
o
f
m
u
l
t
i
p
l
e
f
i
x
e
d
t
a
r
g
e
t
s
b
a
se
d
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
i
st
r
i
b
u
t
e
d
a
r
r
a
y
s,
”
J
o
u
r
n
a
l
o
f
Ph
y
si
c
s:
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s
,
v
o
l
.
2
7
1
8
,
n
o
.
1
,
p
.
0
1
2
0
6
9
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
2
7
1
8
/
1
/
0
1
2
0
6
9
.
[
5
0
]
Y
.
Zh
a
n
g
,
Z.
Ze
n
g
,
a
n
d
D
.
T
a
n
g
,
“
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
a
n
d
K
a
l
ma
n
f
i
l
t
e
r
i
n
g
i
n
so
u
n
d
so
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
,
”
i
n
2
0
2
1
I
EEE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
s i
n
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s
(
AEE
C
A)
,
A
u
g
.
2
0
2
1
,
p
p
.
5
–
8
.
d
o
i
:
1
0
.
1
1
0
9
/
A
EEC
A
5
2
5
1
9
.
2
0
2
1
.
9
5
7
4
1
9
3
.
[
5
1
]
J.
D
a
v
i
l
a
-
C
h
a
c
o
n
,
J.
L
i
u
,
a
n
d
S
.
W
e
r
mt
e
r
,
“
En
h
a
n
c
e
d
r
o
b
o
t
sp
e
e
c
h
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
b
i
o
mi
m
e
t
i
c
b
i
n
a
u
r
a
l
s
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
N
e
u
r
a
l
N
e
t
w
o
rk
s
a
n
d
L
e
a
r
n
i
n
g
S
y
st
e
m
s
,
v
o
l
.
3
0
,
n
o
.
1
,
p
p
.
1
3
8
–
1
5
0
,
Ja
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
N
LS.
2
0
1
8
.
2
8
3
0
1
1
9
.
[
5
2
]
M
.
G
o
t
o
e
t
a
l
.
,
“
U
t
i
l
i
z
i
n
g
Li
D
A
R
d
a
t
a
f
o
r
3
D
s
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
,
”
i
n
AC
M
S
I
G
G
RAPH
2
0
2
3
Po
s
t
e
rs
,
Ju
l
.
2
0
2
3
,
p
p
.
1
–
2
.
d
o
i
:
1
0
.
1
1
4
5
/
3
5
8
8
0
2
8
.
3
6
0
3
6
8
2
.
[
5
3
]
F
.
H
u
,
X
.
S
o
n
g
,
R
.
H
e
,
a
n
d
Y
.
Y
u
,
“
S
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
b
a
se
d
o
n
r
e
si
d
u
a
l
n
e
t
w
o
r
k
a
n
d
c
h
a
n
n
e
l
a
t
t
e
n
t
i
o
n
m
o
d
u
l
e
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
5
4
4
3
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
0
2
3
-
3
2
6
5
7
-
7.
[
5
4
]
H
.
F
e
n
g
,
H
.
Zh
a
n
g
,
Z.
S
h
e
n
,
Z
.
Q
i
u
,
X
.
Zh
a
n
g
,
a
n
d
Z
.
T
a
o
,
“
A
st
u
d
y
o
f
s
o
u
n
d
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
b
a
s
e
d
o
n
i
m
p
r
o
v
e
d
t
i
me
d
e
l
a
y
f
e
a
t
u
r
e
s
a
n
d
t
h
e
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
,
”
i
n
2
0
2
4
2
0
t
h
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
N
a
t
u
r
a
l
C
o
m
p
u
t
a
t
i
o
n
,
F
u
zz
y
S
y
st
e
m
s
a
n
d
K
n
o
w
l
e
d
g
e
D
i
sc
o
v
e
ry
(
I
C
N
C
-
F
S
K
D
)
,
J
u
l
.
2
0
2
4
,
p
p
.
1
–
9
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
N
C
-
F
S
K
D
6
4
0
8
0
.
2
0
2
4
.
1
0
7
0
2
3
0
2
.
[
5
5
]
E.
-
B
.
B
u
l
u
t
,
G
.
M
a
n
t
h
e
i
,
I
.
S
i
r
b
u
,
a
n
d
M
.
G
u
c
k
e
r
t
,
“
R
e
s
e
a
r
c
h
o
f
a
c
o
u
s
t
i
c
e
m
i
ssi
o
n
c
h
a
r
a
c
t
e
r
i
st
i
c
s
a
n
d
a
p
p
l
i
c
a
b
i
l
i
t
y
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
f
o
r
s
o
u
r
c
e
l
o
c
a
l
i
z
a
t
i
o
n
,
”
e
-
J
o
u
rn
a
l
o
f
N
o
n
d
e
s
t
ru
c
t
i
v
e
T
e
s
t
i
n
g
,
v
o
l
.
2
9
,
n
o
.
1
0
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
5
8
2
8
6
/
3
0
2
4
3
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Mu
h
a
m
m
a
d
Ak
m
a
l
Aliff
is
a
re
se
a
rc
h
e
r
c
u
rre
n
tl
y
wo
r
k
in
g
w
it
h
T
M
Re
se
a
rc
h
a
n
d
De
v
e
l
o
p
m
e
n
t,
M
a
lay
sia
.
He
h
o
ld
s
a
M
a
ste
r
o
f
En
g
in
e
e
rin
g
(M
En
g
)
i
n
e
lec
tro
n
ics
a
n
d
c
o
m
m
u
n
ica
ti
o
n
e
n
g
in
e
e
rin
g
fr
o
m
th
e
Un
i
v
e
rsity
o
f
No
tt
in
g
h
a
m
,
Un
it
e
d
Ki
n
g
d
o
m
.
Wi
th
a
stro
n
g
f
o
u
n
d
a
ti
o
n
in
c
u
tt
in
g
-
e
d
g
e
tec
h
n
o
lo
g
ies
,
Ak
m
a
l'
s
p
r
o
fe
ss
io
n
a
l
a
n
d
re
se
a
rc
h
in
tere
sts
fo
c
u
s
o
n
I
n
tern
e
t
o
f
T
h
in
g
s
(
Io
T
)
,
ro
b
o
ti
c
s,
a
n
d
se
n
sin
g
tec
h
n
o
lo
g
i
e
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
a
k
m
a
laliff@t
m
rn
d
.
c
o
m
.
m
y
.
Em
e
r
so
n
J
o
se
p
h
R
a
ja
is
c
u
rre
n
tl
y
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
i
n
th
e
F
a
c
u
lt
y
o
f
En
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
a
t
M
u
lt
ime
d
ia
Un
i
v
e
rsity
(
M
M
U
),
M
a
lay
sia
.
His
tec
h
n
ica
l
e
x
p
e
rti
se
c
e
n
ters
a
ro
u
n
d
a
p
p
l
y
in
g
a
rti
ficia
l
i
n
telli
g
e
n
c
e
tec
h
n
i
q
u
e
s
to
m
o
n
it
o
r
th
e
h
e
a
lt
h
o
f
m
a
c
h
in
e
s
a
n
d
e
n
h
a
n
c
in
g
a
c
c
u
ra
c
y
in
ro
b
o
ti
c
s.
He
h
a
s
p
u
b
l
ish
e
d
se
v
e
ra
l
c
o
n
fe
re
n
c
e
a
n
d
jo
u
r
n
a
l
p
a
p
e
rs
in
h
is
a
re
a
o
f
re
se
a
rc
h
.
He
is
a
se
n
io
r
m
e
m
b
e
r
o
f
I
EE
E.
He
wa
s
h
o
n
o
re
d
wit
h
th
e
n
o
tab
le
c
o
m
m
e
n
d
a
ti
o
n
a
wa
rd
b
y
h
is
a
lma
m
a
ter,
S
RM
Un
i
v
e
rsity
,
In
d
ia.
He
wa
s
a
lso
h
o
n
o
re
d
with
th
e
b
e
st
e
x
e
c
u
ti
v
e
a
wa
rd
a
n
d
g
ro
u
p
CEO
m
e
rit
a
wa
rd
fo
r
th
e
y
e
a
r
2
0
1
4
fr
o
m
TM
,
t
h
e
lea
d
in
g
i
n
teg
ra
ted
tele
c
o
m
m
u
n
ica
ti
o
n
c
o
m
p
a
n
y
i
n
M
a
lay
sia
.
His
p
r
o
fil
e
c
a
n
b
e
fo
u
n
d
a
t
h
tt
p
s://
m
m
u
e
x
p
e
rt
.
m
m
u
.
e
d
u
.
m
y
/em
e
rso
n
ra
ja
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
e
rso
n
.
ra
ja@
m
m
u
.
e
d
u
.
m
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.