I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
9
,
No
.
2
,
A
u
g
u
s
t
2
0
2
5
,
p
p
.
9
0
6
~
9
1
3
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
3
9
.i
2
.
pp
906
-
9
1
3
906
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Enha
ncing
aco
ustic enviro
nment
cl
a
ss
ificatio
n f
o
r he
a
ring
-
impa
ired indivi
d
ua
ls usin
g
hybrid
CNN and
RFE
Su
nil
k
um
a
r
M
.
H
a
t
t
a
ra
k
i
1
,
Sh
a
nk
a
ra
y
y
a
G
.
K
a
m
ba
li
m
a
t
h
2
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
B
.
L
.
D
.
E.
A
’
s
V
.
P
.
D
r
.
P
.
G
.
H
a
l
a
k
a
t
t
i
,
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
V
i
sv
e
sv
e
r
a
y
a
Te
c
h
n
o
l
o
g
i
c
a
l
U
n
i
v
e
r
si
t
y
,
B
e
l
a
g
a
v
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
B
a
s
a
v
e
sh
w
a
r
En
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
V
i
s
v
e
s
v
e
r
a
y
a
Te
c
h
n
o
l
o
g
i
c
a
l
U
n
i
v
e
r
si
t
y
,
B
a
g
a
l
k
o
t
e
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
19
,
2
0
2
4
R
ev
is
ed
Ap
r
16
,
2
0
2
5
Acc
ep
ted
J
u
l
2
,
2
0
2
5
In
d
i
v
id
u
a
ls
wh
o
a
re
d
e
a
f
o
r
h
a
rd
o
f
h
e
a
ri
n
g
e
x
p
e
rien
c
e
c
o
n
sid
e
ra
b
le
d
iffi
c
u
lt
ies
in
d
isti
n
g
u
ish
in
g
so
u
n
d
s
in
v
a
ri
o
u
s
a
c
o
u
stic
e
n
v
ir
o
n
m
e
n
ts,
wh
ic
h
a
ffe
c
ts
th
e
ir
c
o
m
m
u
n
ica
ti
o
n
a
b
i
li
ty
a
n
d
o
v
e
ra
ll
q
u
a
li
t
y
o
f
li
fe
.
Ex
isti
n
g
a
u
d
it
o
ry
a
ss
isti
v
e
tec
h
n
o
lo
g
ies
c
u
rr
e
n
tl
y
fa
c
e
c
h
a
ll
e
n
g
e
s
wit
h
re
a
l
-
ti
m
e
c
las
sifica
ti
o
n
a
n
d
a
d
a
p
tati
o
n
t
o
c
h
a
n
g
i
n
g
n
o
ise
c
o
n
d
it
i
o
n
s,
u
n
d
e
rsc
o
rin
g
t
h
e
n
e
e
d
f
o
r
m
o
re
re
li
a
b
le
a
n
d
a
c
c
u
ra
te
c
las
sifica
ti
o
n
m
o
d
e
ls.
T
h
i
s
re
se
a
rc
h
b
rid
g
e
s
th
e
e
x
isti
n
g
g
a
p
b
y
c
re
a
ti
n
g
a
h
y
b
ri
d
c
las
sifica
ti
o
n
fra
m
e
wo
r
k
t
h
a
t
in
teg
ra
tes
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
s (CNN
)
a
n
d
ra
n
d
o
m
fo
re
st
e
n
se
m
b
le
(RF
E)
to
e
n
h
a
n
c
e
th
e
a
c
c
u
ra
c
y
o
f
e
n
v
ir
o
n
m
e
n
tal
s
o
u
n
d
c
las
sifica
ti
o
n
.
T
h
e
stu
d
y
u
ti
li
z
e
s
M
e
l
-
fre
q
u
e
n
c
y
c
e
p
stra
l
c
o
e
fficie
n
t
s
(
M
F
CCs
)
f
o
r
fe
a
tu
r
e
e
x
trac
ti
o
n
a
n
d
p
ri
n
c
ip
a
l
c
o
m
p
o
n
e
n
t
a
n
a
l
y
sis
(P
CA)
fo
r
d
im
e
n
sio
n
a
li
t
y
re
d
u
c
ti
o
n
,
t
h
u
s
fa
c
il
it
a
ti
n
g
th
e
e
ff
icie
n
t
p
ro
c
e
ss
in
g
o
f
re
a
l
-
wo
rld
a
u
d
i
o
d
a
ta.
Th
e
p
r
o
p
o
se
d
m
e
th
o
d
o
lo
g
y
imp
r
o
v
e
s
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
a
c
ro
ss
v
a
rio
u
s
e
n
v
iro
n
m
e
n
tal
c
o
n
d
i
ti
o
n
s.
E
x
p
e
r
ime
n
tal
e
v
a
lu
a
ti
o
n
s
d
e
m
o
n
stra
te
su
p
e
rio
r
p
e
rfo
rm
a
n
c
e
,
a
c
h
iev
in
g
a
train
i
n
g
a
c
c
u
ra
c
y
o
f
9
4
.
9
3
%
a
n
d
a
tes
ti
n
g
a
c
c
u
ra
c
y
o
f
9
3
.
4
1
%
,
th
e
re
b
y
e
x
c
e
e
d
in
g
c
o
n
v
e
n
ti
o
n
a
l
m
a
c
h
i
n
e
lea
rn
i
n
g
m
e
th
o
d
s.
By
o
v
e
rc
o
m
in
g
li
m
it
a
ti
o
n
s
i
n
e
x
isti
n
g
m
o
d
e
ls,
th
is
re
se
a
rc
h
c
o
n
tri
b
u
tes
to
t
h
e
d
e
v
e
lo
p
m
e
n
t
o
f
a
d
a
p
ti
v
e
h
e
a
rin
g
a
ss
istan
c
e
sy
ste
m
s
with
e
n
h
a
n
c
e
d
n
o
is
e
c
las
sifica
ti
o
n
c
a
p
a
b
il
it
ies
.
T
h
e
re
su
lt
s
h
a
v
e
sig
n
ifi
c
a
n
t
im
p
li
c
a
ti
o
n
s
fo
r
t
h
e
d
e
v
e
lo
p
m
e
n
t
o
f
sm
a
rt
h
e
a
rin
g
a
id
s,
re
a
l
-
ti
m
e
n
o
ise
c
las
sifica
ti
o
n
,
a
n
d
a
u
d
it
o
ry
sc
e
n
e
a
n
a
ly
sis.
Ulti
m
a
tely
,
th
is
re
se
a
rc
h
e
n
h
a
n
c
e
s
a
ss
isti
v
e
h
e
a
rin
g
tec
h
n
o
l
o
g
ies
,
p
r
o
m
o
ti
n
g
g
re
a
ter
a
c
c
e
ss
ib
il
it
y
,
c
o
m
m
u
n
ica
ti
o
n
,
a
n
d
in
c
lu
sio
n
fo
r
h
e
a
rin
g
-
imp
a
ired
in
d
iv
id
u
a
ls,
th
u
s c
o
n
tri
b
u
t
in
g
p
o
siti
v
e
ly
t
o
so
c
iety
.
K
ey
w
o
r
d
s
:
Aco
u
s
tic
en
v
ir
o
n
m
en
t
class
if
icatio
n
C
NN
E
n
s
em
b
le
lear
n
in
g
Hea
r
in
g
aid
s
PC
A
R
an
d
o
m
f
o
r
est
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
:
Su
n
ilk
u
m
ar
M.
Hattar
a
k
i
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
i
n
g
,
B
.
L
.
D.
E
.
A
’
s
V.
P.Dr
.
P.
G.
Hala
k
atti
C
o
lleg
e
o
f
E
n
g
i
n
ee
r
in
g
an
d
T
ec
h
n
o
lo
g
y
,
Vis
v
esv
er
ay
a
T
ec
h
n
o
lo
g
ical
U
n
iv
er
s
ity
B
elag
av
i
-
5
9
0
0
1
8
,
Kar
n
atak
a,
I
n
d
ia
E
m
ail: su
n
ilm
h
0
3
9
@
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
t
ca
n
b
e
v
er
y
d
if
f
icu
lt
f
o
r
p
eo
p
le
with
h
ea
r
i
n
g
im
p
air
m
en
ts
to
ad
j
u
s
t
to
a
v
ar
iety
o
f
ac
o
u
s
tic
en
v
ir
o
n
m
en
ts
,
in
clu
d
in
g
q
u
iet
p
lace
s
,
b
u
s
y
r
estau
r
an
ts
,
an
d
n
o
is
y
s
tr
ee
ts
.
B
ec
au
s
e
tr
ad
it
io
n
al
h
ea
r
in
g
aid
s
ca
n
n
o
t
ac
cu
r
ately
class
if
y
am
b
ien
t
n
o
is
e,
th
ey
f
r
eq
u
en
tly
d
o
n
o
t
o
f
f
er
th
e
b
est
s
u
p
p
o
r
t
u
n
d
er
a
v
ar
iety
o
f
cir
cu
m
s
tan
ce
s
.
B
ec
au
s
e
o
f
th
i
s
,
u
s
er
s
f
in
d
it
d
if
f
icu
lt
to
d
is
ce
r
n
s
p
ee
ch
f
r
o
m
b
ac
k
g
r
o
u
n
d
n
o
is
e,
wh
ich
im
p
air
s
co
m
m
u
n
icatio
n
ef
f
ec
tiv
en
ess
an
d
in
c
r
ea
s
es
co
g
n
itiv
e
lo
ad
.
I
n
o
r
d
er
to
o
v
e
r
co
m
e
th
is
r
es
tr
ictio
n
,
in
tellig
en
t
h
ea
r
in
g
aid
s
th
at
ca
n
d
y
n
am
ic
ally
ad
ju
s
t to
s
h
if
tin
g
au
d
ito
r
y
co
n
d
it
io
n
s
m
u
s
t b
e
d
ev
el
o
p
ed
[
1
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
n
h
a
n
ci
n
g
a
c
o
u
s
tic
en
viro
n
m
en
t c
la
s
s
ifica
tio
n
fo
r
h
ea
r
in
g
-
i
mp
a
ir
ed
…
(
S
u
n
ilku
ma
r
M.
Ha
tta
r
a
ki
)
907
−
Desp
ite
ad
v
an
ce
m
en
ts
in
th
e
class
if
icatio
n
o
f
ac
o
u
s
tic
en
v
ir
o
n
m
en
ts
,
c
u
r
r
e
n
t
m
o
d
els
h
av
e
a
n
u
m
b
er
o
f
d
r
awb
ac
k
s
.
Firstl
y
,
t
h
ey
lac
k
r
ea
l
-
tim
e
ad
ap
ta
b
ilit
y
,
as
th
e
m
ajo
r
ity
o
f
ea
r
lier
m
o
d
els
d
o
n
o
t
in
co
r
p
o
r
ate
ad
ap
tiv
e
lear
n
in
g
tech
n
iq
u
es t
o
d
y
n
a
m
ically
alter
class
if
icati
o
n
o
u
t
p
u
ts
[
2
]
.
−
L
im
itatio
n
s
o
f
f
ea
tu
r
e
ex
tr
ac
ti
o
n
:
tr
ad
itio
n
al
m
eth
o
d
s
m
o
s
tly
u
s
e
m
a
n
u
ally
cr
ea
ted
f
ea
tu
r
es,
wh
ich
m
ig
h
t
n
o
t b
e
a
b
le
to
ad
e
q
u
ately
ca
p
t
u
r
e
in
tr
icate
ac
o
u
s
tic
p
atter
n
s
[
3
]
.
−
L
im
ited
m
o
d
el
g
e
n
er
aliza
tio
n
:
s
in
ce
m
an
y
s
tu
d
ies
o
n
ly
co
n
s
id
er
a
s
m
all
n
u
m
b
e
r
o
f
en
v
ir
o
n
m
e
n
ts
,
th
e
m
o
d
els
’
ap
p
licab
ilit
y
in
ac
tu
al
s
itu
atio
n
s
is
d
im
in
is
h
ed
.
T
h
is
s
tu
d
y
p
r
esen
ts
a
h
y
b
r
id
c
lass
if
icatio
n
m
o
d
el
th
at
co
m
b
i
n
es
r
an
d
o
m
f
o
r
est
e
n
s
em
b
le
(
R
FE
)
an
d
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
etwo
r
k
s
(
C
NNs
)
to
ad
d
r
ess
th
ese
i
s
s
u
es.
M
e
l
-
fre
q
u
e
n
c
y
c
e
p
stra
l
c
o
e
fficie
n
ts
(
MFC
C
s
)
ar
e
u
s
ed
b
y
th
e
C
NN
co
m
p
o
n
en
t
to
ex
tr
ac
t
r
o
b
u
s
t
f
ea
tu
r
es,
an
d
th
e
R
FE
u
s
e
s
f
ea
tu
r
e
s
elec
tio
n
an
d
d
ec
is
io
n
tr
ee
-
b
ased
class
if
icatio
n
to
im
p
r
o
v
e
p
r
ed
ictiv
e
ac
c
u
r
ac
y
.
Th
e
g
o
al
o
f
th
is
r
esear
ch
is
to
cr
ea
te
a
s
tab
le
an
d
ef
f
ec
tiv
e
s
y
s
tem
f
o
r
ca
teg
o
r
izin
g
v
ar
io
u
s
ac
o
u
s
tic
en
v
ir
o
n
m
en
ts
.
T
h
e
s
u
g
g
ested
h
y
b
r
id
m
o
d
el
p
r
o
v
id
es
a
r
elia
b
le
an
s
wer
b
y
co
m
b
in
in
g
th
e
p
r
ed
ictiv
e
ab
ilit
y
o
f
an
R
FE
with
th
e
ab
ilit
y
to
ex
tr
ac
t
f
ea
tu
r
es
u
s
in
g
C
NN.
T
h
is
m
o
d
el
ca
n
d
y
n
a
m
ically
ad
ju
s
t
to
v
ar
io
u
s
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
,
im
p
r
o
v
in
g
s
p
ee
ch
i
n
tellig
ib
ilit
y
in
d
if
f
ic
u
lt
ac
o
u
s
tic
en
v
ir
o
n
m
en
ts
an
d
th
u
s
th
e
lis
ten
in
g
ex
p
er
ien
ce
f
o
r
t
h
o
s
e
wh
o
ar
e
h
a
r
d
o
f
h
ea
r
i
n
g
[
4
]
.
T
h
is
s
tu
d
y
af
f
ec
ts
r
ea
l
-
tim
e
h
ea
r
in
g
aid
s
b
y
allo
win
g
f
o
r
a
u
to
m
atic
en
v
ir
o
n
m
en
tal
ad
ap
t
atio
n
.
T
h
e
r
esear
ch
h
elp
s
cr
ea
te
in
tellig
en
t
h
ea
r
in
g
aid
s
th
at
ca
n
ad
ju
s
t
s
o
u
n
d
o
u
tp
u
t
ac
co
r
d
in
g
to
am
b
ien
t
n
o
is
e,
f
ac
ilit
atin
g
m
o
r
e
ef
f
ec
tiv
e
c
o
m
m
u
n
icatio
n
b
y
in
c
r
ea
s
in
g
t
h
e
p
r
ec
is
io
n
an
d
d
ep
en
d
ab
ili
ty
o
f
en
v
ir
o
n
m
en
t
class
if
icatio
n
.
B
y
m
ak
in
g
au
d
ito
r
y
s
y
s
tem
s
m
o
r
e
r
esp
o
n
s
iv
e
an
d
u
s
er
-
ce
n
ter
ed
,
th
is
wo
r
k
m
ay
less
en
th
e
co
g
n
itiv
e
s
tr
ain
th
at
p
eo
p
le
e
x
p
er
ien
ce
wh
en
s
witch
in
g
b
etw
ee
n
en
v
ir
o
n
m
en
ts
[
5
]
.
T
h
e
r
est
o
f
t
h
is
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
ws:
s
ec
tio
n
2
o
f
f
er
s
a
th
o
r
o
u
g
h
a
n
aly
s
is
o
f
cu
r
r
en
t
m
eth
o
d
s
f
o
r
class
if
y
in
g
en
v
i
r
o
n
m
en
tal
s
o
u
n
d
s
.
T
h
e
s
u
g
g
e
s
ted
m
eth
o
d
o
lo
g
y
,
i
n
clu
d
in
g
f
ea
tu
r
e
ex
tr
ac
tio
n
,
m
o
d
el
d
esig
n
,
a
n
d
d
ataset
p
r
e
p
ar
atio
n
,
is
d
escr
ib
ed
in
s
ec
tio
n
3
.
E
x
p
er
im
en
tal
r
esu
lts
ar
e
s
h
o
wn
i
n
s
ec
tio
n
4
,
wh
ich
co
n
tr
asts
th
e
h
y
b
r
id
C
NN
-
R
FE
m
o
d
el
with
cu
ttin
g
-
ed
g
e
m
eth
o
d
s
.
I
n
co
n
tr
ast,
s
ec
tio
n
5
wr
ap
s
u
p
th
e
s
tu
d
y
an
d
s
u
g
g
ests
ar
ea
s
f
o
r
f
u
r
th
er
r
esear
c
h
.
2.
L
I
T
E
R
AT
U
RE
SU
RVE
Y
Z
ah
ee
r
et
a
l.
[
6
]
p
r
o
v
id
ed
a
co
m
p
r
e
h
en
s
iv
e
r
e
v
iew
o
f
ar
tific
ial
in
tellig
en
ce
(
AI
)
-
b
ase
d
ac
o
u
s
tic
s
o
u
r
ce
id
e
n
tific
atio
n
(
ASI
)
te
ch
n
iq
u
es.
I
n
th
eir
an
aly
s
is
,
t
h
ey
e
x
am
in
ed
th
e
s
tr
en
g
th
s
an
d
wea
k
n
ess
es
o
f
v
ar
io
u
s
AI
-
d
r
iv
en
ASI
p
r
o
ce
s
s
es a
n
d
th
e
m
eth
o
d
s
p
r
o
p
o
s
ed
b
y
r
esear
ch
er
s
in
t
h
e
liter
atu
r
e
.
Ad
d
itio
n
ally
,
th
e
y
co
n
d
u
cte
d
an
in
-
d
ep
t
h
s
u
r
v
e
y
o
f
ASI
a
p
p
licatio
n
s
ac
r
o
s
s
d
iv
er
s
e
f
ield
s
,
in
clu
d
in
g
m
a
ch
in
er
y
,
u
n
d
e
r
wate
r
ac
o
u
s
tics
,
en
v
ir
o
n
m
en
tal/ev
e
n
t
s
o
u
r
ce
r
ec
o
g
n
itio
n
,
h
ea
lth
ca
r
e,
an
d
m
o
r
e.
T
h
e
r
ev
ie
w
also
h
ig
h
lig
h
ts
s
ig
n
if
ican
t r
esear
ch
d
ir
ec
tio
n
s
f
o
r
f
u
tu
r
e
e
x
p
lo
r
atio
n
in
th
is
a
r
ea
.
Ab
ay
o
m
i
-
Alli
et
a
l.
[
7
]
im
p
lem
en
ted
s
cr
ee
n
in
g
ex
cl
u
s
io
n
cr
iter
ia
an
d
s
n
o
wb
allin
g
t
ec
h
n
iq
u
es,
r
esu
ltin
g
in
th
e
s
elec
tio
n
o
f
5
6
ar
ticles.
T
h
ey
id
en
tifie
d
s
ev
er
al
s
h
o
r
tco
m
in
g
s
in
p
r
io
r
r
esear
ch
,
s
u
ch
as
in
s
u
f
f
icien
t,
wea
k
ly
lab
eled
,
im
b
alan
ce
d
,
a
n
d
n
o
is
y
d
a
tasets
,
as
we
ll
as
in
ad
eq
u
ate
s
o
u
n
d
f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
an
d
i
n
ef
f
ec
tiv
e
au
g
m
e
n
tatio
n
s
tr
ateg
ies
th
a
t
h
in
d
e
r
class
if
ier
p
er
f
o
r
m
a
n
c
e.
So
u
n
d
d
atasets
,
f
ea
tu
r
e
e
x
tr
ac
tio
n
tech
n
iq
u
es,
d
ata
au
g
m
en
tatio
n
tech
n
iq
u
es,
an
d
th
eir
ap
p
licatio
n
s
i
n
s
o
u
n
d
class
if
icatio
n
ar
e
al
l
b
r
ief
ly
d
is
cu
s
s
ed
in
th
e
ar
t
icle.
I
n
th
eir
co
n
clu
s
io
n
,
th
e
au
th
o
r
s
p
r
o
v
id
e
an
s
wer
s
to
r
esear
ch
q
u
esti
o
n
s
,
a
s
y
n
o
p
s
is
o
f
th
e
s
y
s
tem
atic
liter
atu
r
e
r
ev
iew
(
SLR),
an
d
s
u
g
g
esti
o
n
s
f
o
r
im
p
r
o
v
in
g
s
o
u
n
d
class
if
icatio
n
task
s
.
Mu
tan
u
et
a
l.
[
8
]
ex
a
m
in
ed
1
2
4
s
tu
d
i
es
s
p
an
n
in
g
eig
h
t
y
ea
r
s
,
em
p
h
asizin
g
im
p
o
r
ta
n
t
ap
p
licatio
n
ar
ea
s
in
f
ea
tu
r
e
ex
tr
ac
tio
n
,
au
d
io
tr
an
s
f
o
r
m
atio
n
,
an
d
b
io
ac
o
u
s
tics
r
esear
ch
.
Alo
n
g
with
d
is
cu
s
s
in
g
th
e
f
ield
’
s
p
r
esen
t
d
if
f
icu
lties
,
p
r
o
s
p
ec
ts
,
an
d
f
u
tu
r
e
d
ir
ec
tio
n
s
,
th
e
s
u
r
v
ey
also
ex
a
m
in
es
th
e
class
if
icatio
n
alg
o
r
ith
m
s
u
s
ed
in
b
io
ac
o
u
s
tics
s
y
s
tem
s
.
Z
h
an
g
et
a
l.
[
9
]
e
x
am
in
e
n
e
w
d
ev
elo
p
m
e
n
ts
in
em
o
tio
n
r
ec
o
g
n
itio
n
s
y
s
tem
s
,
with
an
em
p
h
asis
o
n
ar
ch
itectu
r
es
f
o
r
class
if
icatio
n
th
at
u
s
e
in
p
u
ts
f
r
o
m
tex
t,
au
d
io
,
an
d
v
is
io
n
,
as
well
a
s
f
u
s
io
n
a
n
d
f
ea
tu
r
e
en
g
in
ee
r
i
n
g
tech
n
iq
u
es.
T
o
e
n
ab
le
r
el
iab
le
m
u
lti
-
m
o
d
al
an
al
y
s
is
,
th
e
p
a
p
er
h
ig
h
lig
h
ts
cr
ea
tiv
e
p
ip
elin
e
in
ter
v
en
tio
n
s
,
f
r
o
m
p
r
ep
r
o
ce
s
s
in
g
r
aw
s
i
g
n
als
to
p
r
ed
ictin
g
em
o
tio
n
l
ab
els.
B
y
o
f
f
er
in
g
in
s
ig
h
ts
in
to
th
e
cu
r
r
en
t
s
tate
-
of
-
th
e
-
a
r
t,
h
ig
h
lig
h
tin
g
u
n
r
e
s
o
lv
ed
is
s
u
es,
an
d
in
v
esti
g
atin
g
ex
citin
g
av
en
u
es
in
em
o
tio
n
d
etec
tio
n
v
ia
cr
o
s
s
-
m
o
d
al
lear
n
in
g
,
th
is
s
tu
d
y
s
ee
k
s
to
s
tim
u
late
ad
d
itio
n
al
r
esear
ch
t
h
r
o
u
g
h
th
eo
r
etica
l d
is
cu
s
s
io
n
s
an
d
r
ea
l
-
wo
r
ld
ca
s
e
s
tu
d
ies.
San
g
ala
et
a
l.
[
1
0
]
in
v
esti
g
ates
th
e
cr
ea
tio
n
o
f
a
v
o
ice
as
s
is
tan
t
s
y
s
tem
in
ten
d
ed
f
o
r
p
eo
p
le
with
v
is
u
al
im
p
air
m
en
ts
.
T
h
r
o
u
g
h
t
h
e
u
s
e
o
f
s
o
p
h
is
ticated
s
p
ee
ch
r
ec
o
g
n
itio
n
an
d
n
atu
r
al
lan
g
u
ag
e
p
r
o
c
ess
in
g
,
th
e
s
y
s
tem
m
ak
es
v
o
ice
co
m
m
a
n
d
s
a
s
m
o
o
th
way
to
in
ter
a
ct.
Key
is
s
u
es
lik
e
u
s
ab
ilit
y
,
ac
ce
s
s
ib
ilit
y
,
an
d
co
n
tex
tu
al
u
n
d
er
s
tan
d
in
g
a
r
e
ad
d
r
ess
ed
.
User
r
e
v
iews
attest
to
its
ef
f
icac
y
in
b
o
o
s
tin
g
s
elf
-
r
elian
ce
an
d
en
h
an
cin
g
d
ay
-
to
-
d
a
y
liv
in
g
,
i
n
d
icatin
g
its
p
o
ten
tial a
s
a
u
s
e
f
u
l a
s
s
is
tiv
e
tech
n
o
lo
g
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
2
,
Au
g
u
s
t
20
25
:
906
-
9
1
3
908
2
.
1
.
I
dentif
y
ing
t
he
g
a
p
C
u
r
r
en
t
h
ea
r
in
g
ai
d
s
u
s
e
b
asic
n
o
is
e
s
u
p
p
r
ess
io
n
an
d
am
p
lific
atio
n
tech
n
iq
u
es,
wh
ich
d
o
n
o
t
ad
eq
u
ately
a
d
ju
s
t
to
c
o
m
p
le
x
,
d
y
n
am
ic
lis
ten
in
g
en
v
ir
o
n
m
en
ts
.
Ma
n
y
e
x
is
tin
g
m
o
d
el
s
f
ail
to
ac
cu
r
ately
class
if
y
n
u
an
ce
d
ac
o
u
s
tic
s
ettin
g
s
lik
e
c
o
ck
tail
p
a
r
ty
n
o
i
s
e
o
r
r
ev
e
r
b
er
a
n
t
s
p
ac
es,
lea
d
in
g
to
s
u
b
o
p
tim
al
p
er
f
o
r
m
an
ce
.
Ad
d
itio
n
ally
,
m
o
s
t
class
if
icat
io
n
m
o
d
els
r
ely
o
n
a
s
in
g
le
m
ac
h
i
n
e
-
lear
n
in
g
ap
p
r
o
ac
h
,
wh
ic
h
lim
its
th
e
g
en
er
aliza
tio
n
ab
ilit
y
ac
r
o
s
s
v
ar
ied
ac
o
u
s
tic
en
v
ir
o
n
m
en
ts
[
1
1
]
,
[
1
2
]
.
2
.
2
.
O
v
er
co
m
ing
t
he
gap
T
h
is
r
esear
ch
ad
d
r
ess
es
th
e
g
a
p
b
y
in
teg
r
atin
g
C
NNs
with
R
FE
tech
n
iq
u
es
to
im
p
r
o
v
e
clas
s
if
icatio
n
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
.
T
h
e
h
y
b
r
id
m
o
d
el
tak
es
ad
v
an
tag
e
o
f
C
NN
’
s
ca
p
ab
ilit
y
to
ca
p
tu
r
e
co
m
p
le
x
au
d
io
p
atter
n
s
,
wh
ile
th
e
r
an
d
o
m
f
o
r
est
p
r
o
v
i
d
es
ef
f
ec
tiv
e
g
en
er
aliza
tio
n
ac
r
o
s
s
v
ar
y
in
g
d
ata
d
is
tr
ib
u
tio
n
s
.
Fu
r
th
er
m
o
r
e
,
d
im
e
n
s
io
n
ality
r
ed
u
ctio
n
t
h
r
o
u
g
h
p
r
in
cip
al
co
m
p
o
n
e
n
t
an
aly
s
is
(
PC
A
)
en
s
u
r
es
co
m
p
u
tatio
n
al
ef
f
icien
cy
,
m
a
k
in
g
t
h
e
m
o
d
el
s
u
itab
le
f
o
r
r
ea
l
-
tim
e
a
p
p
licatio
n
s
[
1
3
]
,
[
1
4
]
.
3.
M
E
T
H
O
D
3
.
1
.
M
o
del
a
rc
hite
ct
ure
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
in
teg
r
at
es
C
NNs
an
d
a
R
FE
,
as
illu
s
tr
ated
in
Fig
u
r
e
1
.
T
h
e
C
NN
ex
tr
ac
ts
f
ea
tu
r
es
f
r
o
m
r
aw
au
d
i
o
d
ata
i
n
th
e
f
o
r
m
o
f
MFC
C
s
,
wh
ich
ar
e
wid
ely
u
s
ed
in
a
u
d
io
s
ig
n
a
l
p
r
o
ce
s
s
in
g
.
T
h
ese
f
ea
tu
r
es a
r
e
th
en
r
ed
u
ce
d
in
d
im
en
s
io
n
ality
th
r
o
u
g
h
PC
A
to
en
s
u
r
e
co
m
p
u
tatio
n
al
ef
f
icien
cy
.
Fig
u
r
e
1
.
Pro
p
o
s
ed
m
o
d
el
ar
c
h
itectu
r
e
3
.
2
.
Da
t
a
s
et
a
nd
p
re
pro
ce
s
s
i
ng
T
h
e
d
ataset
in
clu
d
es
r
ea
l
-
w
o
r
ld
ac
o
u
s
tic
en
v
ir
o
n
m
en
ts
,
s
u
ch
as
th
o
s
e
in
T
ab
le
1
.
T
ab
le
1
s
u
m
m
ar
izes
th
e
d
if
f
er
en
t
ty
p
es
o
f
en
v
ir
o
n
m
e
n
ts
an
d
th
e
q
u
an
tity
o
f
au
d
io
f
iles
av
ailab
le
f
o
r
test
in
g
an
d
tr
ain
in
g
.
I
t
d
escr
ib
es
a
wid
e
r
an
g
e
o
f
s
itu
atio
n
s
,
s
u
ch
as
th
o
s
e
th
at
ar
e
q
u
iet,
n
o
is
y
ca
r
s
,
co
ck
tail
p
ar
ties
,
r
estau
r
an
ts
,
s
tr
ee
ts
,
tr
ain
s
tatio
n
s
,
air
p
o
r
ts
,
g
r
o
u
p
s
ettin
g
s
,
r
e
v
er
b
er
a
n
t sp
ac
es,
an
d
p
h
o
n
e
c
o
n
v
er
s
atio
n
s
.
T
ab
le
1
.
Data
s
et
d
is
tr
ib
u
tio
n
f
o
r
en
v
i
r
o
n
m
e
n
tal
s
o
u
n
d
class
i
f
icatio
n
-
tr
ain
in
g
an
d
test
in
g
f
iles
S
.
N
o
.
En
v
i
r
o
n
m
e
n
t
t
y
p
e
Tr
a
i
n
i
n
g
(
A
u
d
i
o
f
i
l
e
s)
Te
st
i
n
g
(
A
u
d
i
o
f
i
l
e
s)
1
Q
u
i
e
t
e
n
v
i
r
o
n
me
n
t
2
,
0
0
0
4
0
0
2
C
a
r
n
o
i
se
e
n
v
i
r
o
n
m
e
n
t
1
0
0
10
3
C
o
c
k
t
a
i
l
e
n
v
i
r
o
n
me
n
t
1
0
0
10
4
R
e
st
a
u
r
a
n
t
e
n
v
i
r
o
n
me
n
t
1
0
0
10
5
S
t
r
e
e
t
e
n
v
i
r
o
n
m
e
n
t
1
0
0
10
6
A
i
r
p
o
r
t
e
n
v
i
r
o
n
me
n
t
1
0
0
10
7
Tr
a
i
n
st
a
t
i
o
n
e
n
v
i
r
o
n
me
n
t
1
0
0
10
8
G
r
o
u
p
se
t
t
i
n
g
e
n
v
i
r
o
n
me
n
t
1
4
0
14
9
R
e
v
e
r
b
e
r
a
n
t
sp
a
c
e
s e
n
v
i
r
o
n
m
e
n
t
50
05
10
Te
l
e
p
h
o
n
e
c
o
n
v
e
r
sa
t
i
o
n
s
1
0
0
10
To
t
a
l
N
o
.
o
f
a
u
d
i
o
f
i
l
e
s
2
,
8
9
0
4
8
9
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
n
h
a
n
ci
n
g
a
c
o
u
s
tic
en
viro
n
m
en
t c
la
s
s
ifica
tio
n
fo
r
h
ea
r
in
g
-
i
mp
a
ir
ed
…
(
S
u
n
ilku
ma
r
M.
Ha
tta
r
a
ki
)
909
I
n
o
r
d
er
to
e
v
alu
ate
an
d
d
ev
el
o
p
au
d
io
p
r
o
ce
s
s
in
g
al
g
o
r
ith
m
s
o
r
m
o
d
els,
ea
ch
ty
p
e
o
f
en
v
i
r
o
n
m
en
t
is
d
is
tin
g
u
is
h
ed
b
y
th
e
n
u
m
b
e
r
o
f
au
d
io
r
ec
o
r
d
in
g
s
th
at
ar
e
av
ailab
le
f
o
r
tr
ain
in
g
a
n
d
test
in
g
.
W
ith
2
,
8
9
0
au
d
io
f
iles
av
ailab
le
f
o
r
tr
ain
i
n
g
an
d
4
8
9
f
o
r
test
in
g
,
a
co
m
p
r
eh
e
n
s
iv
e
an
aly
s
is
an
d
ass
ess
m
en
t
ac
r
o
s
s
a
v
ar
iety
o
f
ac
o
u
s
tic
en
v
ir
o
n
m
e
n
ts
is
m
ad
e
p
o
s
s
ib
le.
Au
d
io
s
am
p
les
we
r
e
co
llected
,
an
d
MFC
C
s
wer
e
ex
tr
ac
ted
as
in
p
u
t
f
ea
tu
r
es.
PC
A
was
ap
p
lied
t
o
r
ed
u
ce
th
e
f
ea
tu
r
e
d
im
e
n
s
io
n
ality
,
wh
ich
also
im
p
r
o
v
ed
tr
ain
in
g
tim
e
with
o
u
t
s
ac
r
if
icin
g
ac
cu
r
ac
y
[
1
5
]
-
[
2
0
]
.
3
.
3
.
F
e
a
t
ure
ex
t
r
a
ct
io
n us
ing
CNNs
T
h
e
C
NN
ex
tr
a
cts
m
ea
n
in
g
f
u
l
f
ea
tu
r
es
f
r
o
m
r
aw
au
d
io
d
ata
u
s
in
g
MFC
C
s
.
T
h
e
MF
C
C
s
f
o
r
an
au
d
io
s
ig
n
al
x
(
n
)
a
r
e
co
m
p
u
ted
as f
o
llo
ws:
a.
Pre
-
em
p
h
asis
f
ilter
[
2
1
]
,
[
2
2
]
:
t
h
e
s
ig
n
al
p
ass
es
th
r
o
u
g
h
a
h
ig
h
-
p
ass
f
ilter
to
b
alan
ce
th
e
f
r
eq
u
e
n
c
y
s
p
ec
tr
u
m
:
(
)
=
(
)
−
(
−
1
)
(
1)
wh
er
e
α
is
ty
p
ically
s
et
to
0
.
9
5
.
b.
Fra
m
in
g
an
d
w
in
d
o
win
g
[
2
3
]
,
[
2
4
]
:
t
h
e
s
ig
n
al
is
d
iv
id
ed
i
n
to
o
v
er
lap
p
i
n
g
f
r
am
es,
ea
ch
m
u
ltip
lied
b
y
a
Ham
m
in
g
win
d
o
w
t
o
m
in
im
iz
e
s
p
ec
tr
al
leak
ag
e:
(
)
=
0
.
54
−
0
.
46
(
2
−
1
)
(
2
)
c.
Sh
o
r
t
-
tim
e
f
o
u
r
ier
tr
a
n
s
f
o
r
m
(
STFT
)
:
e
ac
h
f
r
am
e
’
s
f
r
e
q
u
en
c
y
r
ep
r
esen
tatio
n
is
o
b
tain
ed
b
y
ap
p
ly
in
g
th
e
d
is
cr
ete
f
o
u
r
ier
t
r
an
s
f
o
r
m
(
DFT)
[
2
5
]
.
(
)
=
∑
(
)
−
2
−
1
=
0
(
3
)
d.
Me
l
f
ilter
b
a
n
k
p
r
o
ce
s
s
in
g
:
t
h
e
p
o
wer
s
p
ec
tr
u
m
is
p
ass
ed
th
r
o
u
g
h
a
s
et
o
f
tr
ian
g
u
lar
f
ilter
s
s
p
ac
ed
o
n
th
e
Me
l scale
,
d
ef
in
ed
as:
=
2595
10
(
1
+
700
)
(
4
)
e.
L
o
g
ar
ith
m
a
n
d
d
is
cr
ete
co
s
in
e
tr
an
s
f
o
r
m
(
DC
T
)
:
t
h
e
lo
g
ar
ith
m
o
f
th
e
Me
l
-
f
ilter
ed
en
e
r
g
y
i
s
co
m
p
u
ted
,
f
o
llo
wed
b
y
a
DC
T
to
o
b
tain
MFC
C
s
:
=
∑
(
)
−
1
=
0
[
(
−
1
2
)
]
(
5
)
wh
er
e
L
(
n
)
r
ep
r
esen
ts
th
e
lo
g
-
en
er
g
y
o
u
tp
u
ts
o
f
th
e
Me
l f
ilte
r
b
an
k
s
.
3
.
4
.
Di
m
ens
io
na
lity
re
du
ct
io
n us
ing
P
CA
T
o
im
p
r
o
v
e
co
m
p
u
tatio
n
al
p
er
f
o
r
m
an
ce
,
PC
A
m
in
im
izes th
e
d
im
en
s
io
n
ality
o
f
th
e
g
e
n
er
at
ed
MFC
C
f
ea
tu
r
es.
T
h
e
tr
a
n
s
f
o
r
m
atio
n
is
g
iv
en
b
y
,
=
(
6
)
wh
er
e
W
is
th
e
m
atr
ix
o
f
p
r
in
cip
al
co
m
p
o
n
e
n
ts
,
an
d
X
r
e
p
r
esen
ts
th
e
o
r
ig
in
al
f
ea
tu
r
e
m
atr
ix
.
PC
A
en
s
u
r
es
th
at
o
n
ly
th
e
m
o
s
t r
elev
an
t
f
ea
tu
r
es a
r
e
r
etain
ed
f
o
r
class
if
icatio
n
.
3
.
5
.
Cla
s
s
if
ica
t
io
n
u
s
ing
RF
E
On
ce
th
e
f
ea
tu
r
es
h
a
v
e
b
ee
n
r
etr
iev
ed
a
n
d
r
ef
in
ed
,
th
e
y
ar
e
p
u
t
i
n
to
th
e
r
an
d
o
m
f
o
r
est
cl
ass
if
ier
,
wh
ich
is
m
ad
e
u
p
o
f
s
ev
er
al
d
ec
is
io
n
tr
ee
s
.
E
ac
h
d
ec
is
io
n
tr
ee
is
tr
ain
ed
o
n
a
r
an
d
o
m
p
o
r
t
io
n
o
f
th
e
d
ataset,
an
d
th
e
f
i
n
al
class
if
icatio
n
is
d
eter
m
in
ed
v
ia
m
ajo
r
ity
v
o
tin
g
.
(
=
)
=
1
∑
(
ℎ
(
)
=
1
=
)
(
7
)
wh
er
e
T
is
th
e
t
o
tal
n
u
m
b
er
o
f
tr
ee
s
,
ℎ
(
)
r
ep
r
esen
ts
th
e
p
r
e
d
ictio
n
f
r
o
m
tr
ee
t,
an
d
I
is
an
in
d
icato
r
f
u
n
ctio
n
.
T
h
is
en
s
em
b
le
m
eth
o
d
en
h
an
ce
s
class
if
icatio
n
ac
cu
r
ac
y
an
d
g
e
n
er
aliza
tio
n
p
e
r
f
o
r
m
an
ce
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
2
,
Au
g
u
s
t
20
25
:
906
-
9
1
3
910
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
al
ig
n
s
well
with
t
h
e
r
esear
c
h
o
b
jectiv
es
o
f
en
h
a
n
cin
g
cl
ass
if
icatio
n
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
ac
r
o
s
s
d
iv
er
s
e
en
v
ir
o
n
m
en
ts
.
B
y
u
s
in
g
a
co
m
b
in
atio
n
o
f
C
NNs
a
n
d
R
FE,
th
e
s
y
s
tem
ex
h
ib
ited
b
etter
g
e
n
er
aliza
tio
n
th
an
s
tan
d
alo
n
e
m
o
d
els.
T
h
e
co
n
f
u
s
io
n
m
at
r
ix
as
s
h
o
wn
in
Fig
u
r
e
2
illu
s
tr
ate
th
e
m
o
d
el
’
s
ab
ilit
y
to
ac
cu
r
ate
ly
class
if
y
th
e
test
s
am
p
les wit
h
m
in
im
al
m
is
class
if
icatio
n
s
.
Fig
u
r
e
2
.
C
o
n
f
u
s
io
n
m
atr
i
x
4
.
1
.
L
ink
ing
re
s
ults t
o
o
bje
c
t
iv
es
T
h
e
h
ig
h
ac
cu
r
ac
y
ac
h
iev
ed
i
n
b
o
t
h
tr
ain
in
g
a
n
d
test
in
g
p
h
ases
s
u
p
p
o
r
ts
th
e
o
b
jectiv
e
o
f
d
ev
elo
p
in
g
a
r
o
b
u
s
t
class
if
ier
.
Fu
r
th
er
m
o
r
e,
th
e
p
r
ec
is
io
n
an
d
r
ec
all
s
co
r
es
f
o
r
ch
allen
g
in
g
en
v
ir
o
n
m
en
ts
s
u
ch
as
co
ck
tai
l
n
o
is
e
an
d
tr
ain
s
tatio
n
n
o
is
e
d
em
o
n
s
tr
ate
th
e
m
o
d
el
’
s
ef
f
ec
ti
v
en
ess
in
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
.
T
ab
le
2
h
ig
h
li
g
h
ts
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
h
y
b
r
i
d
C
NN
an
d
R
FE
m
o
d
el
in
cl
ass
if
y
in
g
d
iv
er
s
e
ac
o
u
s
tic
en
v
ir
o
n
m
e
n
ts
.
W
ith
a
h
ig
h
tr
ain
in
g
ac
c
u
r
ac
y
o
f
9
4
.
9
3
%,
th
e
m
o
d
el
ef
f
ec
tiv
ely
lear
n
s
f
r
o
m
th
e
d
ataset,
wh
ile
a
s
t
r
o
n
g
test
ac
cu
r
ac
y
o
f
9
3
.
4
1
%
d
e
m
o
n
s
tr
ates
its
ab
ilit
y
to
g
en
e
r
alize
to
n
ew,
u
n
s
ee
n
d
ata.
T
h
ese
r
esu
lts
r
ef
lect
th
e
m
o
d
el
’
s
r
o
b
u
s
tn
ess
an
d
ac
c
u
r
ac
y
,
m
a
k
in
g
it
a
r
eliab
le
to
o
l
f
o
r
i
m
p
r
o
v
i
n
g
a
u
d
ito
r
y
s
y
s
tem
s
f
o
r
h
ea
r
i
n
g
-
im
p
air
ed
in
d
iv
id
u
als in
v
a
r
io
u
s
r
ea
l
-
wo
r
ld
en
v
ir
o
n
m
e
n
ts
.
Fig
u
r
e
3
d
is
p
lay
s
th
e
ac
cu
r
ac
y
cu
r
v
e
,
wh
ich
s
h
o
ws
th
e
h
y
b
r
id
C
NN
an
d
R
FE
m
o
d
el’
s
tr
ain
in
g
an
d
v
alid
atio
n
p
er
f
o
r
m
a
n
ce
o
v
er
s
ev
er
al
ep
o
ch
s
.
Acc
u
r
ac
y
in
b
o
th
tr
ain
in
g
an
d
v
alid
atio
n
in
cr
ea
s
es
g
r
ad
u
ally
,
ev
en
tu
ally
s
u
r
p
ass
in
g
9
0
%,
i
n
d
icatin
g
th
e
m
o
d
el
’
s
s
tr
o
n
g
g
en
er
aliza
tio
n
to
n
ew
d
ata.
T
h
e
m
o
d
el
is
n
o
t
o
v
er
f
itti
n
g
,
as in
d
icate
d
b
y
th
e
s
m
all
d
if
f
er
en
ce
b
etwe
en
th
e
two
cu
r
v
es.
T
ab
le
2
.
T
r
ai
n
in
g
a
n
d
test
in
g
a
cc
u
r
ac
y
M
e
t
r
i
c
V
a
l
u
e
Tr
a
i
n
i
n
g
a
c
c
u
r
a
c
y
9
4
.
9
3
%
Te
st
a
c
c
u
r
a
c
y
9
3
.
4
1
%
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
n
h
a
n
ci
n
g
a
c
o
u
s
tic
en
viro
n
m
en
t c
la
s
s
ifica
tio
n
fo
r
h
ea
r
in
g
-
i
mp
a
ir
ed
…
(
S
u
n
ilku
ma
r
M.
Ha
tta
r
a
ki
)
911
Fig
u
r
e
3
.
Hy
b
r
id
C
NN
an
d
R
FE
tr
ain
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
y
As
s
ee
n
in
Fig
u
r
e
4
,
ef
f
ec
tiv
e
lear
n
in
g
is
co
n
f
ir
m
e
d
b
y
th
e
lo
s
s
cu
r
v
e,
wh
ich
co
n
s
is
ten
tly
d
ec
r
ea
s
es
tr
ain
in
g
an
d
v
alid
atio
n
lo
s
s
o
v
er
ep
o
ch
s
.
T
h
e
v
alid
atio
n
lo
s
s
an
d
tr
ain
in
g
lo
s
s
ar
e
s
till
v
er
y
s
im
ilar
,
in
d
icatin
g
a
well
-
r
eg
u
lar
ized
m
o
d
el
with
g
o
o
d
g
en
er
aliza
tio
n
p
o
wer
.
T
h
e
d
ec
r
ea
s
e
in
lo
s
s
p
o
in
ts
to
b
etter
p
er
f
o
r
m
an
c
e
in
f
ea
tu
r
e
e
x
tr
ac
tio
n
a
n
d
class
if
icatio
n
.
Fig
u
r
e
4
.
Hy
b
r
id
C
NN
an
d
R
FE
tr
ain
in
g
a
n
d
v
alid
atio
n
lo
s
s
5.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
SCO
P
E
T
h
e
p
r
o
p
o
s
ed
h
y
b
r
id
C
NN
an
d
R
FE
m
o
d
el
s
u
cc
ess
f
u
lly
ad
d
r
ess
es
th
e
g
ap
in
ac
o
u
s
tic
en
v
ir
o
n
m
e
n
t
class
if
icatio
n
f
o
r
h
ea
r
in
g
-
im
p
air
ed
in
d
iv
id
u
als.
B
y
lev
er
ag
i
n
g
th
e
co
m
b
in
ed
s
tr
en
g
th
s
o
f
d
ee
p
lear
n
in
g
an
d
en
s
em
b
le
lear
n
in
g
,
th
e
m
o
d
el
ac
h
iev
es
an
im
p
r
ess
iv
e
tr
ain
in
g
ac
cu
r
ac
y
o
f
9
4
.
9
3
%
an
d
a
test
ac
cu
r
ac
y
o
f
9
3
.
4
1
%,
d
em
o
n
s
tr
atin
g
s
u
p
er
io
r
ac
cu
r
ac
y
,
r
o
b
u
s
tn
ess
,
an
d
ad
ap
tab
ilit
y
ac
r
o
s
s
d
iv
er
s
e
e
n
v
ir
o
n
m
en
ts
.
T
h
is
r
esear
ch
co
n
tr
i
b
u
tes
to
th
e
ad
v
an
ce
m
en
t
o
f
ass
is
tiv
e
h
ea
r
in
g
tech
n
o
l
o
g
ies
an
d
h
o
ld
s
b
r
o
a
d
er
ap
p
licatio
n
s
in
s
m
ar
t d
ev
ices a
n
d
r
ea
l
-
tim
e
e
n
v
ir
o
n
m
e
n
tal
class
if
icatio
n
.
Fu
tu
r
e
wo
r
k
co
u
ld
e
x
p
lo
r
e
o
p
tim
i
zin
g
th
e
m
o
d
el
f
o
r
lo
w
-
p
o
wer
d
ev
ices,
in
te
g
r
atin
g
m
o
r
e
d
i
v
er
s
e
ac
o
u
s
tic
en
v
i
r
o
n
m
en
ts
,
an
d
en
h
a
n
cin
g
r
ea
l
-
tim
e
p
er
f
o
r
m
a
n
ce
f
o
r
g
r
ea
ter
ap
p
licab
ilit
y
in
we
ar
ab
le
tech
n
o
l
o
g
y
a
n
d
e
d
g
e
co
m
p
u
tin
g
s
o
lu
tio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
2
,
Au
g
u
s
t
20
25
:
906
-
9
1
3
912
ACK
NO
WL
E
DG
M
E
N
T
S
We
wo
u
ld
lik
e
to
ex
p
r
ess
m
y
g
r
atitu
d
e
to
t
h
e
R
esear
ch
C
en
tr
e,
Dep
ar
tm
en
t
o
f
E
lectr
o
n
ics
an
d
C
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
i
n
g
a
t Bas
av
esh
war
E
n
g
in
ee
r
in
g
C
o
lleg
e,
B
ag
alk
o
te,
Kar
n
atak
a,
I
n
d
ia.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
d
id
n
o
t
r
ec
eiv
e
an
y
s
p
ec
if
ic
g
r
an
t
f
r
o
m
f
u
n
d
i
n
g
ag
en
cies
in
th
e
p
u
b
lic,
co
m
m
er
cial,
o
r
not
-
f
o
r
-
p
r
o
f
it secto
r
s
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
Su
n
ilk
u
m
ar
M.
Hattar
ak
i,
co
ll
ec
ted
th
e
d
ata,
an
al
y
ze
d
th
e
d
ata,
im
p
lem
en
ted
th
e
p
r
o
p
o
s
e
d
wo
r
k
a
n
d
d
r
af
ted
th
e
co
m
p
lete
m
an
u
s
cr
i
p
t.
Sh
an
k
ar
a
y
y
a
G.
Kam
b
a
lim
ath
d
ef
in
e
d
th
e
p
r
o
b
lem
s
tatem
en
t
an
d
p
r
o
v
id
ed
cr
itical
r
ev
iews.
All a
u
th
o
r
s
r
e
ad
an
d
a
p
p
r
o
v
ed
t
h
e
f
in
al
m
a
n
u
s
cr
ip
t.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Su
n
ilk
u
m
ar
M.
Hattar
ak
i
✓
✓
✓
✓
✓
Sh
an
k
ar
ay
y
a
G.
Kam
b
alim
ath
✓
✓
✓
✓
✓
✓
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
.
RE
F
E
R
E
NC
E
S
[
1
]
B
.
D
.
A
u
e
r
b
a
c
h
a
n
d
H
.
J.
G
r
i
t
t
o
n
,
“
H
e
a
r
i
n
g
i
n
c
o
m
p
l
e
x
e
n
v
i
r
o
n
m
e
n
t
s:
a
u
d
i
t
o
r
y
g
a
i
n
c
o
n
t
r
o
l
,
a
t
t
e
n
t
i
o
n
,
a
n
d
h
e
a
r
i
n
g
l
o
ss
,
”
Fro
n
t
i
e
rs
i
n
N
e
u
ro
s
c
i
e
n
c
e
,
v
o
l
.
1
6
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
i
n
s.
2
0
2
2
.
7
9
9
7
8
7
.
[
2
]
J.
A
b
e
ß
e
r
,
“
A
r
e
v
i
e
w
o
f
d
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
met
h
o
d
s
f
o
r
a
c
o
u
st
i
c
s
c
e
n
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zerl
a
n
d
)
,
v
o
l
.
1
0
,
n
o
.
6
,
p
.
2
0
2
0
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
0
0
6
2
0
2
0
.
[
3
]
D
.
B
o
n
e
t
-
S
o
l
à
a
n
d
R
.
M
.
A
l
s
i
n
a
-
P
a
g
è
s,
“
A
c
o
m
p
a
r
a
t
i
v
e
s
u
r
v
e
y
o
f
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s
i
n
d
i
v
e
r
se
a
c
o
u
s
t
i
c
e
n
v
i
r
o
n
m
e
n
t
s,
”
S
e
n
so
rs (S
w
i
t
zerl
a
n
d
)
,
v
o
l
.
2
1
,
n
o
.
4
,
p
p
.
1
–
2
1
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
1
0
4
1
2
7
4
.
[
4
]
S
.
S
a
c
h
d
e
v
a
a
n
d
M
.
M
u
l
i
m
a
n
i
,
“
A
c
o
u
st
i
c
s
c
e
n
e
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
f
u
si
o
n
o
f
f
e
a
t
u
r
e
s
a
n
d
r
a
n
d
o
m
f
o
r
e
st
c
l
a
ss
i
f
i
e
r
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
2
2
9
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
i
n
g
f
o
r
S
u
s
t
a
i
n
a
b
l
e
G
l
o
b
a
l
D
e
v
e
l
o
p
m
e
n
t
,
I
N
D
I
AC
o
m
2
0
2
2
,
M
a
r
.
2
0
2
2
,
p
p
.
6
5
4
–
6
5
8
,
d
o
i
:
1
0
.
2
3
9
1
9
/
I
N
D
I
A
C
o
m5
4
5
9
7
.
2
0
2
2
.
9
7
6
3
2
7
1
.
[
5
]
K
.
C
.
D
e
S
o
u
s
a
,
V
.
M
a
n
c
h
a
i
a
h
,
D
.
R
.
M
o
o
r
e
,
M
.
A
.
G
r
a
h
a
m
,
a
n
d
D
.
W
.
S
w
a
n
e
p
o
e
l
,
“
Ef
f
e
c
t
i
v
e
n
e
ss
o
f
a
n
o
v
e
r
-
t
h
e
-
c
o
u
n
t
e
r
sel
f
-
f
i
t
t
i
n
g
h
e
a
r
i
n
g
a
i
d
c
o
m
p
a
r
e
d
w
i
t
h
a
n
a
u
d
i
o
l
o
g
i
st
-
f
i
t
t
e
d
h
e
a
r
i
n
g
a
i
d
:
a
r
a
n
d
o
mi
z
e
d
c
l
i
n
i
c
a
l
t
r
i
a
l
,
”
J
A
MA
O
t
o
l
a
r
y
n
g
o
l
o
g
y
-
H
e
a
d
a
n
d
N
e
c
k
S
u
r
g
e
ry
,
v
o
l
.
1
4
9
,
n
o
.
6
,
p
p
.
5
2
2
–
5
3
0
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
1
/
j
a
m
a
o
t
o
.
2
0
2
3
.
0
3
7
6
.
[
6
]
R
.
Za
h
e
e
r
,
I
.
A
h
m
a
d
,
D
.
H
a
b
i
b
i
,
K
.
Y
.
I
sl
a
m,
a
n
d
Q
.
V
.
P
h
u
n
g
,
“
A
s
u
r
v
e
y
o
n
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
-
b
a
se
d
a
c
o
u
st
i
c
s
o
u
r
c
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
6
0
0
7
8
–
6
0
1
0
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
8
3
9
8
2
.
[
7
]
O
.
O
.
A
b
a
y
o
m
i
-
A
l
l
i
,
R
.
D
a
maš
e
v
i
č
i
u
s,
A
.
Q
a
z
i
,
M
.
A
d
e
d
o
y
i
n
-
O
l
o
w
e
,
a
n
d
S
.
M
i
sr
a
,
“
D
a
t
a
a
u
g
me
n
t
a
t
i
o
n
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
met
h
o
d
s
i
n
s
o
u
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
:
a
sy
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
El
e
c
t
ro
n
i
c
s
(
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
1
,
n
o
.
2
2
,
p
.
3
7
9
5
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s1
1
2
2
3
7
9
5
.
[
8
]
L.
M
u
t
a
n
u
,
J
.
G
o
h
i
l
,
K
.
G
u
p
t
a
,
P
.
W
a
g
i
o
,
a
n
d
G
.
K
o
t
o
n
y
a
,
“
A
r
e
v
i
e
w
o
f
a
u
t
o
ma
t
e
d
b
i
o
a
c
o
u
st
i
c
s
a
n
d
g
e
n
e
r
a
l
a
c
o
u
st
i
c
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
r
e
se
a
r
c
h
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
2
1
,
p
.
8
3
6
1
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
2
2
1
8
3
6
1
.
[
9
]
S
.
Z
h
a
n
g
,
Y
.
Y
a
n
g
,
C
.
C
h
e
n
,
X
.
Zh
a
n
g
,
Q
.
Le
n
g
,
a
n
d
X
.
Zh
a
o
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
mu
l
t
i
m
o
d
a
l
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
f
r
o
m
a
u
d
i
o
,
v
i
s
u
a
l
,
a
n
d
t
e
x
t
mo
d
a
l
i
t
i
e
s:
a
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
o
f
r
e
c
e
n
t
a
d
v
a
n
c
e
m
e
n
t
s
a
n
d
f
u
t
u
r
e
p
r
o
s
p
e
c
t
s,
”
E
x
p
e
rt
S
y
st
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
3
7
,
p
.
1
2
1
6
9
2
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
3
.
1
2
1
6
9
2
.
[
1
0
]
T.
S
a
n
g
a
l
a
,
H
.
K
o
s
e
,
S
.
C
h
a
l
k
h
u
r
e
,
S
.
U
mare
,
a
n
d
R
.
C
h
i
l
b
u
l
e
,
“
V
o
i
c
e
a
ssi
s
t
a
n
t
f
o
r
b
l
i
n
d
p
e
r
so
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Re
s
e
a
r
c
h
i
n
S
c
i
e
n
c
e
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
T
e
c
h
n
o
l
o
g
y
,
p
p
.
5
7
8
–
5
8
3
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
4
8
1
7
5
/
i
j
a
r
sct
-
1
8
0
9
3
.
[
1
1
]
P
.
U
.
D
i
e
h
l
e
t
a
l
.
,
“
R
e
st
o
r
i
n
g
s
p
e
e
c
h
i
n
t
e
l
l
i
g
i
b
i
l
i
t
y
f
o
r
h
e
a
r
i
n
g
a
i
d
u
sers
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
2
7
1
9
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
3
-
2
9
8
7
1
-
8.
[
1
2
]
N
.
Z
.
Ta
s
n
i
m
,
A
.
N
i
,
E.
L
o
b
a
r
i
n
a
s
,
a
n
d
N
.
K
e
h
t
a
r
n
a
v
a
z
,
“
A
r
e
v
i
e
w
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
t
h
e
p
e
r
so
n
a
l
i
z
a
t
i
o
n
o
f
a
mp
l
i
f
i
c
a
t
i
o
n
i
n
h
e
a
r
i
n
g
a
i
d
s
,
”
S
e
n
s
o
r
s
,
v
o
l
.
2
4
,
n
o
.
5
,
p
.
1
5
4
6
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
4
0
5
1
5
4
6
.
[
1
3
]
M
.
A
sh
r
a
f
et
a
l
.
,
“
A
h
y
b
r
i
d
C
N
N
a
n
d
R
N
N
v
a
r
i
a
n
t
mo
d
e
l
f
o
r
mu
s
i
c
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
ze
rl
a
n
d
)
,
v
o
l
.
1
3
,
n
o
.
3
,
p
.
1
4
7
6
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
0
3
1
4
7
6
.
[
1
4
]
M
.
Tu
r
a
b
,
T.
K
u
m
a
r
,
M
.
B
e
n
d
e
c
h
a
c
h
e
,
a
n
d
T
.
S
a
b
e
r
,
“
I
n
v
e
st
i
g
a
t
i
n
g
m
u
l
t
i
-
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
a
n
d
e
n
se
mb
l
i
n
g
f
o
r
a
u
d
i
o
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
r
n
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
&
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
3
,
n
o
.
3
,
p
p
.
6
9
–
8
4
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
5
1
2
1
/
i
j
a
i
a
.
2
0
2
2
.
1
3
3
0
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
n
h
a
n
ci
n
g
a
c
o
u
s
tic
en
viro
n
m
en
t c
la
s
s
ifica
tio
n
fo
r
h
ea
r
in
g
-
i
mp
a
ir
ed
…
(
S
u
n
ilku
ma
r
M.
Ha
tta
r
a
ki
)
913
[
1
5
]
S
.
M
.
H
a
t
t
a
r
a
k
i
,
S
.
G
.
K
a
m
b
a
l
i
ma
t
h
,
S
.
H
a
n
a
mare
d
d
y
,
S
.
B
h
u
sa
n
u
r
,
V
.
B
i
l
u
r
,
a
n
d
S
.
M
a
r
a
n
u
r
,
“
A
u
t
o
m
a
t
i
c
d
e
t
e
c
t
i
o
n
a
n
d
f
i
l
t
e
r
i
n
g
o
f
l
i
s
t
e
n
i
n
g
c
o
n
d
i
t
i
o
n
s
i
n
h
e
a
r
i
n
g
a
i
d
s
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
i
n
2
0
2
4
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
n
o
v
a
t
i
o
n
a
n
d
N
o
v
e
l
t
y
i
n
E
n
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
I
N
N
O
VA
2
0
2
4
-
Pro
c
e
e
d
i
n
g
s
,
D
e
c
.
2
0
2
4
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
N
N
O
V
A
6
3
0
8
0
.
2
0
2
4
.
1
0
8
4
7
0
2
7
.
[
1
6
]
S
.
M
.
H
a
t
t
a
r
a
k
i
,
S
.
G
.
K
a
m
b
a
l
i
m
a
t
h
,
P
.
N
.
K
a
r
j
o
l
,
P
.
H
.
G
u
g
g
a
r
i
,
N
.
S
.
P
a
t
i
l
,
a
n
d
B
.
N
a
l
u
d
i
,
“
O
b
j
e
c
t
i
v
e
a
sse
ssm
e
n
t
o
f
s
p
e
e
c
h
si
g
n
a
l
f
i
l
t
e
r
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
h
e
a
r
i
n
g
a
i
d
s,”
i
n
2
0
2
4
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
n
o
v
a
t
i
o
n
a
n
d
N
o
v
e
l
t
y
i
n
En
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
I
N
N
O
VA
2
0
2
4
-
Pro
c
e
e
d
i
n
g
s
,
D
e
c
.
2
0
2
4
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
N
N
O
V
A
6
3
0
8
0
.
2
0
2
4
.
1
0
8
4
7
0
3
8
.
[
1
7
]
S
.
M
.
H
a
t
t
a
r
a
k
i
,
S
.
G
.
K
a
m
b
a
l
i
m
a
t
h
,
B
.
P
.
S
a
v
u
k
a
r
,
S
.
B
a
g
a
l
i
,
U
.
D
.
D
i
x
i
t
,
a
n
d
A
.
S
.
J
a
d
h
a
v
,
“
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
v
a
r
i
o
u
s
l
i
st
e
n
i
n
g
e
n
v
i
r
o
n
m
e
n
t
s
f
o
r
h
e
a
r
i
n
g
-
i
m
p
a
i
r
e
d
i
n
d
i
v
i
d
u
a
l
s
u
s
i
n
g
C
R
N
N
,
”
i
n
2
0
2
4
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
n
o
v
a
t
i
o
n
a
n
d
N
o
v
e
l
t
y
i
n
E
n
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
I
N
N
O
VA
2
0
2
4
-
Pro
c
e
e
d
i
n
g
s
,
D
e
c
.
2
0
2
4
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
N
N
O
V
A
6
3
0
8
0
.
2
0
2
4
.
1
0
8
4
7
0
1
3
.
[
1
8
]
S
.
M
.
H
a
t
t
a
r
a
k
i
,
S
.
G
.
K
a
m
b
a
l
i
mat
h
,
L.
K
h
e
d
a
g
i
,
K
.
H
a
l
e
ma
n
i
,
A
.
B
h
a
i
r
a
g
o
n
d
,
a
n
d
P
.
H
i
r
e
m
a
t
h
,
“
E
v
a
l
u
a
t
i
o
n
o
f
s
p
e
e
c
h
e
n
h
a
n
c
e
me
n
t
a
l
g
o
r
i
t
h
ms
f
o
r
h
e
a
r
i
n
g
a
i
d
s,”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
N
K
C
o
n
2
0
2
4
-
3
r
d
E
d
i
t
i
o
n
o
f
I
EE
E
N
K
S
S
’
s
F
l
a
g
sh
i
p
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
:
D
i
g
i
t
a
l
T
r
a
n
s
f
o
rm
a
t
i
o
n
:
U
n
l
e
a
s
h
i
n
g
t
h
e
Po
w
e
r
o
f
I
n
f
o
rm
a
t
i
o
n
,
S
e
p
.
2
0
2
4
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
N
K
C
o
n
6
2
7
2
8
.
2
0
2
4
.
1
0
7
7
4
6
1
3
.
[
1
9
]
S
.
M
.
H
a
t
t
a
r
a
k
i
a
n
d
S
.
G
.
K
a
mb
a
l
i
mat
h
,
“
D
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
d
i
v
e
r
s
e
l
i
st
e
n
i
n
g
c
o
n
d
i
t
i
o
n
s
f
o
r
h
e
a
r
i
n
g
-
i
m
p
a
i
r
e
d
i
n
d
i
v
i
d
u
a
l
s
u
si
n
g
R
N
N
mo
d
e
l
a
n
d
F
I
R
f
i
l
t
e
r
,
”
J
o
u
r
n
a
l
o
f
B
a
si
c
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
1
,
n
o
.
1
,
p
p
.
5
9
2
–
6
1
2
,
2
0
2
4
.
[
2
0
]
S
.
M
.
H
a
t
t
a
r
a
k
i
a
n
d
S
.
G
.
K
a
mb
a
l
i
ma
t
h
,
“
E
n
h
a
n
c
i
n
g
s
p
e
e
c
h
i
n
t
e
l
l
i
g
i
b
i
l
i
t
y
i
n
h
e
a
r
i
n
g
a
i
d
s
u
s
i
n
g
s
p
e
c
t
r
a
l
su
b
t
r
a
c
t
i
o
n
,
”
G
o
n
g
c
h
e
n
g
K
e
x
u
e
Y
u
J
i
sh
u
/
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
ri
n
g
S
c
i
e
n
c
e
,
v
o
l
.
5
6
,
n
o
.
7
,
p
p
.
4
7
9
3
–
4
8
0
1
,
2
0
2
4
.
[
2
1
]
Z.
Z
h
o
u
e
t
a
l
.
,
“
I
mp
a
c
t
o
f
a
n
a
l
o
g
a
n
d
d
i
g
i
t
a
l
p
r
e
-
e
m
p
h
a
si
s
o
n
t
h
e
s
i
g
n
a
l
-
to
-
n
o
i
se
r
a
t
i
o
o
f
b
a
n
d
w
i
d
t
h
-
l
i
mi
t
e
d
o
p
t
i
c
a
l
t
r
a
n
sc
e
i
v
e
r
s,
”
I
EEE
P
h
o
t
o
n
i
c
s
J
o
u
r
n
a
l
,
v
o
l
.
1
2
,
n
o
.
2
,
p
p
.
1
–
1
2
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
J
P
H
O
T.
2
0
2
0
.
2
9
6
6
6
1
7
.
[
2
2
]
A
.
W
r
i
g
h
t
a
n
d
V
.
V
a
l
i
m
a
k
i
,
“
P
e
r
c
e
p
t
u
a
l
l
o
ss
f
u
n
c
t
i
o
n
f
o
r
n
e
u
r
a
l
m
o
d
e
l
i
n
g
o
f
a
u
d
i
o
s
y
st
e
ms,”
i
n
I
C
AS
S
P,
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
s
t
i
c
s,
S
p
e
e
c
h
a
n
d
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
-
Pr
o
c
e
e
d
i
n
g
s
,
M
a
y
2
0
2
0
,
v
o
l
.
2
0
2
0
-
M
a
y
,
p
p
.
2
5
1
–
2
5
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
S
S
P
4
0
7
7
6
.
2
0
2
0
.
9
0
5
2
9
4
4
.
[
2
3
]
A
.
H
a
n
n
a
h
a
n
d
G
.
K
.
A
g
o
r
d
z
o
,
“
A
d
e
s
i
g
n
o
f
a
l
o
w
-
p
a
ss
F
I
R
f
i
l
t
e
r
u
s
i
n
g
h
a
mm
i
n
g
w
i
n
d
o
w
f
u
n
c
t
i
o
n
s
i
n
M
a
t
l
a
b
,
”
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
7
1
7
6
/
c
e
i
s/
1
1
-
2
-
0
4
.
[
2
4
]
D
.
J.
Jw
o
,
W
.
Y
.
C
h
a
n
g
,
a
n
d
I
.
H
.
W
u
,
“
W
i
n
d
o
w
i
n
g
t
e
c
h
n
i
q
u
e
s
,
t
h
e
w
e
l
c
h
m
e
t
h
o
d
f
o
r
i
m
p
r
o
v
e
m
e
n
t
o
f
p
o
w
e
r
s
p
e
c
t
r
u
m
e
st
i
mat
i
o
n
,
”
C
o
m
p
u
t
e
rs,
Ma
t
e
r
i
a
l
s
a
n
d
C
o
n
t
i
n
u
a
,
v
o
l
.
6
7
,
n
o
.
3
,
p
p
.
3
9
8
3
–
4
0
0
3
,
2
0
2
1
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
mc.
2
0
2
1
.
0
1
4
7
5
2
.
[
2
5
]
M
.
L
i
,
Y
.
L
i
u
,
S
.
Z
h
i
,
T.
W
a
n
g
,
a
n
d
F
.
C
h
u
,
“
S
h
o
r
t
-
t
i
m
e
f
o
u
r
i
e
r
t
r
a
n
sf
o
r
m
u
si
n
g
o
d
d
sy
m
met
r
i
c
w
i
n
d
o
w
f
u
n
c
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
D
y
n
a
m
i
c
s
,
Mo
n
i
t
o
ri
n
g
a
n
d
D
i
a
g
n
o
st
i
c
s
,
v
o
l
.
1
,
n
o
.
1
,
p
p
.
3
7
–
4
5
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
3
7
9
6
5
/
j
d
m
d
.
v
2
i
2
.
3
9
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
u
n
il
k
u
m
a
r
M.
H
a
tt
a
r
a
k
i
is
c
u
rre
n
tl
y
p
u
rsu
in
g
h
is
P
h
.
D.
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
ri
n
g
,
fo
c
u
sin
g
o
n
sig
n
a
l
p
ro
c
e
ss
in
g
,
s
p
e
e
c
h
p
r
o
c
e
ss
in
g
,
a
n
d
a
rti
f
icia
l
in
telli
g
e
n
c
e
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
He
c
o
m
p
lete
d
h
is
M
.
Tec
h
.
in
d
i
g
it
a
l
e
lec
tro
n
ics
a
n
d
c
o
m
m
u
n
ica
ti
o
n
fro
m
Vis
v
e
sv
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
i
v
e
rsity
(VT
U),
Be
lag
a
v
i,
Ka
r
n
a
tak
a
,
i
n
2
0
1
1
,
a
n
d
h
is
B.
E
.
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
ri
n
g
f
ro
m
th
e
sa
m
e
u
n
i
v
e
rsity
in
2
0
0
8
.
W
it
h
1
4
y
e
a
rs
o
f
a
c
a
d
e
m
ic
a
n
d
re
se
a
rc
h
e
x
p
e
rien
c
e
,
h
e
is
p
re
se
n
tl
y
se
rv
i
n
g
a
s
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
E
lec
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
a
t
BLDEA
’
s
V.P
.
Dr.
P
.
G
.
Ha
lak
a
t
ti
Co
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
Vijay
a
p
u
ra
.
He
h
a
s
p
u
b
l
ish
e
d
m
o
re
t
h
a
n
1
5
re
se
a
rc
h
p
a
p
e
rs
i
n
re
p
u
ted
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
jo
u
r
n
a
ls.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
s
u
n
il
m
h
0
3
9
@m
a
il
.
c
o
m
.
Dr
.
S
h
a
n
k
a
r
a
y
y
a
G
.
K
a
m
b
a
li
m
a
th
is
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
C
o
m
m
u
n
ic
a
ti
o
n
En
g
i
n
e
e
rin
g
a
t
Ba
sa
v
e
sh
wa
r
En
g
in
e
e
rin
g
Co
ll
e
g
e
,
Ba
g
a
lk
o
t.
He
h
o
l
d
s
a
P
h
.
D
.
,
M
.
E
.
,
a
n
d
B
.
E
.
,
a
n
d
h
a
s
2
9
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
a
lo
n
g
w
it
h
6
m
o
n
th
s
in
t
h
e
in
d
u
stry
.
He
is
a
c
ti
v
e
ly
in
v
o
l
v
e
d
in
v
a
rio
u
s
a
d
m
in
istrati
v
e
ro
les
,
in
c
lu
d
in
g
TE
QIP
-
III
c
o
o
r
d
in
a
t
o
r
a
n
d
p
lac
e
m
e
n
t
o
ffi
c
e
r.
His
re
se
a
rc
h
in
tere
sts
li
e
in
VLS
I
a
n
d
sig
n
a
l
p
r
o
c
e
ss
in
g
,
a
n
d
h
e
h
a
s
g
u
i
d
e
d
n
u
m
e
ro
u
s
UG
a
n
d
P
G
p
ro
jec
ts.
He
h
a
s
p
u
b
li
s
h
e
d
e
x
ten
siv
e
ly
i
n
re
p
u
ted
c
o
n
fe
re
n
c
e
s
a
n
d
j
o
u
r
n
a
ls
a
n
d
h
a
s
o
r
g
a
n
iz
e
d
a
n
d
a
tt
e
n
d
e
d
n
u
m
e
ro
u
s
p
ro
fe
ss
io
n
a
l
d
e
v
e
l
o
p
m
e
n
t
wo
rk
sh
o
p
s
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
:
k
a
m
b
a
li
m
a
th
1
5
@
g
m
a
il
.
c
o
m
a
n
d
sg
k
e
c
@b
e
c
b
g
k
.
e
d
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.