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.
38
,
No
.
3
,
J
u
n
e
2
0
2
5
,
p
p
.
1
862
~
1
8
6
9
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
38
.i
3
.
p
p
1
8
6
2
-
1
8
6
9
1862
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
A nov
el deep
lear
ning
bas
ed spa
tial
delay
f
ea
tur
e aw
a
re e
nco
der
deco
der mo
dule
f
o
r enhanced
CSI
feedback i
n ma
ss
i
v
e MI
M
O
P
a
rinitha
J
a
y
a
s
ha
nk
a
r
1
,
Chig
a
la
kk
a
pp
a
Ra
ng
a
s
wa
m
y
1
,
B
y
ra
pp
a
N
.
Sh
o
bh
a
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
,
S
J C
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
C
h
i
c
k
b
a
l
l
a
p
u
r
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
EC
E,
B
G
S
I
n
st
i
t
u
e
o
f
Te
c
h
n
o
l
o
g
y
,
A
d
i
c
h
u
n
c
h
a
n
a
g
i
r
i
U
n
i
v
e
r
si
t
y
,
M
a
n
d
y
a
,
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
Mar
18
,
2
0
2
4
R
ev
is
ed
No
v
30
,
2
0
2
4
Acc
ep
ted
Feb
27
,
2
0
2
5
Th
e
a
lg
o
rit
h
m
p
re
se
n
ted
in
th
is
st
u
d
y
a
d
d
re
ss
e
s
th
e
c
h
a
ll
e
n
g
e
o
f
re
c
o
n
stru
c
ti
n
g
d
o
wn
li
n
k
c
h
a
n
n
e
l
sta
te
in
fo
rm
a
ti
o
n
(CS
I)
in
m
a
ss
iv
e
m
u
lt
ip
le
in
p
u
t
m
u
lt
ip
le
o
u
t
p
u
t
(M
IM
O)
sy
ste
m
s
with
a
fo
c
u
s
o
n
e
n
h
a
n
c
in
g
e
fficie
n
c
y
a
n
d
a
c
c
u
ra
c
y
.
It
b
e
g
in
s
b
y
a
c
q
u
iri
n
g
b
o
t
h
d
o
wn
li
n
k
a
n
d
u
p
li
n
k
CS
I
d
a
ta
a
lo
n
g
si
d
e
o
t
h
e
r
c
rit
ica
l
p
a
ra
m
e
ters
su
c
h
a
s
th
e
n
u
m
b
e
r
o
f
it
e
r
a
ti
o
n
s
a
n
d
c
o
n
v
o
lu
ti
o
n
a
l
fil
ter
s
p
e
c
ifi
c
a
ti
o
n
s.
T
h
e
p
r
o
c
e
ss
in
it
iate
s
with
t
h
e
v
e
c
to
riza
ti
o
n
o
f
d
o
w
n
li
n
k
CS
I
d
a
ta
fo
ll
o
we
d
b
y
c
o
m
p
re
ss
io
n
th
r
o
u
g
h
a
fu
ll
y
c
o
n
n
e
c
ted
lay
e
r,
e
ffe
c
ti
v
e
ly
re
d
u
c
i
n
g
d
ime
n
sio
n
a
l
it
y
t
o
m
a
n
a
g
e
c
o
m
p
u
tati
o
n
a
l
c
o
m
p
le
x
it
y
.
Th
e
i
tera
ti
v
e
re
c
o
n
stru
c
ti
o
n
p
h
a
se
th
e
n
u
n
f
o
l
d
s,
wh
e
re
e
a
c
h
it
e
ra
ti
o
n
u
p
d
a
tes
a
n
in
term
e
d
iary
v
a
riab
le
u
si
n
g
a
re
fi
n
e
d
fo
rm
u
la
t
h
a
t
i
n
c
o
rp
o
ra
tes
th
e
c
o
m
p
re
ss
e
d
CS
I
re
p
re
se
n
tatio
n
a
n
d
c
o
rre
c
ti
o
n
fa
c
to
rs.
Th
is
it
e
ra
ti
v
e
re
fin
e
m
e
n
t
a
ims
to
p
ro
g
re
ss
iv
e
ly
e
n
h
a
n
c
e
th
e
a
c
c
u
ra
c
y
o
f
t
h
e
re
c
o
n
str
u
c
ted
CS
I
.
A
p
i
v
o
tal
a
sp
e
c
t
o
f
t
h
e
a
lg
o
rit
h
m
i
n
v
o
lv
e
s
a
n
o
p
ti
m
ize
d
E
n
c
o
d
e
r
-
De
c
o
d
e
r
f
ra
m
e
wo
rk
d
e
sig
n
e
d
t
o
h
a
n
d
le
sp
a
ti
a
l
-
d
e
lay
fe
a
tu
re
s
in
h
e
re
n
t
i
n
M
I
M
O
sy
ste
m
s.
Th
is
fra
m
e
wo
rk
e
m
p
lo
y
s
th
r
e
sh
o
ld
i
n
g
o
p
e
ra
ti
o
n
s
to
e
li
m
in
a
te
in
si
g
n
if
ica
n
t
fe
a
tu
re
s,
e
n
su
rin
g
th
a
t
th
e
re
c
o
n
stru
c
te
d
CS
I
a
c
c
u
ra
tely
re
flec
ts
th
e
c
ru
c
ial
a
sp
e
c
ts
o
f
t
h
e
c
h
a
n
n
e
l.
S
im
u
lt
a
n
e
o
u
sly
,
a
n
in
fo
rm
a
ti
o
n
m
o
d
u
le
u
ti
li
z
e
s
u
p
li
n
k
CS
I
d
a
ta
to
a
d
ju
st
we
ig
h
ts
d
u
ri
n
g
re
c
o
n
stru
c
ti
o
n
,
t
h
e
re
b
y
fu
rt
h
e
r
r
e
fin
in
g
t
h
e
a
c
c
u
ra
c
y
o
f
t
h
e
d
o
w
n
li
n
k
CS
I
e
stim
a
ti
o
n
.
K
ey
w
o
r
d
s
:
C
h
an
n
el
s
tate
in
f
o
r
m
atio
n
Mu
ltip
le
in
p
u
t m
u
ltip
le
o
u
tp
u
t
No
r
m
alize
d
m
ea
n
s
q
u
ar
e
er
r
o
r
Sp
atial
d
elay
f
ea
tu
r
e
awa
r
e
en
co
d
er
-
d
ec
o
d
er
Sp
atial
d
elay
f
ea
tu
r
e
e
x
tr
ac
tio
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
:
Par
in
ith
a
J
ay
ash
an
k
ar
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
,
S J C
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
C
h
ick
b
allap
u
r
,
I
n
d
ia
E
m
ail:
p
ar
in
ith
aj_
1
2
@
r
ed
if
f
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
r
ec
en
t
y
ea
r
s
,
th
e
r
e
h
as
b
ee
n
s
ig
n
if
ican
t
i
n
ter
est
in
m
ass
iv
e
m
u
ltip
le
-
in
p
u
t
m
u
ltip
le
-
o
u
tp
u
t
(
MI
MO
)
s
y
s
tem
s
d
u
e
to
th
eir
p
o
ten
tial
to
g
r
ea
tly
en
h
an
ce
th
e
s
p
ec
tr
al
ef
f
icien
cy
(
SE)
o
f
wir
eless
co
m
m
u
n
icatio
n
n
etwo
r
k
s
[
1
]
.
T
h
is
tech
n
o
lo
g
y
is
cr
u
cial
in
en
ab
l
in
g
th
e
r
ea
lizatio
n
o
f
f
i
f
th
-
g
en
e
r
atio
n
(
5
G)
wir
eless
co
m
m
u
n
icatio
n
n
etwo
r
k
s
.
T
o
ac
h
iev
e
th
e
b
est
s
y
s
tem
SE
an
d
th
r
o
u
g
h
p
u
t
in
a
r
e
al
m
ass
iv
e
MI
MO
s
y
s
tem
,
th
e
b
ase
s
tatio
n
(
B
S)
r
elies
o
n
h
av
in
g
ac
cu
r
ate
ch
an
n
el
s
tate
in
f
o
r
m
atio
n
(
C
SI)
f
o
r
ef
f
icien
t
d
esig
n
[
2
]
.
Pre
cise
ac
q
u
is
itio
n
o
f
th
e
C
SI
m
atr
ix
i
s
cr
u
cial
f
o
r
th
e
BS
in
lar
g
e
MI
MO
s
y
s
t
em
s
,
esp
ec
ially
in
m
u
ltiu
s
er
co
m
m
u
n
icatio
n
s
th
a
t
ar
e
a
f
f
ec
ted
b
y
in
ter
f
er
en
ce
.
I
n
T
DD
s
y
s
tem
s
,
th
e
BS
ca
n
d
ir
ec
tly
esti
m
ate
th
e
u
p
lin
k
C
SI
b
y
u
tili
zin
g
a
p
ilo
t
s
eq
u
en
ce
tr
a
n
s
m
itted
b
y
a
u
s
er
eq
u
ip
m
en
t
(
UE
)
.
B
y
l
ev
er
ag
in
g
ch
an
n
el
r
ec
ip
r
o
city
,
th
e
esti
m
ate
ca
n
b
e
u
tili
ze
d
to
p
r
e
d
ict
th
e
co
r
r
esp
o
n
d
in
g
d
o
w
n
lin
k
C
SI
[
3
]
.
Nev
er
th
eless
,
FDD
m
eth
o
d
s
ar
e
wid
ely
u
tili
ze
d
in
m
o
d
er
n
ce
llu
lar
n
etwo
r
k
s
.
C
o
m
p
r
eh
en
d
in
g
th
e
C
SI
in
FDD
ca
n
p
o
s
e
a
ch
allen
g
e
wh
en
th
e
ch
an
n
el
r
ec
ip
r
o
city
is
d
is
r
u
p
ted
b
y
tr
a
n
s
m
itti
n
g
th
e
(
C
SI)
f
r
o
m
a
UE
b
ac
k
to
th
e
BS
is
cr
u
cial
in
f
r
eq
u
en
c
y
d
iv
is
io
n
d
u
p
lex
(
FDD)
s
y
s
tem
s
[
4
]
-
[
7
]
h
av
e
d
em
o
n
s
tr
ated
th
at
th
e
f
ee
d
b
ac
k
s
ig
n
alin
g
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
A
n
o
ve
l d
ee
p
lea
r
n
in
g
b
a
s
ed
s
p
a
tia
l d
ela
y
fe
a
tu
r
e
a
w
a
r
e
en
c
o
d
er d
ec
o
d
er
… (
P
a
r
in
ith
a
Ja
ya
s
h
a
n
ka
r
)
1863
o
v
er
h
ea
d
o
f
C
SI
f
o
r
m
ass
iv
e
MI
MO
in
cr
ea
s
es
as
th
e
n
u
m
b
er
o
f
B
Ss
an
ten
n
as
an
d
ac
tiv
e
UE
s
g
r
o
ws,
b
o
th
at
th
e
lin
k
an
d
n
etwo
r
k
lev
els.
I
t
is
im
p
o
r
tan
t
to
d
ev
el
o
p
a
n
ef
f
ec
tiv
e
C
SI
f
ee
d
b
ac
k
o
r
r
e
-
ev
alu
ate
th
e
f
ee
d
b
ac
k
ch
an
n
el.
I
n
v
ar
io
u
s
co
m
p
u
ter
v
is
io
n
d
o
m
ain
s
,
d
ee
p
lear
n
in
g
(
DL
)
h
as
p
r
o
v
en
to
b
e
h
ig
h
ly
ef
f
ec
tiv
e
d
u
e
to
its
im
p
r
ess
iv
e
ab
ilit
y
to
ex
tr
ac
t
f
ea
tu
r
es
an
d
tr
an
s
f
er
k
n
o
wled
g
e
ac
r
o
s
s
d
if
f
e
r
en
t
d
o
m
ain
s
[
8
]
,
[
9
]
.
T
h
e
g
r
o
win
g
in
ter
est
in
DL
in
wir
eless
c
o
m
m
u
n
icatio
n
h
as
b
ee
n
d
r
i
v
en
b
y
its
ac
co
m
p
lis
h
m
en
ts
i
n
in
ter
d
is
cip
lin
ar
y
r
esear
ch
[
1
0
]
.
Ad
v
an
ce
d
p
h
y
s
ical
-
lay
er
tech
n
o
lo
g
ies,
s
u
ch
as
p
r
ec
o
d
in
g
d
esig
n
s
u
tili
zin
g
DL
,
ch
an
n
el
esti
m
atio
n
m
eth
o
d
s
en
h
a
n
ce
d
b
y
DL
,
MI
MO
d
etec
tio
n
ap
p
r
o
ac
h
es
b
ased
o
n
DL
,
an
d
s
ec
u
r
ity
tech
n
o
lo
g
ies
em
p
o
wer
ed
b
y
DL
,
n
ee
d
to
b
e
r
ed
esig
n
e
d
to
f
u
lly
lev
er
a
g
e
th
e
ca
p
ab
ilit
ies
o
f
DL
[
1
1
]
.
DL
h
as
b
ee
n
u
tili
ze
d
to
d
ev
elo
p
ef
f
icien
t
C
SI
r
ec
o
n
s
tr
u
ctio
n
an
d
co
m
p
r
ess
io
n
f
o
r
s
y
s
tem
s
th
at
r
eq
u
ir
e
lar
g
e
-
s
ca
le
MI
MO
C
SI
f
ee
d
b
ac
k
,
en
ab
lin
g
o
p
tim
al
u
t
ilizatio
n
o
f
its
ca
p
ab
ilit
ies.
R
e
s
ea
r
ch
co
n
d
u
cted
i
n
[
1
2
]
h
a
s
d
em
o
n
s
tr
ated
th
e
s
ig
n
if
ican
t
p
o
ten
tial
o
f
C
SI
f
ee
d
b
ac
k
m
et
h
o
d
s
th
at
u
tili
ze
DL
.
T
h
ese
m
eth
o
d
s
h
av
e
p
r
o
v
e
n
to
b
e
m
o
r
e
ef
f
ec
tiv
e
th
an
tr
a
d
itio
n
al
r
estri
cted
f
ee
d
b
ac
k
tech
n
iq
u
es
in
r
e
v
ea
lin
g
th
e
u
n
d
er
l
y
in
g
s
tr
u
ctu
r
es
o
f
th
e
C
SI
an
d
im
p
r
o
v
in
g
o
v
er
all
p
er
f
o
r
m
an
ce
.
T
h
is
is
d
u
e
to
th
e
s
p
ar
s
i
ty
o
f
m
ass
iv
e
MI
MO
c
h
an
n
els.
A
cu
ttin
g
-
ed
g
e
n
etwo
r
k
ca
lled
C
s
iNet
was
d
ev
elo
p
ed
to
tack
le
t
h
e
d
if
f
icu
lties
o
f
C
SI
co
m
p
r
ess
io
n
a
n
d
r
ec
o
n
s
tr
u
ctio
n
.
T
h
is
m
o
d
el
c
o
m
b
in
es
a
r
esid
u
al
c
o
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
with
a
f
u
lly
-
co
n
n
ec
te
d
n
e
u
r
al
n
etwo
r
k
(
FNN)
.
T
h
is
ap
p
r
o
ac
h
was
in
s
p
ir
ed
b
y
th
e
im
p
r
ess
iv
e
ac
co
m
p
lis
h
m
en
ts
o
f
th
e
r
esid
u
al
n
etwo
r
k
(
R
esNet)
in
th
e
f
ield
o
f
co
m
p
u
ter
v
is
io
n
.
T
h
e
C
s
iNet
s
h
o
wca
s
ed
ex
ce
p
tio
n
al
p
er
f
o
r
m
a
n
ce
wh
en
co
m
p
ar
ed
to
v
ar
io
u
s
co
n
v
en
tio
n
al
tech
n
iq
u
es,
s
u
ch
as
[
1
3
]
-
[
1
5
]
,
in
ter
m
s
o
f
b
o
th
alg
o
r
ith
m
s
r
u
n
n
in
g
tim
e
an
d
C
SI
r
ec
o
n
s
tr
u
ctio
n
ac
cu
r
ac
y
.
Var
io
u
s
m
et
h
o
d
s
a
r
e
in
v
esti
g
ated
t
o
im
p
r
o
v
e
th
e
ef
f
ec
tiv
en
ess
o
f
lar
g
e
-
s
ca
le
M
I
MO
C
SI
f
ee
d
b
ac
k
with
th
e
h
elp
o
f
C
s
iNet.
T
h
e
p
r
im
ar
y
o
b
jecti
v
e
was
to
d
e
v
elo
p
v
ar
io
u
s
n
eu
r
al
n
etwo
r
k
s
th
at
en
h
an
ce
th
e
p
r
ec
is
io
n
o
f
C
SI
r
ec
o
n
s
tr
u
ct
io
n
an
d
ca
ter
to
p
r
ac
tical
r
e
q
u
ir
em
en
ts
.
I
n
p
r
ev
i
o
u
s
tim
es,
DL
tech
n
iq
u
es
co
m
m
o
n
l
y
r
eg
ar
d
ed
th
e
c
h
an
n
el
m
atr
ix
as
a
two
-
ch
an
n
el
i
m
ag
e.
C
o
m
p
r
ess
io
n
ca
n
b
e
v
i
ewe
d
as
in
tr
o
d
u
cin
g
n
o
is
e
to
th
e
im
ag
e
[
1
6
]
,
[
1
7
]
.
Dec
o
m
p
r
ess
io
n
ca
n
b
e
s
ee
n
as
a
m
eth
o
d
o
f
elim
in
atin
g
u
n
w
an
ted
n
o
is
e
in
o
r
d
er
to
im
p
r
o
v
e
clar
ity
.
Dee
p
co
n
v
o
lu
tio
n
al
n
etwo
r
k
s
h
av
e
d
em
o
n
s
tr
ated
im
p
r
ess
iv
e
ef
f
ec
tiv
en
ess
in
d
en
o
is
in
g
,
as
in
d
icate
d
b
y
th
eir
a
b
ilit
y
to
ex
t
r
ac
t
co
m
p
lex
p
atter
n
s
f
r
o
m
d
ata.
I
f
th
e
p
r
im
ar
y
o
b
jectiv
e
o
f
C
SI
f
ee
d
b
ac
k
is
to
im
p
r
o
v
e
r
ec
o
n
s
tr
u
ctio
n
s
p
ee
d
,
em
p
lo
y
i
n
g
a
d
ee
p
d
ec
o
d
er
n
e
two
r
k
m
ay
o
f
f
er
a
v
iab
le
s
o
lu
t
io
n
.
T
h
e
p
r
o
ce
s
s
o
f
r
ed
u
cin
g
C
SI
f
ee
d
b
ac
k
o
v
er
h
ea
d
in
v
o
lv
es
a
c
o
m
p
r
ess
io
n
a
n
d
d
ec
o
m
p
r
ess
i
o
n
p
r
o
ce
s
s
,
s
im
ilar
to
th
e
ad
d
itio
n
an
d
s
u
b
s
eq
u
e
n
t e
lim
in
atio
n
o
f
n
o
is
e
[
1
8
]
-
[
2
0
]
.
T
h
e
m
o
tiv
atio
n
f
o
r
th
e
r
esear
ch
in
to
ad
v
an
ce
d
C
SI
esti
m
at
io
n
m
eth
o
d
o
l
o
g
ies
s
tem
s
f
r
o
m
th
e
cr
itical
r
o
le
th
at
C
SI
p
lay
s
in
th
e
o
p
tim
izatio
n
o
f
m
ass
iv
e
MI
MO
s
y
s
tem
s
,
wh
ich
ar
e
f
o
u
n
d
atio
n
al
to
th
e
cu
r
r
en
t
an
d
f
u
tu
r
e
g
en
e
r
atio
n
s
o
f
wir
eless
co
m
m
u
n
icatio
n
n
etwo
r
k
s
,
p
ar
t
icu
lar
ly
5
G
an
d
b
ey
o
n
d
.
Acc
u
r
ate
C
SI
i
s
p
iv
o
tal
f
o
r
ef
f
ec
tiv
e
b
ea
m
f
o
r
m
in
g
a
n
d
th
r
o
u
g
h
p
u
t
m
ax
im
izatio
n
in
s
u
ch
s
y
s
tem
s
.
T
h
e
ch
allen
g
es
in
ac
q
u
ir
in
g
r
eliab
le
C
SI
in
f
r
eq
u
en
cy
d
iv
is
io
n
d
u
p
le
x
in
g
(
FDD)
s
y
s
tem
s
,
d
u
e
to
th
e
lack
o
f
c
h
an
n
el
r
ec
i
p
r
o
city
,
n
ec
ess
itate
in
n
o
v
ativ
e
ap
p
r
o
a
ch
es
to
r
ed
u
ce
f
ee
d
b
ac
k
s
ig
n
a
lin
g
o
v
er
h
ea
d
with
o
u
t
co
m
p
r
o
m
is
in
g
th
e
q
u
ality
o
f
in
f
o
r
m
atio
n
.
DL
p
r
esen
ts
a
p
r
o
m
is
in
g
f
r
o
n
tier
in
th
is
r
eg
a
r
d
,
p
r
o
v
en
in
o
th
er
f
ield
s
s
u
ch
as c
o
m
p
u
ter
v
is
io
n
f
o
r
its
s
u
p
er
i
o
r
p
atter
n
r
ec
o
g
n
itio
n
an
d
f
ea
t
u
r
e
e
x
tr
ac
tio
n
ca
p
ab
ilit
ies.
B
y
ap
p
l
y
in
g
DL
to
th
e
d
esig
n
o
f
ef
f
icien
t
C
SI
co
m
p
r
ess
io
n
an
d
r
ec
o
n
s
tr
u
ctio
n
,
th
e
r
e
is
p
o
ten
tial
to
s
ig
n
if
ican
tly
en
h
an
ce
SE
an
d
s
y
s
tem
pe
r
f
o
r
m
an
ce
.
T
h
e
m
o
tiv
atio
n
is
f
u
r
th
er
am
p
lifie
d
b
y
th
e
li
m
itatio
n
s
o
f
tr
ad
itio
n
al
f
ee
d
b
a
ck
m
eth
o
d
s
a
n
d
th
e
d
em
o
n
s
tr
ated
s
u
p
e
r
io
r
ity
o
f
D
L
-
b
ased
m
o
d
els
in
ex
p
lo
itin
g
th
e
in
h
er
en
t
s
p
a
r
s
ity
o
f
m
ass
iv
e
MI
MO
ch
an
n
els
f
o
r
im
p
r
o
v
ed
C
SI
r
ec
o
n
s
tr
u
ctio
n
.
T
h
is
r
esear
c
h
aim
s
to
b
u
ild
u
p
o
n
th
ese
ad
v
an
ce
m
en
ts
,
p
r
o
p
o
s
in
g
a
m
eth
o
d
o
l
o
g
y
th
at
n
o
t
o
n
ly
co
n
tr
ib
u
tes
to
th
e
th
e
o
r
etica
l
u
n
d
er
s
tan
d
in
g
o
f
C
SI
m
an
ag
e
m
e
n
t
b
u
t
also
p
r
o
v
id
es
p
r
ac
tical
s
o
lu
tio
n
s
to
m
ee
t th
e
d
em
an
d
s
o
f
r
ap
id
l
y
ev
o
l
v
in
g
wir
eless
n
etwo
r
k
s
.
−
Dev
elo
p
m
en
t
o
f
a
d
ee
p
lear
n
in
g
-
b
ased
s
p
atial
d
ela
y
f
ea
tu
r
e
awa
r
e
en
co
d
e
r
d
ec
o
d
er
m
o
d
u
le
(
SDFEFD)
f
o
r
im
p
r
o
v
e
d
C
SI
f
ee
d
b
ac
k
in
Ma
s
s
iv
e
MI
MO
s
y
s
tem
s
.
−
I
n
teg
r
atio
n
o
f
s
p
atial
d
elay
f
ea
tu
r
e
e
x
tr
ac
tio
n
with
p
ar
a
m
eter
tu
n
in
g
o
p
tim
izatio
n
,
e
n
h
an
cin
g
C
SI
p
r
o
ce
s
s
in
g
ef
f
icien
c
y
.
−
C
o
m
p
r
eh
en
s
iv
e
p
er
f
o
r
m
an
ce
ev
alu
atio
n
u
s
in
g
th
e
C
OST
2
1
0
0
d
ataset,
d
e
m
o
n
s
tr
ati
n
g
SDFEFD's
s
u
p
er
io
r
ity
in
r
ed
u
ci
n
g
No
r
m
a
lized
Me
an
Sq
u
ar
e
d
E
r
r
o
r
co
m
p
ar
ed
to
ex
is
tin
g
m
eth
o
d
s
.
−
I
llu
s
tr
atio
n
o
f
SDFEFD's
p
o
ten
tial
in
o
p
tim
izin
g
wir
eless
n
e
two
r
k
p
e
r
f
o
r
m
an
ce
,
p
ar
ticu
l
a
r
ly
in
m
ass
iv
e
MI
MO
s
ce
n
ar
io
s
.
T
h
e
r
esear
ch
in
th
is
p
ap
er
is
o
r
g
an
ized
in
4
s
ec
tio
n
s
:
th
e
s
ec
tio
n
1
in
tr
o
d
u
ce
s
in
v
esti
g
ates
C
SI
ee
d
b
ac
k
m
ec
h
a
n
is
m
s
in
m
ass
iv
e
MI
MO
s
y
s
tem
s
,
f
o
cu
s
in
g
o
n
en
h
an
cin
g
d
o
wn
lin
k
C
SI
co
m
p
r
ess
io
n
an
d
f
ee
d
b
ac
k
f
o
r
5
G
an
d
b
ey
o
n
d
.
T
h
e
s
ec
tio
n
2
i
n
tr
o
d
u
ce
s
a
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
as
a
n
o
v
el
d
ee
p
lear
n
in
g
-
b
ased
ap
p
r
o
ac
h
.
T
h
e
s
ec
tio
n
3
ev
alu
ates
th
e
r
esu
lts
in
t
h
e
f
o
r
m
o
f
g
r
ap
h
s
a
n
d
tab
les,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
is
co
m
p
ar
ed
with
s
tate
-
of
-
ar
t
tech
n
iq
u
es
v
alid
ate
d
u
s
in
g
th
e
C
OST
2
1
0
0
ch
a
n
n
el
d
a
taset
an
d
3
GPP
s
p
ec
if
icatio
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.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
8
6
2
-
1
8
6
9
1864
2.
M
E
T
H
O
D
2
.
1
.
P
re
li
m
ina
ry
a
na
l
y
s
is
T
h
e
p
r
elim
in
ar
y
in
clu
d
in
g
d
o
wn
lin
k
C
SI
(
J
f
)
,
u
p
li
n
k
C
SI
(
J
w
)
,
th
e
n
u
m
b
er
o
f
alg
o
r
ith
m
iter
atio
n
s
(
V
)
,
an
d
th
e
n
u
m
b
e
r
o
f
f
ilter
s
in
co
n
v
o
lu
tio
n
al
lay
e
r
s
(
h
p
)
,
s
u
g
g
e
s
ts
a
co
m
p
r
eh
en
s
iv
e
a
p
p
r
o
ac
h
to
ad
d
r
ess
th
e
in
tr
icac
ies
o
f
C
SI
m
an
ag
e
m
e
n
t
in
wir
eless
co
m
m
u
n
icatio
n
s
y
s
tem
s
.
B
y
s
p
ec
if
y
in
g
th
e
s
p
atial
-
d
elay
d
o
m
ain
f
o
r
b
o
th
d
o
wn
lin
k
an
d
u
p
lin
k
C
SI,
th
e
m
eth
o
d
o
lo
g
y
em
p
h
asizes
th
e
s
ig
n
if
ican
ce
o
f
ca
p
tu
r
in
g
s
p
atio
tem
p
o
r
al
ch
ar
ac
ter
is
tics
f
o
r
m
o
r
e
ac
cu
r
ate
tr
an
s
m
is
s
io
n
.
T
h
e
in
clu
s
io
n
o
f
th
e
n
u
m
b
e
r
o
f
iter
atio
n
s
(
V
)
an
d
f
ilter
s
(
h
p
)
u
n
d
er
s
co
r
es
t
h
e
iter
ativ
e
a
n
d
DL
asp
ec
ts
o
f
th
e
alg
o
r
ith
m
,
i
n
d
icatin
g
a
co
m
m
itm
e
n
t
to
e
n
h
an
cin
g
th
e
q
u
ality
o
f
C
SI
r
ec
o
v
er
y
.
O
v
er
all,
th
i
s
p
r
elim
in
ar
y
an
aly
s
is
s
u
g
g
e
s
ts
th
at
th
e
m
eth
o
d
o
lo
g
y
is
p
o
is
ed
to
lev
er
ag
e
ad
v
an
ce
d
tech
n
iq
u
es to
o
p
tim
i
ze
C
SI
h
an
d
lin
g
in
co
m
p
le
x
c
o
m
m
u
n
icatio
n
en
v
ir
o
n
m
e
n
ts
.
2
.
2
.
Sy
s
t
e
m
mo
del a
nd
pro
blem
f
o
r
m
ula
t
io
n
I
n
th
is
s
ec
tio
n
,
th
e
m
eth
o
d
o
lo
g
y
b
e
g
in
s
b
y
in
tr
o
d
u
cin
g
a
s
in
g
le
-
ce
ll
d
o
wn
lin
k
m
ass
iv
e
MI
MO
s
y
s
tem
,
f
ea
tu
r
in
g
P
̃
h
tr
an
s
m
it
an
ten
n
as
at
th
e
BS
an
d
o
n
e
a
n
ten
n
a
at
th
e
UE
,
o
p
er
atin
g
o
v
er
P
v
s
u
b
ca
r
r
ier
s
.
T
h
e
r
ec
eiv
ed
s
ig
n
als,
in
clu
d
in
g
ch
an
n
el
v
ec
to
r
s
,
p
r
ec
o
d
in
g
v
ec
to
r
s
,
d
ata
-
b
ea
r
in
g
s
y
m
b
o
ls
,
an
d
ad
d
itiv
e
n
o
is
e,
ar
e
d
escr
ib
e
d
.
T
h
e
u
s
e
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
to
tr
an
s
f
o
r
m
ch
a
n
n
el
m
atr
ices
in
to
th
e
d
elay
d
o
m
ain
is
h
ig
h
lig
h
ted
,
lead
in
g
to
tr
u
n
ca
ted
m
atr
ices
f
o
r
e
f
f
icien
t
p
r
o
ce
s
s
in
g
.
T
h
e
m
eth
o
d
o
lo
g
y
al
s
o
em
p
h
asizes
th
e
n
ee
d
f
o
r
d
im
e
n
s
io
n
ality
r
ed
u
c
tio
n
d
u
e
t
o
m
as
s
iv
e
MI
MO
s
y
s
tem
s
,
wh
ich
is
ac
h
iev
ed
th
r
o
u
g
h
lin
ea
r
s
en
s
in
g
.
T
h
e
u
ltima
te
g
o
al
is
to
r
ec
o
v
er
d
o
wn
lin
k
C
SI
wh
ile
co
n
s
id
er
in
g
th
e
s
p
ar
s
ity
in
t
h
e
d
elay
d
o
m
ain
a
n
d
ex
p
lo
itin
g
a
u
x
iliar
y
u
p
lin
k
C
SI
to
en
h
a
n
ce
ac
cu
r
ac
y
.
2
.
3
.
P
r
o
po
s
ed
s
pa
t
ia
l dela
y
o
ptim
ized
en
co
der
deco
der
-
ba
s
ed
net
wo
rk
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
co
r
e
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
,
a
Sh
r
i
n
k
ag
e
Alg
o
r
ith
m
f
o
r
C
SI
r
ec
o
v
er
y
.
T
h
e
n
etwo
r
k
ar
ch
ite
ctu
r
e
co
m
p
r
is
es
a
co
m
p
r
ess
io
n
m
o
d
u
le
an
d
a
r
ec
o
n
s
tr
u
ctio
n
m
o
d
u
le,
with
th
e
latter
co
n
s
is
tin
g
o
f
m
u
ltip
le
iter
atio
n
s
(
V
)
.
E
ac
h
iter
atio
n
in
v
o
lv
es
Au
to
-
e
n
co
d
e
r
s
,
an
d
s
p
atial
d
elay
co
n
s
tr
ain
ts
f
o
r
u
p
lin
k
a
n
d
d
o
wn
lin
k
C
SI.
A
p
iv
o
tal
co
m
p
o
n
e
n
t
is
th
e
s
p
atial
d
elay
o
p
tim
ized
E
n
co
d
e
r
Dec
o
d
er
,
d
esig
n
ed
to
lear
n
s
p
atial
d
elay
an
d
in
v
er
s
e
tr
an
s
f
o
r
m
s
f
o
r
b
o
th
u
p
lin
k
an
d
d
o
w
n
lin
k
C
SI.
T
h
e
I
n
f
o
m
o
d
u
le
c
o
m
p
lem
en
ts
th
is
b
y
m
ap
p
in
g
s
p
atial
d
elay
r
ep
r
esen
tatio
n
s
o
f
u
p
lin
k
C
SI
to
m
i
n
im
izatio
n
,
f
u
r
th
er
im
p
r
o
v
in
g
r
ec
o
v
er
y
ac
c
u
r
ac
y
.
C
o
n
v
o
lu
tio
n
al
lay
er
s
an
d
r
ec
t
if
ied
lin
ea
r
u
n
its
(
R
eL
U)
ar
e
d
ep
lo
y
ed
with
in
th
e
in
teg
r
ated
s
p
atial
d
elay
o
p
tim
ized
E
n
c
o
d
er
Dec
o
d
e
r
to
ex
tr
ac
t
ess
en
tial
v
alu
es
f
r
o
m
t
r
an
s
f
o
r
m
ed
C
SIs.
T
h
e
m
eth
o
d
o
l
o
g
y
o
f
t
h
is
r
esear
ch
p
r
o
v
id
es
a
co
m
p
r
eh
e
n
s
iv
e
a
p
p
r
o
ac
h
to
c
o
m
p
r
ess
in
g
an
d
r
ec
o
v
er
in
g
C
SI
in
m
ass
iv
e
MI
MO
s
y
s
tem
s
,
em
p
h
asizin
g
s
p
atial
d
elay
f
ea
tu
r
es,
an
d
lev
er
a
g
in
g
a
d
v
a
n
ce
d
n
eu
r
al
n
etwo
r
k
co
m
p
o
n
en
ts
f
o
r
e
n
h
an
ce
d
ac
c
u
r
ac
y
.
Fig
u
r
e
1
s
h
o
ws
th
e
p
r
o
p
o
s
ed
s
p
atial
d
elay
o
p
tim
ize
d
en
c
o
d
er
d
ec
o
d
er
-
b
ased
n
etwo
r
k
.
Alg
o
r
ith
m
1
s
h
o
ws th
e
p
r
o
p
o
s
ed
ar
c
h
itectu
r
e.
Fig
u
r
e
1.
Pro
p
o
s
ed
s
p
atial
d
el
ay
o
p
tim
ized
e
n
co
d
e
r
d
ec
o
d
er
b
ased
n
etwo
r
k
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
A
n
o
ve
l d
ee
p
lea
r
n
in
g
b
a
s
ed
s
p
a
tia
l d
ela
y
fe
a
tu
r
e
a
w
a
r
e
en
c
o
d
er d
ec
o
d
er
… (
P
a
r
in
ith
a
Ja
ya
s
h
a
n
ka
r
)
1865
2
.
4
.
Alg
o
rit
hm
T
h
e
alg
o
r
ith
m
is
an
ad
v
a
n
c
ed
p
r
o
ce
d
u
r
e
f
o
r
r
ec
o
n
s
tr
u
ct
in
g
d
o
wn
lin
k
C
SI
in
th
e
s
p
atial
-
d
elay
d
o
m
ain
f
o
r
m
ass
iv
e
MI
MO
s
y
s
tem
s
.
I
n
itially
,
it
tak
es
in
t
h
e
C
SI
f
o
r
b
o
th
d
o
w
n
lin
k
a
n
d
u
p
lin
k
,
a
n
d
o
th
er
p
ar
am
eter
s
lik
e
th
e
n
u
m
b
er
o
f
iter
atio
n
s
an
d
co
n
v
o
lu
tio
n
al
f
ilter
s
.
T
h
e
p
r
o
ce
s
s
b
eg
in
s
with
th
e
v
ec
t
o
r
izatio
n
o
f
d
o
wn
lin
k
C
SI,
f
o
l
lo
wed
b
y
its
co
m
p
r
ess
io
n
u
s
in
g
a
f
u
lly
co
n
n
ec
ted
lay
er
to
r
ed
u
ce
d
im
en
s
io
n
ality
.
I
t
th
en
em
b
ar
k
s
o
n
an
iter
ativ
e
r
ec
o
n
s
tr
u
ctio
n
p
h
ase,
wh
er
e
in
ea
c
h
iter
atio
n
,
th
e
alg
o
r
ith
m
u
p
d
ates
an
in
ter
m
ed
iar
y
v
ar
iab
le
th
r
o
u
g
h
a
f
o
r
m
u
la
th
at
r
ef
in
es
th
e
p
r
e
v
io
u
s
C
SI
e
s
tim
ate
b
y
i
n
co
r
p
o
r
atin
g
th
e
c
o
m
p
r
ess
ed
v
e
r
s
io
n
an
d
ap
p
ly
i
n
g
a
co
r
r
ec
tio
n
f
ac
to
r
.
T
h
is
is
f
o
llo
wed
b
y
a
in
t
eg
r
ated
s
p
atial
d
elay
f
ea
tu
r
e
o
p
tim
ized
E
n
co
d
er
Dec
o
d
er
th
at
lear
n
s
th
e
s
p
at
ial
d
elay
f
ea
tu
r
e
f
ea
tu
r
es
an
d
in
v
er
s
es
th
em
f
o
r
r
ec
o
v
er
y
.
A
th
r
esh
o
ld
i
n
g
o
p
er
atio
n
is
ap
p
lied
t
o
elim
in
ate
in
s
ig
n
if
ican
t
f
ea
tu
r
es,
an
d
th
e
in
v
er
s
e
tr
an
s
f
o
r
m
r
ec
o
n
s
t
r
u
cts
th
e
d
o
wn
lin
k
C
SI.
T
h
is
cy
cle
r
ep
ea
ts
f
o
r
a
s
et
n
u
m
b
er
o
f
iter
atio
n
s
.
C
o
n
cu
r
r
en
tly
,
a
n
in
f
o
r
m
atio
n
m
o
d
u
le
u
s
es
u
p
lin
k
C
SI
to
ad
ju
s
t
th
e
weig
h
ts
in
th
e
r
ec
o
n
s
tr
u
ctio
n
,
e
n
h
an
ci
n
g
a
cc
u
r
ac
y
.
T
h
e
f
in
al
o
u
t
p
u
t
is
th
e
m
eticu
lo
u
s
ly
r
ec
o
n
s
tr
u
cted
d
o
wn
lin
k
C
SI,
ex
p
ec
ted
to
s
ig
n
if
ican
tly
im
p
r
o
v
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
wir
el
ess
co
m
m
u
n
icatio
n
n
etwo
r
k
s
.
Alg
o
r
ith
m
1
s
h
o
ws
th
e
p
r
o
p
o
s
ed
ar
c
h
itectu
r
e.
Alg
o
r
ith
m
1
.
Pro
p
o
s
ed
ar
ch
ite
ct
u
r
e
Input:
Downlink CSI in spatial
-
delay domain
J
f
Uplink CSI in spatial
-
delay domain
J
w
Number of iterations for the algorithm,
V
Number of filters in convolutional layers,
h
p
Step 1:
Vectorize Downlink CSI:
−
Convert
J
f
into vectorized form
j
f
Step 2:
Compression Module:
−
Compress
j
f
to
u
using a fully connected (FC) layer, denoted as
i
(
.
)
Step 3:
Initialization:
−
Initialize iterative variables
j
v
−
1
f
and
t
v
Step 4:
Iterative Reconstruction (
v
Iterations):
−
For t from 1 to
v
do:
−
Update
t
v
using the formula:
t
v
=
j
v
−
1
f
+
ϑ
v
Y
(
u
−
i
(
j
v
−
1
f
)
)
−
Apply the integrated spatial delay optimized Encoder Decoder to learn the
spatial delay feature/inverse transform for
t
v
, yielding
h
2
(
t
v
)
Apply the soft thresholding function:
h
2
(
j
v
f
)
=
so
f
t
(
h
2
(
t
v
)
,
θ
y
)
−
Apply the inverse transform to
h
2
(
j
v
f
)
to obtain
j
v
f
Step 5
:
Info Module for Support Information:
−
For each iteration, obtain the support information of the transformed uplink CSI
(
ui
n
v
e
c
)
−
Map
ui
n
v
e
c
to weights
y
using two convolutional layers and a ReLU
Step 7:
Final Output:
The output after the
v
-
th iteration,
j
v
f
, is the reconstructed downlink CSI
J
w
Output:
Reconstructed downlink CSI
J
w
T
h
e
o
u
tp
u
t
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
l
o
g
y
,
b
ased
o
n
th
e
p
r
o
v
id
ed
elem
e
n
ts
o
f
d
o
wn
lin
k
C
SI
(
J
f
)
,
u
p
lin
k
C
SI
,
th
e
n
u
m
b
e
r
o
f
ite
r
atio
n
s
f
o
r
th
e
alg
o
r
ith
m
(
V
)
,
a
n
d
th
e
n
u
m
b
er
o
f
f
ilter
s
in
co
n
v
o
lu
tio
n
al
lay
er
s
(
h
p
)
,
is
ex
p
ec
ted
t
o
b
e
a
h
ig
h
ly
r
ef
in
ed
a
n
d
r
ec
o
n
s
tr
u
cted
C
SI
d
ataset.
T
h
r
o
u
g
h
th
e
alg
o
r
ith
m
'
s
iter
ativ
e
an
d
DL
p
r
o
ce
s
s
es,
it
aim
s
to
co
m
p
r
ess
an
d
r
ec
o
v
er
t
h
e
s
p
atial
-
d
elay
d
o
m
ain
C
SI
with
im
p
r
o
v
ed
ac
cu
r
ac
y
.
T
h
e
f
in
al
o
u
tp
u
t,
r
ep
r
esen
te
d
b
y
th
e
r
ec
o
n
s
tr
u
cted
C
SI,
h
o
ld
s
th
e
p
o
ten
tial
t
o
en
h
an
ce
th
e
p
er
f
o
r
m
a
n
ce
an
d
ef
f
icien
cy
o
f
m
ass
iv
e
MI
MO
s
y
s
tem
s
in
wir
eless
co
m
m
u
n
icatio
n
,
u
ltima
tely
co
n
tr
i
b
u
tin
g
to
m
o
r
e
r
eliab
le
an
d
r
eso
u
r
ce
-
ef
f
icien
t
d
ata
tr
a
n
s
m
is
s
io
n
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
ev
alu
atio
n
o
f
v
ar
io
u
s
m
o
d
els
f
o
r
C
SI
esti
m
atio
n
,
as
p
r
esen
ted
in
th
e
tab
les,
r
ev
ea
ls
a
co
n
s
is
ten
t
tr
en
d
o
f
im
p
r
o
v
em
e
n
t in
p
er
f
o
r
m
an
ce
ac
r
o
s
s
d
if
f
er
en
t e
n
v
i
r
o
n
m
en
ts
.
Star
tin
g
with
C
s
iNet,
wh
ich
co
n
s
is
ten
tly
s
h
o
ws
th
e
least
ef
f
ec
tiv
en
ess
in
b
o
th
i
n
d
o
o
r
an
d
o
u
td
o
o
r
s
ettin
g
s
ac
r
o
s
s
th
e
tab
les,
t
h
er
e
is
a
n
o
tab
le
p
r
o
g
r
ess
io
n
in
th
e
p
er
f
o
r
m
an
ce
o
f
s
u
b
s
eq
u
en
t
m
o
d
els.
C
R
Net
an
d
C
L
Net
d
em
o
n
s
tr
ate
s
lig
h
t
im
p
r
o
v
e
m
en
ts
o
v
er
C
s
iNet,
with
m
ar
g
in
ally
b
etter
s
co
r
es in
b
o
th
en
v
ir
o
n
m
en
ts
.
DC
R
Net,
T
r
an
s
Net,
an
d
STNe
t e
ac
h
p
r
esen
t
f
u
r
th
er
en
h
an
ce
m
en
ts
,
p
ar
ticu
l
a
r
ly
in
in
d
o
o
r
s
ettin
g
s
,
in
d
icatin
g
th
eir
im
p
r
o
v
e
d
ca
p
ab
ilit
y
in
m
o
r
e
c
o
n
tr
o
lle
d
en
v
ir
o
n
m
en
ts
.
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.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
8
6
2
-
1
8
6
9
1866
3
.
1
.
Da
t
a
s
et
det
a
ils
T
h
is
s
ec
tio
n
p
r
o
v
id
es
co
m
p
r
eh
en
s
iv
e
d
etails
ab
o
u
t
th
e
C
o
s
t
2
1
0
0
[
2
1
]
d
atab
ase.
T
h
e
C
OST
(
E
u
r
o
p
ea
n
C
o
o
p
er
atio
n
in
Sci
en
ce
an
d
T
ec
h
n
o
lo
g
y
)
2
1
0
0
c
h
an
n
el
m
o
d
el
is
a
g
eo
m
etr
ic
s
to
ch
asti
c
ch
an
n
el
m
o
d
el
(
GSC
M)
d
esig
n
ed
t
o
r
e
p
licate
th
e
s
to
ch
asti
c
ch
ar
ac
ter
is
tics
o
f
MI
MO
ch
a
n
n
els
ac
r
o
s
s
tim
e,
f
r
eq
u
e
n
cy
,
an
d
s
p
ac
e
d
im
en
s
io
n
s
.
I
t
ch
ar
ac
ter
izes
a
m
u
ltip
ath
c
o
m
p
o
n
en
t
(
MPC
)
in
ter
m
s
o
f
d
elay
an
d
b
o
th
d
ep
a
r
tu
r
e
an
d
a
r
r
iv
al
a
n
g
les
(
s
p
ec
if
icall
y
,
az
im
u
t
h
o
f
d
ep
ar
tu
r
e
(
Ao
D)
,
elev
atio
n
o
f
d
e
p
ar
tu
r
e
(
E
o
D)
,
az
im
u
th
o
f
ar
r
iv
al
(
Ao
A)
,
a
n
d
ele
v
atio
n
o
f
ar
r
i
v
al
(
E
o
A)
)
.
T
h
e
MA
T
L
AB
i
m
p
lem
en
tatio
n
o
f
th
e
co
s
t
2
1
0
0
ch
an
n
el
m
o
d
el
(
C
2
C
M)
ac
co
m
m
o
d
ates
b
o
th
s
in
g
le
an
d
m
u
ltip
le
MI
MO
ch
an
n
el
lin
k
s
.
I
t
i
s
a
p
p
l
i
c
a
b
l
e
i
n
v
a
r
i
o
u
s
c
h
a
n
n
e
l
s
c
e
n
a
r
i
o
s
,
i
n
cl
u
d
i
n
g
i
n
d
o
o
r
e
n
v
i
r
o
n
m
e
n
t
s
a
t
2
8
5
M
H
z
a
n
d
s
e
m
i
-
u
r
b
a
n
e
n
v
i
r
o
n
m
e
n
t
s
at
5
.
3
G
H
z
.
T
h
e
d
a
t
as
et
e
n
c
o
m
p
a
s
s
es
i
n
f
o
r
m
a
t
i
o
n
f
r
o
m
t
w
o
d
is
ti
n
c
t
e
n
v
i
r
o
n
m
e
n
t
s
:
a
n
i
n
d
o
o
r
c
e
ll
u
l
a
r
e
n
v
i
r
o
n
m
e
n
t
a
n
d
a
n
o
u
t
d
o
o
r
c
e
l
l
u
l
a
r
e
n
v
i
r
o
n
m
e
n
t
.
T
h
e
i
n
d
o
o
r
e
n
v
i
r
o
n
m
e
n
t
d
a
t
a
i
s
c
o
l
l
e
ct
e
d
a
t
a
f
r
e
q
u
e
n
c
y
o
f
5
.
3
G
H
z,
w
h
i
l
e
t
h
e
o
u
t
d
o
o
r
e
n
v
i
r
o
n
m
e
n
t
d
a
t
a
i
s
g
at
h
e
r
e
d
a
t
a
h
i
g
h
e
r
f
r
e
q
u
e
n
c
y
o
f
3
0
0
G
H
z
.
3
.
2
.
Resul
t
s
I
n
Fig
u
r
e
2
an
d
T
ab
le
1
th
e
co
m
p
r
ess
io
n
r
atio
f
o
r
1
/4
is
ev
alu
ated
f
o
r
v
ar
i
o
u
s
m
o
d
el
s
f
o
r
C
SI
esti
m
atio
n
,
th
e
p
er
f
o
r
m
an
ce
is
q
u
an
tifie
d
b
y
v
alu
es
in
b
o
th
i
n
d
o
o
r
an
d
o
u
td
o
o
r
s
ettin
g
s
.
C
s
iNet,
wi
th
-
1
7
.
3
6
in
d
o
o
r
a
n
d
-
8
.
7
5
o
u
td
o
o
r
,
is
th
e
least
ef
f
ec
tiv
e.
I
n
th
e
ev
al
u
atio
n
o
f
v
a
r
io
u
s
m
o
d
els
f
o
r
C
SI
est
im
atio
n
,
th
e
p
er
f
o
r
m
an
ce
is
q
u
an
tifie
d
b
y
v
alu
es in
b
o
th
in
d
o
o
r
an
d
o
u
td
o
o
r
s
ettin
g
s
.
C
s
iNet,
with
-
1
7
.
3
6
in
d
o
o
r
an
d
-
8
.
7
5
o
u
td
o
o
r
,
is
th
e
least
ef
f
ec
tiv
e
.
T
h
e
p
er
f
o
r
m
a
n
ce
p
r
o
g
r
ess
iv
ely
im
p
r
o
v
es
with
C
R
Net
(
-
2
6
.
9
9
in
d
o
o
r
,
-
1
2
.
7
out
d
o
o
r
)
,
C
L
Net
(
-
2
9
.
1
6
in
d
o
o
r
,
-
1
2
.
0
9
o
u
td
o
o
r
)
,
DC
R
Net
(
-
3
0
.
6
1
i
n
d
o
o
r
,
-
1
3
.
7
2
o
u
td
o
o
r
)
,
a
n
d
f
u
r
th
e
r
with
T
r
an
s
Net
(
-
3
2
.
3
8
in
d
o
o
r
,
-
1
4
.
8
6
o
u
td
o
o
r
)
a
n
d
STNe
t
(
-
3
1
.
8
1
in
d
o
o
r
,
-
1
2
.
9
1
o
u
td
o
o
r
)
.
E
S
s
h
o
ws
a
s
ig
n
if
ican
t
im
p
r
o
v
em
e
n
t
in
o
u
td
o
o
r
s
ettin
g
s
(
-
1
6
.
3
5
)
co
m
p
a
r
ed
t
o
its
in
d
o
o
r
p
er
f
o
r
m
an
ce
(
-
3
2
.
6
1
)
.
T
h
e
Pro
p
o
s
ed
Mo
d
el
o
u
ts
h
in
es
all
with
th
e
m
o
s
t
ef
f
ec
tiv
e
p
er
f
o
r
m
a
n
ce
,
s
co
r
in
g
-
3
5
.
9
4
in
d
o
o
r
a
n
d
-
1
9
.
8
7
o
u
t
d
o
o
r
,
in
d
icatin
g
its
s
u
p
er
io
r
m
eth
o
d
o
l
o
g
y
i
n
C
SI
esti
m
atio
n
u
n
d
er
b
o
th
e
n
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
.
Fig
u
r
e
2.
C
SI
R
ec
o
n
s
tr
u
ctio
n
r
esu
lts
f
o
r
co
m
p
r
ess
io
n
r
atio
¼
f
r
o
m
0
to
-
40
T
ab
le
1.
C
R
r
esu
lts
f
o
r
¼
CR
C
l
a
s
si
c
a
l
C
S
I
met
h
o
d
s
I
n
d
o
o
r
O
u
t
d
o
o
r
C
si
N
e
t
[
1
9
]
-
1
7
.
3
6
-
8
.
7
5
C
R
N
e
t
[
2
0
]
-
2
6
.
9
9
-
1
2
.
7
C
LN
e
t
[
2
1
]
-
2
9
.
1
6
-
1
2
.
0
9
D
C
R
N
e
t
[
2
2
]
-
3
0
.
6
1
-
1
3
.
7
2
1
/
4
Tr
a
n
sN
e
t
[
2
3
]
-
3
2
.
3
8
-
1
4
.
8
6
S
TN
e
t
[
2
4
]
-
3
1
.
8
1
-
1
2
.
9
1
ES [
2
5
]
-
3
2
.
6
1
-
1
6
.
3
5
Pr
o
p
o
sed
M
o
d
e
l
-
3
5
.
9
4
-
1
9
.
8
7
I
n
Fig
u
r
e
3
an
d
T
ab
le
2
th
e
co
m
p
r
ess
io
n
r
atio
f
o
r
1
/8
is
ev
alu
ated
f
o
r
v
ar
i
o
u
s
m
o
d
el
s
f
o
r
C
SI
esti
m
atio
n
,
th
e
p
er
f
o
r
m
an
ce
is
q
u
an
tifie
d
b
y
v
alu
es
in
b
o
th
i
n
d
o
o
r
an
d
o
u
td
o
o
r
s
ettin
g
s
.
C
s
iNet,
wi
th
-
1
7
.
3
6
in
d
o
o
r
an
d
-
8
.
7
5
o
u
t
d
o
o
r
,
is
th
e
least
ef
f
ec
tiv
e.
T
h
e
p
r
o
v
i
d
ed
tab
le
co
m
p
a
r
es
th
e
p
er
f
o
r
m
an
ce
o
f
v
ar
io
u
s
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
A
n
o
ve
l d
ee
p
lea
r
n
in
g
b
a
s
ed
s
p
a
tia
l d
ela
y
fe
a
tu
r
e
a
w
a
r
e
en
c
o
d
er d
ec
o
d
er
… (
P
a
r
in
ith
a
Ja
ya
s
h
a
n
ka
r
)
1867
m
o
d
els
in
C
SI
esti
m
atio
n
f
o
r
in
d
o
o
r
an
d
o
u
t
d
o
o
r
en
v
ir
o
n
m
en
ts
.
T
h
e
m
o
d
els
a
r
e
C
R
Net,
C
L
Net,
DC
R
Net
,
T
r
an
s
Net,
STNe
t,
E
S,
an
d
a
Pro
p
o
s
ed
Mo
d
el.
C
R
Net
an
d
C
L
Net
s
h
o
w
m
o
d
er
ate
p
er
f
o
r
m
an
ce
with
C
R
Net
s
co
r
in
g
-
1
6
.
0
1
i
n
d
o
o
r
a
n
d
-
8
.
0
4
o
u
td
o
o
r
,
an
d
C
L
Net
with
-
1
5
.
6
in
d
o
o
r
an
d
-
8
.
2
9
o
u
td
o
o
r
.
DC
R
Net
m
ar
k
s
an
im
p
r
o
v
em
e
n
t,
esp
ec
ially
i
n
d
o
o
r
s
,
with
-
1
9
.
9
2
in
d
o
o
r
an
d
-
1
0
.
1
7
o
u
td
o
o
r
.
T
r
an
s
Net
an
d
STNe
t
s
h
o
w
f
u
r
th
e
r
en
h
an
ce
m
e
n
ts
,
with
T
r
an
s
Net
at
-
2
2
.
9
1
in
d
o
o
r
a
n
d
-
9
.
9
9
o
u
t
d
o
o
r
,
an
d
STNe
t
s
co
r
in
g
-
2
1
.
2
8
in
d
o
o
r
a
n
d
-
8
.
5
3
o
u
td
o
o
r
.
E
S
p
er
f
o
r
m
s
co
m
p
a
r
ab
ly
,
esp
ec
ially
well
o
u
td
o
o
r
s
(
-
1
1
.
0
4
)
,
with
-
2
2
.
1
3
in
d
o
o
r
.
T
h
e
Pro
p
o
s
ed
Mo
d
el
o
u
tp
er
f
o
r
m
s
all
o
th
er
s
,
s
co
r
in
g
-
2
5
.
3
6
in
d
o
o
r
an
d
-
1
4
.
7
8
o
u
t
d
o
o
r
,
in
d
icatin
g
its
s
u
p
er
io
r
ca
p
ab
ilit
y
i
n
C
SI
es
tim
atio
n
in
b
o
th
en
v
ir
o
n
m
en
ts
.
T
h
is
p
r
o
g
r
ess
io
n
f
r
o
m
C
R
Net
to
th
e
Pro
p
o
s
ed
Mo
d
el
r
ef
lects
co
n
tin
u
o
u
s
ad
v
an
ce
m
en
ts
in
t
h
e
f
ield
.
Fig
u
r
e
3.
C
SI
r
ec
o
n
s
tr
u
ctio
n
r
esu
lts
f
o
r
co
m
p
r
ess
io
n
r
ati
o
1
/
8
f
r
o
m
0
to
-
40
T
ab
le
2.
C
R
r
esu
lts
f
o
r
1
/8
CR
C
l
a
s
si
c
a
l
C
S
I
met
h
o
d
s
I
n
d
o
o
r
O
u
t
d
o
o
r
C
R
N
e
t
[
1
5
]
-
1
6
.
0
1
-
8
.
0
4
C
LN
e
t
[
1
6
]
-
1
5
.
6
-
8
.
2
9
D
C
R
N
e
t
[
1
8
]
-
1
9
.
9
2
-
1
0
.
1
7
1
/
8
Tr
a
n
sN
e
t
[
1
9
]
-
2
2
.
9
1
-
9
.
9
9
S
TN
e
t
[
2
0
]
-
2
1
.
2
8
-
8
.
5
3
ES [
2
1
]
-
2
2
.
1
3
-
1
1
.
0
4
Pr
o
p
o
sed
M
o
d
e
l
-
2
5
.
3
6
-
1
4
.
7
8
I
n
th
e
co
m
p
ar
is
o
n
o
f
v
ar
io
u
s
m
o
d
els
f
o
r
C
SI
esti
m
atio
n
,
th
e
tab
le
r
ef
lects
th
eir
p
er
f
o
r
m
a
n
ce
in
b
o
th
in
d
o
o
r
an
d
o
u
td
o
o
r
s
ettin
g
s
.
Star
tin
g
with
C
s
iNet
,
it
s
h
o
ws
t
h
e
least
ef
f
ec
tiv
e
n
ess
,
s
co
r
in
g
-
8
.
6
5
i
n
d
o
o
r
a
n
d
-
4
.
5
1
o
u
td
o
o
r
.
C
R
Net
an
d
C
L
Net
d
em
o
n
s
tr
ate
im
p
r
o
v
em
en
t
s
,
with
C
R
Ne
t
at
-
1
1
.
3
5
i
n
d
o
o
r
an
d
-
5
.
4
4
o
u
t
d
o
o
r
,
an
d
C
L
Net
s
lig
h
tly
b
eh
in
d
at
-
1
1
.
1
5
in
d
o
o
r
an
d
-
5
.
5
6
o
u
td
o
o
r
.
DC
R
Net
m
ar
k
s
a
s
ig
n
if
ican
t
en
h
a
n
ce
m
en
t
,
p
ar
ticu
lar
ly
in
d
o
o
r
s
,
s
co
r
i
n
g
-
1
4
.
0
2
in
d
o
o
r
a
n
d
-
6
.
3
5
o
u
t
d
o
o
r
.
T
r
an
s
Net
an
d
STNe
t
f
u
r
th
er
ad
v
an
ce
th
e
p
er
f
o
r
m
an
ce
,
with
T
r
an
s
Net
ac
h
iev
in
g
-
1
5
in
d
o
o
r
an
d
-
7
.
8
2
o
u
td
o
o
r
,
an
d
STNe
t
s
h
o
win
g
-
1
5
.
2
8
in
d
o
o
r
an
d
-
5
.
7
2
o
u
td
o
o
r
.
E
S
is
co
m
p
ar
a
b
le,
s
co
r
in
g
-
1
5
.
2
9
in
d
o
o
r
an
d
-
7
.
0
4
o
u
td
o
o
r
.
T
h
e
Pr
o
p
o
s
ed
Mo
d
el
o
u
ts
h
in
es
all,
lead
in
g
with
th
e
m
o
s
t
ef
f
ec
tiv
e
s
co
r
es
o
f
-
1
8
.
9
8
in
d
o
o
r
a
n
d
-
9
.
7
6
o
u
td
o
o
r
,
in
d
icatin
g
it
s
s
u
p
er
io
r
ab
ilit
y
in
C
SI
esti
m
atio
n
ac
r
o
s
s
b
o
th
en
v
ir
o
n
m
en
ts
.
T
h
is
p
r
o
g
r
e
s
s
io
n
in
d
icate
s
o
n
g
o
in
g
ad
v
an
ce
m
en
ts
in
C
SI
esti
m
atio
n
m
eth
o
d
o
lo
g
ies,
with
th
e
Pro
p
o
s
ed
Mo
d
el
at
t
h
e
f
o
r
ef
r
o
n
t.
4.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
ad
v
an
ce
s
th
e
f
i
eld
o
f
wir
eless
co
m
m
u
n
icatio
n
b
y
in
tr
o
d
u
cin
g
a
d
ee
p
lear
n
in
g
-
b
ased
s
p
atial
d
elay
f
ea
tu
r
e
awa
r
e
e
n
co
d
er
d
ec
o
d
er
m
o
d
u
le
(
SD
FEFD)
f
o
r
e
n
h
an
ce
d
C
SI
Fe
ed
b
ac
k
in
Ma
s
s
iv
e
MI
MO
s
y
s
tem
s
.
T
h
e
n
o
v
el
ap
p
r
o
ac
h
c
o
m
b
in
es
s
p
atial
d
elay
f
ea
tu
r
e
ex
t
r
ac
tio
n
with
p
ar
am
eter
tu
n
in
g
o
p
tim
izatio
n
,
im
p
r
o
v
in
g
C
SI
p
r
o
ce
s
s
in
g
in
u
p
lin
k
an
d
d
o
wn
lin
k
s
ce
n
ar
io
s
.
T
h
e
r
ese
ar
ch
d
em
o
n
s
tr
ates
SDFEFD
's
ef
f
ec
tiv
en
ess
t
h
r
o
u
g
h
r
ig
o
r
o
u
s
ev
alu
atio
n
u
s
in
g
th
e
C
OST
2
1
0
0
d
ataset,
w
h
er
e
it
s
ig
n
if
ican
tly
o
u
tp
er
f
o
r
m
s
ex
is
tin
g
m
eth
o
d
s
in
ter
m
s
o
f
No
r
m
alize
d
Me
an
Sq
u
ar
e
d
E
r
r
o
r
.
T
h
is
in
d
icate
s
its
p
o
ten
tial
to
r
ev
o
lu
tio
n
ize
C
SI
f
ee
d
b
ac
k
in
m
ass
iv
e
MI
MO
s
y
s
tem
s
,
m
ar
k
in
g
a
s
u
b
s
tan
tial
p
r
o
g
r
ess
io
n
in
th
e
o
p
tim
izatio
n
o
f
wir
eless
n
etwo
r
k
p
er
f
o
r
m
a
n
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.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
8
6
2
-
1
8
6
9
1868
ACK
NO
WL
E
DG
E
M
E
NT
We
wo
u
ld
lik
e
to
ex
p
r
ess
o
u
r
s
in
ce
r
e
g
r
atitu
d
e
to
all
th
o
s
e
wh
o
h
a
v
e
s
u
p
p
o
r
ted
an
d
co
n
tr
ib
u
ted
t
o
th
is
r
esear
ch
p
r
o
ject.
Prim
ar
il
y
,
we
ex
ten
d
o
u
r
h
ea
r
tf
elt
th
an
k
s
to
o
u
r
g
u
id
e
f
o
r
h
is
u
n
wav
er
in
g
g
u
id
an
ce
,
in
v
alu
ab
le
in
s
ig
h
ts
,
an
d
en
c
o
u
r
ag
em
e
n
t
th
r
o
u
g
h
o
u
t
th
e
r
esear
ch
p
r
o
ce
s
s
.
No
f
u
n
d
i
n
g
is
r
aised
f
o
r
th
is
r
esear
ch
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
No
f
u
n
d
in
g
is
r
aised
f
o
r
th
is
r
e
s
ea
r
ch
.
AUTHO
R
CO
NT
RI
B
UT
I
O
N
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Par
in
ith
a
J
ay
ash
an
k
ar
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
h
ig
alak
k
ap
p
a
R
an
g
aswam
y
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
B
y
r
ap
p
a
N.
Sh
o
b
h
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
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
Au
th
o
r
d
ec
la
r
es n
o
co
n
f
lict o
f
in
ter
est.
DATA AV
AI
L
AB
I
L
T
Y
Data
s
et
is
u
tili
ze
d
in
th
is
r
esea
r
ch
m
en
tio
n
ed
in
r
ef
er
e
n
ce
[
2
1
]
.
RE
F
E
R
E
NC
E
S
[
1
]
L.
L
u
,
G
.
Y
.
L
i
,
A
.
L
.
S
w
i
n
d
l
e
h
u
r
st
,
A
.
A
sh
i
k
h
mi
n
,
a
n
d
R
.
Z
h
a
n
g
,
“
A
n
o
v
e
r
v
i
e
w
o
f
mass
i
v
e
M
I
M
O
:
b
e
n
e
f
i
t
s
a
n
d
c
h
a
l
l
e
n
g
e
s
,
”
i
n
I
EEE
J
o
u
rn
a
l
o
f
S
e
l
e
c
t
e
d
T
o
p
i
c
s
i
n
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
,
v
o
l
.
8
,
n
o
.
5
,
p
p
.
7
4
2
-
7
5
8
,
O
c
t
.
2
0
1
4
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
TSP
.
2
0
1
4
.
2
3
1
7
6
7
1
.
[
2
]
G
.
N
.
K
a
mg
a
,
M
.
X
i
a
,
a
n
d
S
.
A
ï
ss
a
,
“
S
p
e
c
t
r
a
l
-
e
f
f
i
c
i
e
n
c
y
a
n
a
l
y
si
s
o
f
m
a
ssi
v
e
M
I
M
O
sy
st
e
ms
i
n
c
e
n
t
r
a
l
i
z
e
d
a
n
d
d
i
s
t
r
i
b
u
t
e
d
sch
e
mes
,
”
i
n
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
s,
v
o
l
.
6
4
,
n
o
.
5
,
p
p
.
1
9
3
0
-
1
9
4
1
,
M
a
y
2
0
1
6
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
1
6
0
1
.
0
4
8
2
9
.
[
3
]
V
.
W
.
W
o
n
g
,
R
.
S
c
h
o
b
e
r
,
D
.
W
.
K
.
N
g
,
a
n
d
L
.
-
C
.
W
a
n
g
,
“
K
e
y
t
e
c
h
n
o
l
o
g
i
e
s
f
o
r
5
G
w
i
r
e
l
e
ss
sy
s
t
e
m
s,”
C
a
mb
r
i
d
g
e
,
U
.
K
.
:
C
a
m
b
r
i
d
g
e
U
n
i
v
e
r
si
t
y
P
r
e
ss
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
7
/
9
7
8
1
3
1
6
7
7
1
6
5
5
.
[
4
]
W
.
X
u
e
t
a
l
.
,
“
E
d
g
e
l
e
a
r
n
i
n
g
f
o
r
B
5
G
n
e
t
w
o
r
k
s
w
i
t
h
d
i
s
t
r
i
b
u
t
e
d
s
i
g
n
a
l
p
r
o
c
e
ssi
n
g
:
s
e
ma
n
t
i
c
c
o
mm
u
n
i
c
a
t
i
o
n
,
e
d
g
e
c
o
m
p
u
t
i
n
g
,
a
n
d
w
i
r
e
l
e
s
s
s
e
n
s
i
n
g
,
”
i
n
I
E
EE
J
o
u
r
n
a
l
o
f
S
e
l
e
c
t
e
d
T
o
p
i
c
s
i
n
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
,
v
o
l
.
1
7
,
n
o
.
1
,
p
p
.
9
-
3
9
,
Jan
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
TSP
.
2
0
2
3
.
3
2
3
9
1
8
9
.
[
5
]
W
.
S
h
e
n
,
L.
D
a
i
,
Y
.
S
h
i
,
B
.
S
h
i
m,
a
n
d
Z
.
W
a
n
g
,
“
J
o
i
n
t
c
h
a
n
n
e
l
t
r
a
i
n
i
n
g
a
n
d
f
e
e
d
b
a
c
k
f
o
r
F
D
D
mass
i
v
e
M
I
M
O
s
y
st
e
ms
,
”
i
n
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
Ve
h
i
c
u
l
a
r T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
6
5
,
n
o
.
1
0
,
p
p
.
8
7
6
2
-
8
7
6
7
,
O
c
t
.
2
0
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
TV
T
.
2
0
1
5
.
2
5
0
8
0
3
3
.
[
6
]
K
.
W
e
i
,
J.
X
u
,
W
.
X
u
,
N
.
W
a
n
g
,
a
n
d
D
.
C
h
e
n
,
“
D
i
s
t
r
i
b
u
t
e
d
n
e
u
r
a
l
p
r
e
c
o
d
i
n
g
f
o
r
h
y
b
r
i
d
mm
w
a
v
e
M
I
M
O
c
o
m
mu
n
i
c
a
t
i
o
n
s
w
i
t
h
l
i
m
i
t
e
d
f
e
e
d
b
a
c
k
,
”
i
n
I
EEE
C
o
m
m
u
n
i
c
a
t
i
o
n
s
L
e
t
t
e
rs
,
v
o
l
.
2
6
,
n
o
.
7
,
p
p
.
1
5
6
8
-
1
5
7
2
,
Ju
l
y
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
L
C
O
M
M
.
2
0
2
2
.
3
1
6
7
7
1
2
.
[
7
]
J.
G
u
o
,
C
.
-
K
.
W
e
n
,
a
n
d
S
.
Ji
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
C
S
I
f
e
e
d
b
a
c
k
f
o
r
b
e
a
mf
o
r
mi
n
g
i
n
si
n
g
l
e
-
a
n
d
m
u
l
t
i
-
c
e
l
l
mass
i
v
e
M
I
M
O
sy
st
e
ms
,
”
i
n
I
E
EE
J
o
u
r
n
a
l
o
n
S
e
l
e
c
t
e
d
Are
a
s
i
n
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
3
9
,
n
o
.
7
,
p
p
.
1
8
7
2
-
1
8
8
4
,
J
u
l
y
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
A
C
.
2
0
2
0
.
3
0
4
1
3
9
7
.
[
8
]
Z.
H
u
e
t
a
l
.
,
“
M
R
F
N
e
t
:
a
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
C
S
I
f
e
e
d
b
a
c
k
a
p
p
r
o
a
c
h
o
f
massi
v
e
M
I
M
O
sy
st
e
ms
,
”
i
n
I
EEE
C
o
m
m
u
n
i
c
a
t
i
o
n
s
L
e
t
t
e
rs
,
v
o
l
.
2
5
,
n
o
.
1
0
,
p
p
.
3
3
1
0
-
3
3
1
4
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
LC
O
M
M
.
2
0
2
1
.
3
0
9
9
8
4
1
.
[
9
]
Z.
L
u
,
J.
W
a
n
g
,
a
n
d
J.
S
o
n
g
,
“
B
i
n
a
r
y
n
e
u
r
a
l
n
e
t
w
o
r
k
a
i
d
e
d
C
S
I
f
e
e
d
b
a
c
k
i
n
m
a
ssi
v
e
M
I
M
O
sy
s
t
e
m
,
”
i
n
I
EEE
Wi
r
e
l
e
ss
C
o
m
m
u
n
i
c
a
t
i
o
n
s L
e
t
t
e
rs
,
v
o
l
.
1
0
,
n
o
.
6
,
p
p
.
1
3
0
5
-
1
3
0
8
,
J
u
n
e
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
LW
C
.
2
0
2
1
.
3
0
6
4
9
6
3
.
[
1
0
]
H
.
R
e
n
e
t
a
l
.
,
“
P
e
r
f
o
r
m
a
n
c
e
a
n
a
l
y
si
s
f
o
r
R
I
S
-
a
i
d
e
d
s
e
c
u
r
e
mass
i
v
e
M
I
M
O
s
y
s
t
e
ms
w
i
t
h
s
t
a
t
i
s
t
i
c
a
l
C
S
I
,
”
i
n
I
E
EE
W
i
re
l
e
s
s
C
o
m
m
u
n
i
c
a
t
i
o
n
s L
e
t
t
e
rs
,
v
o
l
.
1
2
,
n
o
.
1
,
p
p
.
1
2
4
-
1
2
8
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
LW
C
.
2
0
2
2
.
3
2
1
8
9
6
1
.
[
1
1
]
P
.
P
u
j
a
r
,
A
.
K
u
m
a
r
,
a
n
d
V
.
K
u
mar
,
“
Ef
f
i
c
i
e
n
t
p
l
a
n
t
l
e
a
f
d
e
t
e
c
t
i
o
n
t
h
r
o
u
g
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
b
a
se
d
o
n
c
o
r
n
l
e
a
f
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
i
n
I
AE
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
1
1
3
9
-
1
1
4
8
,
M
a
r
c
h
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
3
.
i
1
.
p
p
1
1
3
9
-
1
1
4
8
.
[
1
2
]
S
.
H
.
S
r
e
e
d
h
a
r
a
,
V
.
K
u
m
a
r
,
a
n
d
S
.
S
a
l
m
a
,
“
Ef
f
i
c
i
e
n
t
b
i
g
d
a
t
a
c
l
u
s
t
e
r
i
n
g
u
si
n
g
a
d
h
o
c
f
u
z
z
y
C
-
mea
n
s
a
n
d
a
u
t
o
-
e
n
c
o
d
e
r
C
N
N
,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
N
e
t
w
o
r
k
s
a
n
d
S
y
st
e
m
s
,
v
o
l
.
5
6
3
,
S
p
r
i
n
g
e
r
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
19
-
7
4
0
2
-
1
_
2
5
.
[
1
3
]
Z.
G
u
,
Z
.
C
h
e
n
,
J.
Z
h
a
n
g
,
X
.
Zh
a
n
g
a
n
d
Z
.
L.
Y
u
,
“
A
n
o
n
l
i
n
e
i
n
t
e
r
a
c
t
i
v
e
p
a
r
a
d
i
g
m
f
o
r
P
3
0
0
b
r
a
i
n
–
c
o
m
p
u
t
e
r
i
n
t
e
r
f
a
c
e
s
p
e
l
l
e
r
,”
i
n
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
N
e
u
r
a
l
S
y
s
t
e
m
s
a
n
d
Re
h
a
b
i
l
i
t
a
t
i
o
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
7
,
n
o
.
2
,
p
p
.
1
5
2
-
1
6
1
,
F
e
b
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
S
R
E.
2
0
1
9
.
2
8
9
2
9
6
7
.
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
A
n
o
ve
l d
ee
p
lea
r
n
in
g
b
a
s
ed
s
p
a
tia
l d
ela
y
fe
a
tu
r
e
a
w
a
r
e
en
c
o
d
er d
ec
o
d
er
… (
P
a
r
in
ith
a
Ja
ya
s
h
a
n
ka
r
)
1869
[
1
4
]
Q
.
C
a
i
,
C
.
D
o
n
g
,
a
n
d
K
.
N
i
u
,
“
A
t
t
e
n
t
i
o
n
mo
d
e
l
f
o
r
m
a
ssi
v
e
M
I
M
O
C
S
I
c
o
mp
r
e
ss
i
o
n
f
e
e
d
b
a
c
k
a
n
d
r
e
c
o
v
e
r
y
,
”
i
n
P
r
o
c
e
e
d
i
n
g
s
o
f
I
EEE
Wi
r
e
l
e
ss
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
N
e
t
w
o
r
k
i
n
g
C
o
n
f
e
re
n
c
e
(
WC
N
C
)
,
M
a
r
r
a
k
e
s
h
,
M
o
r
o
c
c
o
,
2
0
1
9
,
p
p
.
1
-
5
,
d
o
i
:
1
0
.
1
1
0
9
/
W
C
N
C
.
2
0
1
9
.
8
8
8
5
8
9
7
.
[
1
5
]
J.
J.
P
o
d
mo
r
e
,
T.
P
.
B
r
e
c
k
o
n
,
N
.
K
.
N
.
A
z
n
a
n
a
n
d
J.
D
.
C
o
n
n
o
l
l
y
,
“
O
n
t
h
e
r
e
l
a
t
i
v
e
c
o
n
t
r
i
b
u
t
i
o
n
o
f
d
e
e
p
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
f
o
r
S
S
V
EP
-
b
a
s
e
d
b
i
o
-
s
i
g
n
a
l
d
e
c
o
d
i
n
g
i
n
B
C
I
sp
e
l
l
e
r
a
p
p
l
i
c
a
t
i
o
n
s
,”
i
n
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
N
e
u
ra
l
S
y
st
e
m
s
a
n
d
Re
h
a
b
i
l
i
t
a
t
i
o
n
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
7
,
n
o
.
4
,
p
p
.
6
1
1
-
6
1
8
,
A
p
r
i
l
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
S
R
E.
2
0
1
9
.
2
9
0
4
7
9
1
.
[
1
6
]
A
.
V
a
sw
a
n
i
e
t
a
l
.
,
“
A
t
t
e
n
t
i
o
n
i
s
a
l
l
y
o
u
n
e
e
d
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
3
1
s
t
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
N
e
u
r
a
l
I
n
f
o
rm
a
t
i
o
n
Pro
c
e
ssi
n
g
S
y
s
t
e
m
s,
2
0
1
7
,
p
p
.
6
0
0
0
-
6
0
1
0
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
1
7
0
6
.
0
3
7
6
2
.
[
1
7
]
Y
.
X
u
,
M
.
Y
u
a
n
,
a
n
d
M
.
-
O
.
P
u
n
,
“
Tr
a
n
sf
o
r
mer
e
mp
o
w
e
r
e
d
C
S
I
f
e
e
d
b
a
c
k
f
o
r
mass
i
v
e
M
I
M
O
s
y
st
e
ms
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
3
0
t
h
Wi
r
e
l
e
s
s
a
n
d
O
p
t
i
c
a
l
C
o
m
m
u
n
i
c
a
t
i
o
n
s
C
o
n
f
e
r
e
n
c
e
(
WO
C
C
)
,
Ta
i
p
e
i
,
T
a
i
w
a
n
,
2
0
2
1
,
p
p
.
1
5
7
-
1
6
1
,
d
o
i
:
1
0
.
1
1
0
9
/
W
O
C
C
5
3
2
1
3
.
2
0
2
1
.
9
6
0
2
8
6
3
.
[
1
8
]
S
.
K
u
n
d
u
a
n
d
S
.
A
r
i
,
“
M
s
C
N
N
:
A
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
f
o
r
P
3
0
0
-
b
a
s
e
d
b
r
a
i
n
–
c
o
mp
u
t
e
r
i
n
t
e
r
f
a
c
e
sp
e
l
l
e
r
,”
i
n
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
M
e
d
i
c
a
l
R
o
b
o
t
i
c
s
a
n
d
B
i
o
n
i
c
s
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
8
6
-
9
3
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
T
M
R
B
.
2
0
1
9
.
2
9
5
9
5
5
9
.
[
1
9
]
L.
L
i
u
e
t
a
l
.
,
“
Th
e
C
O
S
T
2
1
0
0
M
I
M
O
c
h
a
n
n
e
l
m
o
d
e
l
,
”
i
n
I
E
EE
Wi
r
e
l
e
ss
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
1
9
,
n
o
.
6
,
p
p
.
9
2
-
9
9
,
D
e
c
.
2
0
1
2
,
d
o
i
:
1
0
.
1
1
0
9
/
M
W
C
.
2
0
1
2
.
6
3
9
3
5
2
3
.
[
2
0
]
C.
-
K
.
W
e
n
,
W
.
-
T.
S
h
i
h
,
a
n
d
S
.
J
i
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
mass
i
v
e
M
I
M
O
C
S
I
f
e
e
d
b
a
c
k
,
”
i
n
I
EEE
Wi
r
e
l
e
s
s
C
o
m
m
u
n
i
c
a
t
i
o
n
s
L
e
t
t
e
rs
,
v
o
l
.
7
,
n
o
.
5
,
p
p
.
7
4
8
-
7
5
1
,
O
c
t
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
LWC
.
2
0
1
8
.
2
8
1
8
1
6
0
.
[
2
1
]
Z.
Lu
,
J
.
W
a
n
g
a
n
d
J.
S
o
n
g
,
“
M
u
l
t
i
-
r
e
so
l
u
t
i
o
n
C
S
I
f
e
e
d
b
a
c
k
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
i
n
mass
i
v
e
M
I
M
O
s
y
st
e
m
,”
I
C
C
2
0
2
0
-
2
0
2
0
I
EEE
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
m
u
n
i
c
a
t
i
o
n
s (I
C
C
)
,
D
u
b
l
i
n
,
I
r
e
l
a
n
d
,
2
0
2
0
,
p
p
.
1
-
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
4
0
2
7
7
.
2
0
2
0
.
9
1
4
9
2
2
9
.
[
2
2
]
S
.
Ji
a
n
d
M
.
L
i
,
“
C
LN
e
t
:
C
o
mp
l
e
x
i
n
p
u
t
l
i
g
h
t
w
e
i
g
h
t
n
e
u
r
a
l
n
e
t
w
o
r
k
d
e
si
g
n
e
d
f
o
r
mass
i
v
e
M
I
M
O
C
S
I
f
e
e
d
b
a
c
k
,”
i
n
I
EEE
W
i
r
e
l
e
s
s
C
o
m
m
u
n
i
c
a
t
i
o
n
s L
e
t
t
e
rs
,
v
o
l
.
1
0
,
n
o
.
1
0
,
p
p
.
2
3
1
8
-
2
3
2
2
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
L
W
C
.
2
0
2
1
.
3
1
0
0
4
9
3
.
[
2
3
]
S
.
Ta
n
g
,
J.
X
i
a
,
L
.
F
a
n
,
X
.
L
e
i
,
W
.
X
u
,
a
n
d
A
.
N
a
l
l
a
n
a
t
h
a
n
,
“
D
i
l
a
t
e
d
c
o
n
v
o
l
u
t
i
o
n
b
a
se
d
C
S
I
f
e
e
d
b
a
c
k
c
o
mp
r
e
ssi
o
n
f
o
r
mass
i
v
e
M
I
M
O
sy
s
t
e
m
s
,
”
i
n
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
Ve
h
i
c
u
l
a
r
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
7
1
,
n
o
.
1
0
,
p
p
.
1
1
2
1
6
-
1
1
2
2
1
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
TV
T
.
2
0
2
2
.
3
1
8
3
5
9
6
.
[
2
4
]
S
.
M
.
B
a
t
h
a
l
a
,
S
.
A
m
u
r
u
,
a
n
d
K
.
K
u
c
h
i
,
“
A
s
p
a
t
i
a
l
l
y
se
p
a
r
a
b
l
e
a
t
t
e
n
t
i
o
n
mec
h
a
n
i
sm
f
o
r
mass
i
v
e
M
I
M
O
C
S
I
f
e
e
d
b
a
c
k
,
”
a
r
Xi
v
p
re
p
ri
n
t
,
2
0
2
2
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
2
2
0
8
.
0
3
3
6
9
.
[
2
5
]
A
.
C
h
a
k
ma,
S
.
S
.
A
l
a
m,
M
.
H
.
R
a
h
man
,
a
n
d
Y
.
M
.
Ja
n
g
,
“
D
e
e
p
d
e
c
o
d
e
r
C
si
N
e
t
f
o
r
F
D
D
mas
si
v
e
M
I
M
O
sy
st
e
m
,
”
i
n
I
EEE
Wi
re
l
e
ss
C
o
m
m
u
n
i
c
a
t
i
o
n
s Le
t
t
e
rs
,
v
o
l
.
P
P
,
n
o
.
1
,
p
p
.
1
-
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
LW
C
.
2
0
2
3
.
3
3
0
7
1
6
4
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
P
a
rinitha
J
a
y
a
s
ha
nk
a
r
e
a
rn
e
d
h
e
r
Ba
c
h
e
lo
rs
o
f
e
n
g
in
e
e
rin
g
in
Tele
c
o
m
m
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rin
g
a
n
d
M
a
ste
r’s
d
e
g
re
e
in
Dig
it
a
l
c
o
m
m
u
n
ica
ti
o
n
a
n
d
Ne
two
rk
in
g
fr
o
m
Visv
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
Un
i
v
e
rsity
(VTU)
,
Be
lg
a
v
i
.
C
u
rre
n
tl
y
sh
e
is
a
p
u
rsu
i
n
g
h
e
r
P
h
.
D
.
i
n
El
e
c
tro
n
i
c
s
a
n
d
c
o
m
m
u
n
ica
ti
o
n
e
n
g
in
e
e
r
i
n
g
fro
m
S
J
C
in
stit
u
te
o
f
tec
h
n
o
l
o
g
y
,
V
TU,
Be
lg
a
v
i.
S
h
e
i
s
wo
rk
i
n
g
a
s
an
a
ss
istan
t
p
ro
fe
ss
o
r
wit
h
a
to
tal
e
x
p
e
rien
c
e
o
f
1
1
y
e
a
rs.
S
h
e
h
a
s
g
u
i
d
e
d
o
v
e
r
1
1
u
n
d
e
r
g
ra
d
u
a
te
p
r
o
jec
ts
a
n
d
p
u
b
li
sh
e
d
1
0
p
a
p
e
rs
i
n
v
a
rio
u
s
Jo
u
rn
a
ls.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
a
rin
it
h
a
j_
1
2
@re
d
iffma
il
.
c
o
m
.
Chi
g
a
l
a
k
k
a
p
p
a
R
a
n
g
a
sw
a
m
y
h
a
s
re
c
e
iv
e
d
P
h
.
D
.
fro
m
Re
v
a
Un
iv
e
rsit
y
Be
n
g
a
lu
r
u
a
n
d
M
.
Tec
h
.
De
g
re
e
fro
m
Visv
e
sv
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsity
,
Be
lag
a
v
i,
Ka
rn
a
tak
a
.
Cu
rre
n
t
ly
w
o
rk
i
n
g
a
s
P
ro
fe
ss
o
r
a
n
d
He
a
d
in
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
i
n
e
e
rin
g
S
JC
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
Ch
ic
k
b
a
ll
a
p
u
r.
He
h
a
s
2
5
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
te
a
c
h
in
g
.
His
a
re
a
o
f
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
s
Im
a
g
e
P
r
o
c
e
ss
in
g
,
Co
m
m
u
n
ica
ti
o
n
.
He
is
IET
E
li
f
e
m
e
m
b
e
r.
He
h
a
s
p
u
b
li
s
h
e
d
1
8
p
a
p
e
rs
i
n
lea
d
i
n
g
re
p
u
ted
Jo
u
rn
a
ls/I
n
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
s/Na
ti
o
n
a
l
Co
n
fe
re
n
c
e
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
th
is
e
m
a
il
:
c
rse
c
e
sa
it
@g
m
a
il
.
c
o
m
a
n
d
h
o
d
e
c
e
@s
jcit.
a
c
.
in
.
Dr
.
By
r
a
p
p
a
N.
S
h
o
b
h
a
is
P
ri
n
c
ip
a
l
o
f
B
G
S
In
stit
u
e
o
f
Tec
h
n
o
lo
g
y
,
BG
Na
g
a
r
Na
g
a
m
a
n
g
a
la,
M
a
n
d
y
a
.
S
h
e
is
h
a
v
in
g
a
to
tal
e
x
p
e
rien
c
e
o
f
3
1
y
e
a
rs.
S
h
e
is
q
u
a
li
fied
in
Ba
c
h
e
lo
r
a
n
d
M
a
ste
r
De
g
re
e
s
in
El
e
c
tro
n
ics
fro
m
Ba
n
g
a
lo
re
u
n
iv
e
rsit
y
,
a
n
d
P
h
.
D
.
fro
m
Ka
rp
a
g
a
m
Un
iv
e
rsity
i
n
t
h
e
field
o
f
El
e
c
tro
n
ics
.
S
h
e
h
a
s
g
u
i
d
e
d
o
v
e
r
6
0
u
n
d
e
rg
ra
d
u
a
te
p
ro
jec
ts,
4
5
p
o
st
g
ra
d
u
a
te
p
ro
jec
ts
a
n
d
g
u
i
d
in
g
4
P
h
.
D.
st
u
d
e
n
ts.
S
h
e
h
a
s
p
u
b
l
ish
e
d
o
v
e
r
2
8
p
a
p
e
rs
in
v
a
ri
o
u
s
Jo
u
r
n
a
ls
a
n
d
h
a
v
e
6
p
a
ten
ts
in
h
e
r
n
a
m
e
.
He
r
a
r
e
a
o
f
i
n
tere
st
is
b
io
–
S
e
n
s
o
r
ima
g
e
p
ro
c
e
ss
in
g
c
o
m
p
u
ter
v
isio
n
e
m
b
e
d
d
e
d
s
y
ste
m
I
o
T.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
t
h
is
e
m
a
il
:
b
n
sh
o
b
h
a
6
7
@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.