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
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
,
p
p
.
2
7
9
~
2
8
7
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
1
.
pp
279
-
2
8
7
279
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Enha
ncing
hy
per
spectral ima
g
e ob
ject cla
ss
ificatio
n
throug
h
ro
bust f
ea
t
ure
ex
t
ra
ction a
nd spa
ti
a
l
-
spectral
fusio
n
using
deep
lea
rning
Vij
a
y
la
x
m
i K
o
cha
ri
1,
2
,
Sa
nje
ev
S
.
Sa
nn
a
k
k
i
1
,
Vij
a
y
S
.
Ra
j
pu
ro
hit
1
,
M
a
hes
h
G
.
H
ud
da
r
3
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
K
.
L.
S
G
o
g
t
e
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
V
i
sv
e
s
v
a
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
,
K
a
r
n
a
t
a
k
a
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
(
A
I
M
L)
,
K
o
l
h
a
p
u
r
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
's
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
(
A
u
t
o
n
o
m
o
u
s)
,
K
o
l
h
a
p
u
r
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
H
i
r
a
s
u
g
a
r
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
V
i
sv
e
sv
a
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
,
K
a
r
n
a
t
a
k
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
J
ul
12
,
2
0
2
4
R
ev
is
ed
Sep
1
,
202
4
Acc
ep
ted
Sep
7
,
2
0
2
4
Hy
p
e
rsp
e
c
tral
ima
g
i
n
g
(HSI)
h
a
s
g
a
i
n
e
d
sig
n
ifi
c
a
n
t
a
tt
e
n
ti
o
n
i
n
re
c
e
n
t
y
e
a
rs
d
u
e
t
o
it
s
b
r
o
a
d
a
p
p
li
c
a
ti
o
n
s
a
c
ro
ss
a
g
ricu
lt
u
re
,
e
n
v
ir
o
n
m
e
n
tal
m
o
n
it
o
rin
g
,
u
rb
a
n
p
lan
n
in
g
,
i
n
fra
stru
c
tu
re
m
a
n
a
g
e
m
e
n
t,
a
n
d
d
e
fe
n
se
a
n
d
se
c
u
rit
y
f
o
r
o
b
jec
t
d
e
tec
ti
o
n
a
n
d
c
las
sifi
c
a
ti
o
n
.
De
sp
it
e
it
s
p
o
ten
ti
a
l
,
c
u
rre
n
t
m
e
th
o
d
o
lo
g
ies
fa
c
e
c
h
a
ll
e
n
g
e
s
su
c
h
a
s
in
s
u
fficie
n
t
fe
a
tu
re
e
x
trac
ti
o
n
,
n
o
ise
in
terfe
re
n
c
e
,
a
n
d
i
n
a
d
e
q
u
a
te
sp
a
ti
a
l
-
sp
e
c
tral
fu
sio
n
,
li
m
it
i
n
g
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
a
n
d
ro
b
u
st
n
e
ss
.
Th
is
st
u
d
y
re
v
iew
s
a
d
v
a
n
c
e
m
e
n
ts
in
HSI
o
b
jec
t
d
e
tec
ti
o
n
a
n
d
c
las
sifica
ti
o
n
m
e
th
o
d
o
l
o
g
ies
,
e
m
p
h
a
siz
in
g
th
e
ro
le
o
f
m
a
c
h
in
e
-
lea
rn
in
g
(
M
L)
a
n
d
d
e
e
p
-
lea
rn
in
g
(DL)
tec
h
n
i
q
u
e
s.
H
e
n
c
e
,
th
is
wo
rk
p
ro
p
o
se
s
a
n
o
v
e
l
fra
m
e
wo
rk
t
o
a
d
d
re
ss
th
e
se
c
h
a
ll
e
n
g
e
s,
p
rio
rit
izi
n
g
ro
b
u
st
fe
a
tu
re
e
x
trac
ti
o
n
,
e
ffe
c
ti
v
e
sp
a
ti
a
l
-
sp
e
c
tral
fu
sio
n
,
a
n
d
c
o
m
p
re
h
e
n
siv
e
n
o
ise
re
m
o
v
a
l
m
e
c
h
a
n
ism
s.
By
i
n
teg
ra
ti
n
g
DL
t
e
c
h
n
iq
u
e
s
a
n
d
train
i
n
g
wit
h
HSI
n
o
isy
d
a
ta,
th
is
fra
m
e
wo
rk
a
ims
to
e
n
h
a
n
c
e
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
a
n
d
r
o
b
u
stn
e
ss
.
Th
e
fin
d
i
n
g
s
s
u
g
g
e
st
th
a
t
th
e
p
ro
p
o
se
d
a
p
p
r
o
a
c
h
si
g
n
if
ica
n
tl
y
i
m
p
ro
v
e
s
t
h
e
r
e
li
a
b
il
it
y
a
n
d
p
e
rfo
r
m
a
n
c
e
o
f
HSI
-
b
a
se
d
o
b
jec
t
c
las
sifica
ti
o
n
s
y
ste
m
s.
Th
is
re
se
a
rc
h
p
ro
v
i
d
e
s
a
p
a
th
wa
y
fo
r
fu
t
u
re
d
e
v
e
lo
p
m
e
n
t
in
th
e
d
o
m
a
in
,
p
ro
m
isi
n
g
t
o
e
lev
a
te
th
e
e
ffe
c
ti
v
e
n
e
ss
o
f
HSI
a
p
p
li
c
a
ti
o
n
s i
n
re
a
l
-
wo
rl
d
sc
e
n
a
rio
s.
K
ey
w
o
r
d
s
:
Dee
p
lear
n
in
g
Fra
m
ewo
r
k
Hy
p
er
s
p
ec
tr
al
im
ag
in
g
Ma
ch
in
e
lear
n
in
g
Ob
ject
class
if
icatio
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
:
Vijay
lax
m
i K
o
ch
ar
i
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
K.
L
.
S Go
g
te
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
,
Vis
v
esv
ar
ay
a
T
e
ch
n
o
lo
g
ical
Un
iv
er
s
r
ity
B
elag
av
i
-
5
9
0
0
1
8
,
Kar
n
atak
a,
I
n
d
ia
E
m
ail: k
o
ch
ar
iv
ijay
la
x
m
i@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Hy
p
er
s
p
ec
tr
al
-
I
m
a
g
in
g
(
HSI
)
ar
e
em
er
g
in
g
as
a
p
o
wer
f
u
l
tech
n
o
lo
g
y
in
r
em
o
te
-
s
en
s
in
g
an
d
v
ar
io
u
s
f
ield
s
b
ec
au
s
e
o
f
its
ca
p
ab
ilit
y
o
f
ca
p
tu
r
in
g
d
etailed
in
f
o
r
m
atio
n
ac
r
o
s
s
h
u
n
d
r
e
d
s
o
f
n
ar
r
o
w
s
p
ec
tr
al
-
b
an
d
s
[
1
]
.
T
h
e
o
v
e
r
all
p
r
o
ce
s
s
o
f
h
o
w
th
e
h
y
p
er
s
p
ec
tr
al
im
ag
e
i
s
tak
en
is
s
h
o
wn
in
Fig
u
r
e
1
.
Un
lik
e
tr
ad
itio
n
al
im
ag
in
g
tech
n
i
q
u
es
th
at
ca
p
t
u
r
e
d
ata
in
th
r
ee
s
p
ec
t
r
al
b
an
d
s
(
R
GB
)
,
h
y
p
er
s
p
ec
tr
al
s
en
s
o
r
s
ac
q
u
ir
e
d
ata
in
n
u
m
er
o
u
s
co
n
tig
u
o
u
s
b
a
n
d
s
,
o
f
f
er
i
n
g
a
wea
lth
o
f
s
p
ec
tr
al
in
f
o
r
m
atio
n
[
2
]
.
T
h
e
ex
te
n
s
iv
e
s
p
ec
tr
al
d
ata
o
b
tain
ed
th
r
o
u
g
h
HSI
allo
ws
s
cien
tis
t
s
to
d
is
tin
g
u
is
h
an
d
id
en
tify
v
ar
io
u
s
o
b
jects
an
d
m
at
er
ials
b
y
an
aly
zin
g
th
eir
d
is
tin
ct
s
p
ec
tr
al
s
ig
n
atu
r
es.
T
h
is
m
ak
es
H
SI
a
cr
u
cial
in
s
tr
u
m
en
t
f
o
r
class
if
y
in
g
an
d
d
etec
tin
g
o
b
jects
[
3
]
.
Fu
r
th
er
,
o
b
ject
class
if
icatio
n
u
s
in
g
HSI
s
in
v
o
lv
es
th
e
p
r
o
ce
s
s
o
f
id
en
tify
in
g
an
d
ca
te
g
o
r
izin
g
o
b
jects
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
279
-
2
8
7
280
m
ater
ials
with
in
a
h
y
p
er
s
p
ec
t
r
al
im
ag
e
b
ased
o
n
t
h
eir
s
p
e
ctr
al
ch
ar
ac
ter
is
tics
[
4
]
.
E
ac
h
m
ater
ial
o
r
o
b
ject
ex
h
ib
its
a
d
is
tin
ct
s
p
ec
tr
al
s
ig
n
atu
r
e
d
u
e
t
o
its
u
n
iq
u
e
ch
em
ical
co
m
p
o
s
itio
n
an
d
p
h
y
s
ical
p
r
o
p
e
r
ties
,
wh
ich
ca
n
b
e
ex
p
lo
ited
f
o
r
ac
cu
r
ate
class
if
icatio
n
[
5
]
.
B
y
an
aly
zi
n
g
th
e
s
p
ec
tr
al
r
e
f
lecta
n
ce
p
atter
n
s
ac
r
o
s
s
m
u
ltip
le
b
an
d
s
,
m
ac
h
i
n
e
-
lear
n
in
g
(
ML
)
an
d
d
ee
p
-
lear
n
in
g
(
DL
)
alg
o
r
ith
m
s
ca
n
b
e
t
r
ain
ed
to
d
if
f
er
en
tiate
b
etwe
en
v
ar
io
u
s
o
b
jects a
n
d
class
if
y
th
em
in
to
p
r
e
d
ef
in
e
d
class
es o
r
ca
teg
o
r
ies [
6
]
.
Fig
u
r
e
1
.
Pro
ce
s
s
o
f
ca
p
tu
r
in
g
HSI
s
T
h
e
ap
p
licatio
n
s
o
f
HSI
s
in
th
e
cu
r
r
en
t r
ea
l w
o
r
ld
ar
e
d
iv
er
s
e
an
d
ex
ten
s
iv
e.
T
h
ey
ar
e
wid
ely
u
s
ed
in
ag
r
icu
ltu
r
e
f
o
r
cr
o
p
h
ea
lth
m
o
n
ito
r
in
g
,
d
is
ea
s
e
d
etec
tio
n
,
an
d
y
ield
p
r
ed
ictio
n
[
7
]
.
I
n
en
v
ir
o
n
m
en
tal
m
o
n
ito
r
in
g
,
HSI
s
ar
e
u
tili
ze
d
f
o
r
v
eg
etatio
n
m
ap
p
in
g
,
wate
r
q
u
ality
ass
ess
m
en
t,
an
d
lan
d
co
v
er
class
if
icatio
n
[
8
]
.
I
n
u
r
b
an
p
lan
n
in
g
an
d
in
f
r
astru
ctu
r
e
m
an
ag
em
e
n
t,
HSI
s
aid
in
id
en
tify
in
g
lan
d
u
s
e
p
atter
n
s
,
m
o
n
ito
r
in
g
p
o
llu
tio
n
lev
els,
a
n
d
ass
ess
in
g
g
eo
lo
g
ical
f
ea
tu
r
es
[
9
]
.
Ad
d
itio
n
ally
,
HSI
s
p
lay
a
cr
u
cial
r
o
le
in
d
e
f
en
s
e
an
d
s
ec
u
r
ity
ap
p
licatio
n
s
s
u
ch
as
t
ar
g
et
d
etec
tio
n
,
ca
m
o
u
f
lag
e
a
n
aly
s
is
,
an
d
s
u
r
v
eillan
ce
HSI
s
h
elp
in
id
en
tify
in
g
o
b
jects
b
y
e
x
p
lo
itin
g
th
eir
s
p
ec
tr
al
s
ig
n
atu
r
es
[
1
0
]
.
E
ac
h
p
ix
el
in
a
HSI
co
n
s
is
ts
o
f
s
p
ec
tr
al
d
ata
ac
r
o
s
s
m
u
ltip
le
b
an
d
s
,
r
e
p
r
esen
tin
g
t
h
e
u
n
iq
u
e
r
ef
lecta
n
ce
p
r
o
p
er
ti
es
o
f
th
e
co
r
r
esp
o
n
d
i
n
g
ar
ea
o
n
th
e
g
r
o
u
n
d
[
1
1
]
.
I
n
HSI
s
,
as
s
ee
n
in
Fig
u
r
e
2
,
u
s
in
g
th
e
r
ef
lecta
n
ce
an
d
w
av
elen
g
th
,
th
e
s
p
ac
e
an
d
s
p
e
ctr
al
d
im
en
s
io
n
ar
e
id
en
tifie
d
an
d
u
s
in
g
t
h
at
a
s
in
g
le
b
an
d
im
a
g
e
is
o
b
tain
ed
.
B
y
an
aly
zin
g
th
ese
s
p
ec
tr
al
s
ig
n
atu
r
es
an
d
ex
tr
ac
tin
g
r
elev
an
t
f
ea
tu
r
es,
ML
an
d
DL
alg
o
r
ith
m
s
ca
n
d
is
tin
g
u
is
h
b
etwe
en
d
if
f
er
en
t
m
ater
ials
an
d
o
b
jects
[
1
2
]
.
ML
ap
p
r
o
ac
h
es
lik
e
s
u
p
p
o
r
t
-
v
ec
to
r
-
m
ac
h
in
e
(
SVM)
[
1
3
]
,
r
a
n
d
o
m
-
f
o
r
est
(
R
F)
[
1
4
]
,
a
n
d
K
-
n
ea
r
est
-
n
eig
h
b
o
r
s
(
k
-
NN)
[
1
5
]
a
r
e
th
e
wid
ely
u
tili
ze
d
ap
p
r
o
ac
h
es
f
o
r
o
b
ject
class
if
icatio
n
b
ased
o
n
ex
tr
ac
ted
s
p
ec
tr
al
f
ea
tu
r
es.
Fig
u
r
e
2
.
HSI
im
ag
e
ex
tr
ac
tio
n
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:
2
5
0
2
-
4
7
52
E
n
h
a
n
ci
n
g
h
y
p
ers
p
ec
tr
a
l ima
g
e
o
b
ject
cla
s
s
ifica
tio
n
th
r
o
u
g
h
r
o
b
u
s
t fe
a
tu
r
e
…
(
V
ija
yla
xm
i Ko
ch
a
r
i
)
281
Ho
wev
er
,
wh
ile
ML
a
n
d
DL
ap
p
r
o
ac
h
es
h
av
e
s
h
o
wn
p
r
o
m
is
in
g
r
esu
lts
in
HSI
o
b
ject
d
et
ec
tio
n
an
d
class
if
icatio
n
,
th
ey
f
ac
e
s
ev
er
al
lim
itatio
n
s
.
On
e
m
ajo
r
lim
i
tatio
n
is
th
e
lack
o
f
em
p
h
asis
o
n
n
o
is
e
r
em
o
v
al
an
d
f
ea
tu
r
e
e
x
tr
ac
tio
n
f
r
o
m
h
y
p
er
s
p
ec
tr
al
d
ata
[
1
6
]
.
Ma
n
y
ex
is
tin
g
m
o
d
els
f
o
c
u
s
o
n
d
ir
ec
tly
d
etec
tin
g
o
r
class
if
y
in
g
o
b
jects
with
o
u
t
ad
eq
u
ately
p
r
ep
r
o
ce
s
s
in
g
th
e
d
ata
to
r
em
o
v
e
n
o
is
e
an
d
ex
tr
ac
t
d
is
cr
im
in
ativ
e
f
ea
tu
r
es
[
1
7
]
.
T
h
is
ca
n
lead
to
s
u
b
o
p
tim
al
p
er
f
o
r
m
a
n
ce
an
d
r
e
d
u
ce
d
ac
cu
r
ac
y
in
c
lass
if
icatio
n
task
s
.
Mo
r
eo
v
er
,
th
e
s
p
atial
-
s
p
ec
tr
al
f
u
s
io
n
tech
n
iq
u
e,
wh
ich
co
m
b
in
es
s
p
atial
an
d
s
p
ec
tr
al
in
f
o
r
m
atio
n
f
o
r
en
h
an
ce
d
f
ea
tu
r
e
r
ep
r
esen
tati
o
n
,
h
as
o
n
ly
r
ec
e
n
tly
g
ain
e
d
atten
tio
n
in
HSI
an
aly
s
is
u
s
in
g
ML
an
d
DL
[
1
8
]
.
Sp
atial
-
f
u
s
io
n
f
ea
tu
r
e
f
u
s
io
n
tech
n
iq
u
es
aim
to
im
p
r
o
v
e
th
e
q
u
ality
o
f
d
etec
ted
o
b
jects
an
d
en
h
an
ce
class
if
icatio
n
ac
cu
r
ac
y
b
y
in
c
o
r
p
o
r
ati
n
g
s
p
atial
co
n
tex
t
alo
n
g
with
s
p
ec
tr
al
in
f
o
r
m
atio
n
.
R
ec
en
tly
,
th
er
e
is
an
im
p
o
r
tan
t
s
h
if
t
i
n
th
e
d
ir
ec
tio
n
o
f
u
tili
zin
g
DL
m
et
h
o
d
s
f
o
r
HSI
o
b
ject
d
etec
tio
n
an
d
class
if
icatio
n
[
1
9
]
.
DL
m
o
d
els,
p
ar
tic
u
lar
ly
r
ec
u
r
r
e
n
t
-
n
eu
r
al
-
n
etwo
r
k
s
(
R
NNs)
[
2
0
]
an
d
co
n
v
o
l
u
tio
n
al
-
n
e
u
r
al
-
n
et
wo
r
k
s
(
C
NNs)
[
2
1
]
,
h
av
e
ac
h
iev
ed
s
u
p
e
r
io
r
p
e
r
f
o
r
m
an
ce
b
ec
au
s
e
o
f
th
eir
a
b
ilit
y
to
lear
n
co
m
p
lex
s
p
ec
tr
al
an
d
s
p
atial
p
atter
n
s
f
r
o
m
HSI
d
ata.
R
NNs,
s
p
ec
if
ically
,
o
f
f
e
r
im
p
r
o
v
ed
p
er
f
o
r
m
an
ce
in
c
o
llectin
g
tem
p
o
r
al
r
elatio
n
s
h
ip
s
in
s
eq
u
en
ce
d
in
f
o
r
m
atio
n
.
T
h
is
ch
ar
ac
ter
is
tic
p
r
o
v
es
ad
v
a
n
tag
eo
u
s
wh
en
ev
alu
atin
g
s
p
e
ctr
u
m
s
eq
u
e
n
ce
s
in
HSI
s
.
T
h
is
s
tu
d
y
aim
s
at
ad
d
r
ess
in
g
ex
is
tin
g
is
s
u
es,
ch
allen
g
es
an
d
lim
itatio
n
s
in
HSI
o
b
ject
class
if
icatio
n
ap
p
r
o
ac
h
es.
Fu
r
th
er
,
t
h
is
wo
r
k
p
r
esen
ts
a
n
o
v
el
f
r
am
ewo
r
k
th
at
f
o
cu
s
es
o
n
n
o
is
e
r
em
o
v
al
,
f
ea
tu
r
e
ex
t
r
ac
tio
n
,
an
d
s
p
atial
-
s
p
ec
tr
al
f
u
s
io
n
u
s
in
g
ad
v
an
ce
d
ML
an
d
DL
tech
n
iq
u
es.
T
h
e
p
r
o
p
o
s
ed
f
r
am
ew
o
r
k
m
ain
aim
is
to
im
p
r
o
v
e
ac
cu
r
ac
y
an
d
p
r
o
v
i
d
e
r
o
b
u
s
tn
ess
f
o
r
HSI
o
b
je
ct
class
if
icat
io
n
b
y
u
s
in
g
s
p
ec
tr
al
an
d
s
p
atial
in
f
o
r
m
atio
n
f
r
o
m
HSI
d
ata.
T
h
e
co
n
tr
ib
u
tio
n
o
f
th
e
w
o
r
k
a
r
e
as f
o
llo
ws
−
T
h
e
s
tu
d
y
ev
alu
ates
th
e
cu
r
r
e
n
t
r
ec
en
t
ap
p
r
o
ac
h
es
u
s
ed
f
o
r
HSI
o
b
ject
d
etec
tio
n
an
d
class
if
icatio
n
.
T
h
is
ev
alu
atio
n
in
cl
u
d
es
ass
ess
in
g
th
e
s
tr
en
g
th
s
an
d
wea
k
n
ess
es
o
f
ex
is
tin
g
ML
an
d
DL
tech
n
iq
u
es
ap
p
lied
to
HSI
d
ata.
−
T
h
r
o
u
g
h
th
e
ev
alu
atio
n
p
r
o
ce
s
s
,
th
e
s
tu
d
y
id
en
tifie
s
th
e
k
ey
is
s
u
es
an
d
ch
allen
g
es
f
ac
ed
b
y
th
e
ex
is
tin
g
ap
p
r
o
ac
h
es in
HSI
o
b
ject
d
ete
ctio
n
an
d
class
if
icatio
n
.
−
T
h
e
s
tu
d
y
p
r
o
p
o
s
es
a
n
o
v
el
f
r
am
ewo
r
k
d
esig
n
ed
s
p
ec
if
i
ca
lly
to
ad
d
r
ess
th
e
id
en
tifi
ed
is
s
u
es
an
d
ch
allen
g
es
in
HSI
o
b
ject
cla
s
s
if
icatio
n
.
T
h
is
f
r
am
ew
o
r
k
in
tr
o
d
u
ce
s
i
n
n
o
v
ativ
e
m
eth
o
d
s
,
i.e
.
,
n
o
is
e
r
em
o
v
al,
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
a
n
d
s
p
atial
-
s
p
ec
tr
al
f
u
s
io
n
,
aim
in
g
to
en
h
a
n
ce
th
e
ac
cu
r
ac
y
a
n
d
r
o
b
u
s
tn
ess
o
f
o
b
ject
class
if
icatio
n
r
esu
lts
.
−
T
h
e
p
r
im
ar
y
co
n
tr
ib
u
tio
n
o
f
th
e
s
tu
d
y
is
to
p
r
o
v
id
e
a
b
etter
HSI
o
b
ject
class
if
icatio
n
ap
p
r
o
ac
h
co
m
p
a
r
ed
to
ex
is
tin
g
m
et
h
o
d
s
.
T
h
e
n
o
v
el
f
r
am
ewo
r
k
tr
ies
to
ad
d
r
ess
es
th
e
lim
itatio
n
s
o
f
cu
r
r
e
n
t
a
p
p
r
o
ac
h
es
an
d
ca
n
im
p
r
o
v
e
ac
cu
r
ac
y
an
d
r
eli
ab
ilit
y
in
class
if
y
in
g
o
b
jects w
ith
in
h
y
p
e
r
s
p
ec
tr
al
im
ag
es.
T
h
e
m
an
u
s
cr
ip
t
is
o
r
g
an
ize
d
i
n
th
e
f
o
llo
win
g
way
.
I
n
s
ec
tio
n
2
,
liter
atu
r
e
s
u
r
v
ey
is
d
is
cu
s
s
ed
,
wh
er
e
d
if
f
er
en
t
ap
p
r
o
ac
h
es
to
HSI
ar
e
d
is
cu
s
s
ed
.
Fu
r
th
e
r
,
in
s
ec
tio
n
3
,
is
s
u
es
an
d
ch
allen
g
es
ar
e
d
is
cu
s
s
ed
f
r
o
m
th
e
ab
o
v
e
liter
atu
r
e
s
u
r
v
ey
.
T
h
en
,
in
s
ec
tio
n
4
,
a
n
o
v
el
f
r
a
m
ewo
r
k
is
p
r
esen
ted
f
o
r
ef
f
icien
t
HSI
o
b
ject
d
etec
tio
n
an
d
class
if
icatio
n
.
T
h
en
i
n
s
ec
tio
n
5
,
c
o
n
clu
s
io
n
o
f
th
e
w
o
r
k
is
p
r
esen
ted
.
2.
L
I
T
E
R
AT
U
RE
SU
RVE
Y
I
n
th
is
s
ec
tio
n
,
v
ar
io
u
s
ML
an
d
DL
ap
p
r
o
ac
h
es
f
o
r
HSI
o
b
ject
d
etec
tio
n
an
d
class
if
i
ca
tio
n
ar
e
d
is
cu
s
s
ed
.
A
n
o
v
el
d
u
al
-
in
ter
a
ctiv
e
g
r
ap
h
-
c
o
n
v
o
lu
tio
n
al
-
n
et
wo
r
k
(
DI
GC
N)
was
d
esig
n
ed
b
y
W
an
et
a
l.
[
2
2
]
.
T
h
is
g
r
ap
h
-
co
n
v
o
lu
tio
n
al
-
n
et
w
o
r
k
(
GC
N)
in
co
r
p
o
r
ated
two
d
is
tin
ct
GC
N
b
r
an
c
h
es
f
o
r
ca
p
tu
r
in
g
s
p
atial
d
ata
at
v
ar
io
u
s
s
ca
les.
T
h
e
G
C
N
b
r
an
ch
es
allo
wed
r
ef
in
em
e
n
t
o
f
g
r
ap
h
d
ata
b
y
lev
er
ag
i
n
g
m
u
lt
is
ca
le
-
s
p
atial
d
ata.
Fu
r
th
er
,
b
y
co
m
b
in
in
g
f
ea
tu
r
e
s
r
ep
r
esen
ted
f
r
o
m
two
GC
N
b
r
an
ch
es,
th
e
ed
g
e
d
ata
was
im
p
r
o
v
e
d
.
Mo
r
eo
v
er
,
by
m
er
g
in
g
ed
g
e
d
ata
f
r
o
m
t
wo
GC
N
b
r
an
ch
es
allo
wed
g
en
er
atio
n
o
f
b
etter
f
ea
tu
r
e
d
es
cr
ip
tio
n
s
in
a
s
in
g
le
b
r
an
ch
.
T
h
er
e
f
o
r
e,
th
e
DI
GC
N
r
ep
r
esen
tatio
n
al
ca
p
a
b
ilit
y
was
im
p
r
o
v
ed
with
t
h
e
u
p
d
at
ed
g
r
a
p
h
d
ata.
I
n
ad
d
itio
n
to
s
p
ee
d
in
g
u
p
th
e
p
r
o
ce
s
s
o
f
c
o
n
v
o
lu
tio
n
,
th
e
DI
GC
N
au
to
m
atica
lly
ac
q
u
ir
e
s
a
d
is
cr
im
in
ato
r
y
r
eg
io
n
-
i
n
d
u
ce
d
-
g
r
a
p
h
th
at
eli
m
in
ates
th
e
d
r
awb
ac
k
s
o
f
th
e
tr
ad
itio
n
ally
g
en
er
ate
d
g
r
ap
h
.
I
n
d
ian
-
Pin
es
[
2
3
]
,
Pav
ia
-
Un
iv
er
s
ity
(
PU)
[
2
4
]
,
Salin
as
(
SA)
[
2
5
]
,
an
d
Ho
u
s
to
n
(
HU)
[
2
6
]
wer
e
u
s
ed
f
o
r
ev
al
u
atio
n
.
E
v
alu
atio
n
was
d
o
n
e
u
s
in
g
Av
er
ag
e
-
Acc
u
r
ac
y
(
AA)
,
Ov
er
all
-
Acc
u
r
ac
y
(
OA)
an
d
Kap
p
a
-
C
o
ef
f
icien
t
(
KC
)
.
Fo
r
I
P,
th
ey
ac
h
iev
ed
OA
o
f
9
4
.
1
6
%,
AA
o
f
9
4
.
4
1
%
an
d
KC
o
f
0
.
9
3
3
4
.
Fo
r
PU
ac
h
iev
ed
OA
o
f
9
3
.
2
4
%,
9
3
.
7
6
%
o
f
AA
an
d
KC
o
f
0
.
9
1
1
4
.
Fo
r
SA
ac
h
iev
ed
9
7
.
6
1
%
o
f
OA,
9
6
.
9
4
%
o
f
AA
an
d
0
.
9
7
3
4
o
f
KC
.
Fo
r
HU
ac
h
iev
ed
9
1
.
7
2
%
o
f
OA,
9
2
.
5
2
%
o
f
A
A,
an
d
0
.
9
1
0
3
o
f
KC
.
Mo
r
e
o
v
er
,
th
is
wo
r
k
h
as
co
n
s
id
er
ed
to
r
em
o
v
e
n
o
is
e
b
ef
o
r
e
ev
alu
atio
n
.
J
ian
g
et
a
l
.
[
2
7
]
in
tr
o
d
u
ce
d
a
la
b
eled
n
o
is
e
clea
n
in
g
tech
n
iq
u
e
th
at
r
elied
o
n
Sp
ec
t
r
al
-
Sp
atial
-
Gr
ap
h
s
(
SS
Gs).
T
h
e
d
ev
elo
p
m
en
t
o
f
an
af
f
in
ity
-
g
r
a
p
h
in
SS
Gs
was
a
k
ey
f
in
d
in
g
o
f
th
is
wo
r
k
.
T
h
e
g
r
ap
h
r
elied
o
n
b
o
t
h
s
p
ec
tr
al
-
s
p
atial
s
im
ilar
ities
,
wh
er
e
p
ix
els
with
in
an
id
en
tical
r
eg
io
n
wer
e
o
b
tain
ed
th
r
o
u
g
h
s
u
p
er
-
p
ix
el
s
eg
m
en
tatio
n
ap
p
r
o
ac
h
.
T
h
e
cr
ea
ted
af
f
in
ity
-
g
r
a
p
h
was
u
tili
ze
d
f
o
r
r
eg
u
lar
izatio
n
an
d
f
o
r
r
em
o
v
al
o
f
n
o
is
e.
Fo
r
ex
p
l
o
itin
g
th
e
s
p
atial
d
ata,
th
e
y
p
r
es
en
ted
m
u
ltis
ca
le
-
s
eg
m
en
tatio
n
-
b
ased
m
u
lti
-
lay
er
SS
Gs
(
M
SS
G
s
)
.
E
v
alu
atio
n
was
d
o
n
e
u
s
in
g
OA,
AA,
an
d
KC
o
n
I
P
an
d
PU.
T
h
ey
h
av
e
also
co
n
d
u
cte
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
279
-
2
8
7
282
ex
p
er
im
en
ts
o
n
n
o
is
e
r
em
o
v
al
.
Fin
d
in
g
s
s
h
o
w
th
e
y
ac
h
iev
e
d
8
3
.
7
1
%
o
f
OA,
9
7
.
5
5
o
f
AA
an
d
0
.
7
9
0
3
o
f
KC
f
o
r
I
P d
ataset
an
d
f
o
r
SA d
ataset,
ac
h
iev
ed
9
1
.
4
2
% o
f
OA,
9
5
.
4
1
% o
f
AA
an
d
0
.
9
0
4
5
o
f
K
C
f
o
r
SA d
ataset.
Gao
et
a
l.
[
2
8
]
in
tr
o
d
u
ce
d
a
n
ew
tech
n
iq
u
e
ca
lled
s
p
ec
tr
al
-
b
an
d
n
o
n
-
l
o
ca
lizatio
n
(
SB
NL
)
.
T
h
is
tech
n
iq
u
e
allo
ws
ex
p
lo
r
atio
n
o
f
n
o
n
-
lo
ca
l
-
s
p
ec
tr
al
in
ter
-
b
a
n
d
co
r
r
elatio
n
s
u
s
in
g
co
n
v
o
l
u
tio
n
al
-
k
er
n
els
th
at
h
av
e
r
estricte
d
f
ield
r
ec
e
p
tiv
ity
.
T
h
ey
also
d
ev
elo
p
ed
an
i
n
n
o
v
ativ
e
m
u
lti
-
s
ca
le
-
s
h
ar
e
in
ce
p
tio
n
-
b
lo
c
k
(
MSI
B
)
f
o
r
u
tili
zin
g
c
r
o
s
s
-
r
elatio
n
s
h
i
p
s
b
etwe
en
th
e
m
u
lti
-
s
ca
le
f
ea
tu
r
es.
Fo
r
ef
f
ec
tiv
ely
u
tili
z
in
g
s
p
atial
-
s
p
ec
tr
al
f
ea
tu
r
es,
p
r
esen
ted
a
Plu
g
a
n
d
Play
Ad
ap
tiv
e
-
Featu
r
e
-
Fu
s
io
n
ap
p
r
o
ac
h
.
B
y
co
m
b
in
in
g
b
o
th
th
e
ap
p
r
o
ac
h
es
th
ey
p
r
esen
ted
th
eir
n
o
v
el
tech
n
iq
u
e
wh
ich
was
ca
lled
as
ad
ap
tiv
e
-
s
p
ec
tr
al
-
s
p
atial
f
ea
tu
r
e
-
f
u
s
io
n
-
n
etwo
r
k
(
AS2
F2
N)
f
o
r
class
if
icatio
n
o
f
HSI
.
T
h
e
ev
alu
atio
n
was
co
n
d
u
cte
d
u
s
in
g
I
P,
PU
an
d
H
U.
E
v
alu
atio
n
was
d
o
n
e
u
s
in
g
OA,
AA,
an
d
KC
.
Fin
d
in
g
s
s
h
o
w
9
8
.
1
1
%
o
f
OA,
9
3
.
6
2
%
o
f
AA,
an
d
KC
o
f
0
.
9
7
8
f
o
r
I
P
d
ataset.
Fu
r
th
er
,
f
o
r
PU
d
ataset
ac
h
ie
v
ed
9
8
.
6
5
%,
9
6
.
8
1
%
an
d
0
.
9
8
3
o
f
OA,
AA
an
d
KC
r
esp
e
ctiv
ely
.
Fin
ally
,
f
o
r
HSI
d
ataset
ac
h
iev
ed
8
9
.
7
7
%,
9
0
.
8
9
%
an
d
0
.
8
8
9
4
o
f
OA,
AA
an
d
KC
r
esp
ec
tiv
ely
.
He
et
a
l.
[
2
9
]
in
tr
o
d
u
ce
d
a
n
ew
o
b
ject
d
etec
tio
n
a
p
p
r
o
a
ch
ca
lled
S2
ADe
t
wh
ich
u
tili
ze
d
g
o
o
d
u
s
e
o
f
th
e
HSI
ab
u
n
d
an
t
s
p
atial
-
s
p
ec
tr
al
f
ea
tu
r
es.
T
h
eir
s
u
g
g
esti
o
n
w
as
to
u
s
e
a
two
-
s
tr
ea
m
n
etw
o
r
k
f
o
r
a
g
g
r
eg
atin
g
s
p
atial
-
s
p
ec
tr
al
f
ea
tu
r
es.
I
n
ad
d
itio
n
,
th
ey
an
n
o
tated
a
lar
g
e
d
ataset
ca
lled
HO
D3
K,
w
h
ich
in
clu
d
ed
t
h
r
ee
o
b
ject
class
es
an
d
3
2
4
2
HSI
s
tak
en
f
r
o
m
v
ar
io
u
s
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
,
in
o
r
d
er
to
o
v
er
co
m
e
th
e
s
h
o
r
tco
m
in
g
s
o
f
cu
r
r
en
t
d
atasets
.
T
h
e
im
ag
es
en
co
m
p
ass
ed
1
6
b
a
n
d
s
b
etwe
en
4
7
0
an
d
6
2
0
n
m
a
n
d
h
a
d
a
p
i
x
el
-
r
eso
lu
tio
n
o
f
5
1
2
×2
5
6
.
E
x
ten
s
iv
e
test
in
g
o
n
two
d
atasets
p
r
o
v
ed
th
at
S2
ADe
t
o
u
tp
er
f
o
r
m
e
d
cu
r
r
en
t
s
tate
-
of
-
th
e
-
ar
t
a
p
p
r
o
ac
h
es.
I
s
lam
et
a
l.
[
3
0
]
,
p
r
esen
te
d
a
DL
ap
p
r
o
ac
h
wh
ich
r
ed
u
ce
d
t
h
e
d
i
m
en
s
io
n
an
d
r
esam
p
le
d
th
e
HSI
im
ag
e
d
u
r
in
g
p
r
ep
r
o
ce
s
s
in
g
.
Fo
r
s
tr
ea
m
lin
i
n
g
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
s
el
ec
tio
n
wh
ile
k
ee
p
in
g
r
ed
u
n
d
an
cy
t
o
least,
th
ei
r
ap
p
r
o
ac
h
u
tili
ze
d
a
u
n
iq
u
e
s
u
b
-
g
r
o
u
p
b
ased
d
im
en
s
io
n
r
e
d
u
ctio
n
ap
p
r
o
ac
h
.
Fu
r
th
er
m
o
r
e
,
f
o
r
s
o
lv
in
g
class
im
b
alan
ce
is
s
u
e,
th
e
r
esam
p
l
ed
d
ata.
A
f
ter
p
r
ep
r
o
c
ess
in
g
,
th
e
d
ata
wen
t
th
r
o
u
g
h
a
h
y
b
r
id
C
NN
ap
p
r
o
ac
h
wh
er
e
th
e
s
p
atial
-
s
p
ec
tr
al
f
ea
t
u
r
es
wer
e
ex
tr
ac
ted
.
B
y
r
esa
m
p
lin
g
,
th
e
ac
h
iev
ed
b
etter
p
er
f
o
r
m
a
n
ce
ev
en
i
n
th
e
ex
is
ten
ce
o
f
n
o
is
e.
E
v
alu
atio
n
s
wer
e
co
n
d
u
cted
u
s
in
g
k
en
n
e
d
y
-
s
p
ac
e
-
ce
n
ter
(
KSC
)
[
3
1
]
SA
an
d
PU
d
ataset.
T
h
e
ap
p
r
o
ac
h
ac
h
iev
ed
OA
o
f
9
9
.
4
6
%,
9
9
.
9
4
%
an
d
9
9
.
9
8
%
f
o
r
KSC
,
SA
an
d
PU
r
esp
ec
tiv
ely
.
F.
Fen
g
et
a
l.
[
3
2
]
,
p
r
esen
ted
a
lo
w
-
r
an
k
-
lim
ited
atten
tio
n
-
e
n
h
a
n
ce
d
-
m
u
ltip
le
f
ea
tu
r
e
-
f
u
s
io
n
-
n
etwo
r
k
(
L
AM
FN)
.
T
h
e
y
p
e
r
f
o
r
m
e
d
s
p
e
c
t
r
a
l
f
e
a
t
u
r
e
s
p
r
e
p
r
o
c
e
s
s
i
n
g
t
o
i
d
e
n
t
i
f
y
a
s
m
a
l
l
n
u
m
b
e
r
o
f
f
e
a
t
u
r
e
s
w
h
i
c
h
c
a
n
b
e
c
h
a
r
a
c
t
e
r
i
z
e
d
u
t
i
l
i
z
i
n
g
t
h
e
i
n
i
t
i
a
l
d
a
t
a
s
e
t
a
n
d
c
o
v
a
r
i
a
n
c
e
d
a
t
a
.
T
h
e
n
e
x
t
r
a
c
t
e
d
d
e
e
p
f
e
a
t
u
r
e
s
u
t
i
l
i
z
i
n
g
a
l
i
g
h
t
w
e
i
g
h
t
a
t
t
e
n
t
i
o
n
-
e
n
h
a
n
c
e
d
3D
-
C
o
n
v
o
l
u
t
i
o
n
a
p
p
r
o
a
c
h
,
a
n
d
t
o
a
d
d
t
o
t
h
e
p
o
s
i
t
i
o
n
-
s
e
n
s
i
t
i
v
e
d
a
t
a
,
a
2
D
c
o
o
r
d
i
n
a
t
e
s
-
a
t
t
e
n
t
i
o
n
n
e
t
w
o
r
k
w
a
s
e
m
p
l
o
y
e
d
.
F
o
u
r
H
S
I
d
a
t
a
s
e
t
,
i
.
e
.
,
W
H
U
-
H
o
n
g
H
u
(
W
H
U
)
[
3
3
]
,
I
P
,
H
U
a
n
d
P
U
w
e
r
e
c
o
n
s
i
d
e
r
e
d
.
T
h
e
y
a
c
h
i
e
v
e
d
7
8
.
1
5
%
f
o
r
I
P
,
9
7
.
1
8
%
f
o
r
P
U
,
8
1
.
3
5
%
f
o
r
H
U
a
n
d
8
7
.
9
3
%
f
o
r
W
H
U
r
e
s
p
e
c
t
i
v
e
l
y
.
Dan
g
et
a
l.
[
3
4
]
,
p
r
esen
ted
n
o
v
el
d
o
u
b
le
-
b
r
a
n
ch
f
ea
tu
r
e
-
f
u
s
i
o
n
tr
an
s
f
o
r
m
er
ap
p
r
o
ac
h
f
o
r
c
lass
if
y
in
g
HSI
.
T
h
ey
d
ev
elo
p
ed
two
atten
tio
n
-
m
o
d
u
les
wh
ich
d
y
n
am
ically
ch
an
g
ed
th
e
weig
h
ts
as
s
ig
n
ed
to
d
if
f
er
e
n
t
s
p
ec
tr
u
m
b
a
n
d
s
an
d
p
i
x
els
in
class
if
y
in
g
HSI
.
Fo
u
r
d
ataset
s
,
i.e
.
,
KSC
,
SA,
PU,
an
d
H
U
wer
e
u
tili
ze
d
f
o
r
ev
alu
atio
n
.
Acc
o
r
d
i
n
g
to
t
h
e
KSC
d
ataset,
th
e
OA
was
9
8
.
6
4
%,
th
e
AA
was
9
7
.
1
3
%,
an
d
th
e
KC
was
0
.
9
8
4
9
.
Fo
r
th
e
SA
d
ataset
OA
was
9
8
.
5
0
%,
AA
was
9
9
.
1
8
%,
an
d
KC
was
0
.
9
8
3
3
,
r
esp
ec
tiv
ely
.
Fo
r
th
e
PU
d
ataset,
ac
h
iev
ed
OA
o
f
9
8
.
7
6
%,
AA
o
f
9
7
.
7
1
%,
an
d
KC
o
f
0
.
9
8
3
6
.
Acc
o
r
d
in
g
to
th
e
HU
d
a
taset,
th
e
OA
was
9
0
.
0
8
%,
th
e
AA
was
9
0
.
5
5
%,
an
d
t
h
e
KC
was
0
.
8
9
2
7
.
W
an
an
d
C
h
en
[
3
5
]
,
p
r
o
p
o
s
ed
m
u
lti
-
s
tr
ateg
y
-
f
u
s
io
n
(
MSF)
f
r
am
ewo
r
k
th
at
r
elied
o
n
bi
-
ex
p
o
n
en
tial
ed
g
e
-
p
r
eser
v
in
g
-
s
m
o
o
t
h
er
(
B
E
E
PS
)
.
A
S
VM
clas
s
if
ier
was
s
u
b
s
eq
u
en
tly
em
p
lo
y
ed
to
d
et
er
m
in
e
th
e
p
ix
els
s
o
f
t
class
if
i
ca
tio
n
p
r
o
b
ab
ilit
y
.
I
n
ad
d
itio
n
,
B
E
E
PS
wa
s
u
s
ed
to
r
o
u
n
d
o
f
f
th
e
s
u
b
s
eq
u
e
n
t
p
r
o
ce
s
s
in
g
o
f
s
o
f
t
class
if
ied
p
r
o
b
ab
ilit
y
m
a
p
s
;
th
is
was
d
o
n
e
to
e
n
h
an
ce
HSI
'
s
class
if
icatio
n
ac
cu
r
ac
y
s
u
b
s
ta
n
tially
b
y
ta
k
in
g
co
n
tex
t
-
awa
r
e
d
ata
r
elate
d
to
all
lab
ele
d
cl
ass
es
in
to
ac
co
u
n
t.
Usi
n
g
th
r
ee
HSI
d
atasets
,
i.e
.
,
I
P,
KSC
,
an
d
HU
an
d
r
an
d
o
m
l
y
s
elec
tin
g
1
%,
6
%,
an
d
5
% o
f
th
e
s
am
p
les to
b
e
lab
eled
f
o
r
tr
ain
in
g
,
MSF
ac
h
iev
ed
OA
o
f
9
9
.
4
7
%,
9
9
.
5
2
%
,
an
d
9
4
.
2
5
%,
r
esp
ec
tiv
ely
.
Y
an
an
d
Ho
n
g
[
3
6
]
,
p
r
esen
ted
a
n
o
v
el
m
eth
o
d
wh
ich
co
m
b
in
e
d
th
e
b
est
f
ea
tu
r
e
s
o
f
th
e
two
m
o
d
els,
i.e
.
,
m
u
l
ti
-
lay
er
p
er
ce
p
tr
o
n
(
ML
P)
an
d
C
NN.
Fo
r
cla
s
s
if
icatio
n
,
th
ey
u
tili
ze
d
m
er
g
e
d
s
p
atial
-
s
p
ec
tr
al
f
ea
tu
r
es
d
ata
d
ir
ec
tly
in
to
ML
P
ar
ch
itectu
r
e
a
f
ter
f
ir
s
t
u
s
in
g
C
NN.
Fu
r
th
er
m
o
r
e,
t
h
ey
p
r
esen
ted
a
m
in
im
alis
tic
ap
p
r
o
ac
h
to
r
em
o
v
e
th
e
ef
f
ec
t
o
f
u
n
n
ec
ess
ar
y
s
p
ec
tr
u
m
f
r
eq
u
en
cies.
E
v
alu
ati
o
n
was
d
o
n
e
o
n
I
P,
PU
an
d
SA.
T
h
e
OA,
AA,
an
d
KC
ac
h
iev
ed
f
o
r
I
P
d
ataset
was
9
9
.
2
8
%,
9
8
.
8
2
%
an
d
0
.
9
9
1
8
.
T
h
e
OA,
AA,
an
d
KC
ac
h
iev
ed
f
o
r
PU
d
ataset
was
9
8
.
9
8
%,
9
8
.
7
4
%
an
d
0
.
9
8
6
5
.
T
h
e
OA,
AA,
an
d
KC
ac
h
iev
ed
f
o
r
SA
d
ataset
was
9
9
.
3
0
%,
9
9
.
3
4
%
an
d
0
.
9
9
2
2
.
Gu
et
a
l.
[
3
7
]
,
p
r
es
en
ted
a
m
u
lti
-
s
ca
le
s
p
atial
-
s
p
ec
tr
al
atten
tio
n
-
n
etwo
r
k
with
f
r
eq
u
en
cy
-
d
o
m
ain
lig
h
tweig
h
t
-
tr
an
s
f
o
r
m
er
(
MS
A
-
L
W
Fo
r
m
er
)
f
o
r
class
if
icatio
n
o
f
HSI
.
B
o
th
th
e
f
r
eq
u
en
cy
-
d
o
m
ain
f
u
s
ed
class
if
ier
an
d
s
p
ec
tr
al
-
s
p
atial
ex
tr
ac
ted
f
ea
tu
r
e
m
o
d
u
les
we
r
e
en
h
an
ce
d
b
y
th
e
tech
n
iq
u
e
'
s
in
co
r
p
o
r
atio
n
o
f
T
r
an
s
f
o
r
m
e
r
,
atten
tio
n
m
ec
h
an
is
m
s
,
alo
n
g
with
C
NN.
I
n
o
r
d
e
r
to
ac
q
u
ir
e
t
h
e
s
h
allo
w
s
p
ec
tr
al
-
s
p
atial
ch
ar
ac
ter
is
tics
alo
n
g
with
ca
p
tu
r
in
g
l
o
n
g
-
r
an
g
e
s
p
ec
tr
al
d
ep
en
d
en
cies,
t
h
e
s
p
ec
tr
al
-
s
p
at
ial
f
ea
tu
r
e
r
et
r
iev
al
m
o
d
u
les
u
s
ed
a
Mu
lti
-
Scale
2
D
-
C
NN
in
teg
r
atin
g
m
u
lti
-
s
ca
le
s
p
ec
tr
al
-
atten
tio
n
(
MS
-
SA)
.
E
x
p
er
im
e
n
ts
wer
e
d
o
n
e
o
n
PU,
I
P a
n
d
SA.
E
v
alu
atio
n
was d
o
n
e
u
s
in
g
OA,
AA,
an
d
KC
.
Fin
d
in
g
s
s
h
o
w
9
8
.
8
7
% o
f
OA,
9
8
.
6
8
%
o
f
AA
an
d
KC
o
f
0
.
9
8
7
1
f
o
r
I
P
d
ataset,
9
9
.
7
9
%
o
f
OA,
9
9
.
6
8
%
o
f
AA
an
d
KC
o
f
0
.
9
9
7
3
f
o
r
PU
d
ataset,
an
d
9
9
.
9
6
%
o
f
OA,
9
9
.
9
5
% o
f
AA
an
d
KC
o
f
0
.
9
9
9
5
f
o
r
SA d
ata
s
et.
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:
2
5
0
2
-
4
7
52
E
n
h
a
n
ci
n
g
h
y
p
ers
p
ec
tr
a
l ima
g
e
o
b
ject
cla
s
s
ifica
tio
n
th
r
o
u
g
h
r
o
b
u
s
t fe
a
tu
r
e
…
(
V
ija
yla
xm
i Ko
ch
a
r
i
)
283
Z
h
an
g
et
a
l.
[
3
8
]
,
p
r
esen
ted
a
n
o
v
el
3
D
-
2
D
h
y
b
r
id
-
co
n
v
o
lu
ti
o
n
an
d
g
r
a
p
h
-
atten
tio
n
-
m
ec
h
a
n
is
m
(
3
D
-
2D
-
GAT
)
b
ased
en
d
-
to
-
en
d
H
SI
class
if
icat
io
n
.
T
o
ac
h
iev
e
h
ig
h
er
class
if
icatio
n
ac
cu
r
ac
y
,
t
h
e
tech
n
iq
u
e
m
a
d
e
u
s
e
o
f
th
e
co
m
b
i
n
ed
ef
f
o
r
ts
o
f
th
e
GAT
co
m
p
o
n
en
t
al
o
n
g
with
th
e
h
y
b
r
id
c
o
n
v
o
lu
tio
n
al
ex
tr
ac
ted
f
ea
tu
r
es
m
o
d
u
le.
GAT
was
u
s
ed
to
l
ea
r
n
s
p
atial
r
elatio
n
s
h
ip
s
ac
r
o
s
s
v
ast
d
is
tan
ce
s
an
d
to
d
if
f
er
en
tiate
b
etwe
en
s
am
p
les
with
co
m
p
ar
ab
le
an
d
v
ar
io
u
s
s
tag
es
o
f
v
ar
iatio
n
with
in
ea
ch
class
.
T
h
e
s
u
g
g
ested
m
eth
o
d
o
u
tp
er
f
o
r
m
ed
p
r
e
v
io
u
s
s
tate
-
of
-
th
e
-
ar
t
m
eth
o
d
s
in
ter
m
s
o
f
class
if
icatio
n
ac
cu
r
ac
y
,
ac
c
o
r
d
in
g
t
o
f
in
d
in
g
s
f
r
o
m
e
x
p
er
im
e
n
ts
o
n
th
e
I
P,
PU,
an
d
SA
d
atasets
.
Fin
d
in
g
s
s
h
o
w
9
9
.
1
9
%
o
f
OA,
9
9
.
3
%
o
f
AA
an
d
KC
o
f
0
.
9
9
0
7
f
o
r
I
P
d
ataset,
9
9
.
7
3
%
o
f
OA,
9
9
.
5
8
%
o
f
AA
an
d
KC
o
f
0
.
9
9
6
4
f
o
r
PU
d
ataset,
a
n
d
9
9
.
4
3
%
o
f
OA,
9
9
.
5
2
%
o
f
AA
an
d
KC
o
f
0
.
9
9
3
7
f
o
r
SA
d
ataset.
Ar
s
h
ad
et
a
l.
[
3
9
]
,
p
r
esen
ted
h
y
b
r
id
co
n
v
o
l
u
tio
n
-
tr
an
s
f
o
r
m
er
wh
er
e
v
is
u
al
tr
a
n
s
f
o
r
m
er
al
o
n
g
with
a
r
esid
u
al
3
D
C
NN
s
tr
u
ctu
r
e
wer
e
k
ey
c
o
m
p
o
n
en
ts
o
f
th
eir
ap
p
r
o
ac
h
.
T
o
f
u
r
th
er
p
r
ev
e
n
t
o
v
er
f
itti
n
g
p
r
o
b
lem
s
ca
u
s
ed
b
y
in
s
u
f
f
icien
t
tr
ain
in
g
d
at
a,
it
em
p
lo
y
e
d
an
o
r
d
er
in
g
ag
g
r
eg
atin
g
lay
er
.
Du
r
in
g
th
e
p
r
o
ce
s
s
o
f
f
ea
tu
r
e
ex
tr
ac
tio
n
,
t
h
eir
s
u
g
g
ested
r
em
ain
in
g
atten
tio
n
-
c
h
a
n
n
e
l
m
o
d
u
l
e
p
r
e
s
e
r
v
e
d
s
p
ec
t
r
a
l
f
e
a
t
u
r
es
a
n
d
a
c
q
u
i
r
e
d
m
o
r
e
c
o
m
p
r
e
h
e
n
s
i
v
e
s
p
at
i
a
l
-
s
p
e
c
tr
a
l
c
o
m
p
l
e
m
e
n
t
a
r
y
d
ata.
T
h
e
y
r
an
test
s
o
n
th
e
SA
an
d
KSC
d
atasets
in
ad
d
itio
n
to
t
h
e
Xu
z
h
o
u
d
ataset
[
4
0
]
.
T
h
e
m
o
d
el
ac
h
iev
ed
9
9
.
7
5
%
o
f
OA,
9
9
.
7
1
%
o
f
A
A,
an
d
0
.
9
9
6
o
f
KC
f
o
r
SA,
9
9
.
4
6
%
o
f
OA,
9
9
.
4
4
%
o
f
AA
an
d
0
.
9
9
3
1
%
o
f
KC
f
o
r
X
u
zh
o
u
d
ataset
an
d
9
9
.
9
5
%
o
f
OA,
9
9
.
9
6
%
o
f
AA
an
d
0
.
9
9
9
5
o
f
KC
f
o
r
KSC
d
ataset.
Ali
et
a
l.
in
[
4
1
]
,
p
r
e
s
e
n
t
e
d
T
B
M
SS
N
,
a
t
w
o
-
b
r
a
n
c
h
m
u
l
t
i
-
s
c
al
e
s
p
e
c
t
r
al
-
s
p
at
ia
l
f
e
a
t
u
r
e
-
e
x
t
r
a
c
ti
o
n
-
n
e
t
w
o
r
k
f
o
r
c
l
a
s
s
i
f
y
i
n
g
H
S
I
s
.
W
i
t
h
t
h
e
g
o
a
l
o
f
e
n
h
a
n
c
e
d
f
e
a
t
u
r
e
r
e
p
r
e
s
e
n
t
at
i
o
n
s
,
t
h
e
y
d
ev
e
l
o
p
e
d
t
h
e
m
u
l
t
i
-
s
c
a
l
e
-
s
p
a
t
i
al
f
e
a
t
u
r
e
-
e
x
t
r
a
c
ti
o
n
(
M
S
AF
E
)
a
n
d
m
u
l
ti
-
s
c
al
e
-
s
p
ec
t
r
a
l
f
e
at
u
r
e
-
e
x
t
r
a
c
ti
o
n
(
M
S
E
FE
)
.
T
h
e
y
i
m
p
r
o
v
e
d
f
e
a
t
u
r
e
e
x
tr
a
c
t
i
o
n
,
r
e
d
u
c
e
d
t
h
e
v
a
n
i
s
h
i
n
g
-
g
r
a
d
i
e
n
t
is
s
u
e
,
a
n
d
a
c
h
i
e
v
e
d
m
a
x
i
m
u
m
e
f
f
e
c
t
i
v
e
n
e
s
s
a
n
d
e
f
f
ic
i
e
n
c
y
b
y
d
e
n
s
e
l
y
c
o
n
n
e
c
t
i
n
g
s
e
r
i
es
o
f
M
S
AF
E
o
r
MS
E
F
E
m
o
d
u
l
e
s
in
a
t
w
o
-
b
r
a
n
c
h
a
r
c
h
it
e
c
t
u
r
e
,
r
es
p
e
c
t
i
v
el
y
.
T
h
e
y
a
c
h
ie
v
e
d
9
9
.
3
2
%
o
f
O
A
,
9
8
.
2
6
%
o
f
A
A
,
0
.
9
9
2
2
o
f
K
C
f
o
r
I
P
d
a
ta
s
e
t
,
9
9
.
8
6
%
o
f
OA
,
9
9
.
7
3
%
o
f
A
A
a
n
d
0
.
9
9
8
1
o
f
K
C
f
o
r
P
U
d
a
t
a
s
et
.
Hu
an
g
et
a
l.
[
4
2
]
d
ev
el
o
p
e
d
a
DL
a
p
p
r
o
ac
h
f
o
r
i
d
en
ti
f
y
in
g
o
il
em
u
ls
io
n
s
u
s
in
g
a
s
p
ec
tr
al
-
s
p
atial
f
ea
tu
r
e
-
f
u
s
io
n
.
T
h
e
y
u
s
ed
th
e
c
o
n
v
e
n
tio
n
al
d
ev
iatio
n
ap
p
r
o
ac
h
f
o
r
f
ilter
in
g
o
u
t
f
ea
tu
r
e
-
b
an
d
s
wh
ich
co
u
ld
d
if
f
er
en
tiate
am
o
n
g
d
if
f
er
en
t
o
il
an
d
s
ea
wate
r
.
T
h
e
ev
alu
atio
n
was
d
o
n
e
u
s
in
g
th
eir
air
b
o
r
n
e
-
v
is
ib
le
in
f
r
ar
ed
-
im
ag
in
g
-
s
p
ec
tr
o
m
e
ter
(
AVI
R
I
S)
d
ataset.
T
h
ey
ac
h
iev
ed
OA
o
f
9
1
.
8
0
%,
KC
o
f
8
6
%
with
f
ea
tu
r
e
s
elec
tio
n
.
Sig
g
er
et
a
l.
[
4
3
]
,
p
r
esen
ted
Dif
f
Sp
ec
tr
alNe
t
m
eth
o
d
a
h
y
b
r
id
o
f
d
if
f
u
s
i
o
n
a
n
d
tr
an
s
f
o
r
m
er
ap
p
r
o
ac
h
es.
T
h
e
d
if
f
u
s
io
n
te
ch
n
iq
u
e
im
p
r
o
v
e
d
HSI
class
if
icatio
n
b
y
ex
tr
ac
tin
g
v
ar
io
u
s
an
d
s
ig
n
if
ican
t
s
p
ec
tr
al
-
s
p
atial
f
ea
tu
r
es.
Util
izin
g
a
p
r
e
-
tr
ain
ed
d
e
n
o
is
in
g
U
-
Net
f
o
r
class
if
icatio
n
,
t
h
ey
d
ev
elo
p
ed
an
u
n
s
u
p
er
v
is
ed
tr
ain
i
n
g
s
tr
u
ct
u
r
e
em
p
lo
y
in
g
th
e
d
i
f
f
u
s
io
n
s
y
s
tem
to
ex
tr
ac
t
h
ig
h
an
d
lo
w
-
lev
el
s
p
atial
-
s
p
ec
tr
al
f
ea
tu
r
es.
T
h
ey
ac
h
iev
ed
9
9
.
0
6
%,
9
9
.
7
4
%
an
d
9
9
.
8
7
%
o
f
OA
f
o
r
I
P,
PU
an
d
S
A
r
esp
ec
tiv
ely
.
Fu
r
th
er
f
o
r
AA,
ac
h
iev
ed
9
8
.
0
0
%,
9
9
.
1
8
%
an
d
9
9
.
8
2
%
f
o
r
I
P,
PU
an
d
SA
r
esp
ec
tiv
ely
.
Fin
ally
,
f
o
r
KC
ac
h
iev
ed
0
.
9
8
9
3
,
0
.
9
9
6
5
an
d
0
.
9
9
8
6
f
o
r
I
P,
PU
an
d
SA
r
esp
ec
tiv
ely
.
Ash
r
af
et
a
l.
[
4
4
]
p
r
esen
ted
a
tten
tio
n
-
3d
-
ce
n
tr
al
-
d
if
f
er
en
ce
-
co
n
v
o
lu
tio
n
al
d
e
n
s
e
-
n
etwo
r
k
(
3
D
-
C
DC
Atten
tio
n
-
Den
s
eNe
t)
.
T
h
e
y
u
s
ed
a
d
en
s
e
ap
p
r
o
ac
h
th
at
in
clu
d
ed
p
i
x
el
-
wis
e
co
m
b
in
a
tio
n
alo
n
g
s
id
e
a
s
p
atial
atten
tio
n
s
y
s
tem
to
co
m
b
in
e
lo
w
-
r
an
k
f
r
e
q
u
en
c
y
ch
ar
ac
ter
is
tics
an
d
d
ir
ec
t
ch
ar
ac
ter
is
tic
tu
n
in
g
in
th
eir
3
D
-
C
DC
m
eth
o
d
,
wh
ich
r
elied
o
n
m
an
ip
u
latin
g
lo
ca
l
b
u
ilt
-
in
in
tr
icate
p
atter
n
s
with
in
th
e
s
p
ec
tr
al
-
s
p
atial
f
ea
tu
r
es
m
ap
s
.
T
h
e
a
p
p
r
o
ac
h
ac
h
iev
e
d
OA
o
f
9
7
.
9
3
%
f
o
r
HU,
9
9
.
8
9
%
f
o
r
PU
an
d
9
9
.
3
8
%
f
o
r
I
P
d
ataset.
G
o
s
wam
i
et
a
l.
[
4
5
]
p
r
esen
te
d
a
HSI
u
s
in
g
a
m
ix
o
f
t
h
r
e
e
tech
n
iq
u
es:
C
NN,
s
ta
tio
n
ar
y
-
wav
elet
-
tr
an
s
f
o
r
m
atio
n
s
(
SW
T
)
an
d
p
r
in
cip
al
-
co
m
p
o
n
en
t
-
a
n
aly
s
is
(
PC
A)
.
Af
ter
r
ed
u
cin
g
d
im
e
n
s
io
n
ality
a
n
d
ex
tr
ac
tin
g
s
p
atial
-
s
p
ec
tr
al
f
ea
t
u
r
es
with
SW
T
an
d
PC
A,
th
e
s
u
g
g
ested
m
eth
o
d
u
s
es
C
NN
f
o
r
class
if
icatio
n
.
W
ith
an
OA
o
f
9
8
.
2
%
o
n
th
e
I
P
d
ataset,
9
9
.
8
6
%
o
n
th
e
SA
d
ataset,
an
d
9
9
.
8
0
%
o
n
th
e
PU
d
ataset,
th
e
r
esu
lt
s
s
h
o
w
th
at
th
e
s
u
g
g
ested
S
W
T
-
PC
A
-
C
NN
m
eth
o
d
o
u
tp
er
f
o
r
m
s
th
e
tr
ad
itio
n
al
tech
n
iq
u
es.
3.
F
I
NDING
S
T
h
e
a
b
o
v
e
f
i
n
d
i
n
g
s
f
r
o
m
t
h
e
l
it
e
r
a
t
u
r
e
s
u
r
v
e
y
h
a
v
e
b
e
e
n
i
d
e
n
t
i
f
i
e
d
w
h
ic
h
i
s
p
r
e
s
e
n
t
e
d
i
n
T
ab
l
e
1
.
T
h
e
f
i
n
d
i
n
g
s
f
r
o
m
t
h
e
a
b
o
v
e
r
e
v
ie
w
s
h
o
ws
m
o
s
t
o
f
t
h
e
w
o
r
k
c
o
n
s
id
e
r
e
d
f
o
r
h
y
p
e
r
s
p
e
c
t
r
al
i
m
a
g
e
o
b
j
e
c
t
i
d
e
n
t
i
f
i
c
at
i
o
n
h
a
v
e
u
s
e
d
DL
i
n
s
t
e
a
d
o
f
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
.
F
u
r
t
h
e
r
,
i
t
h
a
s
b
e
e
n
s
e
e
n
t
h
a
t
a
l
l
t
h
e
w
o
r
k
s
h
a
v
e
c
o
n
s
i
d
e
r
e
d
s
i
m
i
l
ar
m
e
t
r
i
c
s
f
o
r
e
v
a
l
u
a
t
i
o
n
,
i
.
e
.
,
O
A,
A
A
a
n
d
KC
.
Al
s
o
,
t
h
e
d
a
t
as
et
s
u
s
e
d
i
n
t
h
e
i
r
w
o
r
k
s
h
o
ws
t
h
a
t
m
o
s
t
o
f
t
h
e
w
o
r
k
h
a
v
e
u
s
e
d
I
P
,
P
U
,
SA
,
K
SC
a
n
d
H
U
d
a
t
a
s
et
.
V
e
r
y
l
e
s
s
wo
r
k
h
a
s
c
o
n
s
i
d
e
r
e
d
d
i
f
f
e
r
e
n
t
d
a
t
a
s
et
l
i
k
e
[
2
9
]
h
a
s
c
o
n
s
i
d
e
r
e
d
H
OD
3
K
,
[
3
9
]
h
a
s
co
n
s
i
d
e
r
e
d
X
u
z
h
o
u
d
a
t
a
s
e
t
a
n
d
in
[
4
2
]
h
a
v
e
c
o
n
s
i
d
e
r
e
d
a
n
o
i
l
d
a
t
a
s
et
.
Fro
m
th
e
ab
o
v
e
liter
atu
r
e
s
u
r
v
ey
,
it
is
s
ee
n
th
at
s
ev
er
al
n
o
v
el
ap
p
r
o
ac
h
es
h
av
e
b
ee
n
p
r
o
p
o
s
ed
f
o
r
h
y
p
er
s
p
ec
tr
al
im
a
g
e
(
HSI
)
cla
s
s
if
icatio
n
,
ea
ch
o
f
f
er
i
n
g
u
n
iq
u
e
s
tr
en
g
th
s
an
d
ad
v
a
n
ce
m
en
t
s
in
th
e
f
ield
.
T
h
e
ap
p
r
o
ac
h
es
p
r
esen
ted
in
[
2
2
]
,
[
2
7
]
,
i.e
.
,
DI
GC
N
an
d
MSSGs
r
esp
ec
tiv
ely
ar
e
m
ain
ly
f
o
cu
s
ed
o
n
r
em
o
v
in
g
n
o
is
e
an
d
o
b
ject
d
etec
tio
n
.
Fu
r
th
er
,
th
e
n
o
v
el
s
p
ec
tr
al
-
s
p
atial
ag
g
r
eg
atio
n
(
S2
ADe
t)
m
eth
o
d
b
y
He
et
a
l.
[
2
9
]
s
tan
d
s
o
u
t
f
o
r
its
f
o
cu
s
o
n
s
p
ec
tr
al
-
s
p
atial
ag
g
r
eg
atio
n
in
h
y
p
er
s
p
ec
tr
al
o
b
ject
d
et
ec
tio
n
,
f
ea
tu
r
in
g
a
h
y
p
er
s
p
ec
tr
al
in
f
o
r
m
atio
n
d
e
co
u
p
lin
g
(
HI
D)
m
o
d
u
le,
a
tw
o
-
s
tr
ea
m
f
ea
tu
r
e
ex
tr
ac
tio
n
n
etwo
r
k
,
an
d
a
o
n
e
-
s
tag
e
d
etec
tio
n
h
ea
d
.
T
h
is
ap
p
r
o
ac
h
s
h
o
wca
s
es r
o
b
u
s
t a
n
d
r
e
liab
le
r
esu
lts
,
p
ar
ticu
lar
ly
o
u
tp
er
f
o
r
m
in
g
ex
is
tin
g
m
eth
o
d
s
o
n
th
e
HOD3
K
d
at
aset.
An
o
th
er
n
o
tewo
r
t
h
y
c
o
n
tr
ib
u
tio
n
is
th
e
l
o
w
-
r
an
k
co
n
s
tr
ain
ed
atten
tio
n
-
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
279
-
2
8
7
284
en
h
an
ce
d
m
u
ltip
le
f
ea
t
u
r
e
f
u
s
io
n
n
etw
o
r
k
(
L
AM
FN)
b
y
Fen
g
et
a
l.
[
3
2
]
,
wh
ich
lev
e
r
ag
e
s
f
ac
to
r
an
aly
s
is
f
o
r
s
p
ec
tr
al
f
ea
tu
r
e
p
r
ep
r
o
ce
s
s
in
g
,
a
lig
h
tweig
h
t
atten
tio
n
-
en
h
an
ce
d
3
D
c
o
n
v
o
lu
tio
n
m
o
d
u
le
f
o
r
d
ee
p
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
an
d
lo
w
-
r
an
k
s
ec
o
n
d
-
o
r
d
er
p
o
o
lin
g
f
o
r
c
o
n
v
o
lu
t
io
n
al
f
ea
tu
r
e
s
elec
tiv
ity
.
Desp
ite
lim
ited
tr
ain
in
g
d
ata,
L
AM
FN
ac
h
iev
es
s
ig
n
if
ican
t
im
p
r
o
v
em
e
n
ts
in
OA
o
n
d
atasets
lik
e
I
P,
PU,
HU,
an
d
W
HU.
Ad
d
itio
n
ally
,
t
h
e
d
o
u
b
le
-
b
r
an
ch
f
ea
tu
r
e
f
u
s
io
n
tr
a
n
s
f
o
r
m
er
(
DB
FF
T
)
in
tr
o
d
u
ce
d
b
y
Dan
g
et
a
l.
[
3
4
]
e
x
ce
ls
in
h
an
d
lin
g
s
p
ec
tr
al
s
eq
u
e
n
ce
c
h
ar
ac
ter
is
tics
,
ac
h
iev
in
g
h
ig
h
OA,
AA,
an
d
KC
s
co
r
es
ac
r
o
s
s
d
atasets
lik
e
KSC
,
SA,
PU,
an
d
HU.
T
h
ese
m
eth
o
d
s
,
alo
n
g
with
o
th
er
s
lik
e
th
e
m
u
lti
-
s
tr
at
eg
y
f
u
s
io
n
(
MSF)
Fra
m
ewo
r
k
b
y
W
an
an
d
C
h
en
g
[
3
5
]
,
th
e
o
il
em
u
ls
io
n
d
ee
p
-
lea
r
n
in
g
id
e
n
tific
atio
n
m
o
d
el
by
Hu
an
g
et
a
l.
[
4
2
]
,
Dif
f
Sp
ec
tr
alNe
t
b
y
Sig
g
er
et
a
l.
[
4
3
]
,
an
d
3
D
-
C
DC
Atten
tio
n
Den
s
eNe
t
b
y
Ash
r
af
et
a
l.
[
4
4
]
,
co
llect
iv
ely
co
n
tr
ib
u
te
to
ad
v
an
cin
g
th
e
s
tate
-
of
-
th
e
-
ar
t
in
HSI
clas
s
if
icatio
n
b
y
in
teg
r
atin
g
in
n
o
v
ativ
e
tech
n
iq
u
es
s
u
ch
as
d
if
f
u
s
io
n
,
tr
an
s
f
o
r
m
er
,
atten
tio
n
m
ec
h
a
n
is
m
s
,
an
d
f
ea
t
u
r
e
f
u
s
io
n
to
ac
h
iev
e
r
em
ar
k
a
b
le
p
e
r
f
o
r
m
an
ce
g
ain
s
ac
r
o
s
s
v
ar
io
u
s
ev
alu
atio
n
m
etr
ics an
d
d
atasets
.
I
n
th
e
n
ex
t sectio
n
,
i
s
s
u
es a
n
d
ch
allen
g
es a
r
e
d
is
cu
s
s
ed
.
T
ab
le
1
.
Fin
d
in
g
s
f
r
o
m
ab
o
v
e
liter
atu
r
e
r
ev
iew
R
e
f
e
r
e
n
c
e
M
e
t
h
o
d
o
l
o
g
y
P
e
r
f
o
r
ma
n
c
e
me
t
r
i
c
s
D
a
t
a
s
e
t
[
2
2
]
D
e
e
p
Le
a
r
n
i
n
g
(
D
I
G
C
N
)
O
A
,
A
A
,
K
C
I
P
,
S
A
,
P
U
,
H
U
[
2
7
]
D
e
e
p
Le
a
r
n
i
n
g
(
M
S
S
G
s)
N
o
i
se
R
e
m
o
v
a
l
,
O
A
,
A
A
,
K
C
I
P
,
P
U
[
2
8
]
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
(
A
S
2
F
2
N
)
O
A
,
A
A
,
K
C
I
P
,
P
U
,
H
U
[
2
9
]
D
e
e
p
Le
a
r
n
i
n
g
(
S
2
A
D
e
t
)
O
A
,
A
A
,
K
C
H
O
D
3
K
[
3
0
]
D
e
e
p
Le
a
r
n
i
n
g
(
H
y
b
r
i
d
C
N
N
)
O
A
,
A
A
,
K
C
S
A
,
P
U
,
K
S
C
[
3
2
]
D
e
e
p
Le
a
r
n
i
n
g
(
LA
M
F
N
)
O
A
,
A
A
,
K
C
I
P
,
P
U
,
H
U
,
W
H
U
[
3
4
]
D
e
e
p
Le
a
r
n
i
n
g
(
D
B
F
F
T)
O
A
,
A
A
,
K
C
K
S
C
,
S
A
,
P
U
,
H
U
[
3
5
]
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
(
M
S
F
)
O
A
,
A
A
,
K
C
I
P
,
K
S
C
,
H
U
[
3
6
]
D
e
e
p
Le
a
r
n
i
n
g
(
C
N
N
+
Tr
a
n
sf
o
r
mer)
O
A
,
A
A
,
K
C
I
P
,
P
U
,
S
A
[
3
7
]
D
e
e
p
Le
a
r
n
i
n
g
(
M
S
A
-
LWF
o
r
m
e
r
)
O
A
,
A
A
,
K
C
I
P
,
P
U
,
S
A
[
3
8
]
D
e
e
p
Le
a
r
n
i
n
g
(
3
D
–
2D
-
G
A
T)
O
A
,
A
A
,
K
C
I
P
,
P
U
,
S
A
[
3
9
]
D
e
e
p
Le
a
r
n
i
n
g
(
H
y
b
r
i
d
C
o
n
v
o
l
u
t
i
o
n
Tr
a
n
sf
o
r
mer)
O
A
,
A
A
,
K
C
S
A
,
X
u
z
h
o
u
,
K
S
C
[
4
1
]
D
e
e
p
Le
a
r
n
i
n
g
(
T
B
M
S
S
N
)
O
A
,
A
A
,
K
C
I
P
,
P
U
[
4
3
]
D
e
e
p
Le
a
r
n
i
n
g
(
D
i
f
f
S
p
e
c
t
r
a
l
N
e
t
)
O
A
,
A
A
,
K
C
I
P
,
P
U
,
S
A
[
4
4
]
D
e
e
p
Le
a
r
n
i
n
g
(
3
D
-
C
D
C
A
t
t
e
n
t
i
o
n
D
e
n
s
e
N
e
t
)
O
A
,
A
A
,
K
C
H
U
,
P
U
,
I
P
[
4
5
]
D
e
e
p
Le
a
r
n
i
n
g
(
S
W
T
-
P
C
A
-
C
N
N
)
O
A
,
A
A
,
K
C
I
P
,
S
A
,
P
U
4.
I
SS
U
E
S,
CH
A
L
L
E
NG
E
S A
ND
SO
L
U
T
I
O
N
T
h
e
is
s
u
es a
n
d
ch
allen
g
es f
o
r
th
e
wo
r
k
id
e
n
tifie
d
f
r
o
m
th
e
a
b
o
v
e
liter
atu
r
e
s
u
r
v
ey
is
as f
o
llo
ws
:
−
L
im
ited
f
o
cu
s
o
n
f
ea
tu
r
e
ex
tr
ac
tio
n
:
Ma
n
y
e
x
is
tin
g
wo
r
k
s
in
h
y
p
e
r
s
p
ec
tr
al
im
ag
e
(
HSI
)
an
aly
s
is
h
av
e
p
lace
d
less
em
p
h
asis
o
n
r
o
b
u
s
t
an
d
ef
f
ec
tiv
e
f
ea
tu
r
e
ex
tr
ac
tio
n
tech
n
iq
u
es.
T
h
is
lack
o
f
atten
tio
n
ca
n
lead
to
s
u
b
o
p
tim
al
p
er
f
o
r
m
an
ce
in
class
if
icat
io
n
task
s
an
d
h
in
d
er
s
th
e
ab
ilit
y
to
f
u
lly
ex
p
lo
it
th
e
r
ich
in
f
o
r
m
atio
n
p
r
esen
t in
h
y
p
er
s
p
ec
tr
al
d
ata.
−
S
p
a
r
s
e
c
o
n
s
i
d
e
r
a
t
i
o
n
o
f
s
p
a
t
i
a
l
-
s
p
e
c
t
r
a
l
f
u
s
i
o
n
:
S
p
a
t
i
a
l
-
s
p
e
c
t
r
a
l
f
u
s
i
o
n
i
s
a
c
r
i
t
i
c
a
l
a
s
p
e
c
t
o
f
H
S
I
a
n
a
l
y
s
i
s
a
s
i
t
c
o
m
b
i
n
e
s
i
n
f
o
r
m
a
t
i
o
n
f
r
o
m
b
o
t
h
s
p
a
t
i
a
l
a
n
d
s
p
e
c
t
r
a
l
d
o
m
a
i
n
s
,
e
n
h
a
n
c
i
n
g
t
h
e
d
i
s
c
r
i
m
i
n
a
t
i
v
e
p
o
w
e
r
o
f
f
e
a
t
u
r
e
s
.
H
o
w
e
v
e
r
,
v
e
r
y
f
e
w
w
o
r
k
s
h
a
v
e
t
h
o
r
o
u
g
h
l
y
e
x
p
l
o
r
e
d
a
n
d
l
e
v
e
r
a
g
e
d
s
p
a
t
i
a
l
-
s
p
e
c
t
r
a
l
f
u
s
i
o
n
t
e
c
h
n
i
q
u
e
s
,
r
e
s
u
l
t
i
n
g
i
n
m
i
s
s
e
d
o
p
p
o
r
t
u
n
i
t
i
e
s
f
o
r
i
m
p
r
o
v
e
d
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
y
a
n
d
f
e
a
t
u
r
e
r
e
p
r
e
s
e
n
t
a
t
i
o
n
.
−
Neg
lect
o
f
n
o
is
e
in
HSI
d
ata:
No
is
e
is
an
in
h
er
en
t
ch
allen
g
e
in
HSI
,
af
f
ec
tin
g
th
e
q
u
ality
an
d
r
eliab
ilit
y
o
f
ex
tr
ac
ted
f
ea
tu
r
es.
Un
f
o
r
tu
n
ately
,
m
an
y
ex
is
tin
g
ap
p
r
o
a
ch
es
h
av
e
o
v
e
r
lo
o
k
ed
th
e
is
s
u
e
o
f
n
o
is
e
in
HSI
d
ata,
lead
in
g
to
p
o
ten
tial i
n
ac
cu
r
ac
ies an
d
r
ed
u
ce
d
r
o
b
u
s
tn
ess
in
class
if
icat
io
n
m
o
d
els.
−
I
n
s
u
f
f
icien
t
atten
tio
n
to
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
es:
Pre
p
r
o
ce
s
s
in
g
p
lay
s
a
cr
u
cial
r
o
le
in
e
n
h
an
cin
g
th
e
q
u
ality
o
f
h
y
p
er
s
p
ec
tr
al
d
ata
f
o
r
f
ea
tu
r
e
e
x
tr
ac
tio
n
.
Ho
we
v
er
,
th
er
e
h
as
b
ee
n
r
elativ
el
y
litt
le
f
o
cu
s
o
n
co
m
p
r
eh
e
n
s
iv
e
p
r
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
s
u
ch
as
n
o
is
e
r
em
o
v
al
an
d
n
o
r
m
aliza
tio
n
,
wh
ic
h
ar
e
ess
en
tial
f
o
r
im
p
r
o
v
in
g
th
e
r
eliab
ilit
y
an
d
ef
f
ec
tiv
e
n
ess
o
f
f
ea
tu
r
e
ex
t
r
ac
tio
n
p
r
o
ce
s
s
es.
T
o
s
o
lv
e
th
e
ab
o
v
e
is
s
u
es
an
d
ch
allen
g
es,
th
is
wo
r
k
p
r
esen
ts
a
n
o
v
el
f
r
am
ewo
r
k
f
o
r
HSI
.
Fig
u
r
e
3
illu
s
tr
ates
th
e
p
r
o
p
o
s
ed
f
r
a
m
e
wo
r
k
,
wh
ic
h
en
c
o
m
p
ass
es
s
ev
er
al
k
ey
s
tep
s
.
I
n
itially
,
t
h
e
f
r
am
ewo
r
k
c
o
n
s
id
er
s
in
p
u
t,
wh
ich
co
n
s
is
ts
o
f
HSI
s
.
Fo
llo
win
g
th
is
,
th
e
o
b
ject
class
if
icatio
n
p
r
o
ce
s
s
s
tar
ts
.
I
n
itially
,
r
elev
a
n
t
f
ea
tu
r
es
r
elate
d
to
r
ef
lecta
n
ce
ar
e
ex
tr
ac
ted
to
en
h
a
n
ce
s
p
atial
-
s
p
ec
tr
al
f
ea
tu
r
e
f
u
s
io
n
,
a
cr
u
cial
s
tep
in
th
e
o
b
ject
class
if
icatio
n
p
ip
elin
e
.
Su
b
s
eq
u
en
tly
,
a
DL
tech
n
iq
u
e
is
em
p
lo
y
ed
f
o
r
o
b
ject
class
if
icatio
n
,
f
ac
ilit
atin
g
th
e
id
en
tific
atio
n
o
f
o
b
jects
with
in
th
e
HSI
s
.
T
h
e
f
in
al
s
te
p
in
v
o
lv
es
ev
alu
atin
g
th
e
o
u
t
p
u
t
in
te
r
m
s
o
f
OA,
AA,
an
d
KC
m
etr
ics co
m
m
o
n
l
y
u
s
ed
to
ass
ess
clas
s
if
icatio
n
p
er
f
o
r
m
an
ce
.
T
o
en
h
a
n
ce
th
e
class
if
ier
’
s
tr
ain
in
g
an
d
im
p
r
o
v
e
r
o
b
u
s
tn
ess
,
HSI
n
o
is
ed
d
ata
is
u
tili
ze
d
d
u
r
in
g
th
e
tr
ain
in
g
p
h
ase,
co
n
tr
ib
u
tin
g
to
m
o
r
e
r
eliab
le
an
d
ac
c
u
r
ate
class
if
icatio
n
o
u
tco
m
es.
B
y
u
tili
zin
g
th
is
ap
p
r
o
ac
h
,
t
h
e
class
if
ier
ca
n
b
e
tr
a
in
ed
f
o
r
ac
h
iev
in
g
b
etter
o
u
tco
m
es
an
d
ca
n
s
o
lv
e
th
e
cu
r
r
en
t
p
r
o
b
lem
s
f
ac
ed
b
y
th
e
DL
ap
p
r
o
ac
h
es.
I
n
th
e
n
ex
t
s
ec
tio
n
,
th
e
co
n
clu
s
io
n
an
d
f
u
tu
r
e
wo
r
k
is
d
is
cu
s
s
ed
.
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:
2
5
0
2
-
4
7
52
E
n
h
a
n
ci
n
g
h
y
p
ers
p
ec
tr
a
l ima
g
e
o
b
ject
cla
s
s
ifica
tio
n
th
r
o
u
g
h
r
o
b
u
s
t fe
a
tu
r
e
…
(
V
ija
yla
xm
i Ko
ch
a
r
i
)
285
Fig
u
r
e
3
.
Pro
p
o
s
ed
f
r
am
ewo
r
k
f
o
r
HSI
o
b
ject
class
if
icatio
n
5.
CO
NCLU
SI
O
N
T
h
is
wo
r
k
d
elv
ed
in
to
th
e
r
ea
lm
o
f
HSI
o
b
ject
d
etec
tio
n
an
d
class
if
icatio
n
,
ex
p
lo
r
in
g
ex
is
tin
g
ap
p
r
o
ac
h
es,
ch
allen
g
es,
an
d
li
m
itatio
n
s
.
T
h
r
o
u
g
h
a
c
o
m
p
r
e
h
en
s
iv
e
r
ev
iew,
we
id
e
n
tifie
d
k
ey
is
s
u
es
s
u
ch
as
lim
ited
f
o
cu
s
o
n
f
ea
tu
r
e
ex
tr
a
ctio
n
,
n
o
is
e
r
e
m
o
v
al,
an
d
s
p
a
tial
-
s
p
ec
tr
al
f
u
s
io
n
in
c
u
r
r
e
n
t
HSI
class
if
icatio
n
m
o
d
els.
W
e
also
n
o
ted
th
e
p
r
ed
o
m
in
an
t
s
h
if
t
to
war
d
s
DL
tech
n
iq
u
es
d
u
e
to
th
eir
r
ec
u
r
r
e
n
t
n
etwo
r
k
s
,
wh
ich
o
f
f
er
im
p
r
o
v
e
d
r
esu
lts
co
m
p
ar
ed
to
tr
ad
itio
n
al
ML
ap
p
r
o
ac
h
es.
T
o
ad
d
r
ess
th
ese
ch
allen
g
es,
we
p
r
o
p
o
s
ed
a
n
o
v
el
f
r
am
ewo
r
k
d
esig
n
e
d
to
en
h
an
ce
HSI
o
b
ject
class
if
icatio
n
.
Ou
r
f
r
am
ew
o
r
k
p
r
io
r
itize
s
f
ea
tu
r
e
ex
tr
ac
tio
n
,
s
p
atial
-
s
p
ec
tr
al
f
u
s
io
n
,
an
d
n
o
is
e
r
em
o
v
al,
t
h
u
s
ad
d
r
ess
in
g
cr
itical
g
ap
s
in
ex
is
tin
g
m
eth
o
d
o
l
o
g
ies.
B
y
u
tili
zin
g
DL
tech
n
iq
u
es
f
o
r
o
b
ject
class
if
icatio
n
an
d
in
co
r
p
o
r
ati
n
g
HSI
n
o
is
ed
d
ata
d
u
r
in
g
tr
ai
n
in
g
,
o
u
r
f
r
am
ewo
r
k
aim
s
to
d
eliv
er
m
o
r
e
r
o
b
u
s
t
an
d
ac
cu
r
ate
class
if
icatio
n
o
u
tco
m
es.
T
h
r
o
u
g
h
r
ig
o
r
o
u
s
ev
alu
atio
n
u
s
in
g
m
etr
ics
lik
e
OA,
AA,
a
n
d
KC
we
an
ticip
ate
d
em
o
n
s
tr
atin
g
th
e
ef
f
icac
y
an
d
s
u
p
er
io
r
ity
o
f
o
u
r
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
.
W
e
b
eliev
e
th
at
t
h
is
wo
r
k
co
n
tr
ib
u
tes
s
ig
n
if
ican
tly
to
th
e
ad
v
an
ce
m
en
t
o
f
H
SI
o
b
ject
d
etec
tio
n
a
n
d
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
e
t
h
o
d
o
l
o
g
i
e
s
,
o
f
f
e
r
i
n
g
a
p
r
o
m
i
s
i
n
g
a
v
e
n
u
e
f
o
r
f
u
t
u
r
e
r
e
s
e
a
r
c
h
a
n
d
d
e
v
e
l
o
p
m
e
n
t
i
n
t
h
i
s
d
o
m
a
i
n
.
I
n
t
h
e
f
u
t
u
r
e
w
o
r
k
t
h
e
o
b
j
e
c
t
c
l
a
s
s
i
f
i
c
a
t
i
o
n
p
i
p
e
l
i
n
e
w
i
l
l
b
e
f
u
r
t
h
e
r
e
n
h
a
n
c
e
d
t
o
a
c
h
i
e
v
e
b
e
t
t
e
r
o
u
t
c
o
m
e
s
.
RE
F
E
R
E
NC
E
S
[
1
]
J.
N
a
l
e
p
a
,
“
R
e
c
e
n
t
a
d
v
a
n
c
e
s
i
n
m
u
l
t
i
-
a
n
d
h
y
p
e
r
sp
e
c
t
r
a
l
i
ma
g
e
a
n
a
l
y
si
s
,
”
S
e
n
s
o
rs,
v
o
l
.
2
1
,
n
o
.
1
8
,
p
.
6
0
0
2
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
1
1
8
6
0
0
2
.
[
2
]
Z.
A
.
Za
ma
n
,
S
.
B
.
A
h
me
d
,
a
n
d
M
.
I
.
M
a
l
i
k
,
“
A
n
a
l
y
s
i
s
o
f
h
y
p
e
r
s
p
e
c
t
r
a
l
d
a
t
a
t
o
d
e
v
e
l
o
p
a
n
a
p
p
r
o
a
c
h
f
o
r
d
o
c
u
m
e
n
t
i
ma
g
e
s
,
”
S
e
n
so
rs,
v
o
l
.
2
3
,
n
o
.
1
5
,
p
p
.
6
8
4
5
–
6
8
4
5
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
3
1
5
6
8
4
5
.
[
3
]
A
.
K
u
r
a
s,
M
.
B
r
e
l
l
,
J.
R
i
z
z
i
,
a
n
d
I
.
B
u
r
u
d
,
“
H
y
p
e
r
sp
e
c
t
r
a
l
a
n
d
l
i
d
a
r
d
a
t
a
a
p
p
l
i
e
d
t
o
t
h
e
u
r
b
a
n
l
a
n
d
c
o
v
e
r
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
n
e
u
r
a
l
-
n
e
t
w
o
r
k
-
b
a
se
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
:
a
r
e
v
i
e
w
,
”
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
3
,
n
o
.
1
7
,
p
.
3
3
9
3
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
3
1
7
3
3
9
3
.
[
4
]
M
.
T
.
I
sl
a
m,
M
.
R
.
I
sl
a
m,
M
.
P
.
U
d
d
i
n
,
a
n
d
A
.
U
l
h
a
q
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
h
y
p
e
r
s
p
e
c
t
r
a
l
o
b
j
e
c
t
c
l
a
ssi
f
i
c
a
t
i
o
n
a
p
p
r
o
a
c
h
v
i
a
i
mb
a
l
a
n
c
e
d
t
r
a
i
n
i
n
g
sa
mp
l
e
s
h
a
n
d
l
i
n
g
,
”
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
5
,
n
o
.
1
4
,
p
.
3
5
3
2
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
5
1
4
3
5
3
2
.
[
5
]
A
.
A
l
a
k
i
a
n
a
n
d
V
.
A
c
h
a
r
d
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
h
y
p
e
r
s
p
e
c
t
r
a
l
r
e
f
l
e
c
t
a
n
c
e
i
mag
e
s
w
i
t
h
p
h
y
s
i
c
a
l
a
n
d
s
t
a
t
i
st
i
c
a
l
c
r
i
t
e
r
i
a
,”
R
e
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
2
,
n
o
.
1
4
,
p
.
2
3
3
5
,
J
u
l
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
2
1
4
2
3
3
5
.
[
6
]
D
.
D
a
t
t
a
,
P
.
K
.
M
a
l
l
i
c
k
,
A
.
K
.
B
h
o
i
,
M
.
F
.
I
j
a
z
,
J.
S
h
a
f
i
,
a
n
d
J.
C
h
o
i
,
“
H
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
:
p
o
t
e
n
t
i
a
l
s,
c
h
a
l
l
e
n
g
e
s
,
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s
,”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
N
e
u
r
o
sc
i
e
n
c
e
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
3
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
3
8
5
4
6
3
5
.
[
7
]
B
.
L
u
,
P
.
D
a
o
,
J.
Li
u
,
Y
.
H
e
,
a
n
d
J.
S
h
a
n
g
,
“
R
e
c
e
n
t
a
d
v
a
n
c
e
s
o
f
h
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
i
n
g
t
e
c
h
n
o
l
o
g
y
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
i
n
a
g
r
i
c
u
l
t
u
r
e
,
”
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
2
,
n
o
.
1
6
,
p
.
2
6
5
9
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
2
1
6
2
6
5
9
.
[
8
]
R
.
R
a
j
a
b
i
,
A
.
Z
e
h
t
a
b
i
a
n
,
K
.
D
.
S
i
n
g
h
,
A
.
T
a
b
a
t
a
b
a
e
e
n
e
j
a
d
,
P
.
G
h
a
m
i
s
i
,
a
n
d
S
.
H
o
m
a
y
o
u
n
i
,
“
E
d
i
t
o
r
i
a
l
:
H
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
i
n
g
i
n
e
n
v
i
r
o
n
m
e
n
t
a
l
m
o
n
i
t
o
r
i
n
g
a
n
d
a
n
a
l
y
s
i
s
,
”
F
r
o
n
t
i
e
r
s
i
n
E
n
v
i
r
o
n
m
e
n
t
a
l
S
c
i
e
n
c
e
,
v
o
l
.
1
1
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
8
9
/
f
e
n
v
s
.
2
0
2
3
.
1
3
5
3
4
4
7
.
[
9
]
M
.
B
.
S
t
u
a
r
t
,
A
.
J.
M
c
G
o
n
i
g
l
e
,
a
n
d
J.
R
.
W
i
l
l
m
o
t
t
,
“
H
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
i
n
g
i
n
e
n
v
i
r
o
n
m
e
n
t
a
l
m
o
n
i
t
o
r
i
n
g
:
a
r
e
v
i
e
w
o
f
r
e
c
e
n
t
d
e
v
e
l
o
p
me
n
t
s
a
n
d
t
e
c
h
n
o
l
o
g
i
c
a
l
a
d
v
a
n
c
e
s
i
n
c
o
m
p
a
c
t
f
i
e
l
d
d
e
p
l
o
y
a
b
l
e
sy
s
t
e
ms
,”
S
e
n
s
o
rs,
v
o
l
.
1
9
,
n
o
.
1
4
,
p
.
3
0
7
1
,
J
u
l
.
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
s
1
9
1
4
3
0
7
1
.
[
1
0
]
B
.
C
h
e
n
,
L
.
L
i
u
,
Z
.
Z
o
u
,
a
n
d
Z.
S
h
i
,
“
Ta
r
g
e
t
d
e
t
e
c
t
i
o
n
i
n
h
y
p
e
r
sp
e
c
t
r
a
l
r
e
mo
t
e
s
e
n
si
n
g
i
m
a
g
e
:
c
u
r
r
e
n
t
s
t
a
t
u
s
a
n
d
c
h
a
l
l
e
n
g
e
s
,
”
Re
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
5
,
n
o
.
1
3
,
p
p
.
3
2
2
3
–
3
2
2
3
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
5
1
3
3
2
2
3
.
[
1
1
]
Z.
-
Y
.
W
a
n
g
,
Q
.
-
M
.
X
i
a
,
J.
-
W
.
Y
a
n
,
S
.
-
Q
.
X
u
a
n
,
J
.
-
H
.
S
u
,
a
n
d
C
.
-
F
.
Y
a
n
g
,
“
H
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
a
s
e
d
o
n
sp
e
c
t
r
a
l
a
n
d
s
p
a
t
i
a
l
i
n
f
o
r
ma
t
i
o
n
u
si
n
g
m
u
l
t
i
-
sc
a
l
e
R
e
sN
e
t
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s,
v
o
l
.
9
,
n
o
.
2
2
,
p
.
4
8
9
0
,
N
o
v
.
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
9
2
2
4
8
9
0
.
[
1
2
]
А
.
К
у
м
а
р
,
N
.
G
a
u
r
,
S
.
C
h
a
k
r
a
v
a
r
t
y
,
M
.
H
.
A
l
s
h
a
r
i
f
,
P
.
U
t
h
a
n
sa
k
u
l
,
a
n
d
M
.
U
t
h
a
n
s
a
k
u
l
,
“
A
n
a
l
y
si
s
o
f
s
p
e
c
t
r
u
m
s
e
n
s
i
n
g
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms:
C
N
N
s
a
n
d
R
N
N
s,”
A
i
n
S
h
a
m
s
E
n
g
i
n
e
e
r
i
n
g
J
o
u
r
n
a
l
,
v
o
l
.
1
5
,
n
o
.
3
,
p
p
.
1
0
2
5
0
5
–
1
0
2
5
0
5
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
se
j
.
2
0
2
3
.
1
0
2
5
0
5
.
[
1
3
]
O
.
O
k
w
u
a
s
h
i
a
n
d
C
.
E.
N
d
e
h
e
d
e
h
e
,
“
D
e
e
p
su
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
f
o
r
h
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
e
c
l
a
ssi
f
i
c
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
0
3
,
p
.
1
0
7
2
9
8
,
J
u
l
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
2
0
.
1
0
7
2
9
8
.
[
1
4
]
Z.
S
h
u
,
X
.
L
i
,
a
n
d
Y
.
Li
u
,
“
D
e
t
e
c
t
i
o
n
o
f
c
h
i
l
i
f
o
r
e
i
g
n
o
b
j
e
c
t
s
u
si
n
g
h
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
i
n
g
c
o
mb
i
n
e
d
w
i
t
h
c
h
e
mo
met
r
i
c
a
n
d
t
a
r
g
e
t
d
e
t
e
c
t
i
o
n
a
l
g
o
r
i
t
h
ms,
”
F
o
o
d
s
,
v
o
l
.
1
2
,
n
o
.
1
3
,
p
.
2
6
1
8
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
f
o
o
d
s1
2
1
3
2
6
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
279
-
2
8
7
286
[
1
5
]
S
.
Ji
n
e
t
a
l
.
,
“
C
S
K
N
N
:
C
o
s
t
-
se
n
si
t
i
v
e
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
u
si
n
g
h
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
i
n
g
f
o
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
w
h
e
a
t
v
a
r
i
e
t
i
e
s,”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
1
1
,
p
.
1
0
8
8
9
6
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
e
l
e
c
e
n
g
.
2
0
2
3
.
1
0
8
8
9
6
.
[
1
6
]
X
.
L
i
a
n
e
t
a
l
.
,
“
A
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
h
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
e
d
e
n
o
i
si
n
g
b
y
c
o
mb
i
n
i
n
g
sp
a
t
i
a
l
–
s
p
e
c
t
r
a
l
i
n
f
o
r
m
a
t
i
o
n
,
”
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
5
,
n
o
.
2
1
,
p
.
5
1
7
4
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
5
2
1
5
1
7
4
.
[
1
7
]
N
.
W
a
m
b
u
g
u
e
t
a
l
.
,
“
H
y
p
e
r
sp
e
c
t
r
a
l
i
mag
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
n
i
n
su
f
f
i
c
i
e
n
t
-
sa
mp
l
e
a
n
d
f
e
a
t
u
r
e
l
e
a
r
n
i
n
g
u
s
i
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s:
A
r
e
v
i
e
w
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ap
p
l
i
e
d
E
a
rt
h
O
b
ser
v
a
t
i
o
n
a
n
d
G
e
o
i
n
f
o
rm
a
t
i
o
n
,
v
o
l
.
1
0
5
,
p
p
.
1
0
2
6
0
3
–
1
0
2
6
0
3
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
g
.
2
0
2
1
.
1
0
2
6
0
3
.
[
1
8
]
D
.
P
.
Y
a
d
a
v
,
D
.
K
u
mar,
A
.
S
.
J
a
l
a
l
,
B
.
S
h
a
r
ma
,
J.
L
.
W
e
b
b
e
r
,
a
n
d
A
.
M
e
h
b
o
d
n
i
y
a
,
“
A
d
v
a
n
c
i
n
g
h
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
e
a
n
a
l
y
si
s
w
i
t
h
C
TN
e
t
:
a
n
a
p
p
r
o
a
c
h
w
i
t
h
t
h
e
f
u
s
i
o
n
o
f
sp
a
t
i
a
l
a
n
d
sp
e
c
t
r
a
l
f
e
a
t
u
r
e
s
,
”
S
e
n
so
rs,
v
o
l
.
2
4
,
n
o
.
6
,
p
p
.
2
0
1
6
–
2
0
1
6
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
4
0
6
2
0
1
6
.
[
1
9
]
S
.
F
.
A
h
m
e
d
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
l
i
n
g
t
e
c
h
n
i
q
u
e
s
:
c
u
r
r
e
n
t
p
r
o
g
r
e
ss,
a
p
p
l
i
c
a
t
i
o
n
s,
a
d
v
a
n
t
a
g
e
s
,
a
n
d
c
h
a
l
l
e
n
g
e
s,”
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
5
6
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
4
6
2
-
0
2
3
-
1
0
4
6
6
-
8.
[
2
0
]
W
.
Z
h
o
u
a
n
d
S
e
i
i
c
h
i
r
o
-
K
a
m
a
t
a
,
“
M
u
l
t
i
-
sc
a
n
n
i
n
g
b
a
s
e
d
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
h
y
p
e
r
sp
e
c
t
r
a
l
i
ma
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,”
2
0
2
0
2
5
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
(
I
C
PR)
,
M
i
l
a
n
,
I
t
a
l
y
,
2
0
2
1
,
p
p
.
4
7
4
3
-
4
7
5
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
P
R
4
8
8
0
6
.
2
0
2
1
.
9
4
1
3
0
7
1
.
[
2
1
]
Y.
-
L.
C
h
a
n
g
e
t
a
l
.
,
“
C
o
n
s
o
l
i
d
a
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
f
o
r
h
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
R
e
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
4
,
n
o
.
7
,
p
p
.
1
5
7
1
–
1
5
7
1
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
4
0
7
1
5
7
1
.
[
2
2
]
S
.
W
a
n
,
S
.
P
a
n
,
P
.
Z
h
o
n
g
,
X
.
C
h
a
n
g
,
J.
Y
a
n
g
,
a
n
d
C
.
G
o
n
g
,
“
D
u
a
l
i
n
t
e
r
a
c
t
i
v
e
g
r
a
p
h
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
t
w
o
r
k
s
f
o
r
h
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
G
e
o
sc
i
e
n
c
e
a
n
d
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
6
0
,
p
p
.
1
–
1
4
,
J
a
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
t
g
r
s.
2
0
2
1
.
3
0
7
5
2
2
3
.
[
2
3
]
“
H
y
p
e
r
s
p
e
c
t
r
a
l
R
e
m
o
t
e
S
e
n
s
i
n
g
S
c
e
n
e
s
-
G
r
u
p
o
d
e
I
n
t
e
l
i
g
e
n
c
i
a
C
o
m
p
u
t
a
c
i
o
n
a
l
(
G
I
C
)
,
”
w
w
w
.
e
h
u
.
e
u
s.
h
t
t
p
s
:
/
/
w
w
w
.
e
h
u
.
e
u
s/
c
c
w
i
n
t
c
o
/
i
n
d
e
x
.
p
h
p
/
H
y
p
e
r
s
p
e
c
t
r
a
l
_
R
e
m
o
t
e
_
S
e
n
si
n
g
_
S
c
e
n
e
s
#
I
n
d
i
a
n
_
P
i
n
e
s
(
a
c
c
e
ss
e
d
M
a
y
0
6
,
2
0
2
4
)
.
[
2
4
]
“
H
y
p
e
r
s
p
e
c
t
r
a
l
R
e
m
o
t
e
S
e
n
s
i
n
g
S
c
e
n
e
s
-
G
r
u
p
o
d
e
I
n
t
e
l
i
g
e
n
c
i
a
C
o
m
p
u
t
a
c
i
o
n
a
l
(
G
I
C
)
,
”
w
w
w
.
e
h
u
.
e
u
s.
h
t
t
p
s
:
/
/
w
w
w
.
e
h
u
.
e
u
s/
c
c
w
i
n
t
c
o
/
i
n
d
e
x
.
p
h
p
/
H
y
p
e
r
s
p
e
c
t
r
a
l
_
R
e
m
o
t
e
_
S
e
n
si
n
g
_
S
c
e
n
e
s
#
P
a
v
i
a
_
C
e
n
t
r
e
_
a
n
d
_
U
n
i
v
e
r
s
i
t
y
(
a
c
c
e
sse
d
M
a
y
0
6
,
2
0
2
4
)
.
[
2
5
]
“
H
y
p
e
r
s
p
e
c
t
r
a
l
R
e
m
o
t
e
S
e
n
s
i
n
g
S
c
e
n
e
s
-
G
r
u
p
o
d
e
I
n
t
e
l
i
g
e
n
c
i
a
C
o
m
p
u
t
a
c
i
o
n
a
l
(
G
I
C
)
,
”
w
w
w
.
e
h
u
.
e
u
s.
h
t
t
p
s
:
/
/
w
w
w
.
e
h
u
.
e
u
s/
c
c
w
i
n
t
c
o
/
i
n
d
e
x
.
p
h
p
/
H
y
p
e
r
s
p
e
c
t
r
a
l
_
R
e
m
o
t
e
_
S
e
n
si
n
g
_
S
c
e
n
e
s
#
S
a
l
i
n
a
s (a
c
c
e
sse
d
M
a
y
0
6
,
2
0
2
4
)
.
[
2
6
]
“
2
0
1
3
I
EEE
G
R
S
S
D
a
t
a
F
u
s
i
o
n
C
o
n
t
e
st
–
F
u
s
i
o
n
o
f
H
y
p
e
r
sp
e
c
t
r
a
l
a
n
d
Li
D
A
R
D
a
t
a
|
H
y
p
e
r
sp
e
c
t
r
a
l
I
mag
e
A
n
a
l
y
s
i
s
La
b
,
”
h
y
p
e
r
s
p
e
c
t
r
a
l
.
e
e
.
u
h
.
e
d
u
.
h
t
t
p
s:
/
/
h
y
p
e
r
sp
e
c
t
r
a
l
.
e
e
.
u
h
.
e
d
u
/
?
p
a
g
e
_
i
d
=
4
5
9
(
a
c
c
e
sse
d
M
a
y
0
6
,
2
0
2
4
)
.
[
2
7
]
J.
J
i
a
n
g
,
J
.
M
a
,
a
n
d
X
.
L
i
u
,
“
M
u
l
t
i
l
a
y
e
r
sp
e
c
t
r
a
l
–
s
p
a
t
i
a
l
g
r
a
p
h
s
f
o
r
l
a
b
e
l
n
o
i
s
y
r
o
b
u
s
t
h
y
p
e
r
sp
e
c
t
r
a
l
i
m
a
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
I
E
E
E
t
ra
n
s
a
c
t
i
o
n
s
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
s
a
n
d
l
e
a
r
n
i
n
g
sys
t
e
m
s
,
v
o
l
.
3
3
,
n
o
.
2
,
p
p
.
8
3
9
–
8
5
2
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
t
n
n
l
s.
2
0
2
0
.
3
0
2
9
5
2
3
.
[
2
8
]
H
.
G
a
o
,
Z.
C
h
e
n
,
a
n
d
F
.
X
u
,
“
A
d
a
p
t
i
v
e
s
p
e
c
t
r
a
l
-
sp
a
t
i
a
l
f
e
a
t
u
r
e
f
u
s
i
o
n
n
e
t
w
o
r
k
f
o
r
h
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
l
i
m
i
t
e
d
t
r
a
i
n
i
n
g
sam
p
l
e
s,”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
p
p
l
i
e
d
E
a
r
t
h
O
b
serv
a
t
i
o
n
a
n
d
G
e
o
i
n
f
o
rm
a
t
i
o
n
,
v
o
l
.
1
0
7
,
p
.
1
0
2
6
8
7
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
g
.
2
0
2
2
.
1
0
2
6
8
7
.
[
2
9
]
X
.
H
e
,
C
.
Ta
n
g
,
X
.
Li
u
,
W
.
Z
h
a
n
g
,
K
.
S
u
n
,
a
n
d
J.
X
u
,
“
O
b
j
e
c
t
d
e
t
e
c
t
i
o
n
i
n
h
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
e
v
i
a
u
n
i
f
i
e
d
sp
e
c
t
r
a
l
–
sp
a
t
i
a
l
f
e
a
t
u
r
e
a
g
g
r
e
g
a
t
i
o
n
,
”
I
EEE
T
r
a
n
sa
c
t
i
o
n
s
o
n
G
e
o
sc
i
e
n
c
e
a
n
d
R
e
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
6
1
,
p
p
.
1
–
1
3
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
t
g
r
s.
2
0
2
3
.
3
3
0
7
2
8
8
.
[
3
0
]
M
.
T
.
I
sl
a
m,
M
.
R
.
I
sl
a
m,
M
.
P
.
U
d
d
i
n
,
a
n
d
A
.
U
l
h
a
q
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
h
y
p
e
r
s
p
e
c
t
r
a
l
o
b
j
e
c
t
c
l
a
ssi
f
i
c
a
t
i
o
n
a
p
p
r
o
a
c
h
v
i
a
i
mb
a
l
a
n
c
e
d
t
r
a
i
n
i
n
g
sa
mp
l
e
s
h
a
n
d
l
i
n
g
,”
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
5
,
n
o
.
1
4
,
p
.
3
5
3
2
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
5
1
4
3
5
3
2
.
[
3
1
]
“
H
y
p
e
r
s
p
e
c
t
r
a
l
R
e
m
o
t
e
S
e
n
s
i
n
g
S
c
e
n
e
s
-
G
r
u
p
o
d
e
I
n
t
e
l
i
g
e
n
c
i
a
C
o
m
p
u
t
a
c
i
o
n
a
l
(
G
I
C
)
,
”
w
w
w
.
e
h
u
.
e
u
s.
h
t
t
p
s
:
/
/
w
w
w
.
e
h
u
.
e
u
s/
c
c
w
i
n
t
c
o
/
i
n
d
e
x
.
p
h
p
/
H
y
p
e
r
s
p
e
c
t
r
a
l
_
R
e
m
o
t
e
_
S
e
n
si
n
g
_
S
c
e
n
e
s
#
K
e
n
n
e
d
y
_
S
p
a
c
e
_
C
e
n
t
e
r
_
(
K
S
C
)
(
a
c
c
e
ss
e
d
M
a
y
0
6
,
2
0
2
4
)
.
[
3
2
]
F
.
F
e
n
g
,
Y
.
Z
h
a
n
g
,
J
.
Z
h
a
n
g
,
a
n
d
B
.
L
i
u
,
“
L
o
w
-
r
a
n
k
c
o
n
s
t
r
a
i
n
e
d
a
t
t
e
n
t
i
o
n
-
e
n
h
a
n
c
e
d
m
u
l
t
i
p
l
e
s
p
a
t
i
a
l
–
s
p
e
c
t
r
a
l
f
e
a
t
u
r
e
f
u
s
i
o
n
f
o
r
s
m
a
l
l
s
a
m
p
l
e
h
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
,
”
R
e
m
o
t
e
s
e
n
s
i
n
g
,
v
o
l
.
1
5
,
n
o
.
2
,
p
p
.
3
0
4
–
3
0
4
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
5
0
2
0
3
0
4
.
[
3
3
]
Y
.
Zh
o
n
g
,
X
.
H
u
,
C
.
Lu
o
,
X
.
W
a
n
g
,
J.
Z
h
a
o
,
a
n
d
L.
Zh
a
n
g
,
“
W
H
U
-
H
i
:
U
A
V
-
b
o
r
n
e
h
y
p
e
r
s
p
e
c
t
r
a
l
w
i
t
h
h
i
g
h
sp
a
t
i
a
l
r
e
s
o
l
u
t
i
o
n
(
H
2
)
b
e
n
c
h
mar
k
d
a
t
a
set
s
a
n
d
c
l
a
ss
i
f
i
e
r
f
o
r
p
r
e
c
i
se
c
r
o
p
i
d
e
n
t
i
f
i
c
a
t
i
o
n
b
a
s
e
d
o
n
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
w
i
t
h
C
R
F
,
”
Re
m
o
t
e
S
e
n
s
i
n
g
o
f
E
n
v
i
ro
n
m
e
n
t
,
v
o
l
.
2
5
0
,
p
.
1
1
2
0
1
2
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
se.
2
0
2
0
.
1
1
2
0
1
2
.
[
3
4
]
L.
D
a
n
g
,
L
.
W
e
n
g
,
Y
.
H
o
u
,
X
.
Zu
o
,
a
n
d
Y
.
L
i
u
,
“
D
o
u
b
l
e
-
b
r
a
n
c
h
f
e
a
t
u
r
e
f
u
si
o
n
t
r
a
n
sf
o
r
m
e
r
f
o
r
h
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
3
,
n
o
.
1
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
023
-
2
7
4
7
2
-
z.
[
3
5
]
X
.
W
a
n
a
n
d
S
.
C
h
e
n
,
“
H
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
u
s
i
n
g
i
m
p
r
o
v
e
d
m
u
l
t
i
-
s
c
a
l
e
b
l
o
c
k
l
o
c
a
l
b
i
n
a
r
y
p
a
t
t
e
r
n
a
n
d
b
i
-
e
x
p
o
n
e
n
t
i
a
l
e
d
g
e
-
p
r
e
s
e
r
v
i
n
g
s
m
o
o
t
h
e
r
,
”
E
u
r
o
p
e
a
n
J
o
u
r
n
a
l
o
f
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
5
6
,
n
o
.
1
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
0
/
2
2
7
9
7
2
5
4
.
2
0
2
3
.
2
2
3
7
6
5
4
.
[
3
6
]
C
.
Y
a
n
a
n
d
J
.
H
o
n
g
,
“
S
S
F
N
:
a
n
o
v
e
l
sp
a
t
i
a
l
-
s
p
e
c
t
r
a
l
F
u
si
o
n
N
e
t
f
o
r
h
y
p
e
r
sp
e
c
t
r
a
l
i
ma
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
p
h
y
si
c
s,
v
o
l
.
2
5
6
2
,
n
o
.
1
,
p
p
.
0
1
2
0
2
6
–
0
1
2
0
2
6
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
2
5
6
2
/
1
/
0
1
2
0
2
6
.
[
3
7
]
Q
.
G
u
,
H
.
L
u
a
n
,
K
.
H
u
a
n
g
,
a
n
d
Y
.
S
u
n
,
“
H
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
e
c
l
a
s
si
f
i
c
a
t
i
o
n
u
s
i
n
g
m
u
l
t
i
-
s
c
a
l
e
l
i
g
h
t
w
e
i
g
h
t
t
r
a
n
sf
o
r
mer
,
”
El
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
3
,
n
o
.
5
,
p
p
.
9
4
9
–
9
4
9
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
3
0
5
0
9
4
9
.
[
3
8
]
H
.
Zh
a
n
g
,
K
.
Tu
,
H
u
a
n
h
u
a
n
L
v
,
a
n
d
R
.
W
a
n
g
,
“
H
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
a
se
d
o
n
3D
–
2
D
h
y
b
r
i
d
c
o
n
v
o
l
u
t
i
o
n
a
n
d
g
r
a
p
h
a
t
t
e
n
t
i
o
n
m
e
c
h
a
n
i
s
m,”
N
e
u
ra
l
p
r
o
c
e
s
si
n
g
l
e
t
t
e
rs/
N
e
u
r
a
l
Pr
o
c
e
ss
i
n
g
L
e
t
t
e
r
s,
v
o
l
.
5
6
,
n
o
.
2
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
0
6
3
-
024
-
1
1
5
8
4
-
2
.
[
3
9
]
T.
A
r
sh
a
d
,
J
.
Z
h
a
n
g
,
a
n
d
I
.
U
l
l
a
h
,
“
A
h
y
b
r
i
d
c
o
n
v
o
l
u
t
i
o
n
t
r
a
n
sf
o
r
m
e
r
f
o
r
h
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
E
u
r
o
p
e
a
n
j
o
u
r
n
a
l
o
f
remo
t
e
s
e
n
s
i
n
g
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
0
/
2
2
7
9
7
2
5
4
.
2
0
2
4
.
2
3
3
0
9
7
9
.
[
4
0
]
K
.
Ta
n
,
F
.
W
u
,
a
n
d
X
.
W
a
n
g
,
“
X
u
z
h
o
u
H
Y
S
P
EX
d
a
t
a
se
t
,
”
I
EE
E
D
a
t
a
p
o
rt
,
N
o
v
e
mb
e
r
2
,
2
0
1
8
,
d
o
i
:
1
0
.
2
1
2
2
7
/
t
3
c
9
-
h
8
6
2
.
[
4
1
]
A
.
A
l
i
,
C
.
M
u
,
Z.
Zh
a
n
g
,
J.
Zh
u
,
a
n
d
Y
.
L
i
u
,
“
A
t
w
o
-
b
r
a
n
c
h
mu
l
t
i
sca
l
e
s
p
e
c
t
r
a
l
-
sp
a
t
i
a
l
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
n
e
t
w
o
r
k
f
o
r
h
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
i
n
f
o
rm
a
t
i
o
n
a
n
d
i
n
t
e
l
l
i
g
e
n
c
e
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
i
i
x
d
.
2
0
2
4
.
0
3
.
0
0
2
.
[
4
2
]
X
.
H
u
a
n
g
,
Y
.
M
a
,
Z.
J
i
a
n
g
,
a
n
d
J.
Y
a
n
g
,
“
H
y
p
e
r
s
p
e
c
t
r
a
l
r
e
mo
t
e
se
n
s
i
n
g
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
mari
n
e
o
i
l
e
m
u
l
s
i
o
n
s
b
a
sed
o
n
t
h
e
f
u
s
i
o
n
o
f
s
p
a
t
i
a
l
a
n
d
sp
e
c
t
r
a
l
f
e
a
t
u
r
e
s,
”
A
c
t
a
o
c
e
a
n
o
l
o
g
i
c
a
S
i
n
i
c
a
/
A
c
t
a
O
c
e
a
n
o
l
o
g
i
c
a
S
i
n
i
c
a
,
v
o
l
.
4
3
,
n
o
.
3
,
p
p
.
1
3
9
–
1
5
4
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
1
3
1
-
0
2
3
-
2
2
4
9
-
8.
[
4
3
]
N
.
S
i
g
g
e
r
,
Q
.
-
T
.
V
i
e
n
,
S
.
V
.
N
g
u
y
e
n
,
G
.
T
o
z
z
i
,
a
n
d
T
.
T
.
N
g
u
y
e
n
,
“
U
n
v
e
i
l
i
n
g
t
h
e
p
o
t
e
n
t
i
a
l
o
f
d
i
f
f
u
s
i
o
n
m
o
d
e
l
-
b
a
s
e
d
f
r
a
m
e
w
o
r
k
w
i
t
h
t
r
a
n
s
f
o
r
m
e
r
f
o
r
h
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
r
e
p
o
r
t
s
,
v
o
l
.
1
4
,
n
o
.
1
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
4
-
58125
-
4.
[
4
4
]
M
.
A
sh
r
a
f
,
R
.
A
l
h
a
r
t
h
i
,
L.
C
h
e
n
,
M
.
U
mer,
S
.
A
l
s
u
b
a
i
,
a
n
d
A
.
A
.
Esh
m
a
w
i
,
“
A
t
t
e
n
t
i
o
n
3
D
c
e
n
t
r
a
l
d
i
f
f
e
r
e
n
c
e
c
o
n
v
o
l
u
t
i
o
n
a
l
d
e
n
s
e
n
e
t
w
o
r
k
f
o
r
h
y
p
e
r
sp
e
c
t
r
a
l
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
P
l
o
S
o
n
e
,
v
o
l
.
1
9
,
n
o
.
4
,
p
p
.
e
0
3
0
0
0
1
3
–
e
0
3
0
0
0
1
3
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
3
0
0
0
1
3
.
[
4
5
]
T.
G
o
sw
a
mi
,
K
.
N
.
S
h
r
u
t
h
i
,
S
.
C
h
o
k
k
a
r
a
p
u
,
R
.
K
u
n
e
,
a
n
d
M
.
K
.
Tr
i
p
a
t
h
i
,
“
S
W
T
-
P
C
A
-
C
N
N
:
h
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
w
i
t
h
m
u
l
t
i
-
s
t
a
g
e
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
p
a
r
a
me
t
e
r
t
u
n
i
n
g
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
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
S
c
i
e
n
c
e
,
v
o
l
.
3
4
,
n
o
.
1
,
p
p
.
5
9
–
5
9
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
4
.
i
1
.
p
p
5
9
-
6
8
.
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:
2
5
0
2
-
4
7
52
E
n
h
a
n
ci
n
g
h
y
p
ers
p
ec
tr
a
l ima
g
e
o
b
ject
cla
s
s
ifica
tio
n
th
r
o
u
g
h
r
o
b
u
s
t fe
a
tu
r
e
…
(
V
ija
yla
xm
i Ko
ch
a
r
i
)
287
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Vija
y
l
a
x
m
i
K
o
c
h
a
r
i
is
As
sist
a
n
t
P
r
o
fe
ss
o
r
i
n
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
(AIM
L)
Ko
l
h
a
p
u
r
I
n
stit
u
te
o
f
Te
c
h
n
o
l
o
g
y
’s
C
o
ll
e
g
e
o
f
E
n
g
in
e
e
ri
n
g
(A
u
to
n
o
m
o
u
s)
K
o
lh
a
p
u
r,
M
a
h
a
ra
stra
,
In
d
ia.
S
h
e
is
c
u
rre
n
t
ly
p
u
rsu
in
g
P
h
.
D
.
stu
d
ies
a
t
th
e
Visv
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
Un
iv
e
rsity
,
Be
lag
a
v
i,
Ka
rn
a
tak
a
,
In
d
ia
i
n
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
.
S
h
e
re
c
e
iv
e
d
h
e
r
M
a
ste
r
a
n
d
Ba
c
h
e
lo
r
o
f
E
n
g
i
n
e
e
rin
g
d
e
g
re
e
s
in
Co
m
p
u
te
r
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
fro
m
th
e
G
o
g
te
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Be
lag
a
v
i
,
a
ffil
iate
d
to
Visv
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
Un
iv
e
rsity
,
Be
la
g
a
v
i,
Ka
rn
a
tak
a
,
In
d
ia
i
n
2
0
1
7
a
n
d
2
0
1
0
,
re
sp
e
c
ti
v
e
ly
.
S
h
e
c
a
n
b
e
c
o
n
tac
te
d
a
t
e
m
a
il
:
v
ij
a
y
lax
m
irrao
@
g
m
a
il
.
c
o
m
.
S
a
n
je
e
v
S
.
S
a
n
n
a
k
k
i
p
ro
fe
ss
o
r
a
n
d
h
e
a
d
,
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
a
t
K.
L.
S
G
o
g
te
I
n
st
it
u
te
o
f
Tec
h
n
o
lo
g
y
,
Be
l
g
a
u
m
,
Ka
rn
a
tak
a
,
I
n
d
ia.
He
p
u
rsu
e
d
h
is
B.
E.
in
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
fr
o
m
Ka
rn
a
tak
a
Un
i
v
e
rsity
Dh
a
rwa
d
in
2
0
0
4
,
M
.
Tec
h
,
a
n
d
P
h
.
D.
fro
m
VTU,
B
e
lag
a
v
i
in
2
0
0
9
,
a
n
d
2
0
1
6
re
sp
e
c
ti
v
e
ly
.
His
re
se
a
rc
h
a
re
a
s
in
c
lu
d
e
Im
a
g
e
P
r
o
c
e
ss
in
g
,
Clo
u
d
Co
m
p
u
ti
n
g
,
C
o
m
p
u
ter
Ne
two
rk
s,
a
n
d
Da
ta
An
a
ly
ti
c
s.
He
h
a
s
p
u
b
li
sh
e
d
a
g
o
o
d
n
u
m
b
e
r
o
f
p
a
p
e
rs
in
j
o
u
r
n
a
ls,
In
tern
a
ti
o
n
a
l,
a
n
d
Na
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s.
He
is
th
e
re
v
iew
e
r
fo
r
a
fe
w
in
tern
a
ti
o
n
a
l
jo
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
He
is
a
lso
a
li
fe
m
e
m
b
e
r
o
f
CS
I
,
a
n
d
IS
T
E
a
ss
o
c
iatio
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
n
n
a
k
k
isa
n
je
e
v
@g
m
a
il
.
c
o
m
.
Vija
y
S
.
R
a
jp
u
r
o
h
it
is
wo
rk
in
g
a
s
a
P
ro
fe
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
a
t
K.
L.
S
G
o
g
te
In
stit
u
te o
f
Tec
h
n
o
lo
g
y
,
Be
lg
a
u
m
,
Ka
rn
a
tak
a
,
In
d
ia.
He
p
u
rsu
e
d
h
is
B
.
E.
in
Co
m
p
u
ter
S
c
ie
n
c
e
a
n
d
E
n
g
in
e
e
rin
g
fro
m
Ka
rn
a
tak
a
Un
i
v
e
rsity
Dh
a
rwa
d
,
M
.
Tec
h
fr
o
m
N.I.
T.
K
S
u
ra
t
h
k
a
l,
a
n
d
P
h
.
D.
fr
o
m
M
a
n
i
p
a
l
Un
i
v
e
rsity
in
2
0
0
9
.
Hi
s
re
se
a
rc
h
a
re
a
s
in
c
lu
d
e
ima
g
e
p
ro
c
e
ss
in
g
,
c
lo
u
d
c
o
m
p
u
ti
n
g
,
a
n
d
d
a
ta
a
n
a
l
y
ti
c
s
.
He
h
a
s
p
u
b
li
sh
e
d
a
g
o
o
d
n
u
m
b
e
r
o
f
p
a
p
e
rs
in
j
o
u
r
n
a
ls,
In
tern
a
ti
o
n
a
l,
a
n
d
Na
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s.
He
is
th
e
re
v
iew
e
r
f
o
r
a
fe
w
in
ter
n
a
ti
o
n
a
l
jo
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
He
is
th
e
a
ss
o
c
iate
e
d
it
o
r
fo
r
tw
o
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
a
se
n
io
r
m
e
m
b
e
r
o
f
th
e
I
n
tern
a
ti
o
n
a
l
As
so
c
iatio
n
o
f
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
In
f
o
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
.
He
is
a
lso
th
e
li
fe
m
e
m
b
e
r
o
f
S
S
I,
I
S
C,
a
n
d
IS
T
E
a
ss
o
c
iatio
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
ij
a
y
sr
2
k
@y
a
h
o
o
.
c
o
m
.
Ma
h
e
sh
G
.
H
u
d
d
a
r
is
wo
rk
i
n
g
a
s
P
r
o
fe
ss
o
r
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
a
t
Hira
su
g
a
r
I
n
stit
u
t
e
o
f
Tec
h
n
o
l
o
g
y
,
Ni
d
a
so
sh
i,
Be
lag
a
v
i,
I
n
d
ia
a
n
d
h
e
p
u
rsu
e
d
h
is
P
h
.
D.
a
t
th
e
Visv
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
Un
i
v
e
rsity
,
Be
lag
a
v
i,
In
d
ia
fr
o
m
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
.
He
re
c
e
iv
e
d
h
is
M
a
ste
r
a
n
d
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
d
e
g
re
e
s
fro
m
th
e
Visv
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
Un
i
v
e
rsity
,
Be
lag
a
v
i,
In
d
ia
in
2
0
1
4
a
n
d
2
0
0
8
,
re
sp
e
c
ti
v
e
ly
.
He
h
a
s
p
u
b
li
s
h
e
d
m
a
n
y
p
a
p
e
rs
in
j
o
u
r
n
a
ls,
I
n
tern
a
ti
o
n
a
l,
a
n
d
Na
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s.
His
m
a
in
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
m
a
c
h
in
e
lea
rn
i
n
g
,
d
e
e
p
lea
rn
i
n
g
,
m
u
lt
imo
d
a
l
se
n
ti
m
e
n
t
a
n
a
ly
sis,
a
n
d
m
u
lt
im
o
d
a
l
e
m
o
ti
o
n
d
e
tec
ti
o
n
.
He
is
a
m
e
m
b
e
r
o
f
th
e
IEE
E
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
g
h
u
d
d
a
r.
c
se
@h
sit.
a
c
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.