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
6
,
No
.
3
,
Dec
em
b
er
20
24
,
p
p
.
1
8
27
~
1
8
35
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
6
.
i
3
.
pp
1
8
27
-
1
8
35
1827
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
H
ig
h
-
reso
lu
tion a
eria
l mo
nitoring
using
DL
for i
den
tif
y
ing
a
bno
rma
l activ
ity ba
sed o
n vis
ua
l p
a
tt
erns in
drone v
ideo
s
M
uk
esh
K
um
a
r
T
ripa
t
hi
1
,
C
hella
pil
la
V.
K
.
N.
S.
N.
M
o
o
rt
hy
2
,
Sa
nd
ee
p K
a
da
m
3
,
Cha
it
a
li
S
hewa
le
4
,
P
riy
a
S
helk
e
4
,
P
ra
v
in R.
F
uta
ne
4
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
,
V
a
r
d
h
a
ma
n
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
H
y
d
e
r
a
b
a
d
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
M
e
c
h
a
n
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
V
a
s
a
v
i
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
H
y
d
e
r
a
b
a
d
,
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
En
g
i
n
e
e
r
i
n
g
,
K
e
y
s
t
o
n
e
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
i
n
g
,
P
u
n
e
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
V
i
s
h
w
a
k
a
r
m
a
I
n
st
i
t
u
t
e
o
f
I
n
f
o
r
ma
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
P
u
n
e
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
16
,
2
0
2
4
R
ev
is
ed
Au
g
8
,
2
0
2
4
Acc
ep
ted
Sep
2
,
2
0
2
4
Un
m
a
n
n
e
d
a
e
rial
v
e
h
icle
s
(UA
Vs
)
a
n
d
so
p
h
isti
c
a
ted
d
e
e
p
lea
rn
in
g
(DL)
m
o
d
e
ls
h
a
v
e
m
a
d
e
th
e
a
p
p
li
c
a
ti
o
n
o
f
a
rti
ficia
l
i
n
telli
g
e
n
c
e
(
AI)
m
o
re
p
o
p
u
lar.
T
h
is
h
a
s
re
su
lt
e
d
i
n
a
n
in
c
re
a
se
in
th
e
n
u
m
b
e
r
o
f
a
tt
e
m
p
ts
to
imp
ro
v
e
h
i
g
h
-
re
so
lu
ti
o
n
a
e
rial
m
o
n
i
to
ri
n
g
u
si
n
g
DL
fo
r
i
d
e
n
ti
f
y
in
g
a
b
n
o
rm
a
l
a
c
ti
v
it
y
b
a
se
d
o
n
v
is
u
a
l
p
a
tt
e
rn
s
i
n
d
r
o
n
e
v
i
d
e
o
s
.
Th
e
st
u
d
y
in
tro
d
u
c
e
s
a
o
n
e
-
c
las
s
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(OC
-
S
VM)
o
d
d
it
y
l
o
c
a
to
r
fo
r
lo
w
-
a
lt
it
u
d
e
,
li
m
it
e
d
-
sc
o
p
e
UA
Vs
u
se
d
fo
r
e
th
e
re
a
l
v
id
e
o
s
u
rv
e
il
l
a
n
c
e
.
Th
e
p
rima
ry
g
o
a
l
is
t
o
imp
ro
v
e
UA
V
-
b
a
se
d
o
b
se
rv
a
ti
o
n
c
a
p
a
b
i
li
ti
e
s
b
y
id
e
n
ti
f
y
in
g
a
re
a
s
o
r
th
in
g
s
o
f
in
tere
st
with
o
u
t
p
ri
o
r
k
n
o
wle
d
g
e
,
h
e
n
c
e
imp
ro
v
i
n
g
tas
k
s
li
k
e
q
u
e
u
e
c
o
n
tro
l
,
v
e
h
icle
fo
ll
o
wi
n
g
,
a
n
d
h
a
z
a
rd
o
u
s
p
ro
d
u
c
t
i
d
e
n
ti
f
ica
ti
o
n
.
T
h
e
f
ra
m
e
wo
rk
m
a
k
e
s
u
se
o
f
OC
-
S
VM
b
e
c
a
u
se
o
f
it
s
q
u
ick
a
n
d
li
g
h
twe
ig
h
t
se
tu
p
,
m
a
k
in
g
i
t
su
it
a
b
le
fo
r
c
o
n
ti
n
u
o
u
s
o
p
e
ra
ti
o
n
o
n
lo
w
-
c
o
m
p
u
tatio
n
a
l
UA
Vs
.
It
e
m
p
o
we
rs
th
e
id
e
n
ti
f
ica
ti
o
n
o
f
se
v
e
ra
l
p
e
c
u
li
a
rit
ies
n
e
c
e
ss
a
ry
fo
r
lo
w
-
e
lev
a
ti
o
n
re
c
o
n
n
a
issa
n
c
e
b
y
u
sin
g
tex
tu
ra
l
c
h
a
ra
c
teristics
to
re
c
o
g
n
ise
b
o
th
l
a
rg
e
-
sc
a
le
a
n
d
ti
n
y
stru
c
tu
re
s.
E
x
a
m
in
e
th
e
UAV
m
o
sa
ick
in
g
a
n
d
c
h
a
n
g
e
lo
c
a
ti
o
n
(U
M
CD)
d
a
tas
e
t
t
o
d
e
m
o
n
stra
te
th
e
e
ffe
c
ti
v
e
n
e
ss
o
f
th
e
fra
m
e
wo
rk
,
wh
ich
a
c
h
iev
e
s
e
x
c
e
ll
e
n
t
a
c
c
u
ra
c
y
a
n
d
o
u
t
p
e
rfo
rm
s
trad
it
i
o
n
a
l
m
e
th
o
d
s
b
y
a
b
o
u
t
o
n
e
fift
h
in
a
v
a
riet
y
o
f
m
e
tri
c
s.
Th
e
su
g
g
e
ste
d
m
o
d
e
l
c
o
m
p
a
re
s
with
c
u
rre
n
t
m
e
th
o
d
s
,
d
e
m
o
n
stra
ti
n
g
su
p
e
rio
r
a
c
c
u
ra
c
y
a
n
d
p
e
rfo
r
m
a
n
c
e
in
re
c
o
g
n
it
i
o
n
o
f
p
e
c
u
li
a
rit
ies
.
Ev
a
lu
a
ti
o
n
m
e
tri
c
s
in
c
l
u
d
e
F
1
-
sc
o
re
,
re
v
iew
,
e
x
a
c
tn
e
ss
,
a
n
d
a
c
c
u
ra
c
y
.
Th
e
m
o
d
e
l
d
e
m
o
n
stra
tes
t
h
a
t
it
a
lw
a
y
s
e
n
c
o
u
n
ters
a
n
o
d
d
it
y
wi
th
a
re
v
iew
c
o
m
p
ro
m
ise
o
f
u
p
to
se
v
e
n
o
n
ten
,
a
c
h
iev
in
g
c
o
m
p
lete
a
c
c
u
ra
c
y
.
K
ey
w
o
r
d
s
:
Av
er
ag
e
-
b
ased
K
-
m
ea
n
s
C
lu
s
ter
in
g
alg
o
r
ith
m
Dir
ac
d
ep
th
s
ilh
o
u
ette
f
u
n
ctio
n
OC
-
SVM
PEOO
UAVs
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Mu
k
esh
K
u
m
ar
T
r
ip
ath
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
,
Var
d
h
a
m
an
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
Hy
d
er
ab
ad
,
I
n
d
ia
E
m
ail:
m
u
k
esh
tr
ip
ath
i0
1
6
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
r
is
in
g
u
s
ag
e
o
f
u
n
m
an
n
e
d
ae
r
ial
v
eh
icles
(
UAVs)
o
r
d
r
o
n
es
ac
ce
n
tu
ates
th
eir
p
o
r
t
ab
ilit
y
an
d
ad
ap
tab
ilit
y
in
d
if
f
e
r
en
t
a
p
p
licatio
n
s
.
L
ate
h
ea
d
way
s
h
a
v
e
p
r
o
m
p
ted
th
e
im
p
r
o
v
em
e
n
t
o
f
m
o
d
els
th
at
em
p
o
wer
UAVs
to
h
an
d
le
c
o
n
s
tan
t
in
s
ig
h
t,
eith
er
f
r
ee
ly
o
r
with
th
e
b
ac
k
in
g
o
f
a
GPU
-
em
p
o
wer
ed
g
r
o
u
n
d
s
tatio
n
o
r
wir
ed
PC
.
T
h
is
ca
p
ac
ity
co
n
s
id
er
s
u
n
ass
u
m
in
g
th
in
k
in
g
in
lig
h
tweig
h
t
f
r
am
ew
o
r
k
s
,
u
p
g
r
ad
in
g
th
e
UAVs
’
ca
p
ac
ity
to
ad
ju
s
t
to
d
y
n
am
ic
co
n
d
itio
n
s
an
d
task
s
[1
]
-
[
3]
.
I
n
ad
d
itio
n
,
th
e
jo
i
n
in
g
o
f
co
n
tin
u
o
u
s
k
n
o
wled
g
e
em
p
o
wer
s
UAVs
to
f
o
llo
w
o
cc
asio
n
s
an
d
g
i
v
e
p
o
r
tr
a
y
als
p
r
o
g
r
ess
iv
ely
.
T
h
is
u
s
ef
u
ln
ess
is
v
alu
ab
le
in
cir
cu
m
s
tan
ce
s
wh
er
e
h
u
m
an
a
d
m
in
is
tr
ato
r
s
m
ig
h
t
co
n
f
r
o
n
t
p
o
s
s
ib
le
d
an
g
er
s
.
B
y
r
ec
o
m
m
en
d
in
g
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
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
8
27
-
1
8
35
1828
ass
es
s
ed
id
ea
l
o
r
d
er
s
f
o
r
ac
ti
v
ity
,
UAVs
ca
n
ac
t
as
allies
to
h
u
m
an
ad
m
in
is
tr
ato
r
s
,
im
p
r
o
v
in
g
s
itu
atio
n
al
m
in
d
f
u
ln
ess
an
d
s
u
p
p
o
r
tin
g
d
y
n
am
ic
cy
cles.
Gen
er
ally
s
p
e
ak
in
g
,
th
e
d
ev
elo
p
m
en
t
o
f
U
AVs
o
u
tf
itted
with
co
n
s
tan
t
k
n
o
wled
g
e
ca
p
ac
ities
ad
d
r
ess
es
a
cr
itical
p
r
o
g
r
e
s
s
io
n
in
ad
v
a
n
ce
d
m
ec
h
an
ic
s
in
n
o
v
atio
n
,
wit
h
ex
p
ec
ted
ap
p
licatio
n
s
ac
r
o
s
s
d
if
f
er
en
t
b
u
s
in
ess
es,
in
clu
d
in
g
r
ec
o
n
n
aiss
an
ce
,
s
ea
r
ch
an
d
s
alv
ag
e,
ec
o
lo
g
ica
l
ch
ec
k
in
g
,
an
d
f
o
u
n
d
atio
n
e
x
a
m
in
atio
n
[
4
]
-
[
6]
.
T
h
e
s
ec
tio
n
h
ig
h
lig
h
ts
th
e
r
i
s
in
g
p
er
v
asiv
en
ess
o
f
v
is
u
al
r
ec
o
n
n
aiss
an
ce
,
p
r
in
cip
ally
u
s
in
g
s
h
u
t
cir
cu
it
T
V
(
C
C
T
V)
,
in
ten
d
in
g
to
s
ec
u
r
ity
co
n
ce
r
n
s
wo
r
ld
wid
e.
As
cr
im
e
p
er
ce
n
tag
es
r
is
e,
th
e
r
ec
ep
tio
n
o
f
C
C
T
V
in
n
o
v
atio
n
h
as b
ec
o
m
e
ty
p
ical
in
cu
r
r
en
t lif
e,
p
ar
ticu
l
ar
ly
in
ar
ea
s
r
eq
u
ir
in
g
u
p
lifte
d
s
ec
u
r
ity
m
ea
s
u
r
es
[
7
]
.
I
n
an
y
ca
s
e,
s
u
cc
ess
f
u
lly
d
is
tin
g
u
is
h
in
g
ir
r
eg
u
lar
ities
o
r
o
b
jects
o
f
in
ter
est
f
r
o
m
th
e
b
r
o
a
d
v
o
l
u
m
e
o
f
o
b
s
er
v
atio
n
r
ec
o
r
d
in
g
s
r
ep
r
e
s
en
ts
a
cr
itical
test
.
On
g
o
in
g
h
ea
d
way
s
in
r
esear
ch
h
av
e
p
r
o
m
p
ted
th
e
im
p
r
o
v
em
e
n
t
o
f
a
d
if
f
er
e
n
t
ex
h
ib
it
o
f
p
r
esen
t
-
d
ay
a
p
p
r
o
ac
h
es
f
o
r
ir
r
eg
u
lar
ity
lo
ca
tio
n
(
p
r
o
m
o
tio
n
)
in
o
b
s
er
v
atio
n
f
ilm
s
[
8
]
.
T
h
ese
m
eth
o
d
o
l
o
g
ies
ar
e
ess
en
tial
f
o
r
im
p
r
o
v
i
n
g
s
af
ety
ef
f
o
r
ts
an
d
d
is
tin
g
u
is
h
in
g
an
d
an
ticip
atin
g
m
is
h
ap
s
,
b
lo
c
k
a
g
e,
an
d
d
if
f
er
e
n
t
an
o
m
alies.
Fu
r
th
er
m
o
r
e,
p
r
o
m
o
tio
n
s
tr
ateg
ies
ca
n
g
iv
e
s
ig
n
if
ican
t
f
ac
tu
al
b
its
o
f
k
n
o
wled
g
e
in
to
s
tr
ee
t
tr
af
f
ic
s
tatu
s
an
d
o
th
er
o
b
s
er
v
e
d
co
n
d
itio
n
s
.
T
h
u
s
,
d
if
f
er
en
t
PC
v
is
io
n
-
d
r
iv
en
i
n
v
esti
g
atio
n
s
an
d
d
if
f
icu
lties
h
av
e
b
ee
n
d
ir
ec
ted
to
ad
d
r
ess
th
ese
r
e
q
u
ir
em
en
ts
,
in
clu
d
in
g
tr
af
f
ic
ch
ec
k
in
g
,
m
o
v
e
m
en
t
ac
k
n
o
wled
g
m
e
n
t,
cr
is
is
th
e
b
o
ar
d
,
h
u
m
an
co
n
d
u
ct
ex
a
m
in
atio
n
,
o
cc
asio
n
d
is
co
v
er
y
,
a
n
d
t
h
at
’
s
o
n
ly
th
e
tip
o
f
t
h
e
iceb
er
g
.
T
h
ese
u
n
d
er
tak
in
g
s
ex
p
ec
t
to
u
s
e
PC
v
i
s
io
n
in
n
o
v
atio
n
s
to
wo
r
k
o
n
t
h
e
p
r
o
d
u
ctiv
ity
a
n
d
ex
ac
tn
ess
o
f
in
c
o
n
s
is
ten
cy
r
ec
o
g
n
itio
n
f
r
am
ew
o
r
k
s
,
r
ein
f
o
r
c
in
g
g
e
n
er
al
s
ec
u
r
it
y
an
d
s
itu
atio
n
al
m
in
d
f
u
ln
ess
ac
r
o
s
s
d
if
f
er
en
t sp
ac
es [
9
]
,
[
1
0
]
.
T
h
e
p
ass
ag
e
g
iv
es
a
clev
er
o
u
tlin
e
o
f
p
r
o
m
o
tio
n
in
s
id
e
th
e
m
o
r
e
ex
ten
s
iv
e
ar
ea
o
f
co
n
d
u
ct
g
ettin
g
it.
I
t
ch
ar
ac
ter
izes
o
d
d
ities
as
s
u
r
p
r
is
in
g
,
s
tr
an
g
e,
s
p
o
r
ad
ic,
o
r
ec
ce
n
tr
ic
o
cc
asio
n
s
o
r
th
in
g
s
th
at
s
tr
ay
f
r
o
m
s
tan
d
ar
d
e
x
am
p
les
o
r
d
atasets
.
T
h
ese
i
r
r
eg
u
la
r
ities
ar
e
s
et
s
u
b
o
r
d
in
ate
a
n
d
co
n
tr
ast
f
r
o
m
win
n
in
g
e
x
am
p
les
in
s
id
e
th
e
p
ec
u
liar
ity
o
f
in
ter
e
s
t
[
1
1
]
,
[
12
]
.
I
n
d
if
f
er
e
n
t
s
p
ac
es,
f
o
r
ex
am
p
le,
p
u
b
lic
s
ec
u
r
ity
,
wellb
ein
g
,
s
p
o
r
ts
ex
am
in
atio
n
,
b
u
n
c
h
m
o
v
em
e
n
t
ch
ec
k
in
g
,
an
d
v
is
u
al
o
b
s
er
v
atio
n
,
r
o
b
o
tized
p
r
o
m
o
tio
n
as
s
u
m
es
a
b
asic
p
ar
t.
C
o
m
p
u
ter
ized
o
b
s
er
v
atio
n
f
r
a
m
ewo
r
k
s
ar
e
v
alu
ab
le
in
cl
o
g
g
ed
co
n
d
itio
n
s
as
t
h
ey
ca
n
f
o
r
esee
p
h
en
o
m
en
al
an
d
co
m
p
lex
cir
cu
m
s
tan
ce
s
,
h
elp
in
g
with
p
u
r
s
u
in
g
r
ea
s
o
n
ab
le
well
-
b
ein
g
an
d
cr
is
is
co
n
tr
o
l
c
h
o
ices.
T
h
e
s
e
c
t
i
o
n
f
e
a
t
u
r
es
t
h
e
s
i
g
n
i
f
ic
a
n
c
e
o
f
o
b
s
e
r
v
a
t
i
o
n
p
r
o
c
e
d
u
r
e
s
i
n
t
e
s
t
i
n
g
a
n
d
s
w
a
r
m
e
d
c
o
n
d
i
t
i
o
n
s
l
i
k
e
p
o
li
t
i
c
al
c
o
n
v
e
n
t
i
o
n
s
,
o
c
c
u
p
i
e
d
r
o
a
d
s
,
a
i
r
t
e
r
m
i
n
a
l
s
,
s
h
o
p
p
i
n
g
c
e
n
t
e
r
s
,
p
u
b
l
i
c
f
e
s
t
i
v
a
ls
,
a
n
d
t
r
a
i
n
s
t
a
tio
n
s
.
B
y
r
e
c
o
g
n
i
z
i
n
g
a
n
d
o
v
e
r
s
e
e
i
n
g
s
w
a
r
m
s
,
t
h
es
e
r
e
c
o
n
n
a
i
s
s
a
n
c
e
m
e
t
h
o
d
s
a
d
d
t
o
p
u
b
l
i
c
s
e
c
u
r
it
y
a
n
d
w
e
l
l
-
b
ei
n
g
a
n
d
a
c
c
o
m
p
l
i
s
h
m
e
a
s
u
r
a
b
l
e
t
a
r
g
et
s
.
C
o
o
r
d
i
n
a
t
i
n
g
c
o
m
p
u
t
e
r
i
z
e
d
p
r
o
m
o
t
i
o
n
i
n
s
i
d
e
r
e
c
o
n
n
a
i
s
s
a
n
c
e
f
r
am
e
w
o
r
k
s
i
m
p
r
o
v
e
s
s
i
t
u
at
i
o
n
a
l
m
i
n
d
f
u
l
n
es
s
a
n
d
s
u
p
p
o
r
t
s
p
r
o
a
c
t
i
v
e
d
y
n
a
m
i
cs
i
n
d
i
f
f
e
r
e
n
t
g
e
n
u
i
n
e
w
o
r
l
d
s
c
e
n
a
r
i
o
s
[
1
3
]
,
[
1
4
]
.
T
h
e
d
iag
r
am
s
o
f
th
e
s
tr
ateg
y
an
d
d
if
f
icu
lties
r
elate
d
to
ab
n
o
r
m
ality
id
e
n
tific
atio
n
(
p
r
o
m
o
tio
n
)
m
o
d
els
ar
e
g
r
o
u
n
d
e
d
in
co
n
d
u
ct
p
o
r
tr
ay
al.
Pr
o
m
o
tio
n
m
o
d
els
r
em
o
v
e
s
ig
n
if
ican
t
elem
en
ts
f
r
o
m
o
b
s
er
v
atio
n
in
f
o
r
m
atio
n
,
lik
e
o
p
tical
s
tr
ea
m
,
s
p
atio
tem
p
o
r
al
v
o
lu
m
e
,
s
h
ap
e,
an
d
d
ir
ec
tio
n
[
1
5
]
.
T
h
es
e
h
ig
h
lig
h
ts
ac
t
as
co
n
tr
ib
u
tio
n
s
to
th
e
r
ec
o
g
n
it
io
n
cy
cle.
Dif
f
er
en
t
m
eth
o
d
o
lo
g
ies,
in
clu
d
in
g
p
r
in
cip
al
co
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
,
k
-
n
ea
r
est
n
eig
h
b
o
r
(
k
-
NN)
ca
lcu
latio
n
,
a
n
d
r
elatio
n
s
h
ip
ex
a
m
in
atio
n
,
ar
e
u
tili
ze
d
to
u
s
e
th
e
ex
tr
icat
ed
co
n
d
u
ct
h
i
g
h
lig
h
ts
f
o
r
ab
n
o
r
m
ality
id
en
tific
atio
n
.
T
h
e
ess
en
tial
g
o
al
o
f
t
h
ese
s
tr
u
ctu
r
es
is
to
id
en
tify
p
ec
u
liar
ities
u
tili
zin
g
s
tatic
an
d
tim
e
-
v
ar
iatio
n
f
r
am
ewo
r
k
s
.
E
x
tr
a
s
tr
ateg
ies
lik
e
s
lid
in
g
win
d
o
ws
(
SW
s
)
ar
e
in
co
r
p
o
r
ated
with
th
e
m
eth
o
d
o
lo
g
ies
ab
o
v
e
t
o
ad
d
r
ess
d
y
n
am
ic
an
d
tim
e
-
v
ar
iatio
n
o
d
d
ities
.
E
v
e
n
with
th
ese
en
d
ea
v
o
r
s
,
ex
is
tin
g
f
r
a
m
ewo
r
k
s
n
ee
d
ass
is
tan
ce
to
c
atch
tim
e
-
v
ar
iatio
n
m
o
d
el
elem
e
n
ts
ad
eq
u
ately
,
ca
u
s
in
g
tr
o
u
b
le
d
escr
ib
in
g
s
tr
an
g
e
c
o
n
tex
ts
[
1
6
]
,
[
1
7
]
.
T
h
e
u
s
e
o
f
v
is
u
al
s
u
r
v
eillan
ce
alo
n
g
s
id
e
ca
m
er
as
f
o
r
s
ec
u
r
ity
ap
p
licatio
n
s
i
s
b
ec
o
m
in
g
m
o
r
e
ex
p
ec
te
d
with
th
e
ascen
t
o
f
wr
o
n
g
d
o
in
g
all
o
v
er
th
e
p
lan
et.
L
ik
ewise,
it
h
as
tu
r
n
e
d
in
t
o
a
p
e
r
ce
iv
ed
p
iece
o
f
p
r
esen
t
-
d
ay
life
.
C
C
T
V
is
u
s
ed
f
o
r
v
i
d
eo
s
u
r
v
eillan
ce
in
p
lace
s
th
at
e
x
p
ec
t
to
b
e
g
o
tte
n
.
C
o
n
s
eq
u
e
n
tly
,
s
u
cc
ess
f
u
lly
d
ec
id
in
g
p
o
ten
tial
o
d
d
ities
o
r
o
b
jects o
f
in
ter
est f
r
o
m
m
an
y
r
ec
o
n
n
aiss
an
ce
r
ec
o
r
d
in
g
s
h
as
b
ec
o
m
e
a
r
d
u
o
u
s
[
1
8
]
.
Dasar
ir
aju
et
a
l.
[
1
9
]
p
r
esen
t
a
co
n
tin
u
o
u
s
g
r
o
u
p
p
r
o
m
o
tio
n
f
r
am
ewo
r
k
u
s
in
g
a
c
o
n
v
o
lu
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
C
o
n
v
-
L
STM
)
o
r
g
an
izatio
n
.
T
h
e
m
et
h
o
d
o
lo
g
y
u
s
es
d
ee
p
lear
n
in
g
(
DL
)
p
r
o
ce
d
u
r
es
t
o
f
o
r
esee
r
o
u
g
h
e
x
er
cises
an
d
co
n
tin
u
o
u
s
ly
p
r
ep
a
r
e
p
ar
t
n
er
s
f
o
r
s
u
ch
e
v
en
ts
.
T
h
e
C
o
n
v
-
L
STM
n
etwo
r
k
is
ex
p
licitly
u
tili
ze
d
to
ca
tch
v
id
eo
o
u
tlin
es
an
d
r
ec
o
g
n
ize
h
o
r
r
if
ic
ac
ts
in
s
id
e
th
e
g
r
o
u
p
.
T
h
e
f
r
am
ewo
r
k
p
r
o
p
o
s
ed
in
th
e
r
ev
iew
s
h
o
ws
f
u
r
th
er
d
ev
elo
p
ed
p
r
ec
is
io
n
an
d
s
p
ee
d
co
n
tr
asted
with
p
ast
tech
n
iq
u
es.
E
v
en
with
th
ese
h
ea
d
way
s
,
th
e
f
r
a
m
ewo
r
k
’
s
ex
ac
tn
ess
s
h
o
u
ld
b
e
im
p
r
o
v
ed
b
y
t
h
e
in
tr
icac
y
o
f
ch
ar
ac
ter
izi
n
g
in
d
iv
id
u
al
o
r
g
at
h
er
in
g
e
x
er
cises
p
r
ec
is
ely
.
T
h
is
r
ec
o
m
m
en
d
s
th
at
wh
ile
C
o
n
v
-
L
STM
n
etwo
r
k
s
o
f
f
er
p
r
o
m
is
in
g
ca
p
ac
ities
f
o
r
c
o
n
ti
n
u
o
u
s
p
r
o
m
o
tio
n
in
p
ac
k
ed
s
ce
n
es,
f
u
r
th
er
r
ef
in
e
m
en
t
a
n
d
e
n
h
an
ce
m
e
n
t
m
ig
h
t
b
e
ess
en
tial
to
ad
d
r
ess
th
e
d
i
f
f
icu
lties
r
elate
d
to
d
is
tin
g
u
is
h
in
g
an
d
o
r
d
er
in
g
d
if
f
e
r
en
t
e
x
er
cises
in
s
id
e
th
e
g
r
o
u
p
.
T
h
e
r
ev
iew
ad
d
s
to
th
e
ex
p
lo
r
atio
n
o
f
u
s
in
g
p
r
o
f
o
u
n
d
lear
n
in
g
p
r
o
ce
d
u
r
es
f
o
r
co
n
s
tan
t
g
r
o
u
p
p
ec
u
liar
ity
r
ec
o
g
n
itio
n
,
f
ea
tu
r
in
g
b
o
th
t
h
e
h
ea
d
way
m
ad
e
an
d
th
e
co
n
tin
u
o
u
s
d
if
f
icu
ltie
s
in
ac
co
m
p
lis
h
in
g
h
ig
h
p
r
ec
is
io
n
in
co
m
p
lex
g
en
u
in
e
wo
r
ld
s
ce
n
a
r
io
s
[
2
0
]
,
[
2
1
].
W
h
ile
p
r
o
g
r
ess
h
as
b
ee
n
m
a
d
e
in
p
r
o
m
o
tio
n
m
o
d
els
u
s
in
g
co
n
d
u
ct
p
o
r
tr
ay
al,
d
if
f
icu
lti
es,
s
u
ch
as
ca
tch
in
g
tim
e
-
v
ar
iatio
n
elem
e
n
ts
an
d
ten
d
in
g
to
im
p
ed
im
e
n
t
is
s
u
es,
co
n
tin
u
e
to
h
ap
p
e
n
.
Fu
r
th
er
ex
a
m
in
atio
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
Hig
h
-
r
eso
lu
tio
n
a
eria
l m
o
n
ito
r
in
g
u
s
in
g
DL
fo
r
id
en
tifyin
g
…
(
Mu
ke
s
h
K
u
ma
r
Tr
ip
a
th
i
)
1829
an
d
p
r
o
g
r
ess
io
n
s
in
ar
tific
ial
i
n
tellig
en
ce
(
AI
)
m
eth
o
d
s
ar
e
e
s
s
en
tial
to
d
ef
ea
t
th
ese
im
p
ed
i
m
en
ts
an
d
i
m
p
r
o
v
e
ab
n
o
r
m
ality
id
en
tific
atio
n
a
b
ilit
ies
in
o
b
s
er
v
atio
n
f
r
am
ewo
r
k
s
.
T
h
e
ex
ce
s
s
p
iece
o
f
th
is
w
o
r
k
is
o
r
g
an
ized
as
f
o
llo
ws:
t
h
e
r
e
co
m
m
e
n
d
ed
s
tr
ateg
y
is
m
a
d
e
s
en
s
e
o
f
in
s
eg
m
en
t
2
;
th
e
p
r
o
p
o
s
ed
s
y
s
tem
’
s
r
esu
lts
an
d
co
n
v
er
s
atio
n
f
o
cu
s
ed
o
n
ex
ec
u
tio
n
m
ea
s
u
r
em
en
ts
ar
e
s
h
o
w
n
in
ar
ea
3
.
At
lo
n
g
last
,
s
eg
m
en
t
4
s
ig
n
if
ies
th
e
f
in
is
h
o
f
th
e
p
ap
er
.
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
y
f
o
r
a
h
u
m
an
a
n
o
m
aly
d
etec
tio
n
(
AD)
s
y
s
tem
u
s
in
g
UAV
s
y
s
tem
s
aim
s
to
en
h
a
n
ce
s
u
r
v
eillan
ce
b
y
id
en
tify
in
g
u
n
u
s
u
al
h
u
m
a
n
ac
ti
v
ities
in
v
id
eo
f
o
o
ta
g
e
ca
p
t
u
r
ed
b
y
UAVs
[
2
2
]
.
T
h
e
s
y
s
tem
is
d
es
ig
n
ed
to
o
p
er
ate
in
r
ea
l
tim
e,
lev
er
ag
in
g
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
to
d
etec
t
an
o
m
alies
with
o
u
t
p
r
io
r
k
n
o
w
led
g
e
o
f
th
e
en
v
ir
o
n
m
e
n
t.
T
h
e
p
r
im
ar
y
g
o
als
in
clu
d
e
d
ev
el
o
p
in
g
a
lig
h
tweig
h
t
,
ef
f
icien
t
d
etec
tio
n
m
o
d
el
s
u
itab
le
f
o
r
th
e
lim
ited
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
o
f
s
m
all
-
s
ca
le
U
AVs
an
d
en
s
u
r
in
g
h
ig
h
ac
c
u
r
ac
y
a
n
d
r
eliab
ilit
y
i
n
d
iv
er
s
e
a
n
d
d
y
n
am
ic
en
v
ir
o
n
m
en
ts
.
T
h
e
ap
p
r
o
ac
h
i
n
teg
r
a
tes
s
tate
-
of
-
th
e
-
ar
t
tech
n
iq
u
es
in
im
ag
e
p
r
o
ce
s
s
in
g
an
d
p
atter
n
r
ec
o
g
n
itio
n
to
ef
f
ec
tiv
ely
id
en
tify
an
d
c
lass
if
y
an
o
m
alies,
u
ltima
tely
im
p
r
o
v
in
g
th
e
ef
f
i
ca
cy
o
f
UAV
-
b
ased
s
u
r
v
eilla
n
ce
ap
p
licatio
n
s
.
T
h
e
n
o
n
lin
e
ar
f
ea
tu
r
e
m
a
p
p
in
g
(
NFMF
)
co
m
p
o
n
en
t
tr
a
n
s
f
o
r
m
s
in
p
u
t
f
ea
tu
r
es
in
to
a
m
o
r
e
d
is
cr
im
in
ativ
e
s
p
ac
e,
im
p
r
o
v
in
g
t
h
e
m
o
d
el
’
s
ab
ilit
y
to
d
is
tin
g
u
is
h
b
etwe
en
n
o
r
m
al
an
d
an
o
m
alo
u
s
p
at
ter
n
s
.
T
h
e
d
o
u
b
le
B
i
-
d
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
DB
iLST
M
)
ar
ch
itectu
r
e
p
r
o
ce
s
s
es
th
e
s
eq
u
en
tial
d
ata
in
b
o
t
h
f
o
r
war
d
an
d
b
ac
k
war
d
d
ir
ec
tio
n
s
,
en
s
u
r
in
g
a
co
m
p
r
eh
en
s
iv
e
u
n
d
er
s
tan
d
in
g
o
f
te
m
p
o
r
al
d
ep
e
n
d
en
cies.
T
h
is
co
m
b
in
e
d
ap
p
r
o
ac
h
e
n
ab
les
th
e
d
etec
tio
n
s
y
s
tem
t
o
r
o
b
u
s
tly
id
en
tify
an
o
m
alies
i
n
r
ea
l
-
tim
e,
ev
en
with
th
e
lim
ited
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
ty
p
ical
o
f
UAV
s
y
s
tem
s
,
th
er
e
b
y
s
ig
n
if
ican
tly
im
p
r
o
v
in
g
s
u
r
v
eillan
ce
ca
p
ab
ilit
ies.
Fig
u
r
e
1
v
is
u
ally
r
ep
r
esen
ts
th
e
p
r
o
p
o
s
ed
h
u
m
an
AD
s
ch
em
e
f
o
r
v
i
d
eo
s
u
r
v
eillan
ce
u
s
in
g
UAV
s
y
s
tem
s
.
B
lo
ck
d
iag
r
am
s
lik
e
th
is
ar
e
ess
en
tial
f
o
r
u
n
d
er
s
tan
d
in
g
co
m
p
le
x
s
y
s
tem
s
’
in
f
o
r
m
atio
n
f
lo
w
an
d
p
r
o
ce
s
s
in
g
s
tep
s
,
o
f
f
er
in
g
a
clea
r
o
v
er
v
iew
o
f
co
m
p
o
n
e
n
t
in
ter
ac
tio
n
s
an
d
c
o
n
tr
ib
u
ti
o
n
s
to
th
e
m
eth
o
d
’
s
f
u
n
ctio
n
ality
.
T
h
is
f
ig
u
r
e
lik
e
ly
o
u
tlin
es
th
e
s
eq
u
en
ce
o
f
o
p
er
atio
n
s
,
s
tar
tin
g
f
r
o
m
v
id
e
o
in
p
u
t
.
E
ac
h
b
lo
ck
s
y
m
b
o
lizes
a
d
is
tin
ct
p
r
o
ce
s
s
in
g
s
tep
o
r
co
m
p
o
n
en
t,
illu
s
tr
atin
g
h
o
w
th
ese
elem
en
ts
in
teg
r
ate
to
ac
h
iev
e
ef
f
ec
tiv
e
h
u
m
an
AD
in
UAV
-
b
ased
v
id
eo
s
u
r
v
eillan
ce
.
T
h
e
p
r
o
p
o
s
ed
NFMF
-
DB
iLST
M
m
o
d
el
’
s
wo
r
k
in
g
p
r
o
ce
s
s
f
o
r
d
etec
tin
g
h
u
m
an
a
n
o
m
alies
in
v
id
eo
s
u
r
v
eillan
c
e
in
v
o
l
v
es
s
ev
er
al
k
e
y
s
tep
s
.
I
n
itially
,
v
id
eo
d
ata
is
ca
p
tu
r
ed
an
d
p
r
ep
r
o
ce
s
s
ed
to
en
h
an
ce
q
u
ality
an
d
r
em
o
v
e
n
o
is
e.
T
h
e
NFMF
m
o
d
u
le
t
h
en
tr
an
s
f
o
r
m
s
th
e
p
r
ep
r
o
ce
s
s
ed
d
ata
in
to
a
m
o
r
e
d
is
cr
im
in
ativ
e
f
ea
tu
r
e
s
p
a
ce
.
T
h
ese
tr
an
s
f
o
r
m
e
d
f
ea
tu
r
es
ar
e
f
ed
in
to
th
e
DB
iLST
M
n
etwo
r
k
,
wh
ich
p
r
o
ce
s
s
es
th
e
d
ata
f
o
r
war
d
a
n
d
b
ac
k
war
d
,
ca
p
tu
r
in
g
tem
p
o
r
al
d
ep
en
d
en
cies
an
d
p
atter
n
s
ef
f
ec
tiv
ely
.
T
h
e
DB
iLST
M
’
s
b
id
ir
ec
tio
n
al
n
atu
r
e
en
s
u
r
es
a
co
m
p
r
eh
en
s
iv
e
s
eq
u
en
ce
an
al
y
s
is
,
im
p
r
o
v
in
g
AD
ac
c
u
r
ac
y
.
Fin
ally
,
th
e
p
r
o
ce
s
s
ed
d
ata
is
c
lass
if
ied
to
id
en
tify
an
o
m
alie
s
,
with
th
e
m
o
d
el
lev
er
ag
in
g
its
en
h
a
n
ce
d
f
ea
tu
r
e
s
p
ac
e
an
d
tem
p
o
r
al
u
n
d
er
s
tan
d
in
g
to
p
r
o
v
id
e
ac
cu
r
ate
an
d
ef
f
icien
t
d
etec
tio
n
r
esu
lts
s
u
itab
le
f
o
r
r
ea
l
-
tim
e
a
p
p
licatio
n
s
o
n
UAV
s
y
s
tem
s
with
lim
ited
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
.
Fig
u
r
e
1
.
B
lo
ck
d
iag
r
am
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
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
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
8
27
-
1
8
35
1830
2
.
1
.
F
r
a
m
e
c
o
nv
er
s
io
n
I
n
th
is
p
r
o
ce
s
s
,
s
in
ce
th
e
v
id
eo
f
o
r
m
at
is
n
o
t
s
u
itab
le
f
o
r
class
if
icatio
n
p
u
r
p
o
s
es,
th
e
s
u
r
v
eillan
ce
v
id
eo
s
ar
e
tr
an
s
f
o
r
m
ed
in
to
a
s
er
ies
o
f
f
r
a
m
es
b
ased
o
n
a
s
p
ec
if
ied
tim
e
in
te
r
v
al.
T
h
is
co
n
v
er
s
io
n
e
n
s
u
r
es
th
at
ea
ch
v
id
e
o
is
b
r
o
k
en
d
o
wn
in
t
o
a
m
an
a
g
ea
b
le
n
u
m
b
er
o
f
f
r
a
m
es,
wh
ich
ca
n
th
en
b
e
u
s
ed
f
o
r
f
u
r
th
er
a
n
aly
s
is
.
L
et
FF
F
d
en
o
te
th
e
co
n
v
er
ted
f
r
am
es.
2
.
2
.
P
re
pro
ce
s
s
ing
T
h
ese
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
ar
e
cr
u
cial
f
o
r
p
r
ep
a
r
in
g
th
e
d
ata
f
o
r
ac
cu
r
ate
an
d
e
f
f
icien
t
AD
.
T
o
d
etec
t
b
etr
ay
al
b
e
h
av
io
r
s
,
p
r
ep
r
o
ce
s
s
in
g
is
ess
en
tial
d
u
e
to
tim
e
co
n
s
tr
ain
ts
an
d
th
e
s
h
a
d
o
win
g
ef
f
ec
t.
T
h
is
s
tep
in
v
o
lv
es
en
h
a
n
cin
g
th
e
im
ag
e
q
u
ality
an
d
r
ec
o
g
n
izin
g
a
s
et
o
f
tar
g
eted
o
b
jects.
T
h
e
t
wo
m
ain
p
r
o
ce
s
s
es
in
v
o
lv
ed
ar
e:
−
Du
p
licate
f
r
am
e
r
em
o
v
al:
th
is
s
tep
elim
in
ates
r
ed
u
n
d
an
t
f
r
a
m
es
to
en
s
u
r
e
t
h
at
o
n
ly
u
n
iq
u
e
an
d
r
elev
an
t
f
r
am
es a
r
e
an
aly
ze
d
,
th
er
eb
y
o
p
tim
izin
g
p
r
o
ce
s
s
in
g
tim
e
an
d
r
eso
u
r
ce
s
.
−
C
o
n
tr
ast
en
h
an
ce
m
en
t:
th
is
s
tep
im
p
r
o
v
es
th
e
v
is
ib
ilit
y
o
f
th
e
f
r
am
es
b
y
in
cr
ea
s
in
g
th
e
co
n
tr
ast,
wh
ich
h
elp
s
in
b
etter
id
e
n
tific
atio
n
a
n
d
d
if
f
er
en
tiatio
n
o
f
o
b
jects with
in
th
e
f
r
am
es.
2.
3
.
B
a
c
k
g
ro
un
d
s
ub
t
ra
ct
io
n
Fo
r
b
ac
k
g
r
o
u
n
d
an
d
f
o
r
eg
r
o
u
n
d
s
u
b
tr
ac
tio
n
u
s
in
g
a
Gau
s
s
ian
k
er
n
el,
th
e
d
en
s
ity
o
f
an
o
b
ject
with
in
a
g
r
o
u
p
is
esti
m
ated
th
r
o
u
g
h
a
k
er
n
el
f
u
n
ctio
n
.
T
h
e
k
er
n
el
f
u
n
ctio
n
is
K,
th
e
tar
g
eted
o
b
ject
is
x
,
an
d
th
e
b
an
d
wid
th
p
a
r
am
eter
h
co
n
t
r
o
ls
th
e
s
m
o
o
th
in
g
.
T
h
e
b
a
n
d
wid
th
h
is
d
er
iv
ed
u
s
in
g
p
r
o
b
ab
ilis
tic
m
atr
ix
f
ac
to
r
izatio
n
an
d
th
e
b
ac
k
g
r
o
u
n
d
-
s
u
b
tr
ac
ted
im
ag
e
is
th
en
u
s
ed
in
s
u
b
s
eq
u
e
n
t p
h
ases
f
o
r
s
il
h
o
u
ette
f
o
r
m
atio
n
,
wh
er
e
th
e
co
n
t
o
u
r
s
an
d
s
h
ap
es
o
f
th
e
d
etec
ted
o
b
jects
ar
e
ex
t
r
ac
ted
f
o
r
f
u
r
th
e
r
an
aly
s
is
.
Af
ter
th
e
b
ac
k
g
r
o
u
n
d
h
as
b
ee
n
s
u
b
tr
ac
ted
a
n
d
t
h
e
d
en
s
ity
o
f
o
b
jects
h
as
b
ee
n
esti
m
ated
u
s
in
g
th
e
Gau
s
s
ian
k
e
r
n
el,
th
e
n
ex
t
s
tep
is
to
f
o
r
m
s
ilh
o
u
ettes
o
f
th
e
o
b
j
ec
ts
[
2
3
]
.
T
h
is
in
v
o
l
v
es
f
u
r
th
e
r
p
r
o
c
ess
in
g
o
f
t
h
e
b
ac
k
g
r
o
u
n
d
-
s
u
b
tr
ac
ted
im
a
g
e
to
ex
tr
ac
t th
e
co
n
to
u
r
s
an
d
s
h
a
p
es o
f
th
e
d
etec
ted
o
b
jects.
2
.
4
.
Clus
t
er
ing
T
h
e
s
o
r
tin
g
an
d
av
e
r
ag
e
-
b
ased
K
-
m
ea
n
s
(
SA
-
KM
)
clu
s
ter
in
g
alg
o
r
ith
m
is
em
p
lo
y
ed
f
o
l
lo
win
g
th
e
s
ilh
o
u
ette
f
u
n
ctio
n
to
clu
s
te
r
n
o
n
-
h
u
m
an
,
h
u
m
an
,
an
d
s
u
s
p
ec
ted
h
u
m
an
ca
teg
o
r
ies
f
r
o
m
b
ac
k
g
r
o
u
n
d
-
s
u
b
tr
ac
ted
im
ag
es
[
2
4
]
.
T
y
p
i
ca
lly
,
K
-
m
ea
n
s
g
r
o
u
p
s
p
ix
el
s
in
to
th
ese
c
ateg
o
r
ies
b
y
c
o
m
p
u
tin
g
d
is
tan
ce
s
b
etwe
en
in
co
m
in
g
p
ix
els
a
n
d
ex
is
tin
g
clu
s
ter
s
.
Ho
wev
er
,
tr
ad
itio
n
al
m
o
d
els
f
ac
e
th
e
o
u
tlier
p
r
o
b
lem
.
T
o
ad
d
r
ess
th
is
,
a
s
o
r
tin
g
an
d
m
ed
ian
m
eth
o
d
is
p
r
o
p
o
s
e
d
.
T
h
is
m
eth
o
d
s
o
r
ts
th
e
p
ix
els
an
d
u
s
es
m
ed
ian
v
alu
es
to
im
p
r
o
v
e
th
e
clu
s
ter
in
g
p
r
o
ce
s
s
,
ef
f
ec
tiv
ely
m
itig
atin
g
th
e
im
p
ac
t
o
f
o
u
tlier
s
an
d
en
h
an
ci
n
g
th
e
ac
cu
r
ac
y
o
f
th
e
h
u
m
an
an
d
n
o
n
-
h
u
m
a
n
class
if
icatio
n
in
th
e
i
m
ag
es.
2
.
5
.
F
e
a
t
ure
e
x
t
r
a
ct
io
n
Featu
r
e
e
x
tr
ac
tio
n
(
FE)
tr
an
s
f
o
r
m
s
r
aw
d
ata
in
to
n
u
m
er
ical
f
ea
tu
r
es
th
at
ca
n
b
e
ef
f
ec
tiv
el
y
p
r
o
ce
s
s
ed
wh
ile
p
r
eser
v
in
g
th
e
in
f
o
r
m
at
io
n
co
n
tain
ed
in
th
e
o
r
ig
in
al
d
ataset.
T
h
e
d
ata
g
en
er
ate
d
th
r
o
u
g
h
FE
ty
p
ically
y
ield
s
b
etter
o
u
tco
m
es
in
class
if
icatio
n
task
s
u
s
in
g
m
ac
h
in
e
l
ea
r
n
in
g
th
an
r
aw
d
ata
[
2
5
]
.
T
h
e
p
r
im
ar
y
f
ea
t
u
r
es
ex
tr
ac
ted
in
clu
d
e
t
h
e
an
g
le
b
etwe
en
jo
in
ts
,
f
lo
o
r
clip
p
l
an
e,
h
eig
h
t,
wid
t
h
,
v
elo
city
,
ac
ce
ler
atio
n
,
an
d
d
if
f
er
en
ce
s
b
etwe
en
f
r
am
es.
Ad
d
itio
n
al
s
tatis
tical
f
ea
tu
r
es
s
u
ch
as
m
ea
n
,
s
tan
d
ar
d
d
ev
iat
io
n
,
s
k
ewn
ess
,
an
d
v
ar
ian
ce
ar
e
co
n
s
id
er
e
d
.
Mo
r
eo
v
er
,
d
y
n
am
ic
f
ea
t
u
r
es
lik
e
th
e
m
ax
im
al
L
y
ap
u
n
o
v
ex
p
o
n
en
t,
c
o
r
r
elatio
n
d
im
en
s
io
n
,
m
o
tio
n
,
s
ize,
an
d
t
ex
tu
r
e
ar
e
also
e
x
tr
ac
ted
to
r
e
p
r
esen
t th
e
d
ata
c
o
m
p
r
e
h
en
s
iv
ely
.
2.
6
.
F
e
a
t
ure
s
elec
t
io
n
Utilizin
g
th
e
p
r
ed
ictio
n
er
r
o
r
-
o
n
ly
o
p
tim
izatio
n
(
PEOO
)
al
g
o
r
ith
m
,
v
ital
f
ea
tu
r
es
a
r
e
c
h
o
s
en
af
ter
FE.
T
h
e
PEOO
al
g
o
r
ith
m
m
im
ics
th
e
f
o
o
d
-
s
ea
r
c
h
in
g
b
eh
av
io
r
o
f
E
u
r
asian
Oy
s
ter
c
atch
er
s
p
r
o
b
in
g
f
o
r
m
u
s
s
els.
I
n
th
is
alg
o
r
ith
m
,
ea
ch
b
ir
d
in
th
e
p
o
p
u
latio
n
s
er
v
es
as
a
s
ea
r
ch
ag
en
t.
T
h
e
o
p
tim
izatio
n
en
s
u
r
es
a
b
alan
ce
in
t
h
e
m
u
s
s
els
’
s
ize,
ca
lo
r
ies,
an
d
en
er
g
y
.
T
h
e
c
o
n
v
en
tio
n
al
alg
o
r
ith
m
co
n
s
id
er
s
ac
co
u
n
t
le
n
g
th
,
p
o
wer
,
an
d
ca
lo
r
ic
v
alu
e,
all
r
ep
r
esen
ted
b
y
r
an
d
o
m
n
u
m
b
er
s
r
an
g
in
g
f
r
o
m
3
to
5
.
Ho
wev
er
,
th
is
r
esear
ch
m
o
d
el
s
elec
ts
th
ese
v
alu
es
u
s
in
g
th
e
Po
is
s
o
n
f
u
n
ctio
n
to
en
h
an
ce
th
e
s
elec
tio
n
p
r
o
ce
s
s
an
d
p
r
ev
en
t
im
b
alan
ce
s
,
en
s
u
r
in
g
o
p
tim
al
f
ea
tu
r
e
s
elec
tio
n
f
o
r
s
u
b
s
eq
u
e
n
t
class
if
icatio
n
task
s
.
Her
e,
th
e
m
ea
n
n
u
m
b
er
o
f
iter
atio
n
s
is
n
o
tated
as
.
Gr
o
u
n
d
ed
o
n
tr
ial
an
d
test
in
g
,
t
h
ese
v
alu
es
ar
e
ch
o
s
en
.
T
h
e
f
ea
tu
r
es
ar
e
ch
o
s
en
r
esem
b
lin
g
th
is
way
o
f
h
u
n
tin
g
m
u
s
s
els.
ℑ
d
en
o
tes th
e
s
elec
te
d
f
ea
tu
r
es.
T
h
e
p
r
o
p
o
s
ed
PERO p
s
eu
d
o
co
d
e
is
g
iv
en
to
A
lg
o
r
ith
m
1
.
Alg
o
r
ith
m
1
.
PERO p
s
eu
d
o
co
d
e
Input: Extracted features
ℵ
(
)
Output: Selected features
ℑ
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
Hig
h
-
r
eso
lu
tio
n
a
eria
l m
o
n
ito
r
in
g
u
s
in
g
DL
fo
r
id
en
tifyin
g
…
(
Mu
ke
s
h
K
u
ma
r
Tr
ip
a
th
i
)
1831
Begin
Initialize population,
Calculate the fitness of each search agent
Identify the best solution
ℵ
(
)
While
=
1
For
=
1
Compute time, energy, and
caloric value
Update the position of the solution
End for
Calculate the fitness of each search agent
End while
Return
ℑ
End begins
3.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
T
h
e
p
r
o
p
o
s
ed
tech
n
i
q
u
e
’
s
p
er
f
o
r
m
a
n
ce
is
ev
alu
ated
an
d
co
m
p
ar
ed
with
p
r
ev
ailin
g
t
ec
h
n
iq
u
es
im
p
lem
en
ted
u
s
in
g
th
e
Py
th
o
n
p
latf
o
r
m
.
T
h
e
e
v
alu
atio
n
p
r
o
ce
s
s
in
v
o
lv
es
s
ev
er
al
s
tep
s
t
o
co
m
p
r
eh
e
n
s
iv
ely
an
aly
ze
th
e
p
r
o
p
o
s
ed
h
u
m
a
n
AD
s
y
s
tem
.
T
h
e
p
r
o
p
o
s
ed
UAV
s
y
s
tem
s
in
v
o
lv
e
s
ev
er
al
d
etailed
s
tep
s
,
alg
o
r
ith
m
s
,
an
d
tech
n
iq
u
es
to
en
s
u
r
e
r
e
p
licab
ilit
y
an
d
v
ali
d
atio
n
o
f
f
in
d
in
g
s
.
Hig
h
-
r
eso
l
u
tio
n
v
i
d
eo
d
ata
is
in
itially
co
llected
f
r
o
m
UAV
s
f
ly
in
g
at
lo
w
altitu
d
es
to
c
ap
tu
r
e
d
etailed
im
ag
er
y
.
T
h
e
NFMF
alg
o
r
ith
m
tr
an
s
f
o
r
m
s
th
ese
f
r
am
es
in
to
a
m
o
r
e
d
is
cr
im
in
ativ
e
f
ea
tu
r
e
s
p
ac
e,
en
h
an
cin
g
th
e
m
o
d
el
’
s
ab
ilit
y
to
id
en
tify
an
o
m
alies.
T
ex
tu
r
al
f
ea
tu
r
es
ar
e
th
en
ex
tr
ac
ted
u
s
in
g
lo
ca
l
b
in
ar
y
p
atter
n
s
(
L
B
P)
an
d
g
r
ay
-
lev
el
co
-
o
cc
u
r
r
e
n
ce
m
atr
ix
(
GL
C
M)
,
wh
ich
ca
p
tu
r
e
th
e
im
ag
es
’
ess
en
tial
m
icr
o
a
n
d
m
ac
r
o
s
tr
u
ct
u
r
es
[
2
6
]
.
T
h
e
m
o
d
el
is
tr
ain
ed
u
s
in
g
a
n
8
0
-
2
0
tr
ain
-
test
s
p
lit,
with
th
e
Ad
am
o
p
ti
m
izer
an
d
a
lear
n
in
g
r
ate
0
.
0
0
1
to
m
in
im
ize
t
h
e
lo
s
s
f
u
n
ctio
n
.
T
h
e
f
in
al
m
o
d
e
l
class
if
ies
f
r
am
es
as
n
o
r
m
al
o
r
ab
n
o
r
m
al,
with
p
er
f
o
r
m
an
ce
ev
alu
ated
u
s
in
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
m
etr
ics.
T
h
e
s
y
s
te
m
d
em
o
n
s
tr
ates
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
co
m
p
ar
e
d
to
ex
is
tin
g
m
eth
o
d
s
,
with
N
FMF
en
h
an
cin
g
f
ea
tu
r
e
d
is
cr
im
in
atio
n
a
n
d
DB
iLST
M
ef
f
ec
tiv
ely
ca
p
tu
r
in
g
tem
p
o
r
al
p
atter
n
s
,
th
u
s
v
alid
atin
g
th
e
r
o
b
u
s
tn
ess
an
d
s
u
itab
ilit
y
o
f
th
e
p
r
o
ce
s
s
f
o
r
r
ea
l
-
tim
e
UAV
-
b
ased
s
u
r
v
eillan
ce
ap
p
licatio
n
s
.
3
.
1
.
P
er
f
o
r
m
a
nce
a
na
ly
s
is
T
h
e
m
eth
o
d
in
tr
o
d
u
ce
s
a
n
ew
s
p
atial
r
elatio
n
s
h
ip
,
wh
ic
h
r
e
f
er
s
to
th
e
a
r
r
an
g
em
en
t
o
f
p
atch
es
in
th
e
im
ag
e,
r
ep
r
esen
ted
b
y
a
d
is
cr
etize
d
cir
cu
m
f
er
en
ce
th
at
co
n
s
id
er
s
d
is
p
lace
m
en
ts
alo
n
g
all
d
ir
ec
tio
n
s
,
th
er
eb
y
im
p
r
o
v
in
g
p
atch
r
e
p
r
esen
tatio
n
an
d
en
s
u
r
in
g
r
o
tatio
n
i
n
v
ar
ian
ce
.
Gen
er
alize
d
eq
u
atio
n
s
wer
e
d
ev
elo
p
ed
t
o
co
m
p
u
te
Har
alick
’
s
tex
tu
r
al
f
e
atu
r
es
ac
cu
r
ately
with
in
th
e
p
r
o
p
o
s
ed
s
p
atial
r
elatio
n
s
h
ip
.
Dif
f
er
en
t
p
atch
s
izes
an
d
cir
cu
m
f
er
en
ce
s
with
v
ar
y
in
g
r
a
d
ii
wer
e
ev
alu
ate
d
to
o
p
tim
ize
p
er
f
o
r
m
a
n
ce
.
Ov
e
r
all,
th
is
ap
p
r
o
ac
h
d
em
o
n
s
tr
ates
ef
f
ec
tiv
e
n
ess
in
AD
v
ia
tex
tu
r
es,
p
ar
ticu
lar
ly
in
l
o
w
-
altitu
d
e
ae
r
ial
im
ag
es
,
o
f
f
er
in
g
r
ea
l
-
tim
e
ca
p
ab
ilit
ies
an
d
a
lig
h
tweig
h
t
im
p
lem
en
tatio
n
.
T
h
is
m
eth
o
d
lev
er
ag
es
tex
tu
r
al
f
ea
tu
r
es
a
n
d
m
ac
h
in
e
lear
n
i
n
g
tech
n
iq
u
es
with
s
p
ec
if
ic
en
h
an
ce
m
en
ts
to
tr
ad
itio
n
al
m
et
h
o
d
s
,
s
ig
n
if
ican
tly
im
p
r
o
v
in
g
p
er
f
o
r
m
an
ce
a
n
d
p
r
o
v
id
i
n
g
a
p
r
o
m
is
in
g
ap
p
r
o
a
ch
to
AD
in
UAV
-
b
ased
s
u
r
v
eillan
ce
ap
p
licatio
n
s
.
Her
e,
th
e
p
r
o
p
o
s
ed
m
o
d
el
’
s
clu
s
ter
in
g
p
er
f
o
r
m
a
n
ce
,
ce
n
te
r
ed
o
n
clu
s
ter
in
g
ac
cu
r
ac
y
an
d
tim
e,
is
an
aly
ze
d
an
d
co
m
p
ar
ed
with
ex
is
tin
g
m
eth
o
d
s
s
u
ch
as
K
-
m
ea
n
s
,
f
u
zz
y
C
-
m
ea
n
s
(
FC
M)
,
an
d
f
ar
th
est
f
ir
s
t
clu
s
ter
in
g
(
FF
C
)
.
T
h
e
co
m
p
ar
is
o
n
s
h
ig
h
lig
h
t
th
e
im
p
r
o
v
e
m
en
ts
in
ac
cu
r
ately
ca
teg
o
r
izin
g
n
o
n
-
h
u
m
an
,
h
u
m
a
n
,
an
d
s
u
s
p
ec
te
d
h
u
m
an
p
ix
els
an
d
th
e
ef
f
icien
cy
i
n
p
r
o
ce
s
s
in
g
tim
e
ag
ain
s
t th
e
tr
ad
itio
n
al
cl
u
s
ter
in
g
tech
n
i
q
u
es.
T
h
e
im
ag
es
ap
p
ea
r
i
n
Fig
u
r
e
2
d
em
o
n
s
tr
ate
d
if
f
er
en
t
s
tag
es
o
r
m
eth
o
d
s
o
f
p
r
o
ce
s
s
in
g
ae
r
i
al
im
ag
er
y
f
o
r
d
etec
tin
g
an
d
class
if
y
in
g
r
eg
io
n
s
,
with
a
p
ar
ticu
lar
f
o
cu
s
o
n
id
en
tif
y
in
g
a
n
d
h
i
g
h
lig
h
tin
g
th
e
p
r
esen
ce
o
f
a
p
er
s
o
n
.
Fig
u
r
e
2
(
a
)
s
h
o
ws
an
ae
r
ial
v
iew
o
f
a
r
o
ad
with
a
p
er
s
o
n
walk
in
g
alo
n
g
it.
T
h
e
im
ag
e
is
in
n
atu
r
al
co
lo
r
s
an
d
ap
p
ea
r
s
to
b
e
tak
en
d
u
r
in
g
th
e
d
ay
.
A
p
r
o
ce
s
s
ed
v
er
s
io
n
o
f
th
e
ae
r
ial
v
iew
o
v
e
r
laid
with
a
g
r
id
an
d
co
lo
r
-
co
d
ed
s
ec
tio
n
s
.
T
h
e
p
e
r
s
o
n
is
h
ig
h
lig
h
ted
in
r
ed
,
i
n
d
icatin
g
a
d
etec
ted
r
eg
io
n
.
T
h
e
b
ac
k
g
r
o
u
n
d
is
d
iv
id
ed
in
to
g
r
ee
n
an
d
b
lu
e
s
ec
tio
n
s
,
d
is
p
lay
in
g
d
if
f
e
r
en
t
ty
p
es
o
f
ter
r
ain
o
r
ar
ea
s
d
ep
ic
ted
in
Fig
u
r
e
2
(
b
)
.
T
h
e
Fig
u
r
e
2
(
c
)
g
r
id
an
d
co
lo
r
-
co
d
in
g
ar
e
p
r
esen
t,
with
t
h
e
p
er
s
o
n
s
till
h
ig
h
lig
h
te
d
in
r
ed
.
T
h
e
g
r
ee
n
an
d
b
l
u
e
s
ec
tio
n
s
v
ar
y
s
lig
h
tly
,
p
o
ten
ti
ally
s
h
o
win
g
an
o
t
h
er
t
y
p
e
o
f
ter
r
ain
o
r
r
eg
io
n
class
if
icatio
n
.
An
o
th
e
r
v
ar
iatio
n
o
f
th
e
p
r
o
ce
s
s
ed
ae
r
ial
v
iew
with
a
g
r
id
a
n
d
c
o
lo
r
-
co
d
e
d
s
ec
tio
n
s
.
T
h
e
p
er
s
o
n
is
ag
ai
n
h
ig
h
lig
h
ted
in
r
ed
,
b
u
t
th
er
e
is
also
a
y
ello
w
s
ec
tio
n
n
ea
r
th
e
p
er
s
o
n
.
T
h
e
r
est
o
f
th
e
ar
ea
is
d
iv
id
ed
in
to
g
r
ee
n
an
d
b
lu
e
s
ec
tio
n
s
,
s
im
ilar
to
th
e
p
r
ev
io
u
s
im
ag
es d
ep
icted
in
Fig
u
r
e
2
(
d
)
.
T
ab
le
1
co
m
p
ar
es
th
e
p
r
o
p
o
s
ed
m
o
d
el
’
s
p
e
r
f
o
r
m
an
ce
ag
ain
s
t
ex
is
tin
g
clu
s
ter
in
g
m
et
h
o
d
s
,
ex
p
licitly
f
o
cu
s
in
g
o
n
clu
s
ter
in
g
ac
cu
r
a
cy
.
C
lu
s
ter
in
g
ac
cu
r
ac
y
is
a
p
iv
o
tal
m
etr
ic
th
at
ev
alu
ates
h
o
w
p
r
ec
is
ely
o
b
jects
ar
e
g
r
o
u
p
e
d
i
n
to
cl
u
s
ter
s
wh
ile
ac
co
u
n
tin
g
f
o
r
o
u
tlier
s
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
ac
h
iev
es
a
r
e
m
ar
k
ab
le
clu
s
ter
in
g
ac
cu
r
ac
y
o
f
9
8
.
9
2
%.
T
h
is
p
e
r
f
o
r
m
an
ce
is
n
o
ta
b
ly
s
u
p
er
io
r
,
with
th
e
p
r
o
p
o
s
ed
m
o
d
el
o
u
t
p
er
f
o
r
m
in
g
K
-
m
ea
n
s
b
y
2
.
9
2
%,
FC
M
b
y
3
.
8
0
%,
an
d
FF
C
b
y
5
.
9
2
%.
T
h
ese
im
p
r
o
v
e
m
en
ts
h
ig
h
lig
h
t
th
e
m
o
d
el
’
s
ad
v
an
ce
d
ca
p
ab
ilit
y
in
ef
f
ec
tiv
ely
h
an
d
l
in
g
o
u
tlier
s
an
d
en
s
u
r
in
g
ac
c
u
r
ate
o
b
ject
clu
s
ter
in
g
.
T
h
e
r
es
u
lts
u
n
d
er
s
co
r
e
th
at
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
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
8
27
-
1
8
35
1832
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
s
ig
n
if
i
ca
n
tly
m
o
r
e
ef
f
icien
t
th
an
t
h
e
tr
ad
itio
n
al
clu
s
ter
in
g
m
eth
o
d
s
.
K
-
m
ea
n
s
,
wh
ile
ef
f
ec
tiv
e,
n
ee
d
t
o
ca
tch
u
p
to
th
e
p
r
o
p
o
s
ed
m
o
d
el
b
y
a
m
ea
s
u
r
a
b
le
m
ar
g
in
,
in
d
i
ca
tin
g
its
p
o
ten
tial
s
h
o
r
tco
m
in
g
s
in
o
u
tlier
m
a
n
a
g
em
en
t.
Similar
ly
,
FC
M,
d
es
p
ite
its
n
u
an
ce
d
a
p
p
r
o
ac
h
to
clu
s
ter
in
g
th
r
o
u
g
h
f
u
zz
y
lo
g
ic,
d
o
es
n
o
t
m
atch
th
e
p
r
o
p
o
s
ed
m
o
d
el
’
s
p
r
ec
is
io
n
.
FF
C
,
wh
ich
r
elie
s
o
n
in
itia
lizin
g
clu
s
ter
s
with
th
e
f
ar
th
est
p
o
in
ts
,
ex
h
ib
its
th
e
lo
west
ac
cu
r
ac
y
am
o
n
g
th
e
co
m
p
ar
ed
m
et
h
o
d
s
,
em
p
h
asizin
g
th
e
p
r
o
p
o
s
ed
m
o
d
el
’
s
s
u
p
er
io
r
ity
in
co
m
p
l
ex
clu
s
ter
in
g
s
ce
n
ar
io
s
.
Ov
er
all,
th
e
p
r
o
p
o
s
ed
m
o
d
el
d
em
o
n
s
tr
ates
ex
ce
p
tio
n
al
p
er
f
o
r
m
an
ce
,
m
a
k
in
g
it
a
h
ig
h
ly
r
eliab
le
an
d
ef
f
icien
t
s
o
lu
tio
n
f
o
r
clu
s
ter
in
g
task
s
th
at
r
e
q
u
ir
e
h
ig
h
ac
cu
r
ac
y
an
d
r
o
b
u
s
t o
u
tlier
h
an
d
lin
g
.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
2
.
Dif
f
e
r
en
t stag
es o
r
m
eth
o
d
s
o
f
p
r
o
ce
s
s
in
g
ae
r
ial
i
m
ag
er
y
f
o
r
d
etec
tin
g
an
d
class
if
y
in
g
r
e
g
io
n
s
;
(
a)
o
u
t
p
u
t g
e
n
er
ated
u
s
in
g
d
if
f
er
en
t p
atch
s
izes
,
(
b
)
t
h
e
r
e
d
a
n
d
g
r
ee
n
p
atch
es in
d
icate
,
r
es
p
ec
tiv
ely
,
(
c)
an
o
m
alo
u
s
an
d
n
o
r
m
al
p
at
ch
es c
o
r
r
ec
tly
class
if
ied
,
an
d
(
d
)
b
lu
e
p
atch
es c
o
r
r
esp
o
n
d
to
n
o
r
m
al
p
atch
es c
lass
if
ied
T
ab
le
1
.
C
lu
s
ter
in
g
a
cc
u
r
ac
y
a
n
aly
s
is
M
e
t
h
o
d
A
c
c
u
r
a
c
y
P
r
o
p
o
se
d
S
A
-
KM
9
8
.
9
2
%
K
-
me
a
n
s
9
6
%
F
C
M
9
5
.
1
2
%
FFC
9
3
%
T
h
e
p
er
f
o
r
m
a
n
ce
r
esu
lts
o
f
t
h
e
p
r
o
p
o
s
ed
a
n
d
e
x
is
tin
g
m
e
th
o
d
s
ar
e
u
n
v
eiled
i
n
Fig
u
r
e
3
,
with
a
s
p
ec
if
ic
f
o
cu
s
o
n
clu
s
ter
in
g
tim
e,
wh
ich
is
th
e
d
u
r
atio
n
r
eq
u
ir
ed
t
o
co
m
p
lete
th
e
g
r
o
u
p
in
g
p
r
o
ce
s
s
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
d
em
o
n
s
tr
ates
its
s
u
p
er
io
r
ef
f
icien
cy
t
h
r
o
u
g
h
r
em
ar
k
a
b
ly
e
f
f
ec
tiv
e
tim
e
m
an
ag
em
e
n
t.
T
h
e
clu
s
ter
in
g
tim
e
f
o
r
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
5
,
3
2
5
m
illi
s
ec
o
n
d
s
(
m
s
)
,
wh
ich
is
s
u
b
s
tan
tially
lo
wer
co
m
p
ar
ed
to
th
e
p
r
ev
ailin
g
m
o
d
els.
I
n
co
m
p
ar
is
o
n
,
th
e
K
-
m
ea
n
s
alg
o
r
ith
m
r
e
q
u
ir
es
9
,
4
5
2
ms
to
co
m
p
lete
th
e
clu
s
ter
in
g
p
r
o
ce
s
s
,
h
ig
h
lig
h
tin
g
th
e
p
r
o
p
o
s
ed
m
o
d
el
’
s
s
ig
n
if
ican
t
tim
e
-
s
av
in
g
ad
v
a
n
tag
e.
Similar
ly
,
FC
M
h
as
a
clu
s
ter
in
g
tim
e
o
f
1
0
,
769
m
s
,
an
d
FF
C
tak
es
1
3
,
544
m
s
,
b
o
th
o
f
wh
ich
ar
e
c
o
n
s
id
er
ab
ly
h
ig
h
er
th
an
th
e
p
r
o
p
o
s
ed
m
o
d
el.
T
h
is
s
tar
k
d
if
f
er
en
ce
in
cl
u
s
ter
in
g
tim
es
u
n
d
er
s
co
r
es
th
e
p
r
o
p
o
s
ed
m
o
d
el
’
s
ef
f
icien
c
y
in
h
an
d
lin
g
la
r
g
e
d
atasets
an
d
c
o
m
p
lex
clu
s
ter
in
g
task
s
m
o
r
e
s
wif
tly
.
T
h
e
an
aly
s
is
p
r
o
v
es
th
at
th
e
p
r
o
p
o
s
ed
SA
-
KM
m
o
d
el
n
o
t
o
n
ly
m
ain
tain
s
h
ig
h
ac
cu
r
ac
y
b
u
t
also
ac
h
iev
es
f
aster
clu
s
ter
in
g
tim
es,
m
ak
in
g
it
a
h
ig
h
ly
ef
f
icien
t
an
d
p
r
ac
tical
s
o
lu
tio
n
f
o
r
clu
s
ter
in
g
ap
p
licatio
n
s
th
a
t
d
em
an
d
b
o
th
p
r
ec
is
io
n
an
d
s
p
ee
d
.
T
h
e
r
ed
u
ce
d
clu
s
ter
in
g
tim
e
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
en
h
an
ce
s
its
u
s
ab
ili
ty
in
r
ea
l
-
tim
e
a
p
p
licatio
n
s
a
n
d
lar
g
e
-
s
ca
le
d
ata
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
Hig
h
-
r
eso
lu
tio
n
a
eria
l m
o
n
ito
r
in
g
u
s
in
g
DL
fo
r
id
en
tifyin
g
…
(
Mu
ke
s
h
K
u
ma
r
Tr
ip
a
th
i
)
1833
p
r
o
ce
s
s
in
g
,
wh
er
e
tim
e
ef
f
icien
cy
is
cr
u
cial.
Ov
er
all,
th
e
r
esu
lts
v
alid
ate
th
e
p
r
o
p
o
s
ed
m
o
d
el
’
s
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
in
ac
h
iev
in
g
f
ast
er
clu
s
ter
in
g
tim
es
with
o
u
t
co
m
p
r
o
m
is
in
g
ac
cu
r
ac
y
,
th
er
eb
y
estab
lis
h
in
g
it
as
a
m
o
r
e
ef
f
icien
t a
lter
n
ativ
e
to
tr
ad
itio
n
al
clu
s
ter
in
g
m
eth
o
d
s
.
Fig
u
r
e
3
.
C
lu
s
ter
in
g
tim
e
a
n
aly
s
is
4.
CO
NCLU
SI
O
N
T
h
is
wo
r
k
in
tr
o
d
u
ce
s
a
n
o
v
el,
lig
h
tweig
h
t
ap
p
r
o
ac
h
f
o
r
r
ea
l
-
tim
e
an
o
m
aly
d
etec
tio
n
in
lo
w
-
altitu
d
e
ae
r
ial
im
ag
es.
T
h
e
m
eth
o
d
b
eg
in
s
b
y
co
n
v
er
tin
g
in
p
u
t
f
r
am
es
to
g
r
ay
s
ca
le
an
d
d
iv
id
i
n
g
th
e
p
h
o
to
s
in
to
p
atch
es
f
o
r
d
etailed
a
n
aly
s
is
.
GL
C
Ms
ar
e
ex
tr
ac
ted
f
r
o
m
th
ese
p
atch
es,
an
d
tex
tu
r
al
s
tatis
tics
ar
e
d
er
iv
ed
t
o
r
ep
r
esen
t
th
e
p
atch
es.
An
OC
-
SVM
is
th
en
u
s
ed
to
d
etec
t
an
o
m
alies
b
ased
o
n
th
e
e
x
tr
ac
te
d
tex
tu
r
al
s
tatis
tics
.
T
h
is
ap
p
r
o
ac
h
e
n
h
an
ce
s
tr
ad
it
io
n
al
Har
alick
tex
tu
r
al
f
ea
tu
r
e
s
,
ty
p
ically
b
ased
o
n
s
in
g
le
o
f
f
s
et
d
is
p
lace
m
en
ts
.
E
x
p
er
im
en
ts
c
o
n
d
u
cted
o
n
th
e
UM
C
D
d
ataset
d
em
o
n
s
tr
ate
th
e
ef
f
ec
tiv
en
ess
o
f
th
is
ap
p
r
o
ac
h
u
n
d
er
v
a
r
io
u
s
co
n
d
itio
n
s
,
h
ig
h
lig
h
tin
g
its
n
o
v
elty
d
u
e
to
th
e
lac
k
o
f
ex
is
tin
g
m
eth
o
d
s
ad
d
r
ess
in
g
an
o
m
al
y
d
etec
tio
n
th
r
o
u
g
h
tex
tu
r
es
o
n
th
is
d
ataset.
C
o
m
p
ar
is
o
n
s
with
b
aselin
e
Har
ali
ck
tex
tu
r
al
f
ea
t
u
r
es
u
s
in
g
s
in
g
le
d
is
p
lace
m
en
ts
co
n
f
ir
m
th
e
p
r
o
p
o
s
ed
m
eth
o
d
’
s
ef
f
ec
tiv
en
ess
.
T
h
e
im
p
o
r
tan
ce
o
f
p
atch
s
ize
an
d
cir
cu
m
f
er
en
ce
r
ad
iu
s
was
also
id
en
tifie
d
,
p
r
o
v
in
g
cr
itic
al
f
o
r
ac
h
iev
in
g
s
atis
f
ac
to
r
y
p
er
f
o
r
m
an
ce
,
esp
ec
ially
in
s
e
cu
r
ity
ap
p
licatio
n
s
wh
er
e
an
o
m
aly
d
etec
tio
n
is
e
s
s
en
tial.
B
ased
o
n
th
e
r
esu
lts
o
f
all
m
etr
ics,
it
is
co
n
clu
d
e
d
th
at
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
is
h
ig
h
ly
ef
f
icien
t
co
m
p
ar
ed
to
th
e
p
r
e
v
ailin
g
m
o
d
el
s
.
Ho
wev
er
,
th
is
wo
r
k
d
o
es
n
o
t
f
o
cu
s
o
n
o
b
jects
wh
en
th
ey
ar
e
in
a
g
r
o
u
p
.
T
h
er
ef
o
r
e,
f
u
tu
r
e
wo
r
k
will
b
e
ex
ten
d
ed
with
ad
v
a
n
ce
d
tech
n
iq
u
es
to
ef
f
ec
tiv
ely
co
n
s
id
er
an
d
an
aly
ze
p
eo
p
le
w
h
en
th
ey
ar
e
in
a
g
r
o
u
p
.
RE
F
E
R
E
NC
E
S
[
1
]
F
.
Zh
u
,
X
.
Z
h
u
,
Z
.
H
u
a
n
g
,
M
.
D
i
n
g
,
Q
.
Li
,
a
n
d
X
.
Z
h
a
n
g
,
“
D
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
d
a
t
a
-
a
d
a
p
t
i
v
e
d
e
s
c
r
i
p
t
o
r
f
o
r
n
o
n
-
r
i
g
i
d
m
u
l
t
i
-
mo
d
a
l
me
d
i
c
a
l
i
ma
g
e
r
e
g
i
st
r
a
t
i
o
n
,
”
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
,
v
o
l
.
1
8
3
,
p
.
1
0
8
0
2
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
si
g
p
r
o
.
2
0
2
1
.
1
0
8
0
2
3
.
[
2
]
M
.
L.
Te
r
p
st
r
a
,
M
.
M
a
sp
e
r
o
,
A
.
S
b
r
i
z
z
i
,
a
n
d
C
.
A
.
T
.
v
a
n
d
e
n
B
e
r
g
,
“
⊥
-
l
o
ss:
a
s
y
mm
e
t
r
i
c
l
o
ss
f
u
n
c
t
i
o
n
f
o
r
m
a
g
n
e
t
i
c
r
e
s
o
n
a
n
c
e
i
ma
g
i
n
g
r
e
c
o
n
st
r
u
c
t
i
o
n
a
n
d
i
ma
g
e
r
e
g
i
s
t
r
a
t
i
o
n
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Me
d
i
c
a
l
I
m
a
g
e
A
n
a
l
y
si
s
,
v
o
l
.
8
0
,
p
.
1
0
2
5
0
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
e
d
i
a
.
2
0
2
2
.
1
0
2
5
0
9
.
[
3
]
Z.
Z
h
e
n
g
,
W
.
C
a
o
,
Z
.
H
e
,
a
n
d
Y
.
Lu
o
,
“
P
r
o
g
r
e
ss
i
v
e
a
n
a
t
o
m
i
c
a
l
l
y
c
o
n
s
t
r
a
i
n
e
d
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
3
D
d
e
f
o
r
ma
b
l
e
m
e
d
i
c
a
l
i
ma
g
e
r
e
g
i
st
r
a
t
i
o
n
,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
4
6
5
,
p
p
.
4
1
7
–
4
2
7
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
2
1
.
0
8
.
0
9
7
.
[
4
]
P
.
S
i
n
g
h
,
M
.
K
.
Tr
i
p
a
t
h
i
,
M
.
B
.
P
a
t
i
l
,
S
h
i
v
e
n
d
r
a
,
a
n
d
M
.
N
e
e
l
a
k
a
n
t
a
p
p
a
,
“
M
u
l
t
i
m
o
d
a
l
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
mo
d
e
l
v
i
a
h
y
b
r
i
d
mo
d
e
l
w
i
t
h
i
m
p
r
o
v
e
d
f
e
a
t
u
r
e
l
e
v
e
l
f
u
si
o
n
o
n
f
a
c
i
a
l
a
n
d
EEG
f
e
a
t
u
r
e
se
t
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
p
p
.
1
–
3
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
024
-
1
9
1
7
1
-
2.
[
5
]
A
.
L
a
r
a
-
H
e
r
n
a
n
d
e
z
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
i
ma
g
e
r
e
g
i
s
t
r
a
t
i
o
n
i
n
d
y
n
a
m
i
c
my
o
c
a
r
d
i
a
l
p
e
r
f
u
si
o
n
C
T
i
m
a
g
i
n
g
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
M
e
d
i
c
a
l
I
m
a
g
i
n
g
,
v
o
l
.
4
2
,
n
o
.
3
,
p
p
.
6
8
4
–
6
9
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TM
I
.
2
0
2
2
.
3
2
1
4
3
8
0
.
[
6
]
Q
.
Z
h
e
n
g
,
Q
.
W
a
n
g
,
X
.
B
a
,
S
.
Li
u
,
J
.
N
a
n
,
a
n
d
S
.
Z
h
a
n
g
,
“
A
m
e
d
i
c
a
l
i
m
a
g
e
r
e
g
i
s
t
r
a
t
i
o
n
me
t
h
o
d
b
a
s
e
d
o
n
p
r
o
g
r
e
ssi
v
e
i
ma
g
e
s,”
C
o
m
p
u
t
a
t
i
o
n
a
l
a
n
d
M
a
t
h
e
m
a
t
i
c
a
l
Me
t
h
o
d
s i
n
Me
d
i
c
i
n
e
,
v
o
l
.
2
0
2
1
,
p
p
.
1
–
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
4
5
0
4
3
0
6
.
[
7
]
G
.
A
.
B
e
n
v
e
n
u
t
o
,
M
.
C
o
l
n
a
g
o
,
M
.
A
.
D
i
a
s
,
R
.
G
.
N
e
g
r
i
,
E
.
A
.
S
i
l
v
a
,
a
n
d
W
.
C
a
sa
c
a
,
“
A
f
u
l
l
y
u
n
su
p
e
r
v
i
s
e
d
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
f
o
r
n
o
n
-
r
i
g
i
d
f
u
n
d
u
s
i
m
a
g
e
r
e
g
i
s
t
r
a
t
i
o
n
,
”
Bi
o
e
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
9
,
n
o
.
8
,
p
.
3
6
9
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
b
i
o
e
n
g
i
n
e
e
r
i
n
g
9
0
8
0
3
6
9
.
[
8
]
H
.
S
i
e
b
e
r
t
,
L
.
H
a
n
se
n
,
a
n
d
M
.
P
.
H
e
i
n
r
i
c
h
,
“
Le
a
r
n
i
n
g
a
me
t
r
i
c
f
o
r
mu
l
t
i
mo
d
a
l
me
d
i
c
a
l
i
ma
g
e
r
e
g
i
st
r
a
t
i
o
n
w
i
t
h
o
u
t
s
u
p
e
r
v
i
si
o
n
b
a
s
e
d
o
n
c
y
c
l
e
c
o
n
st
r
a
i
n
t
s,
”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
3
,
p
.
1
1
0
7
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
2
0
3
1
1
0
7
.
[
9
]
Y
.
F
u
,
Y
.
L
e
i
,
T
.
W
a
n
g
,
W
.
J
.
C
u
r
r
a
n
,
T.
Li
u
,
a
n
d
X
.
Y
a
n
g
,
“
D
e
e
p
l
e
a
r
n
i
n
g
i
n
me
d
i
c
a
l
i
ma
g
e
r
e
g
i
s
t
r
a
t
i
o
n
:
a
r
e
v
i
e
w
,
”
Ph
y
s
i
c
s
i
n
Me
d
i
c
i
n
e
a
n
d
B
i
o
l
o
g
y
,
v
o
l
.
6
5
,
n
o
.
2
0
,
p
.
2
0
T
R
0
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
8
/
1
3
6
1
-
6
5
6
0
/
a
b
8
4
3
e
.
[
1
0
]
M
.
K
.
Tr
i
p
a
t
h
i
,
M
.
N
e
e
l
a
k
a
n
t
a
p
p
a
,
P
.
N
.
M
a
h
a
l
l
e
,
S
.
V
.
C
h
a
n
n
a
p
a
t
t
a
n
a
,
G
.
D
e
s
h
m
u
k
h
,
a
n
d
G
.
P
r
a
sh
a
n
t
,
“
D
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
m
a
n
g
o
f
r
u
i
t
-
b
a
se
d
o
n
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
p
p
l
y
i
n
g
o
p
t
i
m
i
z
e
d
h
y
b
r
i
d
LA
-
FF
a
l
g
o
r
i
t
h
ms,
”
i
n
D
a
t
a
-
C
e
n
t
r
i
c
A
rt
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
f
o
r
Mu
l
t
i
d
i
sc
i
p
l
i
n
a
ry
Ap
p
l
i
c
a
t
i
o
n
s
,
B
o
c
a
R
a
t
o
n
:
C
h
a
p
m
a
n
a
n
d
H
a
l
l
/
C
R
C
,
2
0
2
4
,
p
p
.
1
7
7
–
1
8
5
.
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
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
8
27
-
1
8
35
1834
[
1
1
]
M
.
K
.
Tr
i
p
a
t
h
i
,
P
.
K
.
R
e
d
d
y
,
M
.
N
e
e
l
a
k
a
n
t
a
p
p
a
,
C
.
V
.
A
n
d
h
a
r
e
,
a
n
d
S
h
i
v
e
n
d
r
a
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
ma
n
g
o
v
a
r
i
e
t
y
u
si
n
g
n
e
a
r
i
n
f
r
a
r
e
d
s
p
e
c
t
r
o
s
c
o
p
y
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
1
,
n
o
.
3
,
p
p
.
1
7
7
6
–
1
7
8
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
3
1
.
i
3
.
p
p
1
7
7
6
-
1
7
8
3
.
[
1
2
]
C
.
P
a
p
a
d
a
k
i
s,
Y
.
Y
i
n
,
M
.
D
a
n
i
k
a
s,
a
n
d
C
.
C
h
a
r
a
l
a
m
b
o
u
s
,
“
S
u
r
f
a
c
e
d
i
s
c
h
a
r
g
e
s
a
n
d
f
l
a
s
h
o
v
e
r
v
o
l
t
a
g
e
s
i
n
n
a
n
o
c
o
m
p
o
si
t
e
X
LPE
s
a
mp
l
e
s
,
”
En
g
i
n
e
e
ri
n
g
,
T
e
c
h
n
o
l
o
g
y
&
Ap
p
l
i
e
d
S
c
i
e
n
c
e
R
e
se
a
rc
h
,
v
o
l
.
8
,
n
o
.
6
,
p
p
.
3
5
0
2
–
3
5
0
4
,
2
0
1
8
,
d
o
i
:
1
0
.
4
8
0
8
4
/
e
t
a
sr
.
2
1
8
6
.
[
1
3
]
G
.
Li
t
j
e
n
s
e
t
a
l
.
,
“
A
s
u
r
v
e
y
o
n
d
e
e
p
l
e
a
r
n
i
n
g
i
n
m
e
d
i
c
a
l
i
ma
g
e
a
n
a
l
y
si
s
,
”
Me
d
i
c
a
l
I
m
a
g
e
A
n
a
l
y
s
i
s
,
v
o
l
.
4
2
,
p
p
.
6
0
–
8
8
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
e
d
i
a
.
2
0
1
7
.
0
7
.
0
0
5
.
[
1
4
]
H
.
R
.
B
o
v
e
i
r
i
,
R
.
K
h
a
y
a
m
i
,
R
.
Ja
v
i
d
a
n
,
a
n
d
A
.
M
e
h
d
i
z
a
d
e
h
,
“
M
e
d
i
c
a
l
i
m
a
g
e
r
e
g
i
st
r
a
t
i
o
n
u
si
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
:
a
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
8
7
,
p
.
1
0
6
7
6
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
e
l
e
c
e
n
g
.
2
0
2
0
.
1
0
6
7
6
7
.
[
1
5
]
X
.
Y
a
n
g
,
R
.
K
w
i
t
t
,
M
.
S
t
y
n
e
r
,
a
n
d
M
.
N
i
e
t
h
a
mm
e
r
,
“
Q
u
i
c
k
si
l
v
e
r
:
f
a
st
p
r
e
d
i
c
t
i
v
e
i
ma
g
e
r
e
g
i
s
t
r
a
t
i
o
n
–
a
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
N
e
u
ro
I
m
a
g
e
,
v
o
l
.
1
5
8
,
p
p
.
3
7
8
–
3
9
6
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
r
o
i
ma
g
e
.
2
0
1
7
.
0
7
.
0
0
8
.
[
1
6
]
F
.
Zh
u
,
M
.
D
i
n
g
,
a
n
d
X
.
Z
h
a
n
g
,
“
S
e
l
f
-
si
m
i
l
a
r
i
t
y
i
n
sp
i
r
e
d
l
o
c
a
l
d
e
s
c
r
i
p
t
o
r
f
o
r
n
o
n
-
r
i
g
i
d
mu
l
t
i
-
mo
d
a
l
i
m
a
g
e
r
e
g
i
st
r
a
t
i
o
n
,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
7
2
,
p
p
.
1
6
–
3
1
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s
.
2
0
1
6
.
0
8
.
0
3
1
.
[
1
7
]
M
.
K
.
Tr
i
p
a
t
h
i
a
n
d
S
h
i
v
e
n
d
r
a
,
“
N
e
u
t
r
o
s
o
p
h
i
c
a
p
p
r
o
a
c
h
b
a
s
e
d
i
n
t
e
l
l
i
g
e
n
t
s
y
st
e
m
f
o
r
a
u
t
o
ma
t
i
c
m
a
n
g
o
d
e
t
e
c
t
i
o
n
,
”
Mu
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
3
,
n
o
.
1
4
,
p
p
.
4
1
7
6
1
–
4
1
7
8
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
2
3
-
1
7
0
3
7
-
7.
[
1
8
]
B
.
D
.
d
e
V
o
s,
F
.
F
.
B
e
r
e
n
d
s
e
n
,
M
.
A
.
V
i
e
r
g
e
v
e
r
,
H
.
S
o
k
o
o
t
i
,
M
.
S
t
a
r
i
n
g
,
a
n
d
I
.
I
šg
u
m
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
f
o
r
u
n
s
u
p
e
r
v
i
s
e
d
a
f
f
i
n
e
a
n
d
d
e
f
o
r
ma
b
l
e
i
ma
g
e
r
e
g
i
st
r
a
t
i
o
n
,
”
Me
d
i
c
a
l
I
m
a
g
e
A
n
a
l
y
si
s
,
v
o
l
.
5
2
,
p
p
.
1
2
8
–
1
4
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
e
d
i
a
.
2
0
1
8
.
1
1
.
0
1
0
.
[
1
9
]
S
.
D
a
sari
r
a
j
u
,
M
.
H
u
o
,
a
n
d
S
.
M
c
C
a
l
l
a
,
“
D
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
i
mm
a
t
u
r
e
l
e
u
k
o
c
y
t
e
s
f
o
r
d
i
a
g
n
o
s
i
s
o
f
a
c
u
t
e
m
y
e
l
o
i
d
l
e
u
k
e
mi
a
u
si
n
g
r
a
n
d
o
m
f
o
r
e
st
a
l
g
o
r
i
t
h
m
,
”
Bi
o
e
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
7
,
n
o
.
4
,
p
p
.
1
–
1
2
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
b
i
o
e
n
g
i
n
e
e
r
i
n
g
7
0
4
0
1
2
0
.
[
2
0
]
V
.
La
v
a
n
y
a
P
,
M
.
K
.
Tr
i
p
a
t
h
i
,
E
.
P
.
H
e
man
d
,
S
.
K
,
a
n
d
J
.
V
.
N
.
R
a
mes
h
,
“
H
y
p
e
r
s
p
e
c
t
r
a
l
c
r
o
p
i
m
a
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
v
i
a
e
n
s
e
mb
l
e
o
f
c
l
a
ss
i
f
i
c
a
t
i
o
n
mo
d
e
l
w
i
t
h
o
p
t
i
m
a
l
t
r
a
i
n
i
n
g
,
”
We
b
I
n
t
e
l
l
i
g
e
n
c
e
,
p
p
.
1
–
3
1
,
2
0
2
4
,
d
o
i
:
1
0
.
3
2
3
3
/
w
e
b
-
2
3
0
2
0
9
.
[
2
1
]
A
.
T.
S
a
l
a
w
u
d
e
e
n
,
M
u
’
a
z
u
,
M
.
B
.
,
Y
.
A
.
S
h
a
’
a
b
a
n
,
a
n
d
E.
A
.
A
d
e
d
o
k
u
n
,
“
O
n
t
h
e
d
e
v
e
l
o
p
me
n
t
o
f
a
n
o
v
e
l
sme
l
l
a
g
e
n
t
o
p
t
i
mi
z
a
t
i
o
n
(
S
A
O
)
f
o
r
o
p
t
i
mi
z
a
t
i
o
n
p
r
o
b
l
e
ms
,
”
2
0
1
8
.
[
2
2
]
G
.
D
h
i
ma
n
,
M
.
G
a
r
g
,
A
.
N
a
g
a
r
,
V
.
K
u
mar,
a
n
d
M
.
D
e
h
g
h
a
n
i
,
“
A
n
o
v
e
l
a
l
g
o
r
i
t
h
m
f
o
r
g
l
o
b
a
l
o
p
t
i
mi
z
a
t
i
o
n
:
r
a
t
s
w
a
r
m
o
p
t
i
m
i
z
e
r
,
”
J
o
u
rn
a
l
o
f
Am
b
i
e
n
t
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
H
u
m
a
n
i
ze
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
2
,
n
o
.
8
,
p
p
.
8
4
5
7
–
8
4
8
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
6
5
2
-
020
-
0
2
5
8
0
-
0.
[
2
3
]
M
.
K
.
Tr
i
p
a
t
h
i
a
n
d
S
h
i
v
e
n
d
r
a
,
“
I
mp
r
o
v
e
d
d
e
e
p
b
e
l
i
e
f
n
e
t
w
o
r
k
f
o
r
e
s
t
i
m
a
t
i
n
g
m
a
n
g
o
q
u
a
l
i
t
y
i
n
d
i
c
e
s
a
n
d
g
r
a
d
i
n
g
:
a
c
o
mp
u
t
e
r
v
i
s
i
o
n
-
b
a
se
d
n
e
u
t
r
o
s
o
p
h
i
c
a
p
p
r
o
a
c
h
,
”
N
e
t
w
o
rk:
C
o
m
p
u
t
a
t
i
o
n
i
n
N
e
u
r
a
l
S
y
st
e
m
s
,
v
o
l
.
3
5
,
n
o
.
3
,
p
p
.
2
4
9
–
2
7
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
0
/
0
9
5
4
8
9
8
X
.
2
0
2
3
.
2
2
9
9
8
5
1
.
[
2
4
]
J.
G
u
e
t
a
l
.
,
“
R
e
c
e
n
t
a
d
v
a
n
c
e
s
i
n
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,”
Pa
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
7
7
,
p
p
.
3
5
4
–
3
7
7
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
1
7
.
1
0
.
0
1
3
.
[
2
5
]
S
.
A
l
b
a
w
i
,
O
.
B
a
y
a
t
,
S
.
A
l
-
A
z
a
w
i
,
a
n
d
O
.
N
.
U
c
a
n
,
“
S
o
c
i
a
l
t
o
u
c
h
g
e
st
u
r
e
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
N
e
u
r
o
sc
i
e
n
c
e
,
v
o
l
.
2
0
1
8
,
p
p
.
1
–
1
0
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
8
/
6
9
7
3
1
0
3
.
[
2
6
]
F
.
Z
ö
l
l
n
e
r
,
“
M
u
l
t
i
m
o
d
a
l
g
r
o
u
n
d
t
r
u
t
h
d
a
t
a
se
t
s
f
o
r
a
b
d
o
mi
n
a
l
m
e
d
i
c
a
l
i
ma
g
e
r
e
g
i
s
t
r
a
t
i
o
n
i
s
t
a
k
e
n
f
r
o
m
,
”
h
e
i
D
ATA
,
2
0
2
2
.
h
t
t
p
s
:
/
/
h
e
i
d
a
t
a
.
u
n
i
-
h
e
i
d
e
l
b
e
r
g
.
d
e
/
d
a
t
a
s
e
t
.
x
h
t
m
l
?
p
e
r
si
s
t
e
n
t
I
d
=
d
o
i
:
1
0
.
1
1
5
8
8
/
d
a
t
a
/
I
C
S
F
U
S
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Dr
.
Mu
k
e
sh
K
u
m
a
r
Tr
ip
a
th
i
re
c
e
iv
e
d
a
P
h
.
D.
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
fr
o
m
VTU,
Be
lag
a
v
i.
He
h
a
s
1
5
y
e
a
rs
o
f
tea
c
h
in
g
a
n
d
a
d
m
in
istrati
v
e
e
x
p
e
rien
c
e
.
He
h
a
s
su
p
e
rv
ise
d
a
n
d
c
o
-
s
u
p
e
rv
ise
d
m
o
re
t
h
a
n
fi
v
e
m
a
ste
rs
a
n
d
2
0
B.
E
.
stu
d
e
n
ts.
He
is
w
o
rk
i
n
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
wi
th
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
Va
r
d
h
a
m
a
n
C
o
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
,
Hy
d
e
ra
b
a
d
,
In
d
ia.
He
is
a
u
t
h
o
re
d
o
r
co
-
a
u
th
o
re
d
m
o
re
t
h
a
n
twe
n
ty
p
u
b
li
c
a
ti
o
n
s
a
n
d
m
o
re
th
a
n
3
0
0
c
it
a
ti
o
n
s.
His
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
s
o
ft
c
o
m
p
u
t
in
g
,
m
a
c
h
in
e
lea
rn
i
n
g
,
i
n
telli
g
e
n
t
sy
ste
m
s,
ima
g
e
p
ro
c
e
ss
in
g
,
a
n
d
h
y
p
e
rsp
e
c
tral.
He
c
a
n
b
e
c
o
n
t
a
c
ted
a
t
e
m
a
il
:
m
u
k
e
sh
tri
p
a
t
h
i0
1
6
@g
m
a
il
.
c
o
m
.
Dr
.
Chella
p
il
l
a
V.
K
.
N.
S
.
N.
Mo
o
r
th
y
is
wo
rk
i
n
g
a
s
Dire
c
to
r
RD,
Va
sa
v
i
Co
ll
e
g
e
o
f
E
n
g
in
e
e
rin
g
,
H
y
d
e
ra
b
a
d
,
Tela
n
g
a
n
a
,
In
d
ia.
He
re
c
e
iv
e
d
M
a
ste
r
o
f
Tec
h
n
o
l
o
g
y
b
o
t
h
in
th
e
fiel
d
s
o
f
C
o
m
p
u
ter
S
c
ien
c
e
En
g
in
e
e
ri
n
g
a
n
d
He
a
t
P
o
we
r
Re
frig
e
ra
ti
o
n
a
n
d
Ai
r
Co
n
d
it
io
n
i
n
g
.
He
re
c
e
iv
e
d
d
o
c
to
ra
l
d
e
g
re
e
fo
r
re
se
a
rc
h
fro
m
G
ITAM
Un
iv
e
rsity
,
a
n
d
p
u
rsu
i
n
g
h
is d
o
c
t
o
ra
l
d
e
g
re
e
in
t
h
e
field
o
f
m
a
c
h
in
e
lea
rn
in
g
t
o
o
.
H
e
h
a
s
re
se
a
rc
h
e
x
p
e
rien
c
e
with
a
t
o
tal
re
se
a
rc
h
g
ra
n
t
o
f
4
2
4
.
4
6
K
USD
fro
m
DS
T,
g
o
v
e
rn
m
e
n
t
o
f
In
d
ia,
m
o
re
t
h
a
n
5
0
re
se
a
rc
h
p
u
b
li
c
a
ti
o
n
s,
in
tern
a
ti
o
n
a
l
re
se
a
r
c
h
c
o
ll
a
b
o
ra
ti
o
n
s,
a
wa
rd
s
a
n
d
p
a
ten
ts
to
h
is
c
re
d
it
.
His
th
ru
st
a
re
a
s
o
f
re
se
a
rc
h
in
c
l
u
d
e
c
o
g
n
it
i
v
e
sc
ien
c
e
,
AI
a
n
d
ML
,
a
n
d
c
o
m
p
u
tatio
n
a
l
fl
u
id
d
y
n
a
m
ics
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
rish
n
a
.
t
u
rb
o
@g
m
a
il
.
c
o
m
.
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
Hig
h
-
r
eso
lu
tio
n
a
eria
l m
o
n
ito
r
in
g
u
s
in
g
DL
fo
r
id
en
tifyin
g
…
(
Mu
ke
s
h
K
u
ma
r
Tr
ip
a
th
i
)
1835
Dr
.
S
a
n
d
e
e
p
K
a
d
a
m
w
o
r
k
in
g
a
s
p
ri
n
c
ip
a
l
o
f
Ke
y
st
o
n
e
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
rin
g
,
P
u
n
e
,
In
d
ia.
He
is
h
a
v
in
g
2
0
+
y
e
a
rs
in
a
c
a
d
e
m
ics
a
n
d
in
d
u
str
y
.
His
re
se
a
rc
h
a
re
a
is
c
y
b
e
r
se
c
u
ri
t
y
a
n
d
so
ftwa
re
e
n
g
i
n
e
e
rin
g
,
i
n
c
lu
d
e
so
ft
c
o
m
p
u
ti
n
g
,
m
a
c
h
in
e
lea
rn
in
g
,
in
tell
ig
e
n
t
sy
ste
m
s,
ima
g
e
p
r
o
c
e
ss
in
g
,
a
n
d
h
y
p
e
r
sp
e
c
tral.
He
is
P
h
.
D
.
re
se
a
rc
h
Co
-
S
u
p
e
rv
iso
r
i
n
Co
m
p
u
ter
E
n
g
in
e
e
rin
g
.
He
is
a
u
th
o
re
d
o
r
c
o
-
a
u
t
h
o
re
d
m
o
re
th
a
n
twe
n
ty
-
fi
v
e
p
u
b
li
c
a
ti
o
n
s
a
n
d
m
o
re
t
h
a
n
1
0
0
c
it
a
ti
o
n
s.
His
re
se
a
rc
h
in
tere
sts.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
n
d
ip
k
a
d
a
m
@g
m
a
il
.
c
o
m
.
Pro
f
.
Cha
ita
li
S
h
e
wa
le
is
wo
rk
i
n
g
a
s
As
sista
n
t
P
ro
fe
ss
o
r
in
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
De
p
a
rtme
n
t
a
t
Vish
wa
k
a
rm
a
In
stit
u
te
o
f
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
,
P
u
n
e
,
I
n
d
ia.
S
h
e
h
a
s
c
o
m
p
lete
d
h
e
r
M
a
ste
rs
i
n
C
o
m
p
u
ter
E
n
g
i
n
e
e
rin
g
a
n
d
p
u
r
su
in
g
P
h
.
D
.
i
n
C
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
.
He
r
re
se
a
rc
h
a
re
a
in
m
a
c
h
in
e
lea
rn
in
g
,
d
a
ta
sc
ien
c
e
,
c
y
b
e
r
se
c
u
rit
y
a
n
d
b
lo
c
k
c
h
a
i
n
.
S
h
e
h
a
s
p
u
b
li
s
h
e
d
m
o
re
3
0
re
se
a
rc
h
a
rti
c
les
in
v
a
ri
o
u
s
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls
o
f
re
p
u
t
e
.
S
h
e
is
h
a
v
in
g
m
o
re
th
a
n
1
2
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
in
th
e
field
o
f
in
f
o
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
c
h
a
it
a
li
.
sh
e
wa
le@
v
ii
t.
a
c
.
in
.
Dr
.
Priy
a
S
h
e
lk
e
h
o
ld
s a
Do
c
t
o
r
o
f
P
h
il
o
s
o
p
h
y
d
e
g
re
e
in
Co
m
p
u
ter en
g
i
n
e
e
rin
g
fro
m
S
a
v
it
rib
a
i
P
h
u
le
P
u
n
e
U
n
iv
e
rsity
,
P
u
n
e
,
I
n
d
ia.
S
h
e
h
a
s
re
c
e
iv
e
d
h
e
r
m
a
ste
r’s
(M
.
Tec
h
.
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
)
d
e
g
re
e
f
ro
m
Vis
v
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
Un
i
v
e
rsity
,
Be
lg
a
v
i
in
2
0
0
9
.
S
h
e
is
wo
r
k
in
g
a
s
a
n
As
so
c
iate
P
ro
fe
ss
o
r
i
n
In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
De
p
a
rtme
n
t
o
f
Vish
wa
k
a
rm
a
In
st
it
u
te
o
f
In
f
o
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
,
Ko
n
d
h
wa
(b
k
)
,
P
u
n
e
.
S
h
e
is
h
a
v
i
n
g
2
0
y
e
a
rs
o
f
w
o
rk
i
n
g
e
x
p
e
rien
c
e
.
He
r
a
re
a
o
f
in
tere
st
is
ima
g
e
p
r
o
c
e
ss
in
g
a
n
d
b
lo
c
k
c
h
a
in
tec
h
n
o
lo
g
y
.
S
h
e
h
a
s
p
u
b
li
s
h
e
d
o
v
e
r
4
0
p
a
p
e
rs
in
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
j
o
u
r
n
a
ls.
S
h
e
is
a
li
fe
ti
m
e
m
e
m
b
e
r
o
f
IS
TE
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
riy
a
.
sh
e
l
k
e
@v
ii
t
.
a
c
.
in
.
Dr
.
Pra
v
in
R
.
Fu
t
a
n
e
is
c
u
rre
n
tl
y
a
ss
o
c
iate
d
wit
h
Vish
wa
k
a
rm
a
In
stit
u
te
o
f
In
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
(VIIT)
,
P
u
n
e
a
s
a
P
ro
fe
ss
o
r
in
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
a
n
d
He
a
d
,
IT
De
p
a
rtme
n
t
fro
m
las
t
t
h
re
e
y
e
a
rs.
Earlier
h
a
v
e
w
o
rk
e
d
a
s
a
P
ro
fe
ss
o
r
in
C
o
m
p
u
ter
En
g
i
n
e
e
rin
g
a
t
P
CCo
E
f
o
r
3
.
2
y
e
a
rs
a
n
d
He
a
d
o
f
IT
d
e
p
a
rtme
n
t
f
o
r
a
lmo
st
2
y
e
a
rs
a
n
d
wa
s
a
ss
o
c
iate
d
a
s
P
ro
fe
ss
o
r
a
n
d
He
a
d
o
f
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
En
g
in
e
e
rin
g
,
S
in
h
g
a
d
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
P
u
n
e
.
He
is
h
a
v
i
n
g
t
o
tal
2
4
+
y
e
a
rs
o
f
e
x
p
e
rien
c
e
with
2
3
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
i
n
c
lu
d
in
g
1
5
y
e
a
rs
o
f
a
d
m
i
n
istrativ
e
e
x
p
e
rien
c
e
a
n
d
1
0
y
e
a
rs
o
f
r
e
se
a
rc
h
e
x
p
e
rien
c
e
p
a
ra
ll
e
ll
y
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
ra
v
in
.
fu
ta
n
e
@v
ii
t.
a
c
.
i
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.