T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n Co
m
pu
t
i
ng
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
2
2
,
No
.
6
,
Dec
em
b
er
2
0
2
4
,
p
p
.
1
5
1
1
~1
516
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
2
2
i6
.
2
5
8
7
0
1511
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//telko
mn
ika
.
u
a
d
.
a
c.
i
d
Reducing
feature
di
m
e
nsi
o
na
lity fo
r cloud
i
m
a
g
e cla
ss
ificatio
n
using
lo
ca
l bina
ry
patter
ns
descri
pt
o
r
T
ho
ng
cha
i
S
urinw
a
ra
ng
k
o
o
n
1
,
Vinh
T
r
uo
ng
H
o
a
ng
2
,
K
it
t
ikh
un
M
ee
t
ho
ng
j
a
n
3
1
D
e
p
a
r
t
me
n
t
o
f
B
u
si
n
e
ss C
o
m
p
u
t
e
r
,
C
o
l
l
e
g
e
o
f
I
n
n
o
v
a
t
i
o
n
a
n
d
M
a
n
a
g
e
me
n
t
,
S
u
a
n
S
u
n
a
n
d
h
a
R
a
j
a
b
h
a
t
U
n
i
v
e
r
si
t
y
,
B
a
n
g
k
o
k
,
T
h
a
i
l
a
n
d
2
D
e
p
a
r
t
me
n
t
o
f
D
a
t
a
S
c
i
e
n
c
e
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
,
H
o
C
h
i
M
i
n
h
C
i
t
y
O
p
e
n
U
n
i
v
e
r
si
t
y
,
H
o
C
h
i
M
i
n
h
,
V
i
e
t
n
a
m
3
D
e
p
a
r
t
me
n
t
o
f
A
p
p
l
y
S
c
i
e
n
c
e
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
S
u
a
n
S
u
n
a
n
d
h
a
R
a
j
a
b
h
a
t
U
n
i
v
e
r
si
t
y
,
B
a
n
g
k
o
k
,
T
h
a
i
l
a
n
d
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
1
8
,
2023
R
ev
i
s
ed
Sep
1
,
2
0
2
4
A
cc
ep
ted
Sep
6
,
2
0
2
4
Clo
u
d
s
p
lay
a
c
ru
c
ial
ro
le
i
n
p
re
c
ip
it
a
ti
o
n
a
n
d
w
e
a
th
e
r
p
re
d
ictio
n
.
Id
e
n
ti
f
y
in
g
a
n
d
d
iff
e
re
n
ti
a
ti
n
g
c
lo
u
d
s
a
c
c
u
ra
tel
y
p
o
se
s
a
sig
n
if
ica
n
t
c
h
a
ll
e
n
g
e
.
In
t
h
is
p
a
p
e
r,
w
e
p
re
s
e
n
t
a
n
o
v
e
l
a
p
p
ro
a
c
h
th
a
t
u
ti
li
z
e
s
th
e
lo
c
a
l
b
in
a
ry
p
a
tt
e
rn
s
(L
B
P
)
f
e
a
tu
re
d
e
sc
rip
to
r
to
e
x
trac
t
c
o
lo
r
c
lo
u
d
i
m
a
g
e
s.
W
e
e
m
p
lo
y
fe
a
tu
re
f
u
sio
n
to
c
o
m
b
in
e
L
B
P
f
e
a
tu
re
s
f
ro
m
th
e
in
d
e
p
e
n
d
e
n
t
c
h
a
n
n
e
ls
o
f
th
e
RG
B
c
o
l
o
r
sp
a
c
e
.
F
u
r
th
e
rm
o
re
,
w
e
a
p
p
ly
f
i
v
e
we
ll
-
k
n
o
w
n
f
e
a
tu
re
se
lec
ti
o
n
m
e
th
o
d
s,
n
a
m
e
ly
Re
li
e
f
F
,
Ilfs,
c
o
rre
latio
n
-
b
a
se
d
f
e
a
tu
re
se
lec
ti
o
n
(CF
S
)
,
F
is
h
e
r,
a
n
d
L
a
ss
o
,
to
se
lec
t
re
lev
a
n
t
a
n
d
u
se
f
u
l
f
e
a
tu
re
s.
T
h
e
se
se
lec
t
e
d
f
e
a
tu
re
s
a
re
th
e
n
f
e
d
in
to
a
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM)
c
las
si
f
ier.
Ex
p
e
rime
n
tal
re
su
lt
s
d
e
m
o
n
stra
te
th
a
t
o
u
r
p
ro
p
o
se
d
a
p
p
r
o
a
c
h
a
c
h
iev
e
s
su
p
e
rio
r
p
e
rf
o
rm
a
n
c
e
b
y
si
g
n
if
ic
a
n
tl
y
re
d
u
c
in
g
th
e
n
u
m
b
e
r
o
f
f
e
a
tu
re
s w
h
il
e
m
a
in
tain
in
g
p
re
d
ic
ti
o
n
a
c
c
u
ra
c
y
.
K
ey
w
o
r
d
s
:
C
lo
u
d
i
m
ag
e
s
Featu
r
e
r
an
k
i
n
g
Featu
r
e
s
elec
t
io
n
L
o
ca
l b
in
ar
y
p
atter
n
s
Su
p
p
o
r
t v
ec
to
r
m
ac
h
i
n
e
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
:
Kittik
h
u
n
Me
e
th
o
n
g
j
an
Dep
ar
t
m
en
t o
f
A
p
p
l
y
Scie
n
ce
,
Facu
lt
y
o
f
Scie
n
ce
a
n
d
T
ec
h
n
o
lo
g
y
,
S
u
an
S
u
n
an
d
h
a
R
aj
ab
h
at
Un
i
v
er
s
it
y
1
U
T
h
o
n
g
No
k
R
d
,
Du
s
it,
Du
s
it Dis
tr
ict,
B
an
g
k
o
k
1
0
3
0
0
,
T
h
aila
n
d
E
m
ail:
k
itti
k
h
u
n
.
m
e@
s
s
r
u
.
ac
.
th
1.
I
NT
RO
D
UCT
I
O
N
C
lo
u
d
s
h
a
v
e
a
d
ir
ec
t
i
m
p
ac
t
o
n
t
h
e
w
ea
t
h
er
an
y
w
h
er
e
i
n
t
h
e
w
o
r
ld
.
C
lo
u
d
s
ar
e
t
h
e
r
o
o
t
ca
u
s
e
o
f
all
r
ain
.
B
y
o
b
s
er
v
i
n
g
a
n
d
d
if
f
er
e
n
tiati
n
g
th
e
c
lo
u
d
s
,
w
e
ca
n
p
r
ed
ict
w
ea
t
h
er
u
s
i
n
g
a
w
o
r
ld
w
i
d
e
n
o
r
m
an
d
it
i
s
a
ch
alle
n
g
i
n
g
tas
k
.
No
w
ad
a
y
s
,
w
ea
t
h
er
f
o
r
ec
asti
n
g
h
as
ev
o
l
v
ed
w
ith
s
i
g
n
i
f
ica
n
t
tech
n
o
lo
g
i
ca
l
ad
v
an
ce
m
e
n
t
s
,
in
cl
u
d
in
g
av
iatio
n
,
ag
r
icu
l
tu
r
e
,
r
em
o
te
s
en
s
i
n
g
,
co
m
p
u
ter
v
i
s
io
n
[
1
]
.
T
h
e
n
u
m
b
er
o
f
p
h
o
to
g
r
ap
h
s
o
f
th
e
s
k
y
an
d
clo
u
d
s
tak
e
n
f
r
o
m
t
h
e
g
r
o
u
n
d
is
r
is
i
n
g
as
a
r
esu
lt
of
th
e
ab
s
en
ce
of
r
ad
io
w
a
v
es
a
n
d
s
atellite
o
b
s
er
v
atio
n
s
in
s
p
ac
e.
T
h
is
p
r
o
ce
d
u
r
e
h
as
p
r
o
d
u
ce
d
a
lar
g
e
a
m
o
u
n
t
o
f
clo
u
d
/
s
k
y
i
m
a
g
e
d
ata
o
v
er
a
lo
n
g
p
er
io
d
o
f
ti
m
e.
C
a
m
er
as
h
a
v
e
o
p
en
ed
u
p
n
e
w
o
p
p
o
r
tu
n
itie
s
f
o
r
m
o
n
ito
r
in
g
t
h
e
E
ar
th
’
s
at
m
o
s
p
h
er
e.
T
h
is
ad
d
s
v
alu
e
to
s
atelli
te
i
m
a
g
in
g
by
g
i
v
in
g
g
eo
lo
g
i
s
ts
ac
ce
s
s
to
les
s
e
x
p
en
s
iv
e,
q
u
ick
er
,
a
n
d
m
o
r
e
p
r
ec
is
e
d
ata.
T
h
e
s
u
cc
ess
f
u
l
r
ec
o
g
n
itio
n
o
f
clo
u
d
p
atter
n
s
in
s
k
y
/clo
u
d
p
h
o
to
g
r
ap
h
s
i
s
t
h
e
m
o
s
t
b
as
ic
is
s
u
e
w
it
h
clo
u
d
p
h
o
to
g
r
ap
h
y
.
B
ec
au
s
e
clo
u
d
s
lac
k
a
n
y
p
ar
ticu
lar
s
tr
u
ctu
r
e,
b
o
u
n
d
ar
ies,
s
h
ap
e,
o
r
s
ize,
it
is
a
d
if
f
ic
u
lt
p
r
o
b
lem
to
s
o
lv
e
[
2
]
.
C
lo
u
d
p
h
o
to
g
r
ap
h
y
,
a
s
a
n
a
tu
r
all
y
s
tr
i
ated
s
tr
u
ct
u
r
e,
o
f
ten
d
i
s
p
la
y
s
s
ig
n
i
f
ica
n
t
i
n
tr
in
s
ic
v
ar
ian
ce
s
d
u
e
to
v
ar
iatio
n
s
i
n
i
llu
m
i
n
atio
n
,
e
n
v
ir
o
n
m
e
n
t,
a
n
d
d
is
to
r
tio
n
.
I
n
r
ec
en
t
y
ea
r
s
,
n
u
m
er
o
u
s
ap
p
r
o
ac
h
es
h
av
e
b
e
en
p
r
o
p
o
s
ed
to
ef
f
ec
ti
v
el
y
e
x
tr
ac
t
d
is
cr
i
m
i
n
ati
v
e
in
f
o
r
m
atio
n
f
r
o
m
clo
u
d
i
m
a
g
es
.
T
h
ese
tech
n
iq
u
es
ai
m
to
en
h
an
ce
o
u
r
u
n
d
er
s
tan
d
in
g
o
f
clo
u
d
f
o
r
m
atio
n
s
,
i
m
p
r
o
v
e
w
ea
t
h
er
f
o
r
ec
asti
n
g
,
an
d
aid
in
v
ar
io
u
s
o
th
er
ap
p
licatio
n
s
[
3
]
,
[
4
]
.
Sev
er
al
s
t
u
d
ies
h
a
v
e
b
ee
n
d
ev
elo
p
ed
to
r
ec
o
g
n
ize
an
d
cla
s
s
i
f
ied
clo
u
d
i
m
a
g
es
ac
co
r
d
in
g
to
th
eir
b
u
l
k
,
f
o
r
m
,
t
h
ic
k
n
ess
,
h
ei
g
h
t,
an
d
c
o
v
er
ag
e.
Am
o
n
g
th
e
m
,
t
h
e
cla
s
s
i
f
icatio
n
o
f
t
h
e
s
k
y
an
d
clo
u
d
s
h
as
m
ad
e
h
ea
v
y
u
s
e
o
f
co
lo
r
.
T
o
ad
d
r
ess
th
i
s
is
s
u
e,
n
u
m
er
o
u
s
m
et
h
o
d
s
b
ased
o
n
v
ar
io
u
s
co
lo
r
p
att
er
n
s
a
n
d
s
p
ec
tr
u
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
22
,
No
.
6
,
Dec
em
b
er
20
24
:
1
5
1
1
-
1
516
1512
−
w
a
v
ele
n
g
t
h
s
h
av
e
b
ee
n
d
ev
elo
p
ed
[
5
]
.
B
ec
au
s
e
of
th
e
w
id
e
d
if
f
er
en
ce
s
in
ill
u
m
i
n
a
tio
n
,
cli
m
ate,
an
d
d
is
to
r
tio
n
,
clo
u
d
i
m
ag
in
g
is
a
t
y
p
e
of
n
at
u
r
all
y
te
x
t
u
r
ed
s
tr
u
c
tu
r
e
an
d
h
a
s
a
v
er
y
g
r
ea
t
i
n
tr
i
n
s
ic
d
iv
er
s
i
t
y
.
C
lo
u
d
id
en
ti
f
icatio
n
[
6
]
is
a
to
p
ic
t
h
at
can
be
ap
p
lied
to
m
a
n
y
p
r
ac
ti
ca
l
ap
p
licatio
n
s
s
u
c
h
as
w
ea
t
h
er
f
o
r
ec
asti
n
g
,
r
ain
an
d
s
u
n
p
r
ed
ictio
n
f
o
r
in
ter
n
e
t
o
f
th
in
g
s
(
I
o
T
)
d
ev
ices.
I
t
h
as
b
ee
n
s
u
g
g
ested
th
at
t
h
e
lo
ca
l
b
in
ar
y
p
atter
n
s
(
L
B
P
)
[
7
]
an
d
its
v
ar
iatio
n
s
b
e
u
s
ed
as
th
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
m
e
t
h
o
d
f
o
r
ca
teg
o
r
izin
g
n
at
u
r
al
tex
t
u
r
e
p
h
o
to
g
r
ap
h
s
.
L
o
w
co
m
p
lex
it
y
an
d
r
esil
ien
ce
to
m
o
n
o
to
n
ic
b
r
ig
h
t
n
es
s
v
ar
iatio
n
s
ar
e
t
w
o
p
r
o
p
er
ties
of
L
B
P
f
ea
t
u
r
es.
H
o
w
ev
e
r
,
b
e
c
au
s
e
th
e
L
B
P
i
s
d
e
p
e
n
d
en
t
o
n
d
if
f
e
r
en
c
es
in
in
t
en
s
i
ty
,
i
t
is
p
a
r
t
i
cu
l
ar
ly
s
e
n
s
it
iv
e
t
o
n
o
i
s
e
a
n
d
d
o
e
s
n
o
t
p
e
r
f
o
r
m
w
e
l
l
o
n
p
o
r
t
i
o
n
s
o
f
“
f
l
a
t
”
t
ex
tu
r
e
d
im
a
g
es
.
I
n
o
r
d
e
r
t
o
r
em
o
v
e
i
r
r
e
le
v
an
t
f
ea
tu
r
e
o
f
th
e
e
x
t
r
ac
t
i
o
n
p
r
o
c
es
s
,
f
e
a
tu
r
e
s
el
ec
t
i
o
n
(
FS
)
is
w
i
d
e
ly
a
p
p
l
i
e
d
f
o
r
m
an
y
t
as
k
r
e
l
at
e
d
t
o
p
a
t
t
e
r
n
r
e
c
o
g
n
i
ti
o
n
[8
]
–
[
1
0
]
.
Desp
ite
d
ee
p
lear
n
i
n
g
(
D
L
)
m
et
h
o
d
s
ar
e
d
e
m
o
n
s
tr
ated
its
ef
f
ec
ti
v
en
e
s
s
,
s
o
m
e
w
o
r
k
s
ar
e
co
m
b
in
ed
F
S
an
d
DL
i
n
o
r
d
er
to
en
h
an
ce
t
h
e
p
a
tt
er
n
r
ec
o
g
n
it
io
n
[
1
1
]
–
[
1
3
]
.
I
n
th
i
s
p
ap
er
,
w
e
p
r
o
p
o
s
e
to
s
tu
d
y
t
h
e
ef
f
icac
y
o
f
a
F
S
ap
p
r
o
ac
h
f
o
r
class
i
f
y
in
g
clo
u
d
i
m
ag
e
s
.
W
e
u
tili
ze
th
e
s
u
p
p
o
r
t
v
ec
to
r
m
a
ch
in
e
(
SVM)
cla
s
s
i
f
ier
a
n
d
L
B
P
d
escr
ip
to
r
to
class
i
f
y
t
h
e
clo
u
d
i
m
a
g
e
s
,
an
d
ev
alu
a
te
o
u
r
p
r
o
p
o
s
ed
ap
p
r
o
a
ch
o
n
t
w
o
d
if
f
er
en
t
d
ataset
s
.
T
h
e
r
e
m
ai
n
i
n
g
s
ec
tio
n
s
o
f
th
i
s
p
ap
er
ar
e
o
r
g
an
ized
as
f
o
llo
w
s
:
s
ec
tio
n
2
in
tr
o
d
u
ce
s
t
h
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
an
d
s
elec
tio
n
m
et
h
o
d
s
th
at
r
e
l
y
o
n
lo
ca
l
i
m
a
g
e
d
escr
ip
to
r
s
.
Sectio
n
3
pr
ese
n
t
s
o
u
r
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
an
d
th
e
e
x
p
er
i
m
e
n
tal
r
es
u
lt
s
.
L
a
s
tl
y
,
in
s
ec
tio
n
4
,
we
d
is
cu
s
s
t
h
e
co
n
clu
s
io
n
of
o
u
r
s
tu
d
y
.
2.
T
H
E
F
E
AT
UR
E
E
XT
R
ACT
I
O
N
AND
S
E
L
E
C
T
I
O
N
M
E
T
H
O
DS
T
h
is
s
ec
tio
n
r
ev
ie
w
s
clo
u
d
f
ea
t
u
r
e
ex
tr
ac
tio
n
b
y
u
s
i
n
g
L
B
P
m
e
th
o
d
,
an
d
FS
m
eth
o
d
s
w
h
ich
co
m
p
o
s
e
o
f
L
a
s
s
o
,
R
e
lief
F
,
c
o
r
r
elatio
n
-
b
ased
f
ea
tu
r
e
s
elec
t
io
n
(
C
F
S)
,
Fi
s
h
er
,
a
n
d
I
lf
s
.
T
h
ese
m
et
h
o
d
s
w
er
e
ap
p
lied
to
th
e
ex
p
er
im
e
n
t
s
.
B
r
ief
r
ev
ie
w
i
n
g
s
f
o
r
th
ese
tec
h
n
i
q
u
es a
r
e
ex
p
lain
ed
b
elo
w
.
2
.
1
.
L
o
ca
l bina
ry
pa
t
t
er
n
s
T
h
e
P
,
R
(
,
)
co
d
e
o
f
ea
ch
p
ix
el
(
,
)
is
d
eter
m
i
n
ed
b
y
co
m
p
ar
i
n
g
th
e
g
r
a
y
v
alu
e
o
f
th
e
ce
n
tr
al
p
ix
e
l
w
i
th
t
h
e
g
r
a
y
v
al
u
es
{
}
=
0
−
1
o
f
its
P
n
eig
h
b
o
r
s
,
as (
1
)
[
7
]
:
P
,
R
=
∑
Φ
(
−
)
−
1
=
0
2
(
1
)
w
h
er
e
g
c
is
th
e
g
r
a
y
v
alu
e
of
th
e
ce
n
tr
al,
g
p
is
t
h
e
g
r
a
y
v
al
u
e
of
P
,
R
is
t
h
e
r
ad
iu
s
of
th
e
cir
cle
a
n
d
Φ
(
−
)
is
ca
lcu
lated
b
y
:
Φ
(
−
)
=
{
1
if
(
−
)
≥
0
,
0
othe
r
wi
s
e
.
(
2
)
2
.
2
.
F
e
a
t
ure
s
elec
t
io
n
FS
is
a
m
e
th
o
d
to
r
ed
u
ce
r
ed
u
n
d
an
t
at
tr
ib
u
tes
f
r
o
m
g
i
v
e
n
s
e
t
o
f
f
ea
tu
r
e
s
,
s
o
it
allo
w
s
to
d
ec
r
ea
s
e
th
e
s
to
r
ag
e
an
d
i
n
cr
ea
s
e
t
h
e
ti
m
e
p
r
o
ce
s
s
in
g
.
I
n
s
o
m
e
ca
s
es,
i
t
ac
h
iev
e
s
b
etter
p
er
f
o
r
m
a
n
ce
an
d
h
as
a
co
m
p
ac
t
r
ep
r
esen
tatio
n
.
W
e
p
r
esen
t
h
er
e
th
e
co
m
m
o
n
f
ea
tu
r
e
s
ele
ctio
n
ap
p
r
o
ac
h
co
n
s
id
er
ed
in
th
i
s
p
ap
er
.
L
as
s
o
en
ab
les
FS
b
y
as
s
u
m
i
n
g
a
li
n
ea
r
d
ep
en
d
en
ce
b
et
w
ee
n
in
p
u
t
f
ea
tu
r
e
s
an
d
o
u
tp
u
t
v
alu
e
s
.
W
h
en
t
h
e
s
u
m
o
f
ab
s
o
lu
te
v
al
u
es
o
f
r
eg
r
e
s
s
io
n
co
ef
f
icie
n
t
s
is
b
elo
w
a
ce
r
tain
co
n
s
tan
t,
L
as
s
o
m
i
n
i
m
izes
t
h
e
s
u
m
o
f
s
q
u
ar
es
o
f
r
esid
u
als,
r
es
u
lti
n
g
in
ce
r
tai
n
r
eg
r
ess
io
n
co
ef
f
icie
n
ts
b
ei
n
g
p
r
ec
is
el
y
s
et
to
ze
r
o
[
1
4
]
,
[
1
5
]
.
R
elie
f
F
[
1
6
]
is
an
e
x
ten
s
io
n
o
f
t
h
e
R
elie
f
al
g
o
r
ith
m
[
1
7
]
to
ass
is
t
w
it
h
t
h
e
m
u
ltic
lass
is
s
u
e.
R
elief
F
ap
p
ea
r
s
to
b
e
a
p
o
ten
tial
h
eu
r
is
tic
f
u
n
c
ti
o
n
th
a
t
co
u
ld
h
elp
cu
r
r
en
t
in
d
u
cti
v
e
lear
n
in
g
alg
o
r
ith
m
s
o
v
er
co
m
e
th
eir
m
y
o
p
ia.
P
r
io
r
to
lea
r
n
in
g
,
Kir
a
an
d
R
e
n
d
ell
u
s
ed
R
elie
f
F
as
a
p
r
ep
r
o
ce
s
s
o
r
to
r
em
o
v
e
p
o
in
tles
s
attr
ib
u
tes
f
r
o
m
t
h
e
d
ata
d
escr
ip
tio
n
.
R
elief
F
is
co
m
p
r
eh
e
n
s
i
v
e,
co
m
p
ar
ativ
el
y
e
f
f
ec
ti
v
e,
an
d
tr
u
s
t
w
o
r
t
h
y
en
o
u
g
h
to
d
ir
ec
t sear
ch
d
u
r
i
n
g
th
e
lear
n
i
n
g
p
r
o
ce
s
s
[
1
8
]
.
C
FS
m
o
s
tl
y
u
s
es
h
e
u
r
is
tic
ap
p
r
o
ac
h
es
to
d
e
ter
m
i
n
e
t
h
e
i
m
p
ac
t
o
f
ea
ch
g
r
o
u
p
’
s
u
n
iq
u
e
f
ea
t
u
r
e
to
p
r
o
d
u
ce
th
e
b
est
p
o
s
s
ib
le
s
u
b
s
et
o
f
attr
ib
u
tes.
Fis
h
er
[
1
9
]
aim
s
to
d
is
co
v
er
a
s
et
o
f
f
ea
tu
r
e
s
th
at
m
a
x
i
m
ize
th
e
in
ter
-
c
lass
d
is
ta
n
ce
s
b
et
w
ee
n
s
a
m
p
le
s
w
h
ile
m
i
n
i
m
izi
n
g
t
h
e
i
n
tr
a
-
c
lass
d
is
ta
n
ce
s
.
Fis
h
er
ch
o
o
s
es
t
h
e
to
p
f
ea
t
u
r
es
b
ased
o
n
its
s
co
r
es.
I
lf
s
[
2
0
]
in
v
o
l
v
es
t
h
r
ee
s
tep
s
,
w
h
ic
h
in
cl
u
d
e
f
ea
tu
r
e
w
ei
g
h
tin
g
u
s
in
g
a
f
u
l
l
y
co
n
n
ec
ted
n
et
w
o
r
k
w
it
h
i
n
ea
ch
n
o
d
e
th
at
co
n
n
ec
ts
all
f
e
atu
r
es,
a
s
w
ell
as
p
r
ep
r
o
ce
s
s
in
g
.
T
o
ass
ess
th
e
co
r
r
esp
o
n
d
en
ce
b
etw
ee
n
th
e
p
ath
len
g
t
h
an
d
th
e
f
ea
t
u
r
e,
en
er
g
y
s
co
r
es
o
f
th
e
p
ath
len
g
th
ar
e
ca
lcu
lated
,
en
ab
lin
g
t
h
e
r
an
k
in
g
o
f
t
h
eir
s
ig
n
if
ican
ce
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
R
ed
u
cin
g
fe
a
tu
r
e
d
imen
s
io
n
a
li
ty
fo
r
clo
u
d
ima
g
e
cl
a
s
s
ifica
ti
o
n
u
s
in
g
…
(
Th
o
n
g
ch
a
i
S
u
r
in
w
a
r
a
n
g
ko
o
n
)
1513
3.
P
RO
P
O
SE
D
AP
P
RO
ACH
AND
E
XP
E
RIM
E
NT
A
L
R
E
SUL
T
S
In
th
i
s
s
ec
tio
n
,
th
e
ex
p
er
i
m
en
t
an
d
th
e
r
esu
lts
ar
e
ex
p
lain
e
d
.
Data
s
et
ar
e
p
r
ep
a
r
ed
f
o
r
tr
ain
i
n
g
an
d
test
i
n
g
s
tag
e.
Af
ter
t
h
at,
th
e
e
x
p
er
im
e
n
tal
r
es
u
lt
s
ar
e
s
h
o
w
n
a
n
d
d
is
cu
s
s
ed
.
3
.
1
.
E
x
peri
m
ent
a
l set
up
T
o
co
n
d
u
ct
th
e
ex
p
er
i
m
en
t,
t
h
e
Si
n
g
ap
o
r
e
w
h
o
le
-
s
k
y
i
m
a
g
in
g
ca
te
g
o
r
ies
(
SW
I
MC
A
T
)
d
ataset
[
5
]
,
[
2
1
]
,
[
2
2
]
is
co
n
s
id
er
ed
to
ev
a
lu
ate
t
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
.
T
h
is
d
ataset
co
n
s
is
ts
o
f
7
8
4
im
ag
e
s
(
Fi
g
u
r
e
1
)
o
f
th
e
s
k
y
an
d
clo
u
d
s
t
h
at
h
a
v
e
b
ee
n
d
iv
id
ed
i
n
to
5
ca
teg
o
r
ies:
a
clea
r
-
b
lu
e
s
k
y
,
p
atter
n
,
t
h
ic
k
-
d
ac
k
,
t
h
ic
k
-
w
h
i
te,
an
d
co
v
er
.
A
d
d
itio
n
all
y
,
a
n
e
w
d
atase
t
w
as
d
e
v
elo
p
ed
u
s
in
g
t
h
e
co
n
ce
p
t
o
f
th
e
SW
I
MC
A
T
d
atase
t’
s
clo
u
d
/s
k
y
s
e
g
m
e
n
tat
io
n
,
b
u
t
w
it
h
a
h
i
g
h
er
n
u
m
b
er
o
f
p
h
o
t
o
s
an
d
m
o
r
e
clo
u
d
/s
k
y
ca
teg
o
r
ies,
n
a
m
el
y
C
lo
u
d
-
I
m
VN
1
.
0
[
2
3
]
-
[2
5
]
.
T
h
is
d
ataset
h
a
s
2
,
1
0
0
im
ag
e
s
(
Fi
g
u
r
e
2
)
o
f
th
e
s
k
y
a
n
d
clo
u
d
s
ca
teg
o
r
ized
in
to
6
ca
teg
o
r
ies.
Fig
u
r
e
1
.
Sev
er
al
s
elec
ted
i
m
a
g
es
f
r
o
m
SW
I
MC
A
T
d
ataset
Fig
u
r
e
2
.
Sev
er
al
s
elec
ted
i
m
a
g
es
f
r
o
m
C
lo
u
d
-
I
m
VN
1
.
0
d
ataset
W
e
ex
tr
ac
t
L
B
P
f
ea
tu
r
es
f
r
o
m
3
co
m
p
o
n
en
ts
o
f
R
GB
co
lo
r
s
p
ac
e,
w
it
h
d
if
f
er
en
t
v
alu
es
o
f
p
ar
am
eter
s
r
=1
,
2
,
3
,
4
an
d
p
=8
,
1
2
.
T
h
e
SVM
class
if
ier
is
ap
p
lied
af
ter
FS
p
r
o
ce
s
s
.
E
ac
h
d
ataset
is
d
iv
id
ed
in
to
t
h
e
tr
ai
n
in
g
te
s
ti
n
g
s
et
b
y
u
s
i
n
g
K
-
f
o
ld
m
et
h
o
d
(
w
ith
k
=5
)
.
T
h
e
ex
p
er
i
m
e
n
t
i
s
co
n
d
u
cted
an
d
s
i
m
u
lated
b
y
M
A
T
L
A
B
2
0
2
0
a
an
d
u
n
d
e
r
a
P
C
w
ith
C
P
U
2
.
2
6
GHz
,
4
8
GB
o
f
R
A
M.
3
.
2
.
Resul
t
s
T
ab
le
1
,
F
ig
u
r
e
s
3
a
n
d
4
s
h
o
w
t
h
e
ac
c
u
r
ac
y
o
b
tai
n
ed
b
y
L
B
P
w
it
h
r
a
n
d
p
p
ar
am
eter
b
y
in
co
r
p
o
r
atin
g
FS
m
e
th
o
d
s
.
W
e
o
b
s
er
v
e
th
at
th
e
FS
m
et
h
o
d
s
clea
r
l
y
ac
h
ie
v
e
b
etter
p
er
f
o
r
m
an
ce
,
n
o
t
o
n
l
y
i
m
p
r
o
v
i
n
g
t
h
e
ac
c
u
r
ac
y
b
u
t
also
r
ed
u
cin
g
th
e
d
i
m
e
n
s
io
n
s
p
ac
e.
A
lt
h
o
u
g
h
w
it
h
D
L
m
i
g
h
t
ac
h
ie
v
e
b
etter
r
esu
lt
s
,
h
o
w
e
v
er
it
r
eq
u
ir
es
m
o
r
e
r
eso
u
r
ce
s
th
a
n
tr
ad
itio
n
al
m
et
h
o
d
s
.
I
n
t
h
is
ca
s
e,
FS
is
a
g
o
o
d
ca
n
d
id
ate
f
o
r
th
is
k
i
n
d
o
f
task
s
i
n
ce
w
e
o
b
tain
g
o
o
d
r
esu
lt
s
w
ith
le
s
s
s
to
r
ag
e.
T
h
is
m
o
d
el
ca
n
b
e
e
m
b
ed
d
ed
in
to
tin
y
m
ac
h
in
e
a
n
d
u
s
ed
f
o
r
I
o
T
s
y
s
t
e
m
s
f
o
r
w
ea
t
h
er
f
o
r
ec
asti
n
g
.
Af
ter
FS
,
t
h
e
SW
I
MC
A
T
d
ataset
h
ad
th
e
m
a
x
i
m
u
m
ac
cu
r
ac
y
of
9
7
.
9
6
%
(
T
ab
le
1
)
w
it
h
o
n
l
y
9
2
.
0
0
%
of
th
e
f
ea
tu
r
e
ar
e
u
s
e
d
.
T
h
e
r
esu
lt
is
alr
ea
d
y
100%
g
r
ea
ter
th
a
n
t
h
e
n
u
m
b
er
of
f
ea
tu
r
e
s
(
9
7
.
8
2
%)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
22
,
No
.
6
,
Dec
em
b
er
20
24
:
1
5
1
1
-
1
516
1514
w
h
e
n
u
s
i
n
g
L
B
P
(
r
=2
,
p
=8
)
a
n
d
Fis
h
er
,
an
d
t
h
e
n
u
m
b
er
o
f
f
ea
tu
r
es
i
s
f
u
r
th
er
r
ed
u
ce
d
b
y
8
%.
Ho
w
e
v
er
,
th
er
e
is
a
p
o
ten
tial
L
B
P
(
r
=1
,
p
=
1
2
)
alter
n
ativ
e
t
h
at
u
s
es
C
FS
a
n
d
y
ield
s
a
r
esu
lt
o
f
9
7
.
9
4
%
(
s
till
h
ig
h
er
b
y
0
.
1
2
%)
w
h
ile
u
s
i
n
g
o
n
l
y
4
1
%
o
f
th
e
in
itial
c
h
ar
ac
ter
is
tic
n
u
m
b
er
.
A
lt
h
o
u
g
h
th
e
ac
c
u
r
ac
y
i
s
o
n
l
y
0
.
0
2
%
lo
w
er
th
a
n
th
e
h
ig
h
e
s
t
ac
cu
r
ac
y
(
9
7
.
9
6
%),
th
e
m
e
m
o
r
y
u
s
ag
e
h
as
n
o
t
d
ec
r
ea
s
ed
by
h
al
f
(
4
1
%),
w
h
ic
h
m
a
k
es
it
id
ea
l
f
o
r
m
ac
h
in
e
s
w
it
h
le
s
s
s
to
r
ag
e
m
e
m
o
r
y
.
Si
m
i
lar
to
th
e
C
lo
u
d
-
I
m
VN
1
.
0
d
ataset,
th
e
ac
h
iev
ed
ac
cu
r
ac
y
is
9
5
.
4
3
%
(
r
=1
,
p
=8
,
C
FS
)
w
h
en
u
s
i
n
g
o
n
l
y
20%
of
th
e
o
r
i
g
in
al
f
ea
t
u
r
es.
T
h
is
r
ed
u
ctio
n
in
f
ea
t
u
r
es
co
r
r
esp
o
n
d
s
to
an
80%
d
ec
r
ea
s
e,
y
et
th
e
ac
cu
r
ac
y
r
e
m
ain
s
s
i
g
n
if
ica
n
tl
y
h
ig
h
er
t
h
an
t
h
e
o
r
ig
in
al
4
.
4
3
%
ac
cu
r
ac
y
.
T
ab
le
1
.
L
B
P
f
ea
tu
r
es
-
r
es
u
lt
s
ac
h
iev
ed
w
it
h
d
if
f
er
en
t
FS
m
e
th
o
d
s
(
%)
S
W
I
M
C
A
T
C
l
o
u
d
-
I
mV
N
1
.
0
r
,
p
F
A
c
c
FS
r
,
p
F
A
c
c
FS
C
F
S
F
i
sh
e
r
I
l
f
s
L
a
ss
o
R
e
l
i
e
f
f
C
F
S
F
i
sh
e
r
I
l
f
s
L
a
ss
o
R
e
l
i
e
f
f
A
c
c
1,
8
9
7
.
5
7
9
7
.
6
9
9
7
.
8
2
9
7
.
5
7
9
7
.
5
7
9
7
.
5
7
1,
8
9
1
.
0
0
95
9
4
.
8
1
9
5
.
4
3
9
5
.
1
4
9
4
.
4
3
S
t
d
0
.
4
1
0
.
4
3
0
.
5
5
0
.
5
5
0
.
5
5
0
.
8
7
0
.
9
7
1
.
0
8
0
.
8
2
0
.
9
6
D
i
m
97
97
47
76
86
56
86
20
48
77
A
c
c
1,
12
9
7
.
8
1
9
7
.
9
4
9
7
.
8
1
9
7
.
8
1
9
7
.
8
3
9
7
.
8
2
1,
12
9
1
.
1
4
9
4
.
7
1
9
4
.
7
1
9
4
.
8
6
9
4
.
7
1
9
4
.
7
1
S
t
d
0
.
8
7
1
.
3
0
1
.
3
0
0
.
9
4
1
.
7
6
1
.
0
0
1
.
2
5
1
.
1
2
1
.
8
2
1
.
1
3
D
i
m
41
1
0
0
10
85
27
24
72
2
98
6
A
c
c
2,
8
9
7
.
6
9
9
7
.
8
2
9
7
.
9
6
9
7
.
6
9
9
7
.
6
9
9
7
.
8
2
2,
8
9
7
.
6
9
9
4
.
1
4
9
4
.
5
2
9
4
.
2
9
9
4
.
3
3
9
3
.
5
7
S
t
d
0
.
9
8
0
.
6
8
1
.
4
6
1
.
4
6
1
.
2
5
0
.
3
6
0
.
8
1
1
.
6
8
2
.
1
5
1
.
6
0
D
i
m
96
92
88
97
98
52
93
15
38
42
A
c
c
2,
12
9
7
.
3
2
9
7
.
8
2
9
7
.
4
4
9
7
.
4
4
9
7
.
4
4
9
7
.
6
9
2,
12
9
1
.
2
9
9
4
.
8
1
9
5
.
1
4
9
4
.
1
9
9
4
.
9
1
9
4
.
7
1
S
t
d
0
.
8
8
0
.
6
8
0
.
7
8
1
.
0
9
1
.
0
7
1
.
5
0
1
.
7
0
2
.
0
0
1
.
5
7
1
.
4
4
D
i
m
96
92
9
75
56
4
.
3
85
24
51
86
A
c
c
3,
8
9
7
.
0
8
9
7
.
0
8
9
7
.
4
6
9
7
.
2
1
9
7
.
2
1
9
7
.
4
6
3,
8
9
2
.
2
4
94
9
3
.
6
2
9
3
.
3
3
9
4
.
1
9
9
3
.
4
8
S
t
d
0
.
6
4
0
.
9
6
0
.
9
0
1
.
1
0
1
.
1
4
1
.
7
6
1
.
7
7
1
.
5
3
0
.
8
2
1
.
6
0
D
i
m
93
67
60
56
87
53
86
22
31
44
A
c
c
3,
12
9
7
.
2
1
9
7
.
2
1
9
7
.
6
9
9
7
.
3
3
9
7
.
3
3
9
7
.
8
3
3,
12
9
2
.
5
2
9
4
.
2
9
9
4
.
7
6
9
4
.
0
5
9
4
.
5
7
9
3
.
8
6
S
t
d
1
.
2
6
1
.
3
2
1
.
4
0
1
.
3
3
0
.
7
0
1
.
9
7
1
.
1
7
0
.
9
4
1
.
6
0
1
.
4
3
D
i
m
1
0
0
68
6
66
39
52
82
4
66
19
A
c
c
4,
8
9
6
.
4
4
9
6
.
8
3
9
6
.
6
9
9
6
.
5
7
9
6
.
6
9
9
7
.
4
6
4,
8
9
3
.
3
8
9
4
.
0
5
9
3
.
9
1
9
3
.
7
1
9
4
.
0
5
94
S
t
d
1
.
1
2
1
.
4
6
0
.
9
9
0
.
9
8
0
.
9
6
1
.
5
9
1
.
8
3
1
.
5
3
1
.
6
6
0
.
8
7
D
i
m
71
69
56
76
66
69
86
96
60
49
A
c
c
4,
12
9
6
.
6
9
9
7
.
0
7
9
6
.
9
4
9
6
.
9
4
9
7
.
0
4
9
7
.
4
4
4,
12
9
3
.
9
5
9
4
.
5
2
9
4
.
6
2
9
4
.
2
9
9
4
.
2
9
9
4
.
1
9
S
t
d
1
.
5
6
1
.
1
8
1
.
1
8
1
.
1
2
0
.
7
8
1
.
4
3
0
.
9
9
1
.
2
3
1
.
3
3
0
.
7
8
D
i
m
98
16
16
95
81
59
99
13
94
90
*
A
c
c
:
max
a
c
c
u
r
a
c
y
;
r
,
p
F
A
c
c
:
r
a
n
d
p
o
f
L
B
P
d
e
scri
p
t
o
r
,
a
c
c
u
r
a
c
y
w
i
t
h
f
u
l
l
f
e
a
t
u
r
e
;
d
i
m:
p
e
r
c
e
n
t
a
g
e
o
f
se
l
e
c
t
e
d
f
e
a
t
u
r
e
s
Fig
u
r
e
3
.
SVM
clas
s
if
ier
on
L
B
P
f
ea
tu
r
es
(
SW
I
MC
A
T
)
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
R
ed
u
cin
g
fe
a
tu
r
e
d
imen
s
io
n
a
li
ty
fo
r
clo
u
d
ima
g
e
cl
a
s
s
ifica
ti
o
n
u
s
in
g
…
(
Th
o
n
g
ch
a
i
S
u
r
in
w
a
r
a
n
g
ko
o
n
)
1515
Fig
u
r
e
4
.
SVM
clas
s
if
ier
on
L
B
P
f
ea
tu
r
es
(
C
lo
u
d
-
I
m
V
N
1
.
0
)
4.
CO
NCLU
SI
O
N
Desp
ite
li
m
ited
r
eso
u
r
ce
s
f
o
r
tr
ain
i
n
g
,
FS
ap
p
r
o
ac
h
es
can
s
till
be
h
ig
h
l
y
r
ele
v
an
t
in
t
h
is
s
tu
d
y
,
p
r
o
v
id
in
g
s
e
v
er
al
b
en
ef
its
t
h
at
ar
e
w
el
l
-
s
u
ited
f
o
r
th
e
ac
tu
al
s
itu
a
tio
n
.
FS
r
e
m
a
in
s
ad
v
an
ta
g
eo
u
s
a
s
it
r
ed
u
ce
s
d
ata
d
im
e
n
s
io
n
alit
y
,
en
h
a
n
ce
s
ac
cu
r
ac
y
,
r
ed
u
ce
s
p
r
o
ce
s
s
in
g
ti
m
e,
a
n
d
ca
n
be
in
teg
r
ated
i
n
t
o
I
o
T
s
y
s
te
m
s
.
T
h
e
f
u
tu
r
e
p
at
h
f
o
r
i
m
p
r
o
v
in
g
p
er
f
o
r
m
a
n
ce
in
t
h
i
s
w
o
r
k
is
th
r
o
u
g
h
th
e
co
m
b
i
n
ed
u
s
e
of
FS
an
d
DL
ap
p
r
o
ac
h
es,
lev
er
ag
i
n
g
th
e
s
tr
e
n
g
th
s
of
b
o
th
tech
n
iq
u
e
s
to
ac
h
iev
e
o
p
ti
m
al
r
esu
lt
s
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
s
t
u
d
y
r
ec
ei
v
ed
co
llab
o
r
ativ
e
s
u
p
p
o
r
t
f
r
o
m
S
u
an
S
u
n
a
n
d
h
a
R
aj
ab
h
at
U
n
i
v
er
s
it
y
(
S
SR
U)
an
d
Ho
C
h
i M
in
h
C
i
t
y
Op
e
n
Un
i
v
er
s
i
t
y
(
HC
M
C
OU)
.
RE
F
E
R
E
NC
E
S
[
1
]
F
.
L
i
n
,
Y
.
Z
h
a
n
g
,
a
n
d
J.
W
a
n
g
,
“
R
e
c
e
n
t
a
d
v
a
n
c
e
s
i
n
i
n
t
r
a
-
h
o
u
r
so
l
a
r
f
o
r
e
c
a
st
i
n
g
:
A
r
e
v
i
e
w
o
f
g
r
o
u
n
d
-
b
a
se
d
s
k
y
i
mag
e
me
t
h
o
d
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
F
o
re
c
a
s
t
i
n
g
,
v
o
l
.
3
9
,
n
o
.
1
,
p
p
.
2
4
4
–
2
6
5
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
f
o
r
e
c
a
st
.
2
0
2
1
.
1
1
.
0
0
2
.
[
2
]
S
.
L
i
u
,
L
.
Z
h
a
n
g
,
Z
.
Z
h
a
n
g
,
C
.
W
a
n
g
,
a
n
d
B
.
X
i
a
o
,
“
A
u
t
o
mat
i
c
c
l
o
u
d
d
e
t
e
c
t
i
o
n
f
o
r
a
l
l
-
sk
y
i
mag
e
s
u
si
n
g
su
p
e
r
p
i
x
e
l
se
g
me
n
t
a
t
i
o
n
,
”
I
EEE
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
L
e
t
t
e
rs
,
v
o
l
.
1
2
,
n
o
.
2
,
p
p
.
3
5
4
–
3
5
8
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/
L
G
R
S
.
2
0
1
4
.
2
3
4
1
2
9
1
.
[
3
]
T
.
K
l
i
a
n
g
su
w
a
n
a
n
d
A
.
H
e
e
d
n
a
c
r
a
m
,
“
F
F
T
f
e
a
t
u
r
e
s
a
n
d
h
i
e
r
a
r
c
h
i
c
a
l
c
l
a
s
si
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
m
s
f
o
r
c
l
o
u
d
i
mag
e
s,
”
E
n
g
i
n
e
e
ri
n
g
Ap
p
l
i
c
a
t
i
o
n
s
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
7
6
,
p
p
.
4
0
–
5
4
,
N
o
v
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
1
8
.
0
8
.
0
0
8
.
[
4
]
S
.
L
i
u
a
n
d
M
.
L
i
,
“
M
u
l
t
i
mo
d
a
l
G
A
N
f
o
r
En
e
r
g
y
Ef
f
i
c
i
e
n
c
y
a
n
d
C
l
o
u
d
C
l
a
ssi
f
i
c
a
t
i
o
n
i
n
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s,
”
I
EEE
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
J
o
u
rn
a
l
,
v
o
l
.
6
,
n
o
.
4
,
p
p
.
6
0
3
4
–
6
0
4
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T
.
2
0
1
8
.
2
8
6
6
3
2
8
.
[
5
]
H
.
D
.
T
.
H
o
n
g
a
n
d
V
.
T
.
H
o
a
n
g
,
“
A
C
o
mp
a
r
a
t
i
v
e
S
t
u
d
y
o
f
C
o
l
o
r
S
p
a
c
e
s
f
o
r
C
l
o
u
d
I
mag
e
s
R
e
c
o
g
n
i
t
i
o
n
B
a
se
d
o
n
L
B
P
a
n
d
L
T
P
F
e
a
t
u
r
e
s,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
N
e
t
w
o
r
k
s a
n
d
S
y
s
t
e
m
s
,
v
o
l
.
1
3
6
,
2
0
2
1
,
p
p
.
3
7
5
–
3
8
2
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
030
-
4
9
2
6
4
-
9
_
3
4
.
[
6
]
Y
.
W
a
n
g
,
C
.
S
h
i
,
C
.
W
a
n
g
,
a
n
d
B
.
X
i
a
o
,
“
G
r
o
u
n
d
-
b
a
se
d
c
l
o
u
d
c
l
a
s
si
f
i
c
a
t
i
o
n
b
y
l
e
a
r
n
i
n
g
st
a
b
l
e
l
o
c
a
l
b
i
n
a
r
y
p
a
t
t
e
r
n
s,
”
At
m
o
s
p
h
e
r
i
c
Re
se
a
r
c
h
,
v
o
l
.
2
0
7
,
p
p
.
7
4
–
8
9
,
J
u
l
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
t
mo
sr
e
s.2
0
1
8
.
0
2
.
0
2
3
.
[
7
]
T
.
O
j
a
l
a
,
M
.
P
i
e
t
i
k
ä
i
n
e
n
,
a
n
d
D
.
H
a
r
w
o
o
d
,
“
A
c
o
mp
a
r
a
t
i
v
e
st
u
d
y
o
f
t
e
x
t
u
r
e
me
a
su
r
e
s
w
i
t
h
c
l
a
ssi
f
i
c
a
t
i
o
n
b
a
se
d
o
n
f
e
a
t
u
r
e
d
d
i
s
t
r
i
b
u
t
i
o
n
s,
”
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
,
v
o
l
.
2
9
,
n
o
.
1
,
p
p
.
5
1
–
5
9
,
J
a
n
.
1
9
9
6
,
d
o
i
:
1
0
.
1
0
1
6
/
0
0
3
1
-
3
2
0
3
(
9
5
)
0
0
0
6
7
-
4.
[
8
]
R
.
V
a
d
d
i
a
n
d
P
.
M
a
n
o
h
a
r
a
n
,
“
C
N
N
b
a
se
d
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
u
s
i
n
g
u
n
s
u
p
e
r
v
i
se
d
b
a
n
d
se
l
e
c
t
i
o
n
a
n
d
st
r
u
c
t
u
r
e
-
p
r
e
se
r
v
i
n
g
sp
a
t
i
a
l
f
e
a
t
u
r
e
s,
”
I
n
f
r
a
re
d
Ph
y
s
i
c
s
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
1
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
r
a
r
e
d
.
2
0
2
0
.
1
0
3
4
5
7
.
[
9
]
A
.
A
l
sah
a
f
,
N
.
P
e
t
k
o
v
,
V
.
S
h
e
n
o
y
,
a
n
d
G
.
A
z
z
o
p
a
r
d
i
,
“
A
f
r
a
mew
o
r
k
f
o
r
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
t
h
r
o
u
g
h
b
o
o
st
i
n
g
,
”
E
x
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
8
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
s
w
a
.
2
0
2
1
.
1
1
5
8
9
5
.
[
1
0
]
S
.
N
u
a
n
me
e
sr
i
,
L
.
P
o
o
mh
i
r
u
n
,
P
.
K
e
d
ma
t
e
e
k
a
r
u
n
,
a
n
d
S
.
C
h
o
p
v
i
t
a
y
a
k
u
n
,
“
I
mp
r
o
v
i
n
g
t
h
e
w
a
t
e
r
q
u
a
l
i
t
y
c
l
a
ssi
f
i
c
a
t
i
o
n
mo
d
e
l
f
o
r
v
a
r
i
o
u
s
f
a
r
ms
u
si
n
g
f
e
a
t
u
r
e
s
b
a
se
d
o
n
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
T
EM
J
o
u
rn
a
l
,
v
o
l
.
1
2
,
n
o
.
4
,
p
p
.
2
1
4
4
-
2
1
5
6
,
No
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
8
4
2
1
/
T
E
M
1
2
4
-
25
.
[
1
1
]
M
.
I
.
S
h
a
r
i
f
,
J.
P
.
L
i
,
M
.
A
.
K
h
a
n
,
a
n
d
M
.
A
.
S
a
l
e
e
m,
“
A
c
t
i
v
e
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
f
e
a
t
u
r
e
s
sel
e
c
t
i
o
n
f
o
r
s
e
g
me
n
t
a
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
o
f
b
r
a
i
n
t
u
mo
r
s
u
si
n
g
M
R
I
i
mag
e
s,
”
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
L
e
t
t
e
rs
,
v
o
l
.
1
2
9
,
p
p
.
1
8
1
–
1
8
9
,
Ja
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
r
e
c
.
2
0
1
9
.
1
1
.
0
1
9
.
[
1
2
]
A
.
M
i
r
z
a
e
i
,
V
.
P
o
u
r
a
h
ma
d
i
,
M
.
S
o
l
t
a
n
i
,
a
n
d
H
.
S
h
e
i
k
h
z
a
d
e
h
,
“
D
e
e
p
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
u
si
n
g
a
t
e
a
c
h
e
r
-
st
u
d
e
n
t
n
e
t
w
o
r
k
,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
3
8
3
,
p
p
.
3
9
6
–
4
0
8
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m
.
2
0
1
9
.
1
2
.
0
1
7
.
[
1
3
]
S
.
N
u
a
n
me
e
sr
i
,
“
U
t
i
l
i
z
a
t
i
o
n
o
f
m
u
l
t
i
-
c
h
a
n
n
e
l
h
y
b
r
i
d
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
a
v
o
c
a
d
o
r
i
p
e
n
e
ss
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
E
n
g
i
n
e
e
ri
n
g
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
22
,
No
.
6
,
Dec
em
b
er
20
24
:
1
5
1
1
-
1
516
1516
T
e
c
h
n
o
l
o
g
y
&
Ap
p
l
i
e
d
S
c
i
e
n
c
e
Re
s
e
a
rch
,
v
o
l
.
1
4
,
n
o
.
4
,
p
p
.
1
4
8
6
2
–
1
4
8
6
7
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
4
8
0
8
4
/
e
t
a
sr
.
7
6
5
1
.
[
1
4
]
J.
C
a
i
,
J
.
L
u
o
,
S
.
W
a
n
g
,
a
n
d
S
.
Y
a
n
g
,
“
F
e
a
t
u
r
e
se
l
e
c
t
i
o
n
i
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
:
A
n
e
w
p
e
r
sp
e
c
t
i
v
e
,
”
N
e
u
r
o
c
o
m
p
u
t
i
n
g
,
v
o
l
.
3
0
0
,
p
p
.
70
–
7
9
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.2
0
1
7
.
1
1
.
0
7
7
.
[
1
5
]
M
.
Y
a
ma
d
a
,
W
.
J
i
t
k
r
i
t
t
u
m,
L
.
S
i
g
a
l
,
E
.
P
.
X
i
n
g
,
a
n
d
M
.
S
u
g
i
y
a
ma,
“
H
i
g
h
-
D
i
me
n
s
i
o
n
a
l
F
e
a
t
u
r
e
S
e
l
e
c
t
i
o
n
b
y
F
e
a
t
u
r
e
-
W
i
se
K
e
r
n
e
l
i
z
e
d
L
a
sso
,
”
N
e
u
r
a
l
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
2
6
,
n
o
.
1
,
p
p
.
1
8
5
–
2
0
7
,
J
a
n
.
2
0
1
4
,
d
o
i
:
1
0
.
1
1
6
2
/
N
E
C
O
_
a
_
0
0
5
3
7
.
[
1
6
]
I
.
K
o
n
o
n
e
n
k
o
,
“
Est
i
m
a
t
i
n
g
a
t
t
r
i
b
u
t
e
s
:
A
n
a
l
y
si
s
a
n
d
e
x
t
e
n
si
o
n
s
o
f
R
EL
I
E
F
,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
su
b
s
e
ri
e
s
L
e
c
t
u
re
N
o
t
e
s
i
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
re
N
o
t
e
s
i
n
B
i
o
i
n
f
o
rm
a
t
i
c
s)
,
v
o
l
.
7
8
4
L
N
C
S
,
1
9
9
4
,
p
p
.
1
7
1
–
182
,
d
o
i
:
1
0
.
1
0
0
7
/
3
-
5
4
0
-
5
7
8
6
8
-
4
_
5
7
.
[
1
7
]
K
.
K
i
r
a
a
n
d
L
.
A
.
R
e
n
d
e
l
l
,
“
A
P
r
a
c
t
i
c
a
l
A
p
p
r
o
a
c
h
t
o
F
e
a
t
u
r
e
S
e
l
e
c
t
i
o
n
,
”
i
n
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
Pro
c
e
e
d
i
n
g
s
1
9
9
2
,
El
se
v
i
e
r
,
1
9
9
2
,
p
p
.
2
4
9
–
256
,
d
o
i
:
1
0
.
1
0
1
6
/
B
9
7
8
-
1
-
5
5
8
6
0
-
247
-
2
.
5
0
0
3
7
-
1.
[
1
8
]
I
.
K
o
n
o
n
e
n
k
o
,
E.
Š
i
me
c
,
a
n
d
M
.
R
o
b
n
i
k
-
Š
i
k
o
n
j
a
,
“
O
v
e
r
c
o
mi
n
g
t
h
e
M
y
o
p
i
a
o
f
I
n
d
u
c
t
i
v
e
L
e
a
r
n
i
n
g
A
l
g
o
r
i
t
h
ms
w
i
t
h
R
EL
I
E
F
F
,
”
Ap
p
l
i
e
d
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
3
9
–
5
5
,
1
9
9
7
,
d
o
i
:
1
0
.
1
0
2
3
/
A
:
1
0
0
8
2
8
0
6
2
0
6
2
1
.
[
1
9
]
N
.
L
a
n
g
e
,
C
.
M
.
B
i
s
h
o
p
,
a
n
d
B
.
D
.
R
i
p
l
e
y
,
“
N
e
u
r
a
l
N
e
t
w
o
r
k
s
f
o
r
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
t
h
e
Am
e
ri
c
a
n
S
t
a
t
i
st
i
c
a
l
Asso
c
i
a
t
i
o
n
,
v
o
l
.
9
2
,
n
o
.
4
4
0
,
p
.
1
6
4
2
,
D
e
c
.
1
9
9
7
,
d
o
i
:
1
0
.
2
3
0
7
/
2
9
6
5
4
3
7
.
[
2
0
]
T.
M
i
f
t
a
h
u
sh
u
d
u
r
,
C
.
B
.
A
.
W
a
e
l
,
a
n
d
T
.
P
r
a
l
u
d
i
,
“
I
n
f
i
n
i
t
e
L
a
t
e
n
t
F
e
a
t
u
r
e
S
e
l
e
c
t
i
o
n
T
e
c
h
n
i
q
u
e
f
o
r
H
y
p
e
r
sp
e
c
t
r
a
l
I
mag
e
C
l
a
ssi
f
i
c
a
t
i
o
n
,
”
J
u
rn
a
l
El
e
k
t
ro
n
i
k
a
d
a
n
T
e
l
e
k
o
m
u
n
i
k
a
s
i
,
v
o
l
.
1
9
,
n
o
.
1
,
p
.
3
2
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
1
4
2
0
3
/
j
e
t
.
v
1
9
.
3
2
-
37.
[
2
1
]
V
.
T
.
H
o
a
n
g
,
“
Ad
a
p
t
i
v
e
T
e
r
n
a
r
y
P
a
t
t
e
r
n
B
a
se
d
o
n
S
u
p
e
r
v
i
se
d
L
e
a
r
n
i
n
g
A
p
p
r
o
a
c
h
f
o
r
G
r
o
u
n
d
-
B
a
se
d
C
l
o
u
d
T
y
p
e
C
l
a
ssi
f
i
c
a
t
i
o
n
,
”
i
n
Ad
v
a
n
c
e
s
i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
2
0
0
A
I
S
C
,
2
0
2
1
,
p
p
.
2
8
0
–
286
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
5
1
8
5
9
-
2
_
2
5
.
[
2
2
]
Y
.
N
i
e
,
X
.
L
i
,
Q
.
P
a
l
e
t
t
a
,
M
.
A
r
a
g
o
n
,
A
.
S
c
o
t
t
,
a
n
d
A
.
B
r
a
n
d
t
,
“
O
p
e
n
-
so
u
r
c
e
sk
y
i
m
a
g
e
d
a
t
a
se
t
s
f
o
r
so
l
a
r
f
o
r
e
c
a
st
i
n
g
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
:
A
c
o
mp
r
e
h
e
n
si
v
e
su
r
v
e
y
,
”
Re
n
e
w
a
b
l
e
a
n
d
S
u
s
t
a
i
n
a
b
l
e
E
n
e
r
g
y
Re
v
i
e
w
s
,
v
o
l
.
1
8
9
,
p
.
1
1
3
9
7
7
,
Jan
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
se
r
.
2
0
2
3
.
1
1
3
9
7
7
.
[
2
3
]
S
.
D
e
v
,
F
.
M
.
S
a
v
o
y
,
Y
.
H
.
L
e
e
,
a
n
d
S
.
W
i
n
k
l
e
r
,
“
D
e
si
g
n
o
f
l
o
w
-
c
o
st
,
c
o
mp
a
c
t
a
n
d
w
e
a
t
h
e
r
-
p
r
o
o
f
w
h
o
l
e
sk
y
i
mag
e
r
s
f
o
r
h
i
g
h
-
d
y
n
a
mi
c
-
r
a
n
g
e
c
a
p
t
u
r
e
s,
”
i
n
2
0
1
5
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
G
e
o
sci
e
n
c
e
a
n
d
Re
m
o
t
e
S
e
n
si
n
g
S
y
m
p
o
si
u
m
(
I
G
AR
S
S
)
,
Ju
l
.
2
0
1
5
,
p
p
.
5
3
5
9
–
53
62
,
d
o
i
:
1
0
.
1
1
0
9
/
I
G
A
R
S
S
.
2
0
1
5
.
7
3
2
7
0
4
6
.
[
2
4
]
V
.
T
.
H
o
a
n
g
,
“
C
l
o
u
d
-
I
mV
N
1
.
0
,
”
Me
n
d
e
l
e
y
D
a
t
a
,
V
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
7
6
3
2
/
v
w
d
d
9
g
r
v
d
p
.
2
.
[
2
5
]
K
.
T
r
a
n
-
T
r
u
n
g
,
H
.
D
.
T
.
H
o
n
g
,
a
n
d
V
.
T
.
H
o
a
n
g
,
“
W
e
a
t
h
e
r
F
o
r
e
c
a
st
B
a
se
d
o
n
C
o
l
o
r
C
l
o
u
d
I
mag
e
R
e
c
o
g
n
i
t
i
o
n
u
n
d
e
r
t
h
e
C
o
mb
i
n
a
t
i
o
n
o
f
L
o
c
a
l
I
mag
e
D
e
scri
p
t
o
r
a
n
d
H
i
st
o
g
r
a
m
S
e
l
e
c
t
i
o
n
,
”
El
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
1
,
n
o
.
2
1
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
1
2
1
3
4
6
0
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Th
o
n
g
c
h
a
i
S
u
r
in
w
a
r
a
n
g
k
o
o
n
re
c
e
iv
e
d
th
e
B
.
S
c
.
d
e
g
re
e
in
M
a
th
e
m
a
ti
c
s
fr
o
m
Ch
ian
g
M
a
i
Un
iv
e
rsit
y
,
T
h
a
il
a
n
d
,
i
n
1
9
9
5
.
He
re
c
e
iv
e
d
th
e
M
.
S
c
.
in
M
a
n
a
g
e
m
e
n
t
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
f
ro
m
Wala
il
a
k
Un
iv
e
rsit
y
,
T
h
a
il
a
n
d
i
n
2
0
0
5
a
n
d
P
h
.
D.
in
in
f
o
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
f
ro
m
Kin
g
M
o
n
g
k
u
t
’s
Un
iv
e
rs
it
y
o
f
Tec
h
n
o
lo
g
y
N
o
rth
Ba
n
g
k
o
k
,
T
h
a
il
a
n
d
i
n
2
0
1
4
.
C
u
rre
n
tl
y
,
h
e
is
a
n
a
ss
istan
t
p
ro
f
e
ss
o
r
a
t
De
p
a
rt
m
e
n
t
o
f
Bu
s
in
e
ss
Co
m
p
u
ter,
Co
ll
e
g
e
o
f
In
n
o
v
a
ti
o
n
a
n
d
M
a
n
a
g
e
m
e
n
t,
a
n
d
t
h
e
De
p
u
ty
De
a
n
f
o
r
A
d
m
in
istratio
n
o
f
G
ra
d
u
a
te
S
c
h
o
o
l,
S
u
a
n
S
u
n
a
n
d
h
a
Ra
jab
h
a
t
Un
iv
e
rsit
y
,
Ba
n
g
k
o
k
,
T
h
a
il
a
n
d
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
im
a
g
e
p
ro
c
e
ss
in
g
,
m
a
c
h
in
e
lea
rn
in
g
,
a
rti
f
icia
l
in
telli
g
e
n
c
e
,
b
u
sin
e
ss
in
telli
g
e
n
c
e
,
a
n
d
m
o
b
il
e
a
p
p
li
c
a
ti
o
n
d
e
v
e
lo
p
m
e
n
t
f
o
r
b
u
si
n
e
ss
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
i
l:
th
o
n
g
c
h
a
i.
su
@s
sru
.
a
c
.
th
.
V
i
n
h
T
r
u
o
n
g
H
o
a
n
g
re
c
e
i
v
e
d
h
is
M
a
ste
r’s
d
e
g
re
e
f
ro
m
t
h
e
Un
iv
e
rsity
o
f
M
o
n
t
p
e
ll
ier
in
2
0
0
9
a
n
d
h
is
P
h
.
D.
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
th
e
Un
iv
e
rsity
o
f
th
e
L
it
to
ra
l
Op
a
l
Co
a
st,
F
ra
n
c
e
.
He
is
c
u
rre
n
t
ly
a
n
a
ss
istan
t
p
ro
f
e
ss
o
r,
He
a
d
o
f
Da
ta
S
c
ien
c
e
De
p
a
rtm
e
n
t,
a
n
d
th
e
V
ice
De
a
n
o
f
F
a
c
u
lt
y
o
f
I
n
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
Ho
Ch
i
M
in
h
Ci
ty
Op
e
n
Un
iv
e
rsit
y
in
V
iet
n
a
m
.
His
re
se
a
rc
h
in
t
e
re
sts
in
c
lu
d
e
d
e
e
p
lea
rn
in
g
,
f
e
a
tu
re
se
lec
ti
o
n
,
tex
tu
re
c
las
si
f
ica
ti
o
n
,
l
o
c
a
l
b
in
a
ry
p
a
tt
e
rn
s,
a
n
d
f
a
c
e
re
c
o
g
n
it
io
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
in
h
.
t
h
@o
u
.
e
d
u
.
v
n
.
K
itti
k
h
u
n
M
e
e
th
o
n
g
ja
n
re
c
e
iv
e
d
h
is
B.
S
c
.
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
fr
o
m
S
u
a
n
S
u
n
a
n
d
h
a
Ra
jab
h
a
t
Un
iv
e
rsity
,
T
h
a
il
a
n
d
,
in
1
9
9
0
,
a
M
a
ste
r’s
d
e
g
re
e
in
C
o
m
p
u
ter
a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
f
ro
m
Kin
g
M
o
n
g
k
u
t’s
Un
iv
e
rsity
o
f
T
e
c
h
n
o
lo
g
y
T
h
o
n
b
u
ri
(KMUT
T
),
T
h
a
il
a
n
d
,
i
n
2
0
0
0
,
a
n
d
t
h
e
P
h
.
D.
in
c
o
m
p
u
ter
g
ra
p
h
ic
f
ro
m
th
e
Un
iv
e
rsity
o
f
T
e
c
h
n
o
lo
g
y
M
a
la
y
sia
in
2
0
1
3
.
C
u
rre
n
tl
y
,
h
e
is
a
n
a
ss
istan
t
p
r
o
f
e
s
so
r
a
t
th
e
Co
m
p
u
ter
S
c
ien
c
e
P
r
o
g
ra
m
,
He
a
d
o
f
A
p
p
l
y
S
c
ien
c
e
De
p
a
rt
m
e
n
t,
F
a
c
u
lt
y
o
f
S
c
ie
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
S
u
a
n
S
u
n
a
n
d
h
a
Ra
jab
h
a
t
Un
iv
e
rsity
(
S
S
RU),
T
h
a
il
a
n
d
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
c
o
m
p
u
ter
g
ra
p
h
ics
,
im
a
g
e
p
ro
c
e
ss
in
g
,
a
rti
f
icia
l
in
telli
g
e
n
t,
b
i
o
m
e
tri
c
s,
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
,
so
f
t
c
o
m
p
u
ti
n
g
tec
h
n
iq
u
e
s
,
a
n
d
a
p
p
li
c
a
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
it
ti
k
h
u
n
.
m
e
@s
sru
.
a
c
.
th
.
Evaluation Warning : The document was created with Spire.PDF for Python.