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
8
,
No
.
1
,
A
p
r
il
20
2
5
,
p
p
.
64
9
~
65
6
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
8
.
i
1
.
pp
64
9
-
65
6
649
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Autom
a
ted
ha
nd
writing a
na
ly
sis
and perso
na
lity a
t
t
ribute
discernm
en
t
usin
g
self
-
a
tt
ention m
ulti
-
reso
lu
tion a
n
a
ly
sis
Ya
s
ho
m
a
t
i R
.
Dhum
a
l
1
,
Aru
nd
ha
t
i A
.
Sh
i
nd
e
2
,
Ro
s
h
na
de
v
i J
a
is
ing
Sa
pk
a
l
1
,
Sa
t
is
h B
ha
ira
nn
a
wa
r
3
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
T
e
l
e
c
o
mm
u
n
i
c
a
t
i
o
n
,
B
h
a
r
a
t
i
V
i
d
y
a
p
e
e
t
h
’
s
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
f
o
r
W
o
me
n
,
P
u
n
e
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
B
h
a
r
t
i
V
i
d
y
a
p
e
e
t
h
(
D
U
)
,
C
O
E,
P
u
n
e
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
S
D
M
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
D
h
a
r
w
a
d
,
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
Ma
y
4
,
2
0
2
4
R
ev
is
ed
Oct
7
,
2
0
2
4
Acc
ep
ted
Oct
3
0
,
2
0
2
4
Ha
n
d
writt
e
n
d
o
c
u
m
e
n
t
a
n
a
l
y
sis
i
s
a
m
e
th
o
d
u
se
d
in
a
c
a
d
e
m
ia
th
a
t
e
x
a
m
in
e
s
th
e
p
a
tt
e
rn
s
a
n
d
stro
k
e
s
o
f
a
p
e
rso
n
’
s
h
a
n
d
writi
n
g
in
o
rd
e
r
to
g
e
t
a
d
e
e
p
e
r
u
n
d
e
rsta
n
d
i
n
g
o
f
t
h
a
t
p
e
rso
n
’
s
p
e
rso
n
a
li
t
y
a
n
d
c
h
a
ra
c
ter.
In
sp
it
e
o
f
th
e
fa
c
t
th
a
t
th
e
re
a
re
a
n
u
m
b
e
r
o
f
m
o
d
e
ls
a
n
d
m
e
th
o
d
s
t
h
a
t
m
a
y
b
e
u
s
e
d
in
th
e
in
v
e
stig
a
t
io
n
o
f
a
u
t
o
m
a
ted
g
ra
p
h
o
lo
g
y
,
t
h
e
re
a
re
a
fe
w
c
h
a
ll
e
n
g
e
s
th
a
t
n
e
e
d
to
b
e
s
o
lv
e
d
.
Am
o
n
g
t
h
e
se
c
h
a
ll
e
n
g
e
s
is
th
e
id
e
n
ti
fica
ti
o
n
o
f
e
fficie
n
t
c
las
sifica
ti
o
n
te
c
h
n
iq
u
e
s
th
a
t
p
ro
v
id
e
th
e
h
ig
h
e
st
p
o
ss
ib
le
d
e
g
re
e
o
f
a
c
c
u
ra
c
y
.
Wi
th
i
n
t
h
e
sc
o
p
e
o
f
th
i
s
stu
d
y
,
we
p
r
o
p
o
se
a
u
to
m
a
ted
h
a
n
d
writi
n
g
a
n
a
ly
sis
a
n
d
p
e
rso
n
a
li
ty
a
tt
ri
b
u
t
e
d
isc
e
rn
m
e
n
t
u
sin
g
se
lf
-
a
tt
e
n
ti
o
n
m
u
lt
i
-
re
so
lu
ti
o
n
a
n
a
l
y
sis
(M
RA)
w
h
e
re
th
e
d
a
ta
is
p
re
p
ro
c
e
ss
e
d
u
si
n
g
h
isto
g
ra
m
e
q
u
a
li
z
a
ti
o
n
a
n
d
t
h
e
sp
u
rio
u
s
li
n
e
se
g
m
e
n
t
se
c
ti
o
n
is
a
tt
a
c
h
e
d
to
th
e
g
e
n
u
in
e
li
n
e
se
g
m
e
n
t
p
o
rti
o
n
in
o
r
d
e
r
t
o
se
g
m
e
n
t
t
h
e
su
c
c
e
e
d
in
g
li
n
e
fro
m
th
e
a
u
th
e
n
ti
c
p
ictu
re
o
f
t
h
e
d
o
c
u
m
e
n
t.
A
d
e
e
p
d
e
n
se
n
e
two
r
k
is
c
o
m
b
in
e
d
wit
h
se
lf
-
a
tt
e
n
ti
o
n
M
RA
i
n
o
rd
e
r
t
o
p
r
o
v
i
d
e
a
n
o
v
e
l
a
p
p
ro
a
c
h
to
t
h
e
in
v
e
stig
a
ti
o
n
o
f
a
u
th
e
n
ti
c
h
a
n
d
writt
e
n
tex
t.
Us
in
g
th
e
m
o
st
re
c
e
n
t
a
n
d
c
u
tt
in
g
-
e
d
g
e
sta
n
d
a
rd
s
th
a
t
a
re
c
u
rre
n
tl
y
i
n
u
s
e
,
a
n
e
v
a
lu
a
ti
o
n
is
p
e
rf
o
rm
e
d
to
d
e
term
in
e
wh
e
th
e
r
o
r
n
o
t
t
h
e
p
ro
p
o
se
d
st
ra
teg
y
is
fe
a
sib
le
.
It
is
o
b
se
rv
e
d
t
h
a
t
th
e
p
ro
p
o
se
d
m
e
th
o
d
o
b
tain
e
d
n
e
a
rly
9
8
%
a
c
c
u
ra
c
y
with
p
re
c
isio
n
o
f
9
9
%
.
K
ey
w
o
r
d
s
:
Attr
ib
u
te
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
Dee
p
d
en
s
e
n
etwo
r
k
Mu
ltire
s
o
lu
tio
n
a
n
aly
s
is
Per
s
o
n
ality
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
:
Yash
o
m
ati
R
.
Dh
u
m
al
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
T
elec
o
m
m
u
n
icatio
n
B
h
ar
ati
Vid
y
ap
ee
th
C
o
lleg
e
o
f
E
n
g
in
ee
r
i
n
g
f
o
r
W
o
m
en
Dh
an
k
awa
d
i,
Pu
n
e
,
I
n
d
ia
E
m
ail: y
ash
o
m
atid
h
u
m
al@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Gr
ap
h
o
lo
g
y
,
wh
ic
h
is
an
o
th
er
n
am
e
f
o
r
h
an
d
wr
itin
g
an
aly
s
is
,
is
a
p
r
o
ce
s
s
th
at
is
u
s
ef
u
l
f
o
r
id
en
tify
in
g
ce
r
tain
p
e
r
s
o
n
ality
tr
aits
th
at
ar
e
a
s
s
o
ciate
d
wi
th
a
p
ar
ticu
lar
in
d
iv
id
u
al.
I
t
i
s
p
o
s
s
ib
le
to
th
in
k
ab
o
u
t h
a
n
d
wr
itin
g
a
n
d
s
ig
n
atu
r
es a
s
v
is
u
al
r
ep
r
esen
tatio
n
s
th
at
ar
e
d
is
tin
g
u
is
h
ed
b
y
a
r
an
g
e
o
f
p
atter
n
s
.
T
h
ese
p
atter
n
s
m
ay
b
e
u
s
ed
f
o
r
a
v
ar
iety
o
f
r
ea
s
o
n
s
,
in
clu
d
i
n
g
th
e
p
r
ed
ictio
n
o
f
p
er
s
o
n
ality
ch
ar
ac
ter
is
tics
.
Han
d
wr
itin
g
an
aly
s
ts
,
wh
o
ar
e
also
o
f
ten
r
ef
er
r
ed
to
as
g
r
ap
h
o
lo
g
is
ts
,
ar
e
th
e
in
d
iv
id
u
als
wh
o
ar
e
r
esp
o
n
s
ib
le
f
o
r
an
aly
zin
g
th
e
h
a
n
d
wr
itin
g
o
f
a
p
er
s
o
n
in
o
r
d
e
r
to
d
r
aw
c
o
n
clu
s
io
n
s
ab
o
u
t th
e
p
s
y
ch
o
lo
g
ical
ch
ar
ac
ter
is
tics
o
f
th
e
wr
iter
b
ein
g
an
aly
ze
d
.
T
h
e
s
tu
d
y
o
f
h
an
d
wr
itin
g
,
wh
i
ch
is
o
f
ten
r
ef
er
r
e
d
to
as
g
r
ap
h
o
lo
g
y
,
is
a
s
u
b
f
ield
o
f
p
s
y
c
h
o
lo
g
y
th
at
s
ee
k
s
to
d
ec
ip
h
er
th
e
p
e
r
s
o
n
ality
tr
aits
,
p
o
in
ts
o
f
v
iew,
attitu
d
es,
an
d
f
ee
lin
g
s
t
h
at
ar
e
co
n
v
ey
e
d
v
ia
th
e
wr
itten
wo
r
d
s
o
f
an
in
d
iv
i
d
u
al.
I
n
ad
d
itio
n
,
it
s
ee
k
s
to
g
ain
an
u
n
d
er
s
tan
d
in
g
o
f
th
e
wa
y
s
in
wh
ich
th
e
s
ev
er
al
c
o
m
p
o
n
en
t
s
o
f
id
e
n
tity
in
ter
ac
t
with
o
n
e
an
o
th
e
r
to
p
r
o
d
u
ce
th
e
f
lu
i
d
s
tr
u
ctu
r
e
th
at
we
k
n
o
w
as
th
e
p
er
s
o
n
ality
o
f
t
h
e
wr
iter
.
I
n
o
r
d
er
t
o
id
en
tif
y
th
e
tr
aits
,
attr
ib
u
tes,
d
is
p
o
s
itio
n
s
,
em
o
tio
n
s
,
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
8
,
No
.
1
,
Ap
r
il
20
2
5
:
64
9
-
65
6
650
p
o
s
tu
r
es
th
at
ar
e
r
ef
lecte
d
in
a
p
er
s
o
n
’
s
wr
itin
g
,
g
r
ap
h
o
lo
g
is
ts
ex
am
in
e
th
e
h
an
d
wr
itin
g
o
f
th
at
in
d
iv
id
u
al
u
s
in
g
th
e
co
n
ce
p
ts
th
at
ar
e
d
e
r
iv
ed
f
r
o
m
m
ath
em
atica
l g
r
ap
h
o
lo
g
y
t
h
eo
r
y
.
Mc
Nich
o
l
an
d
Nelso
n
[
1
]
also
m
ak
e
an
ef
f
o
r
t
t
o
ap
p
r
ec
iat
e
h
o
w
th
e
d
if
f
er
e
n
t
co
m
p
o
n
e
n
ts
o
f
a
n
in
d
iv
id
u
al
’
s
id
en
tity
m
ig
h
t
c
o
m
e
to
g
eth
er
to
f
o
r
m
th
e
i
n
tr
icate
s
tr
u
c
tu
r
e
th
at
we
r
ef
er
to
as
th
e
wr
iter
’
s
p
er
s
o
n
ality
.
T
h
ese
co
m
p
o
n
en
ts
ar
e
d
is
cu
s
s
ed
in
m
o
r
e
d
et
ail
b
elo
w.
On
e
o
f
th
e
o
u
tco
m
es
o
f
th
e
r
esear
ch
co
n
d
u
cte
d
o
n
th
e
h
an
d
wr
itin
g
o
f
p
atien
ts
with
m
en
tal
d
is
o
r
d
er
s
[
2
]
was
th
e
cr
ea
tio
n
o
f
a
p
er
s
o
n
ality
in
v
en
to
r
y
.
Sp
ec
if
ic
c
h
ar
ac
ter
i
s
tics
o
f
an
in
d
i
v
id
u
al
’
s
p
e
r
s
o
n
ality
m
ig
h
t
b
e
em
p
lo
y
ed
i
n
o
r
d
er
to
id
en
tif
y
b
etwe
en
th
e
v
ar
io
u
s
ty
p
es
o
f
h
an
d
wr
itin
g
.
I
n
th
e
a
r
ea
o
f
i
d
en
tific
atio
n
,
s
ig
n
atu
r
es
ar
e
o
f
t
en
u
s
ed
as
a
m
ea
n
s
o
f
d
is
tin
g
u
is
h
in
g
d
if
f
er
e
n
t
in
d
iv
id
u
als
f
r
o
m
o
n
e
an
o
th
e
r
.
T
h
er
e
a
r
e
a
n
u
m
b
er
o
f
way
s
[
3
]
,
[
4
]
in
wh
ich
s
ig
n
atu
r
es
m
ay
b
e
r
ec
o
g
n
ized
,
in
clu
d
in
g
th
e
ex
is
ten
ce
o
f
d
o
ts
,
s
tr
ea
k
s
,
f
o
r
m
s
,
o
r
lo
wer
li
n
es
th
at
r
esem
b
le
a
s
h
ell.
I
t
is
p
o
s
s
ib
le
th
at
th
e
g
r
ap
h
o
lo
g
y
in
s
p
ec
tio
n
p
r
o
ce
d
u
r
e
will
tak
e
a
s
ig
n
if
ican
t
am
o
u
n
t
o
f
t
im
e
if
it
is
ca
r
r
ied
o
u
t
m
an
u
ally
.
Ad
d
itio
n
ally
,
th
e
s
u
cc
ess
o
f
th
e
h
an
d
wr
itin
g
an
aly
s
is
[
5
]
-
[
7
]
is
d
ir
e
ctly
p
r
o
p
o
r
tio
n
al
t
o
th
e
lev
el
o
f
e
x
p
er
tis
e
h
ad
b
y
th
e
an
aly
s
t
at
th
e
tim
e.
Desp
ite
th
e
f
ac
t
th
at
it
h
as
b
ee
n
s
h
o
wn
th
at
in
clu
d
i
n
g
p
er
s
o
n
s
in
th
e
p
r
o
ce
s
s
o
f
an
a
ly
zin
g
h
an
d
wr
itin
g
m
a
y
b
e
b
en
ef
icial,
it
is
ess
en
tial
to
k
e
ep
in
m
in
d
th
at
th
is
ap
p
r
o
ac
h
m
ay
b
e
b
o
th
ex
p
en
s
iv
e
an
d
ta
x
in
g
o
n
th
e
b
o
d
y
.
I
n
th
e
co
n
tex
t
o
f
o
n
lin
e
h
an
d
wr
itin
g
r
ec
o
g
n
itio
n
,
th
ese
f
ea
t
u
r
es
in
clu
d
e
th
e
p
r
ess
u
r
e
th
at
is
ap
p
lied
d
u
r
in
g
s
tr
o
k
es,
th
e
m
an
n
er
in
wh
ich
ce
r
tain
letter
s
ar
e
cr
e
ated
th
at
ar
e
id
en
tifie
d
,
s
u
ch
as
th
e
tr
ajec
to
r
y
o
f
wr
itin
g
.
I
n
s
p
ite
o
f
t
h
e
f
ac
t
th
at
th
er
e
ar
e
a
n
u
m
b
er
o
f
m
o
d
els
an
d
ap
p
r
o
ac
h
es
av
ail
ab
le
in
t
h
e
ar
ea
o
f
au
to
m
ated
g
r
ap
h
o
lo
g
y
s
tu
d
y
,
th
er
e
a
r
e
a
n
u
m
b
er
o
f
p
r
o
b
lem
s
th
at
n
ee
d
to
b
e
s
o
lv
e
d
.
T
o
a
d
d
r
ess
th
ese
p
r
o
b
lem
s
,
it
is
n
ec
ess
ar
y
to
p
i
ck
ac
ce
p
tab
le
p
r
e
-
p
r
o
ce
s
s
in
g
ap
p
r
o
ac
h
es
an
d
im
ag
e
p
r
o
ce
s
s
in
g
alg
o
r
ith
m
s
f
o
r
th
e
ex
tr
ac
tio
n
o
f
h
a
n
d
wr
itin
g
ch
ar
ac
ter
is
tics
.
Ad
d
itio
n
all
y
,
it
is
n
ec
ess
ar
y
to
s
elec
t
p
r
o
p
er
class
if
icatio
n
s
tr
ateg
ies
in
o
r
d
er
t
o
ac
h
iev
e
th
e
h
ig
h
est
p
o
s
s
ib
le
lev
el
o
f
ac
c
u
r
ac
y
.
Fu
r
th
e
r
m
o
r
e,
th
er
e
is
a
c
o
n
n
ec
ti
o
n
b
etwe
en
p
er
s
o
n
ality
f
ea
tu
r
es
an
d
a
v
ar
iety
o
f
asp
ec
ts
o
f
life
,
s
u
ch
as,
b
u
t
n
o
t
lim
ited
to
,
th
e
p
r
o
g
r
ess
o
f
o
n
e
’
s
ca
r
ee
r
[
8
]
,
[
9
]
,
t
h
e
p
r
o
v
is
io
n
o
f
in
d
iv
id
u
alize
d
m
e
d
ical
tr
ea
t
m
en
t
[
1
0
]
,
a
n
d
th
e
p
r
esen
ce
o
f
p
h
y
s
ical
d
is
o
r
d
er
s
ac
co
m
p
an
ied
b
y
p
s
y
ch
o
lo
g
ica
l sy
m
p
to
m
s
[
1
1
]
,
[
1
2
]
.
I
n
lig
h
t
o
f
th
e
p
r
o
b
lem
s
th
at
wer
e
b
r
o
u
g
h
t
u
p
b
e
f
o
r
e,
o
u
r
g
o
al
is
to
d
ev
elo
p
a
s
y
s
tem
th
at
is
ca
p
ab
le
o
f
id
e
n
ti
f
y
in
g
p
er
s
o
n
ality
att
r
ib
u
tes
o
f
a
p
e
r
s
o
n
b
y
a
n
aly
zin
g
th
eir
h
an
d
wr
itten
p
atter
n
s
.
A
m
eth
o
d
f
o
r
ev
alu
atin
g
ex
am
p
les o
f
h
an
d
w
r
itten
wr
itin
g
th
at
h
av
e
b
ee
n
o
b
tain
ed
f
r
o
m
r
ea
l
-
wo
r
ld
s
itu
atio
n
s
is
p
r
esen
ted
in
th
is
s
tu
d
y
.
T
h
is
m
eth
o
d
m
ak
es
u
s
e
o
f
th
e
m
o
s
t
r
ec
en
t
te
ch
n
ical
b
r
ea
k
th
r
o
u
g
h
s
.
I
n
o
r
d
er
to
id
en
tify
th
e
p
ar
ticu
lar
b
eh
av
i
o
r
al
p
atter
n
s
th
at
ar
e
ass
o
ciate
d
w
ith
th
e
p
er
s
o
n
,
th
e
an
aly
s
is
is
ca
r
r
i
ed
o
u
t
o
n
s
p
ec
if
ic
p
o
r
tio
n
s
o
f
th
e
d
ata.
C
h
ar
ac
t
er
is
tics
o
f
a
p
er
s
o
n
’
s
d
is
p
o
s
itio
n
ar
e
u
n
ch
a
n
g
in
g
an
d
tim
eless
.
Alt
h
o
u
g
h
th
e
ac
tiv
ities
th
o
s
e
in
d
iv
id
u
als
en
g
ag
e
in
ch
an
g
e
d
ep
e
n
d
in
g
o
n
th
e
cir
cu
m
s
tan
ce
s
in
wh
ich
th
ey
f
in
d
th
em
s
elv
es,
th
er
e
is
alwa
y
s
s
o
m
e
u
n
d
er
ly
in
g
p
atter
n
th
at
r
e
v
ea
ls
th
e
tr
u
e
n
atu
r
e
o
f
th
e
in
d
iv
id
u
al.
Per
s
o
n
’
s
b
eh
a
v
io
r
is
im
m
ed
iately
in
f
lu
en
ce
d
b
y
th
e
tr
aits
th
at
th
ey
p
r
esen
t
to
th
e
wo
r
ld
.
I
t
is
p
o
s
s
ib
le
to
d
ef
in
e
ch
ar
ac
ter
is
tics
in
a
n
u
m
b
er
o
f
d
if
f
er
en
t
wa
y
s
.
T
h
er
e
is
a
wid
esp
r
ea
d
co
n
s
en
s
u
s
th
at
p
s
y
ch
o
lo
g
y
,
wh
ic
h
is
th
e
s
tu
d
y
o
f
th
e
m
in
d
an
d
h
u
m
a
n
b
eh
a
v
io
r
,
is
an
in
co
n
s
is
ten
t
s
cien
tific
d
is
cip
lin
e
.
An
in
d
iv
id
u
al
’
s
ab
ilit
y
to
r
e
co
g
n
ize
th
eir
o
wn
u
n
iq
u
e
n
ess
is
o
n
e
o
f
th
e
f
ew
way
s
to
g
et
en
tr
y
to
th
is
r
ea
lm
.
T
h
e
u
s
e
o
f
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs)
h
as b
ee
n
u
s
ed
b
y
Sin
g
h
et
a
l.
[
1
3
]
in
o
r
d
er
to
ex
p
e
d
ite
th
e
p
r
o
ce
s
s
o
f
id
en
tify
in
g
e
s
s
en
tial p
er
s
o
n
al
ity
ch
ar
ac
ter
is
tics
v
ia
th
e
an
aly
s
is
o
f
g
r
ap
h
o
lo
g
y
(
h
a
n
d
wr
itin
g
)
.
T
h
e
u
s
e
o
f
a
tr
an
s
f
o
r
m
er
-
b
ased
(
T
B
)
tech
n
o
lo
g
y
was
th
e
b
asis
f
o
r
th
e
u
n
iq
u
e
m
eth
o
d
f
o
r
p
er
s
o
n
ality
ass
ess
m
en
t
th
at
was
p
r
esen
ted
b
y
Dh
u
m
al
et
a
l.
[
1
4
]
.
T
h
e
co
n
v
en
tio
n
al
m
eth
o
d
s
o
f
in
f
o
r
m
ati
o
n
ex
tr
ac
ti
o
n
o
f
ten
in
clu
d
e
th
e
u
s
e
o
f
a
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)n
etwo
r
k
,
f
o
llo
wed
b
y
s
ig
n
atu
r
e
-
b
ased
s
tr
u
ctu
r
al
r
ep
r
esen
tatio
n
o
f
t
h
e
tex
tu
al
co
n
ten
t.
Ho
wev
er
,
o
u
r
m
eth
o
d
o
l
o
g
y
r
em
o
v
es b
o
t
h
s
tep
s
o
f
th
e
p
r
o
ce
s
s
.
T
h
e
m
eth
o
d
in
[
1
5
]
in
tr
o
d
u
ce
d
f
r
esh
m
e
th
o
d
s
f
o
r
d
etec
tin
g
ess
en
tial
p
er
s
o
n
ality
ch
ar
ac
ter
is
tics
v
ia
th
e
u
s
e
o
f
g
r
ap
h
o
lo
g
ical
an
al
y
s
is
.
I
n
o
r
d
er
to
ac
co
m
p
lis
h
t
h
is
o
b
jectiv
e,
th
ey
tr
ain
ed
th
r
ee
v
is
u
al
g
eo
m
etr
y
g
r
o
u
p
-
16
(
VGG1
6
)
C
NNs
b
y
m
ak
in
g
u
s
e
o
f
a
d
ata
b
ase
th
at
in
clu
d
ed
ex
a
m
p
les
o
f
h
an
d
wr
i
tt
en
tex
t.
T
h
e
wo
r
k
p
r
esen
ted
in
[
1
6
]
aim
ed
to
estab
lis
h
a
r
eliab
le
ap
p
r
o
ac
h
f
o
r
id
e
n
tify
in
g
p
er
s
o
n
alit
y
ch
ar
ac
ter
is
tics
in
h
an
d
wr
itin
g
s
am
p
les.
T
h
eir
e
f
f
o
r
ts
wer
e
f
o
cu
s
ed
o
n
d
ev
elo
p
in
g
th
is
m
eth
o
d
.
I
m
ag
e
p
r
o
c
ess
in
g
an
d
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
th
at
ar
e
c
o
n
s
id
er
ed
to
b
e
cu
ttin
g
ed
g
e
co
n
tr
ib
u
te
to
th
e
ac
h
iev
e
m
en
t
o
f
th
is
o
b
jectiv
e.
So
m
e
o
f
th
ese
tech
n
iq
u
es
in
clu
d
e
f
ilter
in
g
,
th
r
esh
o
ld
in
g
,
an
d
n
o
r
m
aliza
tio
n
.
T
h
e
w
o
r
k
in
[
1
7
]
u
s
ed
a
s
y
s
tem
atic
ap
p
r
o
ac
h
to
ex
tr
a
c
tin
g
im
p
o
r
tan
t
f
ea
tu
r
es
f
r
o
m
t
h
ese
s
ig
n
als.
Acc
o
r
d
in
g
to
th
e
f
in
d
in
g
s
o
f
t
h
eir
r
esear
ch
,
th
er
e
is
a
s
ig
n
if
ican
t
co
n
n
ec
tio
n
b
etwe
en
th
ese
ch
ar
ac
ter
is
tics
an
d
th
e
d
is
tr
ess
-
r
elate
d
s
en
s
atio
n
s
o
f
h
o
p
eless
n
ess
,
an
x
iety
,
an
d
s
tr
ess
.
I
n
o
r
d
er
to
class
if
y
t
h
e
attr
ib
u
te
v
ec
to
r
s
th
at
h
a
v
e
b
ee
n
c
r
ea
ted
,
a
b
id
ir
ec
t
io
n
al
-
L
STM
(
B
iLST
M)
n
etwo
r
k
is
tak
en
in
to
co
n
s
id
er
atio
n
.
Sati
an
d
Ku
m
ar
[
1
8
]
p
r
o
p
o
s
es
a
u
n
iq
u
e
m
o
d
el
f
o
r
an
al
y
zin
g
p
e
r
s
o
n
ality
f
ea
tu
r
es
an
d
q
u
alities
b
ased
o
n
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
o
lo
g
ies
ap
p
lied
to
h
an
d
wr
itin
g
s
am
p
les.
T
h
e
m
o
d
el
an
aly
s
es
th
e
h
an
d
wr
itin
g
s
am
p
les
o
f
in
d
i
v
id
u
als.
Gh
o
s
h
et
a
l.
[
1
9
]
,
p
r
o
p
o
s
ed
an
alg
o
r
ith
m
ic
tech
n
iq
u
e
to
id
en
tif
y
in
g
h
u
m
a
n
b
eh
av
io
r
b
ased
o
n
h
a
n
d
wr
itten
E
n
g
lis
h
letter
s
f
r
o
m
a
to
z
th
at
ar
e
lo
wer
ca
s
e.
I
n
o
r
d
er
to
f
o
r
m
u
late
a
h
y
p
o
th
esis
,
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
y
i
n
v
o
lv
es
ex
tr
ac
tin
g
s
tr
u
ctu
r
al
elem
en
ts
f
r
o
m
v
ar
i
o
u
s
r
eg
io
n
s
o
f
in
d
iv
id
u
al
ch
ar
ac
ter
im
ag
es.
T
h
e
d
ictio
n
ar
y
o
f
g
r
a
p
h
o
lo
g
ical
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
A
u
to
ma
ted
h
a
n
d
w
r
itin
g
a
n
a
ly
s
is
a
n
d
p
ers
o
n
a
lity a
ttr
ib
u
te
d
i
s
ce
r
n
men
t u
s
in
g
…
(
Ya
s
h
o
ma
t
i R
.
Dh
u
ma
l
)
651
p
r
in
cip
les
is
u
s
ed
to
ac
co
m
p
li
s
h
th
is
.
T
h
e
co
n
ce
p
t
th
at
em
er
g
ed
f
r
o
m
th
is
p
r
o
ce
s
s
m
ay
b
e
u
s
ed
to
class
if
y
th
e
d
is
tin
ctiv
e
tr
aits
o
f
a
p
er
s
o
n
,
in
ad
d
i
tio
n
to
th
eir
p
o
s
itiv
e
a
n
d
b
a
d
s
o
cial
attr
ib
u
tes.
R
ah
m
an
an
d
Halim
[
2
0
]
p
u
t
f
o
r
war
d
th
e
c
o
n
n
ec
tio
n
b
etwe
en
a
p
er
s
o
n
’
s
tem
p
er
a
m
en
t
an
d
th
e
attr
i
b
u
tes
o
f
h
is
h
an
d
wr
itin
g
.
T
h
e
id
en
tific
atio
n
o
f
a
p
er
s
o
n
’
s
d
is
p
o
s
itio
n
class
if
icatio
n
v
ia
th
e
u
s
e
o
f
th
eir
d
is
tin
ct
wr
itin
g
s
ty
le
an
d
o
r
g
an
izatio
n
al
te
n
d
en
cies m
ay
b
e
ac
co
m
p
lis
h
ed
th
r
o
u
g
h
th
e
u
s
e
o
f
a
m
eth
o
d
k
n
o
wn
as
h
an
d
wr
itin
g
an
aly
s
is
.
T
h
e
o
u
tco
m
e
o
f
th
e
s
u
r
v
e
y
i
m
p
lies
m
an
y
er
r
o
r
s
in
th
e
g
en
er
ated
tex
t
r
esu
lt
f
r
o
m
t
h
e
s
y
s
tem
’
s
im
p
r
o
p
e
r
in
ter
p
r
etatio
n
o
f
th
e
h
an
d
wr
itin
g
.
T
h
is
lead
to
n
o
n
s
en
s
e,
m
is
p
r
o
n
o
u
n
ce
d
wo
r
d
s
,
o
r
m
is
in
ter
p
r
eted
ch
ar
ac
ter
s
th
at
o
v
e
r
lap
,
ex
tr
e
m
ely
s
ty
led
h
an
d
wr
itin
g
,
o
r
l
o
w
im
ag
e
q
u
ality
ca
n
all
lea
d
to
m
is
id
en
tific
atio
n
.
T
h
is
o
cc
u
r
r
e
d
if
th
e
s
y
s
tem
’
s
alg
o
r
ith
m
is
n
’
t
s
u
itab
le
f
o
r
th
e
task
,
th
e
h
an
d
wr
itin
g
is
to
o
illeg
ib
le,
o
r
th
e
i
n
p
u
t
im
ag
e
is
ex
ce
s
s
iv
ely
d
is
to
r
ted
.
Fo
r
e
v
er
y
ch
ar
ac
ter
o
r
p
h
r
ase
th
at
is
d
etec
ted
,
s
ev
er
al
h
an
d
wr
itin
g
r
ec
o
g
n
itio
n
p
r
o
g
r
a
m
s
in
clu
d
e
co
n
f
i
d
en
ce
lev
els
th
at
s
h
o
w
h
o
w
lik
el
y
it
is
th
at
th
e
r
ec
o
g
n
itio
n
is
ac
cu
r
ate.
B
etter
p
o
s
t
-
p
r
o
ce
s
s
in
g
o
r
h
u
m
a
n
in
s
p
ec
ti
o
n
is
m
ad
e
p
o
s
s
ib
le
as
a
r
esu
lt.
T
h
is
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
ws:
s
ec
tio
n
2
d
escr
ib
es
th
e
p
r
o
p
o
s
ed
m
eth
o
d
.
I
n
s
ec
tio
n
3
th
e
r
esu
lts
ar
e
d
is
cu
s
s
ed
.
Fin
ally
,
th
e
co
n
cl
u
s
io
n
with
f
u
tu
r
e
wo
r
k
is
d
is
cu
s
s
ed
in
s
ec
tio
n
4
.
2.
M
E
T
H
O
D
As
a
r
esu
lt
o
f
th
e
f
ac
t
t
h
at
th
e
ap
p
r
o
ac
h
we
h
av
e
s
h
o
wn
in
Fi
g
u
r
e
1
is
b
ased
o
n
th
e
ass
u
m
p
t
io
n
th
at
a
p
ar
ticu
lar
h
an
d
wr
itten
d
o
c
u
m
en
t
h
as
b
ee
n
co
r
r
ec
tly
s
ca
n
n
e
d
,
it
o
n
ly
tak
es
in
to
c
o
n
s
id
er
atio
n
th
e
s
k
ew
th
at
was
im
p
o
s
ed
b
y
u
s
.
T
h
r
o
u
g
h
o
u
t
th
e
en
tire
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase,
a
n
u
m
b
e
r
o
f
d
if
f
er
en
t
im
ag
e
p
r
o
ce
s
s
in
g
m
eth
o
d
s
,
s
u
ch
as
a
tech
n
iq
u
e
ca
lled
h
is
to
g
r
am
e
q
u
aliza
tio
n
,
wh
er
e
o
n
e
ca
n
en
h
a
n
ce
an
im
ag
e
’
s
b
r
ig
h
tn
ess
an
d
co
n
tr
ast
b
y
r
ed
is
tr
ib
u
tin
g
th
e
in
t
en
s
ities
o
f
its
p
ix
els
h
a
v
e
b
ee
n
u
s
ed
.
T
h
e
p
r
im
ar
y
o
b
jectiv
e
o
f
th
is
is
to
d
eter
m
in
e
th
e
p
a
r
ticu
lar
h
eig
h
ts
o
f
r
is
in
g
s
eg
m
e
n
ts
an
d
to
co
u
n
t
t
h
e
n
u
m
b
e
r
o
f
as
ce
n
d
in
g
s
eg
m
en
ts
.
B
y
tak
in
g
th
e
a
v
er
ag
e
o
f
th
e
clim
b
s
th
at
co
m
e
b
ef
o
r
e
t
h
e
th
r
esh
o
ld
,
th
e
h
eig
h
t
o
f
t
h
e
th
r
esh
o
ld
m
a
y
b
e
d
eter
m
in
ed
.
Fig
u
r
in
g
o
u
t
if
th
e
h
eig
h
t
o
f
ea
ch
r
is
in
g
c
o
m
p
o
n
en
t
is
m
o
r
e
t
h
an
o
r
eq
u
al
t
o
th
e
lim
it
th
at
h
as
b
ee
n
estab
lis
h
ed
.
I
t
is
p
o
s
s
ib
le
to
ac
cu
r
ately
ex
tr
ac
t
th
e
lin
e
f
r
o
m
th
e
b
i
n
ar
y
d
o
cu
m
e
n
t
p
ictu
r
e
b
y
m
a
k
in
g
u
s
e
o
f
th
e
r
is
in
g
a
r
ea
o
f
th
e
h
o
r
i
zo
n
tal
h
is
to
g
r
am
,
p
r
o
v
id
e
d
t
h
at
th
e
p
r
ed
eter
m
in
e
d
co
n
d
iti
o
n
s
ar
e
tak
e
n
in
to
co
n
s
id
er
atio
n
.
I
t
is
p
o
s
s
ib
le
th
at
th
e
r
is
in
g
ar
ea
will
b
e
d
is
r
eg
ar
d
ed
as
a
co
m
p
o
n
en
t
o
f
th
e
lin
e
th
at
i
s
m
ea
n
in
g
less
if
th
e
c
r
iter
ia
th
a
t
h
as
b
ee
n
s
tated
is
n
o
t
s
at
is
f
ied
.
T
h
ese
im
a
g
in
ar
y
r
is
in
g
p
a
r
ts
ar
e
m
o
s
t
lik
ely
th
e
r
esu
lt
o
f
t
h
e
ju
n
ctio
n
o
f
two
s
tr
o
k
es
o
r
a
b
ar
e
x
is
tin
g
in
a
n
u
p
p
er
ca
s
e
c
h
ar
ac
ter
.
I
t
is
p
o
s
s
ib
le
to
h
av
e
b
o
t
h
o
u
tco
m
es.
Nex
t,
lin
e
s
eg
m
en
t
atio
n
is
p
er
f
o
r
m
e
d
w
h
er
e
t
h
e
h
an
d
wr
itin
g
p
ictu
r
e
was
th
u
s
d
i
v
id
ed
in
to
two
d
is
tin
ct
s
ec
tio
n
s
:
th
e
s
cr
ip
t
r
e
g
io
n
an
d
th
e
s
ig
n
atu
r
e
r
e
g
io
n
.
B
o
th
o
f
th
ese
r
eg
io
n
s
wo
r
k
ed
in
d
ep
en
d
en
tly
o
f
o
n
e
an
o
th
er
.
I
t
is
v
ia
th
e
ap
p
licatio
n
o
f
th
e
p
r
ed
eter
m
i
n
ed
w
r
itin
g
p
r
ess
u
r
e
th
at
th
e
li
n
es
o
f
tex
t
ar
e
r
etr
iev
e
d
f
r
o
m
th
e
b
in
ar
y
d
o
c
u
m
en
t
p
ic
tu
r
e.
W
e
p
r
o
v
i
d
e
an
im
p
r
o
v
e
d
m
eth
o
d
f
o
r
h
o
r
izo
n
tally
p
r
o
jectin
g
p
h
o
t
o
g
r
a
p
h
s
to
s
ep
ar
ate
lin
es
o
f
tex
t
i
n
t
h
is
m
o
s
t
r
ec
en
t
p
iece
o
f
r
ese
ar
ch
b
ee
n
p
u
b
lis
h
ed
.
T
h
e
v
e
r
tical
s
eg
m
en
tatio
n
p
r
o
ce
s
s
b
eg
in
s
b
y
d
iv
id
i
n
g
an
im
ag
e
in
to
th
r
ee
d
is
tin
ct
p
ar
t
s
b
e
f
o
r
e
m
o
v
i
n
g
o
n
to
th
e
n
e
x
t
s
tep
.
A
th
o
r
o
u
g
h
ex
am
in
atio
n
an
d
ev
alu
atio
n
o
f
th
e
p
ag
e
m
ar
g
i
n
s
o
n
eith
er
s
id
e
o
f
th
e
p
ictu
r
e
is
ca
r
r
ied
o
u
t
b
y
th
is
tech
n
iq
u
e.
On
th
e
o
th
er
h
an
d
,
an
e
x
am
in
atio
n
o
f
th
e
lin
e
s
p
ac
in
g
is
ca
r
r
ied
o
u
t
o
n
th
e
le
f
t
s
id
e
o
f
th
e
p
ag
e.
W
h
en
d
o
in
g
h
o
r
izo
n
tal
s
eg
m
en
tatio
n
,
th
e
f
ir
s
t
s
tep
is
to
d
iv
id
e
an
im
ag
e
i
n
to
th
ir
d
s
an
d
th
en
t
h
e
n
e
x
t
s
tep
is
to
co
n
ce
n
tr
at
e
o
n
th
e
ar
ea
th
at
co
n
tai
n
s
th
e
m
id
d
le
th
ir
d
.
Fig
u
r
e
1
.
Ar
c
h
itectu
r
e
o
f
i
n
ten
d
ed
s
y
s
tem
T
h
e
id
en
tific
atio
n
o
f
lin
e
s
eg
m
en
ts
in
s
id
e
an
im
ag
e
is
m
ad
e
p
o
s
s
ib
le
as
a
r
esu
lt
o
f
th
is
.
T
h
e
x
an
d
y
co
o
r
d
in
ates
ar
e
p
o
s
itio
n
ed
at
th
e
to
p
lef
t
co
r
n
er
an
d
b
o
tto
m
r
ig
h
t
co
r
n
er
o
f
th
e
b
o
x
r
esp
e
ctiv
ely
.
T
h
is
is
th
e
f
ir
s
t
s
tep
.
Af
ter
d
eter
m
in
in
g
t
h
e
v
alu
e
o
f
th
e
b
lack
p
ix
el,
d
esig
n
ated
b
y
th
e
letter
x
,
cr
o
p
X1
will
b
e
s
to
r
ed
.
Fo
llo
win
g
th
is
,
co
n
tin
u
e
s
ea
r
ch
in
g
f
o
r
x
u
n
til
th
er
e
ar
e
n
o
m
o
r
e
b
lack
p
ix
els
th
at
h
av
e
n
o
t
b
ee
n
f
o
u
n
d
.
C
r
o
p
X2
’
s
y
-
a
x
is
h
as
to
b
e
s
h
if
ted
to
t
h
e
p
o
i
n
t
th
at
is
th
e
f
u
r
th
est
to
t
h
e
r
ig
h
t.
Fo
r
C
r
o
p
Y1
an
d
C
r
o
p
Y
2
,
r
ep
ea
t
th
is
p
r
o
ce
s
s
,
s
tar
tin
g
at
th
e
b
o
tto
m
an
d
wo
r
k
in
g
y
o
u
r
way
u
p
.
T
h
e
m
et
h
o
d
d
escr
ib
ed
ab
o
v
e
was
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
8
,
No
.
1
,
Ap
r
il
20
2
5
:
64
9
-
65
6
652
u
tili
ze
d
s
o
as
to
ca
teg
o
r
ize
an
ex
ten
s
iv
e
r
a
n
g
e
o
f
d
i
f
f
er
e
n
tiated
co
m
p
o
n
en
ts
,
s
u
ch
a
s
d
o
m
in
an
ce
z
o
n
es,
b
aselin
e
p
atter
n
s
,
an
d
in
ter
-
wo
r
d
g
ap
s
,
a
m
o
n
g
s
t
o
th
er
th
in
g
s
.
T
h
e
ap
p
r
o
ac
h
th
at
m
ay
b
e
co
n
s
id
er
e
d
as
a
s
u
cc
ess
io
n
o
f
co
n
s
ec
u
tiv
e
esti
m
atio
n
s
o
f
a
g
iv
e
n
f
u
n
ctio
n
,
f
(
t)
,
d
o
n
e
at
v
ar
io
u
s
lev
els
o
f
r
e
s
o
lu
tio
n
is
r
ef
er
r
ed
to
as
“
m
u
ltire
s
o
lu
tio
n
an
aly
s
is
”
(
MRA)
in
th
is
ap
p
licatio
n
[
2
1
]
.
T
o
p
u
t
it
an
o
th
er
way
,
M
R
A
m
ay
b
e
s
ee
n
as
a
s
er
ies
o
f
co
n
s
ec
u
tiv
e
esti
m
a
tio
n
s
o
f
a
ce
r
tain
f
u
n
ctio
n
.
I
n
o
r
d
er
to
ex
p
lain
an
ap
p
r
o
x
im
a
tio
n
o
f
a
f
u
n
ctio
n
f
(
t)
th
at
h
as
a
r
eso
lu
tio
n
o
f
2
j
,
th
e
ter
m
“
o
r
th
o
g
o
n
al
p
r
o
jectio
n
o
f
f
(
t)
o
n
a
s
u
b
s
p
ac
e
Vj
”
is
u
s
ed
.
A
s
u
cc
ess
f
u
l
u
s
e
o
f
th
e
MRA
ap
p
r
o
ac
h
h
a
s
b
ee
n
u
s
ed
in
p
r
ac
tice.
E
v
e
n
if
th
e
eq
u
atio
n
s
h
a
v
e
n
o
t
b
ee
n
co
n
v
er
ted
in
to
m
atr
ix
eq
u
atio
n
s
,
it
is
s
till
p
o
s
s
ib
le
to
co
r
r
ec
tly
h
an
d
le
th
e
m
in
r
ea
l
s
p
ac
e.
W
h
en
u
s
ed
w
h
ile
s
o
lv
in
g
in
teg
r
al
an
d
p
ar
tial
d
if
f
e
r
en
tial
eq
u
ati
o
n
s
,
th
e
ter
m
MRA
r
ef
er
s
to
a
n
u
m
er
ical
f
r
a
m
ewo
r
k
th
at
is
as
f
lex
ib
le
a
s
p
o
s
s
ib
le.
T
h
e
ap
p
licatio
n
s
o
f
t
h
is
p
ar
ad
ig
m
,
in
p
a
r
ticu
lar
,
h
a
v
e
s
h
o
wn
to
b
e
b
e
n
ef
icial
in
t
h
e
f
ield
s
o
f
p
h
y
s
ic
s
an
d
ch
em
is
tr
y
.
T
h
r
o
u
g
h
t
h
e
u
s
e
o
f
MRA,
it
is
p
o
s
s
ib
le
t
o
co
n
s
tr
u
ct
an
o
r
th
o
n
o
r
m
al
f
r
am
ewo
r
k
th
at
h
as
ad
ap
tiv
e
r
eso
lu
tio
n
an
d
th
e
p
o
s
s
ib
ilit
y
f
o
r
co
n
s
is
ten
t
im
p
r
o
v
em
en
t.
As
a
co
n
s
eq
u
en
ce
o
f
th
is
,
th
e
lev
el
o
f
p
r
ec
is
io
n
th
at
ca
n
b
e
ac
co
m
p
lis
h
ed
v
ia
th
e
u
s
e
o
f
th
is
tech
n
o
lo
g
y
is
n
o
t e
s
p
ec
ially
e
x
ten
s
iv
e
[
2
2
]
.
W
h
en
th
e
d
etail
co
ef
f
icien
ts
ex
h
ib
it
o
s
cillato
r
y
b
eh
a
v
io
r
,
s
u
ch
as
th
at
wh
ich
is
in
d
u
ce
d
b
y
a
d
en
s
ity
wav
e,
it
is
s
im
p
le
to
d
eter
m
in
e
th
e
s
ig
n
if
ican
ce
o
f
ce
r
tain
s
ig
n
al
f
r
eq
u
e
n
cies.
T
h
is
is
b
ec
a
u
s
e
th
e
o
s
cillatio
n
s
o
cc
u
r
i
n
clo
s
e
p
r
o
x
im
ity
to
t
h
e
f
r
e
q
u
en
cies
th
at
ar
e
o
f
in
t
er
est.
T
h
e
o
s
cillatio
n
s
ar
e
ca
u
s
ed
b
y
th
e
d
en
s
ity
wav
e,
wh
ich
is
th
e
r
ea
s
o
n
b
e
h
in
d
th
is
.
Utilizin
g
th
e
h
ig
h
est
p
er
m
is
s
ib
le
v
alu
e
in
th
e
d
et
ail
co
ef
f
icien
ts
m
ay
b
e
o
f
ass
is
tan
ce
in
th
e
p
r
o
ce
s
s
o
f
tr
a
n
s
ien
t
d
etec
tio
n
.
T
h
is
is
d
u
e
to
t
h
e
f
ac
t
t
h
at
it
en
ab
les
r
o
u
te
tr
ac
in
g
ac
r
o
s
s
s
ev
er
al
lev
els o
f
s
ig
n
al
d
ec
o
m
p
o
s
itio
n
.
I
t is n
ec
ess
ar
y
f
o
r
th
er
e
to
b
e
r
eg
u
lar
ity
in
th
e
wav
elet
in
o
r
d
er
to
g
et
a
s
ig
n
if
ican
t
lev
el
o
f
ac
c
u
r
ate
tr
an
s
ien
t
id
en
tif
icatio
n
[
2
3
]
.
T
h
e
f
ield
o
f
d
ata
s
cien
ce
k
n
o
wn
as
d
ee
p
lear
n
in
g
is
s
ee
in
g
a
r
ate
o
f
e
x
p
an
s
io
n
th
a
t
h
as
n
ev
er
b
ee
n
s
ee
n
b
ef
o
r
e
.
Dee
p
lear
n
in
g
r
ef
e
r
s
to
a
co
lle
ctio
n
o
f
alg
o
r
ith
m
s
th
at
ar
e
d
esig
n
ed
to
ef
f
ec
tiv
ely
an
aly
ze
a
b
r
o
a
d
v
ar
iet
y
o
f
u
n
s
tr
u
ctu
r
ed
in
p
u
t.
T
h
ese
alg
o
r
ith
m
s
ar
e
b
ased
o
n
s
o
m
e
k
in
d
o
f
a
r
tific
ial
n
eu
r
al
n
etwo
r
k
.
W
h
en
r
ef
e
r
r
in
g
to
th
is
ca
teg
o
r
y
o
f
alg
o
r
ith
m
s
,
th
e
ter
m
“
d
ee
p
lear
n
in
g
”
is
an
ap
p
r
o
p
r
iate
te
r
m
to
u
s
e.
As
f
a
r
as
d
ee
p
lear
n
i
n
g
[
2
4
]
al
g
o
r
ith
m
s
a
r
e
co
n
ce
r
n
ed
,
th
ese
d
ata
s
ets
ar
e
well
wi
th
in
th
eir
ca
p
ab
ilit
i
es.
a)
L
o
s
s
f
u
n
ctio
n
:
t
h
e
s
u
m
o
f
two
cr
o
s
s
-
en
tr
o
p
y
f
u
n
ctio
n
H
is
t
h
e
l
o
s
s
f
u
n
ctio
n
o
f
d
is
cr
im
in
at
o
r
.
(
)
=
(
,
1
)
+
(
1
,
0
)
=
[
−
1
×
l
og
(
)
−
(
1
−
1
)
l
og
(
1
−
(
)
)
]
+
[
−
0
×
(
)
−
(
1
−
0
)
l
og
(
1
−
(
)
)
]
=
−
(
)
−
(
1
−
(
)
(1
)
Her
e
~
(
)
i.e
.
,
is
an
im
ag
e
r
eg
io
n
ex
tr
ac
ted
f
r
o
m
th
e
tr
ain
in
g
d
ataset
an
d
is
an
im
ag
e
r
eg
io
n
o
f
th
e
test
in
g
d
at
aset.
b)
T
im
e
c
o
m
p
lex
ity
:
t
h
e
am
o
u
n
t
o
f
tim
e
s
p
en
t
in
to
tal
b
y
th
e
s
y
s
tem
b
ein
g
r
ec
o
m
m
e
n
d
ed
i
n
s
tu
d
y
in
g
ea
ch
co
n
v
o
l
u
tio
n
lay
er
.
(
∑
−
1
.
1
2
=
1
.
1
.
1
2
)
(
2
)
I
t
h
as
b
ee
n
d
eter
m
in
ed
t
h
at
th
e
co
n
v
o
lu
tio
n
al
lay
er
,
wh
ich
i
s
d
en
o
ted
b
y
th
e
in
d
ex
1
,
a
n
d
th
e
to
tal
n
u
m
b
er
o
f
c
o
n
v
o
lu
tio
n
lay
er
s
th
at
ar
e
p
r
esen
t
in
th
e
n
etwo
r
k
,
wh
ich
is
d
e
n
o
ted
b
y
th
e
v
a
r
iab
le
d
,
h
av
e
ea
c
h
b
ee
n
ass
ig
n
ed
v
alu
es
th
at
ar
e
s
u
itab
le
f
o
r
th
em
.
At
th
e
lev
el
l,
th
e
v
alu
e
n
r
e
p
r
esen
ts
th
e
to
tal
n
u
m
b
er
o
f
f
ilter
s
th
at
h
av
e
b
ee
n
a
p
p
lied
,
wh
ich
is
also
r
ef
er
r
ed
to
as
th
e
to
tal
n
u
m
b
er
o
f
u
n
iq
u
e
in
p
u
t
ch
an
n
els.
Fo
r
th
e
p
u
r
p
o
s
e
o
f
r
ef
er
r
in
g
to
t
h
is
p
a
r
ticu
lar
v
alu
e
,
th
e
p
h
r
ase
“
f
ilt
er
in
g
ca
p
ab
ilit
ies
o
f
t
h
e
lay
er
”
is
o
f
ten
em
p
lo
y
ed
.
On
e
o
th
er
way
to
ex
p
r
ess
th
e
v
alu
e
th
at
was
p
r
o
v
id
ed
is
to
wr
ite
it
as
th
e
to
tal
o
f
all
o
f
t
h
e
f
ilter
s
th
at
wer
e
ap
p
lied
to
th
e
lth
lay
e
r
.
I
n
s
p
i
te
o
f
th
e
f
ac
t
th
at
th
e
f
ilter
s
e
em
s
to
b
e
o
f
a
s
ize
o
f
s
,
th
e
f
ea
tu
r
e
m
ap
th
at
is
g
en
er
ated
as
a
co
n
s
eq
u
en
ce
o
f
th
e
co
n
v
o
l
u
tio
n
al
p
r
o
ce
s
s
h
as
a
s
p
atial
d
im
en
s
io
n
o
f
m
d
u
e
to
th
e
f
ac
t
th
at
it
is
co
n
s
tr
u
cted
.
I
n
s
p
ite
o
f
th
is
,
it
wo
u
ld
s
ee
m
th
at
th
e
f
ilter
h
as
an
s
-
len
g
th
d
im
en
s
io
n
.
I
t
is
co
m
m
o
n
f
o
r
f
u
lly
-
lin
k
ed
lay
er
s
an
d
p
o
o
lin
g
lay
e
r
s
to
b
e
ac
co
u
n
tab
le
f
o
r
a
p
o
r
tio
n
o
f
th
e
o
v
er
all
tim
e
co
s
t,
wh
ich
ty
p
ically
r
an
g
es
f
r
o
m
f
iv
e
to
ten
p
er
ce
n
t
o
f
th
e
to
tal
tim
e
s
p
en
t
ca
lc
u
latin
g
.
W
h
en
th
e
p
r
e
v
io
u
s
w
r
itin
g
was
d
o
n
e,
th
e
co
n
s
id
er
atio
n
o
f
th
e
am
o
u
n
t
o
f
tim
e
th
at
was
s
p
en
t
was
n
o
t
in
clu
d
ed
.
F
o
r
th
e
s
ak
e
o
f
th
is
d
is
cu
s
s
io
n
,
we
will
d
esig
n
ate
th
e
f
ir
s
t
o
u
tco
m
e
g
en
er
ated
b
y
th
e
m
o
d
u
le
f
o
r
d
ee
p
n
eu
r
al
lear
n
in
g
as
th
e
f
ir
s
t
r
e
s
u
lt
Y=
[
y
1
,
…,
y
i,
…
,
y
N]
.
R
eg
ar
d
in
g
th
e
p
o
s
ter
io
r
p
r
o
b
a
b
ilit
y
at
th
e
lev
el
o
f
f
r
am
es
o
f
C
cla
s
s
es
an
d
with
a
to
tal
o
f
N
f
r
am
es
i
n
th
e
d
ata
(
test
o
r
tr
ain
i
n
g
)
;
th
at
is
Y
∈
R
^(
C
×N
)
,
s
im
ilar
o
u
tco
m
e
is
ac
q
u
ir
ed
f
o
r
t
h
e
s
ec
o
n
d
s
u
b
s
y
s
tem
.
Z
=[
z_
1
,
⋯
,
z_
i,
⋯
,
z
_
N]
∈
R
^(
C
×N
)
.
As
th
e
d
etails
we
’
r
e
f
ilter
in
g
th
r
o
u
g
h
is
a
r
ep
r
esen
tatio
n
o
f
m
ed
ical
tr
an
s
cr
ip
ts
,
o
u
r
s
am
p
le
s
ize
o
f
N=
1
0
,
0
0
0
an
d
a
n
ass
u
r
an
ce
lev
el
o
f
C
=1
,
0
0
0
.
L
in
ea
r
en
s
em
b
le
lear
n
in
g
is
u
s
ed
to
c
r
ea
te
th
e
o
u
tp
u
t o
f
th
e
in
teg
r
ated
s
tr
u
ctu
r
e
at
ea
ch
f
r
am
e
i=1
,
2
,
3
,
4
,
…
,
Ni
to
b
e.
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
A
u
to
ma
ted
h
a
n
d
w
r
itin
g
a
n
a
ly
s
is
a
n
d
p
ers
o
n
a
lity a
ttr
ib
u
te
d
i
s
ce
r
n
men
t u
s
in
g
…
(
Ya
s
h
o
ma
t
i R
.
Dh
u
ma
l
)
653
+
∈
(
3
)
A
s
er
ies,
d
en
o
ted
b
y
i=1
,
3,
4,
…
N,
i=
1
,
2,
.
.
.
,
N
is
g
i
v
e
n
as
in
p
u
t
in
to
a
d
is
tin
ct
d
e
n
s
e
m
o
d
el
in
o
r
d
er
to
cr
ea
te
test
p
h
o
n
em
e
o
r
s
tr
in
g
o
f
wo
r
d
s
.
T
h
e
two
m
atr
ices,
〖
∈
〗
^
(
×
)
〖
∈
〗
^
(
×
)
,
a
r
e
th
e
v
ar
iab
les
th
at
m
ay
b
e
am
en
d
ed
as
p
er
t
h
e
n
ec
ess
ity
ess
en
tial
d
u
r
in
g
tr
ain
in
g
a
n
d
will
b
e
d
is
cu
s
s
ed
in
d
etail
b
elo
w.
T
h
e
p
r
o
ce
d
u
r
e
o
f
ac
q
u
ir
in
g
th
e
v
alu
es
o
f
u
n
k
n
o
wn
p
ar
a
m
eter
s
in
a
s
tatis
tical
m
o
d
el
b
ased
o
n
o
b
s
er
v
ed
d
ata
is
ca
lled
p
ar
a
m
eter
esti
m
atio
n
.
I
n
o
r
d
e
r
to
ac
h
iev
e
p
r
o
f
icien
cy
in
th
e
c
o
n
ce
p
ts
o
f
V
an
d
W
,
it
is
n
ec
ess
ar
y
to
e
n
g
ag
e
in
th
e
g
u
id
ed
lear
n
in
g
e
n
v
ir
o
n
m
en
t
.
T
h
e
s
u
p
er
v
is
o
r
y
s
ig
n
al
in
th
is
ex
p
e
r
im
en
tal
co
n
f
ig
u
r
atio
n
is
th
e
p
r
e
-
allo
ca
ted
class
o
f
o
b
jectiv
es th
at
ar
e
lim
ited
to
th
e
f
r
a
g
m
en
t le
v
el
o
f
th
e
d
ata
s
ets.
=
[
1
,
⋯
,
,
⋯
,
]
∈
×
(
4
)
T
h
e
tr
ain
in
g
d
ata
in
p
u
t
c
o
n
s
is
ts
o
f
th
e
p
o
s
s
ib
ilit
ies
d
er
iv
ed
f
r
o
m
t
h
e
r
et
r
o
s
p
ec
tiv
e
i
n
f
o
r
m
atio
n
o
b
tain
ed
i
n
Y=
[
y
_
1
,
⋯
,
y
_
i,
⋯
,
y
_
N]
an
d
Z
=[
z_
1
,
⋯
,
z_
i,
⋯
,
z_
N]
.
T
h
e
v
ar
i
ab
le
N
r
ep
r
esen
ts
th
e
to
tal
q
u
an
tity
o
f
p
h
o
to
s
u
s
ed
th
r
o
u
g
h
o
u
t
th
e
tr
ain
i
n
g
p
r
o
ce
d
u
r
e.
I
n
o
r
d
er
t
o
ac
h
iev
e
th
is
o
b
jectiv
e,
th
e
T
SE
lo
s
s
f
u
n
ctio
n
will
b
e
u
s
ed
.
T
h
e
tr
ain
in
g
g
o
al
f
u
n
ctio
n
is
f
o
r
m
ed
b
y
in
clu
d
in
g
L
_
2
r
eg
u
l
ar
izatio
n
.
=
1
2
∑
∥
+
−
∥
2
+
λ
1
∥
∥
2
+
λ
2
∥
∥
2
(
5
)
T
h
e
h
y
p
er
-
p
ar
am
ete
r
s
,
λ
1
an
d
λ
2
ar
e
ex
p
er
im
en
tal
L
ag
r
a
n
g
e
m
u
ltip
lier
s
,
ad
ap
ted
u
s
in
g
b
o
th
tr
ain
ed
an
d
v
er
if
ied
d
ata.
Ma
k
in
g
f
ew
ad
j
u
s
tm
en
ts
to
(
2
)
e
n
h
an
ce
s
its
q
u
ality
.
∂E
/∂V=0
an
d
∂E
/∂W
=0
(
6
)
T
h
e
p
r
o
ce
s
s
o
f
ac
q
u
is
itio
n
is
u
n
d
er
tak
en
.
∑
(
+
−
)
+
λ
1
=
0
(
7
)
∑
(
+
−
)
+
λ
2
=
0
(
8
)
T
h
e
eq
u
atio
n
s
with
in
th
is
co
llectio
n
h
av
e
t
h
e
p
o
te
n
tial to
b
e
s
im
p
lifie
d
to
a
m
o
r
e
co
n
cise f
o
r
m
.
(
+
λ
1
)
+
(
)
=
(
9
)
(
)
+
(
+
λ
2
)
=
(
1
0
)
T
h
e
r
eso
lu
tio
n
t
o
th
e
q
u
an
d
a
r
y
o
f
lear
n
i
n
g
u
s
in
g
an
an
al
y
tical
ap
p
r
o
ac
h
:
[
,
]
=
[
,
]
[
+
λ
1
+
λ
2
]
−
1
(
1
1
)
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
m
ag
e
s
am
p
les
o
f
p
e
o
p
le
’
s
h
a
n
d
wr
itin
g
an
d
s
ig
n
atu
r
es
n
ee
d
to
b
e
ac
q
u
ir
e
d
f
r
o
m
a
v
ar
iety
o
f
s
o
u
r
ce
s
in
o
r
d
er
to
c
o
m
p
lete
th
e
im
a
g
e
p
r
ep
r
o
ce
s
s
in
g
an
d
co
llect
t
h
e
d
ata
th
at
is
n
ec
ess
ar
y
f
o
r
th
is
p
r
o
ject.
Dig
ital
m
eth
o
d
s
ar
e
u
s
ed
in
o
r
d
er
t
o
ac
q
u
ir
e
th
e
s
am
p
les,
s
u
ch
as
s
ca
n
n
in
g
t
h
e
h
an
d
wr
itten
s
cr
ip
t
s
o
f
1
,
0
0
0
s
am
p
les
f
o
r
th
e
p
u
r
p
o
s
e
o
f
tr
ai
n
in
g
d
at
a
an
d
20
s
am
p
les f
o
r
t
h
e
p
u
r
p
o
s
e
o
f
test
in
g
d
ata.
3
.
1
.
P
er
f
o
r
m
a
nce
pa
ra
m
et
e
rs
Fo
r
class
if
icatio
n
m
o
d
els
to
b
e
ev
alu
ated
,
ac
cu
r
ac
y
is
an
im
p
o
r
tan
t
m
etr
ic.
As
a
b
in
ar
y
class
if
icatio
n
tech
n
i
q
u
e,
ac
c
u
r
ac
y
c
an
also
b
e
ca
lcu
lated
b
y
co
u
n
tin
g
th
e
p
o
s
itiv
es
an
d
n
eg
ativ
es
as
f
o
ll
o
ws:
w
e
ev
alu
ated
th
e
d
ep
en
d
ab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
u
s
in
g
th
e
f
o
llo
w
in
g
cr
iter
ia
b
ased
o
n
well
-
k
n
o
wn
s
tate
-
of
-
th
e
-
a
r
t
m
eth
o
d
o
l
o
g
ies.
On
th
e
s
am
e
d
ataset,
th
e
s
am
e
tr
ain
in
g
a
n
d
test
in
g
p
r
o
ce
d
u
r
e
is
u
s
ed
to
im
p
lem
e
n
t
an
d
ev
alu
ate
th
e
well
-
k
n
o
wn
s
tate
o
f
th
e
ar
t
m
eth
o
d
.
=
(
+
)
/
(
+
)
(
1
2
)
=
(
)
/
(
+
)
(
1
3
)
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
8
,
No
.
1
,
Ap
r
il
20
2
5
:
64
9
-
65
6
654
T
h
e
ac
cu
r
ac
y
o
f
d
if
f
e
r
en
t
class
es
is
s
h
o
wn
in
Fig
u
r
e
2
.
T
h
e
x
,
y
a
x
is
r
ep
r
esen
ts
d
is
p
o
s
itio
n
attr
ib
u
tes
an
d
th
e
lev
el
o
f
co
r
r
ec
tn
ess
in
ter
m
s
o
f
a
cc
u
r
ac
y
r
esp
e
ctiv
ely
.
T
h
e
p
r
o
p
o
s
ed
tech
n
i
q
u
e
h
as
an
av
er
ag
e
ac
cu
r
ac
y
o
f
0
.
9
8
,
s
u
r
p
ass
in
g
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
class
ic
VGG
-
b
ased
ap
p
r
o
ac
h
.
Pre
cisi
o
n
is
ca
lcu
lated
b
y
k
n
o
win
g
th
e
n
u
m
b
er
o
f
tr
u
e
p
o
s
it
iv
es,
f
alse
p
o
s
it
iv
es,
an
d
tr
u
e
n
eg
ativ
es.
T
h
e
p
r
ec
is
io
n
o
f
d
if
f
er
en
t
class
es
i
s
s
h
o
wn
in
Fig
u
r
e
3
.
T
h
e
x
,
y
ax
is
r
ep
r
esen
ts
d
is
p
o
s
itio
n
attr
ib
u
tes
an
d
th
e
lev
el
o
f
co
r
r
ec
tn
ess
in
ter
m
s
o
f
p
r
ec
is
io
n
r
esp
ec
tiv
ely
.
T
h
e
p
r
o
p
o
s
ed
tech
n
i
q
u
e
h
as
an
av
er
ag
e
p
r
ec
is
io
n
o
f
0
.
9
9
,
s
u
r
p
ass
in
g
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
th
e
class
ic
VGG
-
b
ased
ap
p
r
o
ac
h
.
Fig
u
r
e
2
.
C
o
m
p
a
r
is
o
n
o
f
a
cc
u
r
ac
y
Fig
u
r
e
3.
C
o
m
p
a
r
is
o
n
o
f
p
r
ec
i
s
io
n
3
.
2
.
Co
m
pa
riso
n wit
h
o
t
her
t
ec
hn
iqu
e
s
T
ab
le
1
s
u
m
m
ar
izes
th
e
f
in
d
in
g
s
f
r
o
m
a
co
m
p
ar
is
o
n
o
f
th
e
s
u
g
g
ested
h
an
d
wr
itten
r
ec
o
g
n
itio
n
with
s
o
m
e
o
f
th
e
ex
is
tin
g
m
eth
o
d
o
l
o
g
ies.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
’
s
d
etec
tio
n
ac
cu
r
ac
y
is
p
r
o
v
e
d
to
b
e
h
ig
h
e
r
th
an
th
e
ex
is
tin
g
tech
n
iq
u
es.
T
h
is
is
m
ain
ly
b
ec
au
s
e
o
f
th
e
co
m
b
in
atio
n
o
f
h
is
to
g
r
am
en
h
a
n
ce
m
en
t
with
MRA
f
o
llo
wed
b
y
class
if
icatio
n
u
s
in
g
d
en
s
e
C
NN.
Fu
r
th
er
we
h
a
v
e
cr
ea
ted
o
u
r
o
wn
d
ataset
f
o
r
wo
r
s
t
ca
s
e
wr
itin
g
an
d
ac
h
iev
e
d
clo
s
e
to
9
8
% a
cc
u
r
ac
y
with
9
9
% p
r
ec
is
io
n
c
o
m
p
ar
ed
to
e
x
is
tin
g
tech
n
iq
u
es.
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
A
u
to
ma
ted
h
a
n
d
w
r
itin
g
a
n
a
ly
s
is
a
n
d
p
ers
o
n
a
lity a
ttr
ib
u
te
d
i
s
ce
r
n
men
t u
s
in
g
…
(
Ya
s
h
o
ma
t
i R
.
Dh
u
ma
l
)
655
T
ab
le
1
.
Per
f
o
r
m
an
ce
c
o
m
p
a
r
is
o
n
A
u
t
h
o
r
s
Te
c
h
n
i
q
u
e
M
a
x
i
m
u
m
a
c
c
u
r
a
c
y
i
n
%
X
i
n
g
a
n
d
Q
i
a
o
[
2
5
]
M
u
l
t
i
st
r
e
a
m
C
N
N
9
1
.
3
5
P
a
t
h
a
k
e
t
a
l
.
[
2
6
]
D
i
scret
e
m
a
t
h
e
m
a
t
i
c
a
l
s
c
i
e
n
c
e
9
7
.
7
P
r
o
p
o
se
d
M
R
A
+
C
N
N
9
7
.
8
5
4.
CO
NCLU
SI
O
N
T
h
e
s
tu
d
y
o
f
p
eo
p
le
’
s
p
er
s
o
n
alities
h
as
th
e
p
o
ten
tial
to
p
r
o
v
id
e
in
s
ig
h
ts
o
n
th
e
b
eh
a
v
io
r
s
,
q
u
alities
,
an
d
f
ea
t
u
r
es
o
f
in
d
iv
i
d
u
als.
T
h
e
o
cc
u
r
r
en
ce
o
f
th
ese
p
h
e
n
o
m
en
a
p
r
o
v
id
es
in
s
ig
h
ts
o
n
th
e
f
u
n
ctio
n
in
g
o
f
p
eo
p
le
’
s
th
o
u
g
h
ts
,
th
e
way
s
in
wh
ich
p
eo
p
le
ac
t,
an
d
t
h
e
way
s
in
wh
ich
in
d
iv
i
d
u
a
ls
th
r
iv
e
in
u
n
iq
u
e
cir
cu
m
s
tan
ce
s
.
Usi
n
g
d
ata
f
r
o
m
an
in
d
iv
id
u
al
’
s
h
an
d
wr
itin
g
an
d
u
s
in
g
m
ac
h
i
n
e
lear
n
i
n
g
alg
o
r
ith
m
s
,
th
is
r
esear
ch
r
ev
ea
ls
a
g
r
o
u
n
d
-
b
r
ea
k
in
g
m
et
h
o
d
f
o
r
ass
ess
in
g
an
in
d
iv
i
d
u
al
’
s
p
e
r
s
o
n
ality
tr
aits
in
a
co
n
s
is
ten
t
m
an
n
er
.
I
n
th
e
f
ir
s
t
s
tag
e
o
f
th
is
n
o
v
el
m
eth
o
d
f
o
r
c
h
ar
ac
ter
i
zin
g
tex
tu
al
in
f
o
r
m
atio
n
b
y
m
ea
n
s
o
f
a
s
ig
n
atu
r
e
-
b
ased
s
tr
u
ctu
r
al
r
ep
r
esen
tatio
n
,
MRA is u
s
ed
.
I
n
th
e
s
u
b
s
eq
u
en
t step
,
we
u
s
e
a
d
ee
p
d
en
s
e
n
etwo
r
k
in
o
r
d
er
to
f
u
r
th
er
e
n
h
an
ce
t
h
e
g
en
e
r
al
im
ag
e.
T
h
e
o
b
jectiv
e
o
f
th
i
s
in
q
u
ir
y
is
to
g
et
a
d
ee
p
er
u
n
d
er
s
tan
d
i
n
g
o
f
h
an
d
wr
itin
g
in
t
h
e
s
en
s
e
th
at
is
m
o
r
e
co
n
v
en
tio
n
ally
u
n
d
er
s
to
o
d
.
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
o
b
tain
ed
m
o
r
e
ac
cu
r
ac
y
co
m
p
a
r
ed
to
e
x
is
tin
g
m
eth
o
d
s
.
I
n
o
r
d
e
r
to
ac
h
iev
e
th
e
u
ltima
te
o
b
jectiv
e
o
f
b
e
in
g
ab
le
to
p
r
ed
ic
t
in
d
iv
id
u
al
ch
a
r
ac
ter
is
tics
,
th
e
b
asic
in
ten
tio
n
in
f
u
tu
r
e
is
to
d
ev
elo
p
a
co
m
p
u
ter
ized
p
r
o
g
r
am
w
h
ich
will
p
er
f
o
r
m
b
eh
a
v
io
r
al
a
n
aly
s
is
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
M
c
N
i
c
h
o
l
a
n
d
J.
A
.
N
e
l
so
n
,
H
a
n
d
w
ri
t
i
n
g
A
n
a
l
a
y
si
s:
Pu
t
t
i
n
g
I
t
t
o
W
o
rk
f
o
r
Y
o
u
.
M
c
G
r
a
w
H
i
l
l
P
r
o
f
e
ss
i
o
n
a
l
,
1
9
9
4
.
[
2
]
F
.
L
a
g
a
n
a
r
o
,
M
.
M
a
z
z
a
,
G
.
M
a
r
a
n
o
,
E.
P
i
u
z
z
i
,
a
n
d
A
.
P
a
l
l
o
t
t
i
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
-
b
a
se
d
scr
e
e
n
i
n
g
o
f
d
e
p
r
e
ss
i
v
e
d
i
s
o
r
d
e
r
p
a
t
i
e
n
t
s
t
h
r
o
u
g
h
g
r
a
p
h
,
h
a
n
d
w
r
i
t
i
n
g
a
n
d
v
o
i
c
e
s
i
g
n
a
l
s,
”
i
n
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
W
o
rksh
o
p
o
n
B
i
o
m
e
d
i
c
a
l
A
p
p
l
i
c
a
t
i
o
n
s,
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
S
e
n
so
rs (BAT
S
)
,
S
e
p
.
2
0
2
3
,
p
p
.
6
–
1
0
,
d
o
i
:
1
0
.
1
1
0
9
/
B
A
TS
5
9
4
6
3
.
2
0
2
3
.
1
0
3
0
3
1
0
4
.
[
3
]
P
.
P
o
r
w
i
k
,
“
T
h
e
c
o
m
p
a
c
t
t
h
r
e
e
st
a
g
e
s
me
t
h
o
d
o
f
t
h
e
s
i
g
n
a
t
u
r
e
r
e
c
o
g
n
i
t
i
o
n
,
”
i
n
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
a
n
d
I
n
d
u
s
t
ri
a
l
M
a
n
a
g
e
m
e
n
t
A
p
p
l
i
c
a
t
i
o
n
s (CI
S
I
M
’
07)
,
Ju
n
.
2
0
0
7
,
p
p
.
2
8
2
–
2
8
7
,
d
o
i
:
1
0
.
1
1
0
9
/
C
I
S
I
M
.
2
0
0
7
.
6
5
.
[
4
]
S
.
M
u
sh
t
a
q
a
n
d
A
.
H
.
M
i
r
,
“
S
i
g
n
a
t
u
r
e
v
e
r
i
f
i
c
a
t
i
o
n
:
a
st
u
d
y
,
”
i
n
2
0
1
3
4
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
C
o
m
p
u
t
e
r
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
I
C
C
C
T
)
,
S
e
p
.
2
0
1
3
,
p
p
.
2
5
8
–
2
6
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
C
T.
2
0
1
3
.
6
7
4
9
6
3
7
.
[
5
]
Y
.
Ta
n
g
,
X
.
W
u
,
a
n
d
W
.
B
u
,
“
O
f
f
l
i
n
e
t
e
x
t
-
i
n
d
e
p
e
n
d
e
n
t
w
r
i
t
e
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
si
n
g
st
r
o
k
e
f
r
a
g
m
e
n
t
a
n
d
c
o
n
t
o
u
r
b
a
se
d
f
e
a
t
u
r
e
s,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
1
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
B
i
o
m
e
t
r
i
c
s
,
I
C
B
2
0
1
3
,
2
0
1
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
B
.
2
0
1
3
.
6
6
1
2
9
8
8
.
[
6
]
H
.
N
.
C
h
a
mp
a
a
n
d
K
.
R
.
A
n
a
n
d
a
K
u
mar,
“
A
u
t
o
mat
e
d
h
u
ma
n
b
e
h
a
v
i
o
r
p
r
e
d
i
c
t
i
o
n
t
h
r
o
u
g
h
h
a
n
d
w
r
i
t
i
n
g
a
n
a
l
y
s
i
s,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
1
st
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
g
ra
t
e
d
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
i
n
g
,
I
C
I
I
C
2
0
1
0
,
2
0
1
0
,
p
p
.
1
6
0
–
1
6
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
I
C
.
2
0
1
0
.
2
9
.
[
7
]
M
.
N
a
g
h
i
b
o
l
h
o
sse
i
n
i
a
n
d
F
.
B
a
h
r
a
m
i
,
“
A
b
e
h
a
v
i
o
r
a
l
m
o
d
e
l
o
f
w
r
i
t
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
I
C
E
C
E
2
0
0
8
-
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
E
l
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r E
n
g
i
n
e
e
r
i
n
g
,
2
0
0
8
,
p
p
.
9
7
0
–
9
7
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
EC
E.
2
0
0
8
.
4
7
6
9
3
5
3
.
[
8
]
I
.
Za
a
r
o
u
r
,
L.
H
e
u
t
t
e
,
P
.
Le
r
a
y
,
J
.
La
b
i
c
h
e
,
B
.
Et
e
r
,
a
n
d
D
.
M
e
l
l
i
e
r
,
“
C
l
u
s
t
e
r
i
n
g
a
n
d
b
a
y
e
si
a
n
n
e
t
w
o
r
k
a
p
p
r
o
a
c
h
e
s
f
o
r
d
i
sc
o
v
e
r
i
n
g
h
a
n
d
w
r
i
t
i
n
g
s
t
r
a
t
e
g
i
e
s
o
f
p
r
i
m
a
r
y
s
c
h
o
o
l
c
h
i
l
d
r
e
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
a
n
d
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
8
,
n
o
.
7
,
p
p
.
1
2
3
3
–
1
2
5
1
,
2
0
0
4
,
d
o
i
:
1
0
.
1
1
4
2
/
S
0
2
1
8
0
0
1
4
0
4
0
0
3
7
4
5
.
[
9
]
R
.
S
u
d
i
r
ma
n
,
N
.
T
a
b
a
t
a
b
a
e
y
-
M
a
s
h
a
d
i
,
a
n
d
I
.
A
r
i
f
f
i
n
,
“
A
s
p
e
c
t
s
o
f
a
s
t
a
n
d
a
r
d
i
z
e
d
a
u
t
o
ma
t
e
d
s
y
st
e
m
f
o
r
scr
e
e
n
i
n
g
c
h
i
l
d
r
e
n
’
s
h
a
n
d
w
r
i
t
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
1
s
t
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
f
o
rm
a
t
i
c
s
a
n
d
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
,
I
C
I
2
0
1
1
,
2
0
1
1
,
p
p
.
4
9
–
5
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
.
2
0
1
1
.
1
9
.
[
1
0
]
N
.
M
.
N
o
r
,
A
.
W
a
h
a
b
,
N
.
K
a
maru
d
d
i
n
,
a
n
d
H
.
M
a
j
i
d
,
“
P
o
st
a
c
c
i
d
e
n
t
a
n
a
l
y
si
s
o
f
d
r
i
v
e
r
a
f
f
e
c
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
C
o
n
su
m
e
r E
l
e
c
t
r
o
n
i
c
s,
I
S
C
E
,
2
0
1
1
,
p
p
.
2
7
8
–
2
8
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
C
E.
2
0
1
1
.
5
9
7
3
8
3
2
.
[
11]
S
.
B
.
B
h
a
s
k
o
r
o
a
n
d
S
.
H
.
S
u
p
a
n
g
k
a
t
,
“
A
n
e
x
t
r
a
c
t
i
o
n
o
f
m
e
d
i
c
a
l
i
n
f
o
r
m
a
t
i
o
n
b
a
se
d
o
n
h
u
ma
n
h
a
n
d
w
r
i
t
i
n
g
s,
”
i
n
2
0
1
4
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
S
y
st
e
m
s
a
n
d
I
n
n
o
v
a
t
i
o
n
,
I
C
I
T
S
I
2
0
1
4
-
Pr
o
c
e
e
d
i
n
g
s
,
2
0
1
4
,
p
p
.
2
5
3
–
2
5
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
TS
I
.
2
0
1
4
.
7
0
4
8
2
7
3
.
[
1
2
]
P
.
D
r
o
t
á
r
,
J.
M
e
k
y
s
k
a
,
Z.
S
m
é
k
a
l
,
I
.
R
e
k
t
o
r
o
v
á
,
L.
M
a
s
a
r
o
v
á
,
a
n
d
M
.
F
a
u
n
d
e
z
-
Z
a
n
u
y
,
“
P
r
e
d
i
c
i
t
i
o
n
p
o
t
e
n
t
i
a
l
o
f
d
i
f
f
e
r
e
n
t
h
a
n
d
w
r
i
t
i
n
g
t
a
s
k
s f
o
r
d
i
a
g
n
o
s
i
s
o
f
P
a
r
k
i
n
s
o
n
’
s,
”
i
n
2
0
1
3
E
-
H
e
a
l
t
h
a
n
d
B
i
o
e
n
g
i
n
e
e
r
i
n
g
C
o
n
f
e
r
e
n
c
e
(
EH
B)
,
2
0
1
3
,
p
p
.
1
–
4
.
[
1
3
]
P
.
S
i
n
g
h
,
S
.
V
e
r
ma
,
S
.
C
h
a
u
d
h
a
r
y
,
a
n
d
S
.
G
u
p
t
a
,
“
P
e
r
so
n
a
l
i
t
y
t
r
a
i
t
d
e
t
e
c
t
i
o
n
u
si
n
g
h
a
n
d
w
r
i
t
i
n
g
a
n
a
l
y
si
s
b
y
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
o
f
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
R
e
c
e
n
t
T
r
e
n
d
s
i
n
C
o
m
p
u
t
i
n
g
:
I
C
R
T
C
,
2
0
2
3
,
v
o
l
.
6
0
0
,
p
p
.
3
8
7
–
3
9
6
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
19
-
8
8
2
5
-
7
_
3
3
.
[
1
4
]
Y
.
R
.
D
h
u
ma
l
,
A
.
S
h
i
n
d
e
,
K
.
C
h
a
u
d
h
a
r
i
,
S
.
O
z
a
,
R
.
S
a
p
k
a
l
,
a
n
d
S
.
I
t
k
a
r
k
a
r
,
“
A
u
t
o
ma
t
i
c
h
a
n
d
w
r
i
t
i
n
g
a
n
a
l
y
s
i
s
a
n
d
p
e
r
so
n
a
l
i
t
y
t
r
a
i
t
d
e
t
e
c
t
i
o
n
u
s
i
n
g
m
u
l
t
i
-
t
a
s
k
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
,
”
i
n
1
0
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
i
n
g
f
o
r
S
u
st
a
i
n
a
b
l
e
G
l
o
b
a
l
D
e
v
e
l
o
p
m
e
n
t
(
I
N
D
I
AC
o
m
)
,
2
0
2
3
,
p
p
.
3
4
8
–
3
5
4
.
[
1
5
]
D
.
G
a
g
i
u
a
n
d
D
.
S
e
n
d
r
e
sc
u
,
“
D
e
t
e
c
t
i
o
n
o
f
h
a
n
d
w
r
i
t
i
n
g
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
u
si
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
i
n
2
0
2
3
2
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
a
rp
a
t
h
i
a
n
C
o
n
t
ro
l
C
o
n
f
e
re
n
c
e
(
I
C
C
C
)
,
Ju
n
.
2
0
2
3
,
p
p
.
1
5
7
–
1
6
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
C
5
7
0
9
3
.
2
0
2
3
.
1
0
1
7
8
9
3
6
.
[
1
6
]
S
a
msu
r
y
a
d
i
,
R
.
K
u
r
n
i
a
w
a
n
,
J
.
S
u
p
a
r
d
i
,
S
u
k
e
m
i
,
a
n
d
F
.
S
.
M
o
h
a
m
a
d
,
“
A
f
r
a
mew
o
r
k
f
o
r
d
e
t
e
r
m
i
n
i
n
g
t
h
e
b
i
g
f
i
v
e
p
e
r
so
n
a
l
i
t
y
t
r
a
i
t
s
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
c
a
t
i
o
n
t
h
r
o
u
g
h
g
r
a
p
h
o
l
o
g
y
,
”
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
0
2
3
,
p
p
.
1
–
1
5
,
Jan
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
3
/
1
2
4
9
0
0
4
.
[
1
7
]
A
.
U
.
R
a
h
ma
n
a
n
d
Z.
H
a
l
i
m
,
“
I
d
e
n
t
i
f
y
i
n
g
d
o
mi
n
a
n
t
e
m
o
t
i
o
n
a
l
st
a
t
e
u
si
n
g
h
a
n
d
w
r
i
t
i
n
g
a
n
d
d
r
a
w
i
n
g
sam
p
l
e
s
b
y
f
u
si
n
g
f
e
a
t
u
r
e
s
,
”
Ap
p
l
i
e
d
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
5
3
,
n
o
.
3
,
p
p
.
2
7
9
8
–
2
8
1
4
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
8
9
-
0
2
2
-
0
3
5
5
2
-
x.
[
1
8
]
K
.
S
a
t
i
a
n
d
D
.
K
u
m
a
r
,
“
I
d
e
n
t
i
f
y
i
n
g
t
h
e
p
e
r
s
o
n
a
l
i
t
y
t
r
a
i
t
s
b
a
s
e
d
o
n
h
a
n
d
w
r
i
t
i
n
g
u
si
n
g
A
N
N
a
n
d
M
LP
c
o
n
c
e
p
t
,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
u
s
t
a
i
n
a
b
l
e
C
o
m
p
u
t
i
n
g
a
n
d
S
m
a
r
t
S
y
s
t
e
m
s
(
I
C
S
C
S
S)
,
Ju
n
.
2
0
2
3
,
p
p
.
5
2
4
–
5
2
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
C
S
S
5
7
6
5
0
.
2
0
2
3
.
1
0
1
6
9
3
5
4
.
[
1
9
]
S
.
G
h
o
s
h
,
P
.
S
h
i
v
a
k
u
mar
a
,
P
.
R
o
y
,
U
.
P
a
l
,
a
n
d
T.
L
u
,
“
G
r
a
p
h
o
l
o
g
y
b
a
s
e
d
h
a
n
d
w
r
i
t
t
e
n
c
h
a
r
a
c
t
e
r
a
n
a
l
y
s
i
s
f
o
r
h
u
m
a
n
b
e
h
a
v
i
o
u
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
C
A
AI
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
t
e
l
l
i
g
e
n
c
e
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
5
,
n
o
.
1
,
p
p
.
5
5
–
6
5
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
4
9
/
t
r
i
t
.
2
0
1
9
.
0
0
5
1
.
[
2
0
]
A
.
U
.
R
a
h
ma
n
a
n
d
Z.
H
a
l
i
m,
“
P
r
e
d
i
c
t
i
n
g
t
h
e
b
i
g
f
i
v
e
p
e
r
so
n
a
l
i
t
y
t
r
a
i
t
s
f
r
o
m
h
a
n
d
-
w
r
i
t
t
e
n
t
e
x
t
f
e
a
t
u
r
e
s
t
h
r
o
u
g
h
semi
-
s
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
,
”
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
,
v
o
l
.
8
1
,
n
o
.
2
3
,
p
p
.
3
3
6
7
1
–
3
3
6
8
7
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
0
4
2
-
0
2
2
-
1
3
1
1
4
-
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
8
,
No
.
1
,
Ap
r
il
20
2
5
:
64
9
-
65
6
656
[
2
1
]
“
C
h
a
p
t
e
r
5
W
a
v
e
l
e
t
si
g
n
a
l
p
r
o
c
e
ss
i
n
g
,
”
i
n
W
a
v
e
l
e
t
An
a
l
y
s
i
s
a
n
d
I
t
s
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
,
n
o
.
C
,
1
9
9
8
,
p
p
.
1
6
7
–
1
9
0
,
d
o
i
:
1
0
.
1
0
1
6
/
S
1
8
7
4
-
6
0
8
X
(
9
8
)
8
0
0
5
0
-
2
.
[
2
2
]
Á
.
V
á
z
q
u
e
z
–
M
a
y
a
g
o
i
t
i
a
,
W
.
S
.
T
h
o
r
n
t
o
n
,
J.
R
.
H
a
mm
o
n
d
,
a
n
d
R
.
J
.
H
a
r
r
i
so
n
,
“
Q
u
a
n
t
u
m
c
h
e
m
i
st
r
y
m
e
t
h
o
d
s
w
i
t
h
mu
l
t
i
w
a
v
e
l
e
t
b
a
s
e
s
o
n
mass
i
v
e
p
a
r
a
l
l
e
l
c
o
mp
u
t
e
r
s,
”
i
n
A
n
n
u
a
l
Re
p
o
rt
s
i
n
C
o
m
p
u
t
a
t
i
o
n
a
l
C
h
e
m
i
st
ry
,
El
s
e
v
i
e
r
,
2
0
1
4
,
p
p
.
3
–
2
4
.
[
2
3
]
A
.
P
r
i
e
t
o
-
G
u
e
r
r
e
r
o
a
n
d
G
.
Esp
i
n
o
s
a
-
P
a
r
e
d
e
s,
“
Li
n
e
a
r
s
i
g
n
a
l
p
r
o
c
e
ss
i
n
g
m
e
t
h
o
d
s
a
n
d
d
e
c
a
y
r
a
t
i
o
e
st
i
ma
t
i
o
n
,
”
i
n
L
i
n
e
a
r
a
n
d
N
o
n
-
L
i
n
e
a
r
S
t
a
b
i
l
i
t
y
A
n
a
l
y
s
i
s
i
n
Bo
i
l
i
n
g
W
a
t
e
r R
e
a
c
t
o
rs
,
El
s
e
v
i
e
r
,
2
0
1
9
,
p
p
.
2
6
9
–
3
1
4
.
[
2
4
]
P
.
S
i
n
g
h
,
S
.
V
e
r
ma
,
S
.
C
h
a
u
d
h
a
r
y
,
a
n
d
S
.
G
u
p
t
a
,
“
P
e
r
so
n
a
l
i
t
y
t
r
a
i
t
d
e
t
e
c
t
i
o
n
u
si
n
g
h
a
n
d
w
r
i
t
i
n
g
a
n
a
l
y
si
s
b
y
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
o
f
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Re
c
e
n
t
T
ren
d
s
i
n
C
o
m
p
u
t
i
n
g
,
I
C
R
T
C
,
2
0
2
3
,
v
o
l
.
6
0
0
,
p
p
.
3
8
7
–
3
9
6
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
19
-
8
8
2
5
-
7
_
3
3
.
[
2
5
]
L.
X
i
n
g
a
n
d
Y
.
Q
i
a
o
,
“
D
e
e
p
W
r
i
t
e
r
:
a
mu
l
t
i
-
st
r
e
a
m
d
e
e
p
C
N
N
f
o
r
t
e
x
t
-
i
n
d
e
p
e
n
d
e
n
t
w
r
i
t
e
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
F
ro
n
t
i
e
rs
i
n
H
a
n
d
w
ri
t
i
n
g
Re
c
o
g
n
i
t
i
o
n
,
I
C
FH
R
,
2
0
1
6
,
v
o
l
.
0
,
p
p
.
5
8
4
–
5
8
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
F
H
R
.
2
0
1
6
.
0
1
1
2
.
[
2
6
]
A
.
R
.
P
a
t
h
a
k
,
A
.
R
a
u
t
,
S
.
P
a
w
a
r
,
M
.
N
a
n
g
a
r
e
,
H
.
S
.
A
b
b
o
t
t
,
a
n
d
P
.
C
h
a
n
d
a
k
,
“
P
e
r
so
n
a
l
i
t
y
a
n
a
l
y
si
s
t
h
r
o
u
g
h
h
a
n
d
w
r
i
t
i
n
g
r
e
c
o
g
n
i
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
D
i
scr
e
t
e
Ma
t
h
e
m
a
t
i
c
a
l
S
c
i
e
n
c
e
s
a
n
d
C
r
y
p
t
o
g
r
a
p
h
y
,
v
o
l
.
2
3
,
n
o
.
1
,
p
p
.
1
9
–
3
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
0
/
0
9
7
2
0
5
2
9
.
2
0
2
0
.
1
7
2
1
8
5
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ya
sho
m
a
ti
R
.
Dhu
m
a
l
is
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
a
t
Bh
a
ra
ti
Vid
y
a
p
e
e
th
’
s
Co
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
f
o
r
W
o
m
e
n
,
P
u
n
e
.
S
h
e
h
o
ld
s
a
M
-
Tec
h
d
e
g
re
e
in
El
e
c
tro
n
ics
E
n
g
i
n
e
e
rin
g
wit
h
s
p
e
c
i
a
l
iz
a
t
i
o
n
i
n
im
a
g
e
p
r
o
c
e
ss
i
n
g
.
H
e
r
re
se
a
rc
h
a
re
a
s
a
r
e
im
a
g
e
p
r
o
c
e
s
s
i
n
g
,
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
a
n
d
p
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
.
H
i
s
r
e
s
e
a
r
c
h
i
n
t
e
r
e
s
t
s
i
n
c
l
u
d
e
i
m
a
g
e
p
r
o
c
e
ss
i
n
g
,
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
a
n
d
a
r
t
i
f
i
c
ia
l
i
n
t
e
l
l
i
g
e
n
c
e
.
S
h
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
y
a
s
h
o
m
a
t
i
.
d
h
u
m
a
l
@
b
h
a
r
a
t
i
v
i
d
y
a
p
e
e
t
.
e
d
u
.
Dr
.
Ar
u
n
d
h
a
ti
A.
S
h
in
d
e
is
p
ro
fe
ss
o
r
a
t
De
p
a
rtme
n
t
o
f
ECE
,
Bh
a
ra
ti
Vid
y
a
p
e
e
th
’
s
Un
i
v
e
rsity
,
COE
P
u
n
e
.
He
r
re
se
a
rc
h
a
re
a
s
a
re
i
m
a
g
e
p
ro
c
e
ss
in
g
,
m
a
c
h
i
n
e
lea
rn
in
g
,
a
n
d
p
a
tt
e
rn
re
c
o
g
n
it
io
n
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
i
m
a
g
e
p
ro
c
e
ss
in
g
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
a
rti
ficia
l
i
n
telli
g
e
n
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
a
sh
in
d
e
@b
v
u
c
o
e
p
.
e
d
u
.
in
.
Ro
shn
a
d
e
v
i
J
a
isin
g
S
a
p
k
a
l
is
a
ss
istan
t
p
r
o
fe
ss
o
r
i
n
El
e
c
tro
n
ics
a
n
d
Tele
c
o
m
m
u
n
ica
ti
o
n
De
p
a
rtme
n
t
a
t
Bh
a
ra
ti
Vid
y
a
p
e
e
th
’
s
c
o
l
leg
e
o
f
En
g
in
e
e
rin
g
fo
r
Wo
m
e
n
,
P
u
n
e
,
M
a
h
a
ra
sh
tra,
In
d
ia.
S
h
e
h
o
ld
s
a
M
E.
d
e
g
re
e
in
El
e
c
tro
n
i
c
s
a
n
d
Tele
c
o
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
wit
h
sp
e
c
ializa
ti
o
n
in
VLS
I
a
n
d
Emb
e
d
d
e
d
S
y
ste
m
s.
He
r
re
se
a
rc
h
a
r
e
a
s
a
re
ima
g
e
/sig
n
a
l
p
r
o
c
e
ss
in
g
,
d
r
o
n
e
/
UA
V,
m
e
d
ica
l
ima
g
e
a
n
a
ly
sis
,
a
n
d
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
r
o
s
h
n
a
.
sa
p
k
a
l@
b
h
a
ra
ti
v
id
y
a
p
e
e
th
.
e
d
u
.
S
a
tish
Bh
a
ira
n
n
a
wa
r
is
p
ro
f
e
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
ECE
a
n
d
De
a
n
CIII
a
t
S
DM
Co
l
leg
e
o
f
En
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
lo
g
y
,
Dh
a
rwa
d
,
Ka
rn
a
tak
a
.
He
h
a
s
m
a
n
y
f
u
n
d
e
d
p
ro
jec
ts
fro
m
VG
S
T
a
n
d
DST
in
th
e
a
re
a
o
f
VLS
I
f
o
r
im
a
g
e
a
n
d
v
i
d
e
o
p
ro
c
e
ss
in
g
a
p
p
li
c
a
ti
o
n
s.
He
h
a
s
o
n
e
p
a
ten
t
g
ra
n
ted
b
y
I
n
d
ian
I
P
R
t
o
h
is
a
c
c
o
u
n
t.
He
h
a
s
a
tt
e
n
d
e
d
v
a
rio
u
s
c
o
n
fe
re
n
c
e
s
a
s
k
e
y
n
o
te
sp
e
a
k
e
r
.
He
h
a
s
p
u
b
li
c
a
ti
o
n
s
i
n
d
e
x
e
d
in
S
CIE,
S
COPUS
,
a
n
d
W
o
S
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
ti
sh
b
h
a
iran
n
wa
r@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.