I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
1
6
,
No
.
4
,
A
u
g
u
s
t
20
2
6
,
p
p
.
2
0
9
6
~
2
1
0
5
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
1
6
i
4
.
pp
2
0
9
6
-
2
1
0
5
2096
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Edg
e
-
a
wa
re c
o
ff
e
e aro
ma
clas
sifica
tion usin
g
mul
ti
-
represen
tatio
n f
e
a
ture
e
x
trac
tion a
nd Lig
ht
G
BM
on
J
etso
n Nano
Denda
Dew
a
t
a
m
a
1,
2
,
E
rni Y
ud
a
nin
g
t
y
a
s
1
,
M
u
ha
m
m
a
d F
a
uza
n E
dy
P
urno
m
o
1
,
Set
y
a
wa
n P
urno
m
o
Sa
k
t
i
3
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
,
B
r
a
w
i
j
a
y
a
U
n
i
v
e
r
si
t
y
,
M
a
l
a
n
g
,
I
n
d
o
n
e
s
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
S
t
a
t
e
P
o
l
y
t
e
c
h
n
i
c
s
o
f
M
a
l
a
n
g
,
M
a
l
a
n
g
,
I
n
d
o
n
e
s
i
a
3
D
e
p
a
r
t
me
n
t
o
f
P
h
y
si
c
s,
B
r
a
w
i
j
a
y
a
U
n
i
v
e
r
s
i
t
y
,
M
a
l
a
n
g
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
3
,
2
0
2
6
R
ev
is
ed
Ap
r
1
5
,
2
0
2
6
Acc
ep
ted
Ap
r
2
6
,
2
0
2
6
Ob
jec
ti
v
e
c
o
ffe
e
a
ro
m
a
e
v
a
l
u
a
ti
o
n
re
m
a
in
s
c
h
a
ll
e
n
g
in
g
o
u
tsi
d
e
c
o
n
tro
ll
e
d
lab
o
ra
to
r
y
se
tt
in
g
s,
a
n
d
m
o
st
e
lec
tro
n
ic
n
o
se
stu
d
ies
n
e
g
lec
t
e
m
b
e
d
d
e
d
d
e
p
lo
y
m
e
n
t
c
o
n
stra
in
ts.
T
h
is
w
o
rk
p
ro
p
o
se
s
a
n
e
d
g
e
-
a
wa
re
c
o
ffe
e
a
ro
m
a
c
las
sifica
ti
o
n
fra
m
e
wo
rk
th
a
t
in
teg
ra
tes
m
u
lt
i
-
re
p
re
se
n
tati
o
n
fe
a
tu
re
e
x
trac
ti
o
n
wit
h
Li
g
h
tG
BM
a
n
d
e
v
a
lu
a
tes
b
o
t
h
p
re
d
icti
v
e
p
e
rfo
r
m
a
n
c
e
a
n
d
c
o
m
p
u
tati
o
n
a
l
e
fficie
n
c
y
.
A
six
-
se
n
so
r
m
e
tal
-
o
x
i
d
e
se
m
ico
n
d
u
c
t
o
r
(M
OS)
e
-
n
o
se
wa
s
d
e
v
e
lo
p
e
d
,
p
ro
d
u
c
i
n
g
a
b
a
lan
c
e
d
d
a
tas
e
t
o
f
1
,
0
8
0
tr
ials
fro
m
1
2
a
ro
m
a
c
las
s
e
s.
F
iv
e
fe
a
tu
re
re
p
re
se
n
tatio
n
s
we
re
in
v
e
stig
a
ted
,
in
c
lu
d
in
g
b
a
se
li
n
e
sig
n
a
ls,
a
u
t
o
e
n
c
o
d
e
r
e
m
b
e
d
d
in
g
s,
a
n
d
c
o
n
v
o
l
u
ti
o
n
a
l
fe
a
tu
re
s
d
e
riv
e
d
fr
o
m
p
se
u
d
o
-
ima
g
e
tra
n
sfo
rm
a
ti
o
n
.
E
x
p
e
rime
n
ts
o
n
a
n
NV
IDIA
Je
tso
n
Na
n
o
u
sin
g
stra
ti
fie
d
fi
v
e
-
fo
ld
c
r
o
ss
-
v
a
li
d
a
ti
o
n
sh
o
we
d
th
a
t
re
sid
u
a
l
-
b
a
se
d
re
p
re
se
n
tatio
n
s
sig
n
ifi
c
a
n
t
l
y
imp
r
o
v
e
d
p
e
rf
o
rm
a
n
c
e
.
Th
e
li
g
h
twe
ig
h
t
re
sid
u
a
l
n
e
tw
o
rk
a
c
h
iev
e
d
a
n
a
c
c
u
ra
c
y
o
f
0
.
9
9
7
2
with
lo
w
train
i
n
g
ti
m
e
a
n
d
me
m
o
ry
u
sa
g
e
.
P
a
re
to
a
n
a
l
y
si
s
c
o
n
firms
t
h
a
t
o
p
ti
m
a
l
p
e
rfo
r
m
a
n
c
e
is
a
c
h
iev
e
d
b
y
b
a
la
n
c
in
g
a
c
c
u
ra
c
y
a
n
d
re
so
u
rc
e
c
o
n
stra
in
ts,
t
h
e
re
b
y
e
n
a
b
li
n
g
re
li
a
b
le d
e
p
l
o
y
m
e
n
t
in
e
d
g
e
a
n
d
I
o
T
e
n
v
iro
n
m
e
n
ts.
K
ey
w
o
r
d
s
:
C
o
f
f
ee
ar
o
m
a
class
if
icatio
n
E
d
g
e
co
m
p
u
tin
g
E
lectr
o
n
ic
n
o
s
e
Featu
r
e
r
ep
r
esen
tatio
n
L
ig
h
tGB
M
MO
S sen
s
o
r
ar
r
ay
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
:
Sety
awa
n
Pu
r
n
o
m
o
Sak
ti
Dep
ar
tm
en
t o
f
Ph
y
s
ics,
B
r
awi
jay
a
Un
iv
er
s
ity
J
l.
Vete
r
an
,
Keta
wan
g
g
ed
e,
L
o
wo
k
war
u
,
Ko
ta
Ma
lan
g
,
J
aw
a
T
im
u
r
6
5
1
4
5
,
I
n
d
o
n
esia
E
m
ail: sak
ti@
u
b
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
C
o
f
f
ee
ar
o
m
a
p
lay
s
a
cr
itical
r
o
le
in
d
eter
m
in
in
g
p
r
o
d
u
ct
q
u
ality
an
d
co
m
m
er
cial
v
alu
e
,
p
ar
ticu
lar
ly
in
m
ajo
r
p
r
o
d
u
ci
n
g
c
o
u
n
tr
ies
s
u
ch
as
I
n
d
o
n
esia,
B
r
az
il,
a
n
d
E
th
io
p
ia
[
1
]
–
[
3
]
.
C
o
n
v
en
tio
n
al
ev
alu
atio
n
r
elies
o
n
s
en
s
o
r
y
cu
p
p
in
g
,
wh
ich
is
in
h
er
en
tly
s
u
b
jectiv
e
an
d
s
en
s
itiv
e
to
ev
alu
ato
r
f
atig
u
e,
en
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
,
an
d
in
co
n
s
is
ten
cies
ac
r
o
s
s
s
es
s
io
n
s
[
4
]
,
[
5
]
.
T
h
ese
lim
itatio
n
s
m
o
tiv
ate
th
e
d
ev
elo
p
m
en
t
o
f
o
b
jectiv
e
an
d
r
ep
r
o
d
u
ci
b
le
s
en
s
in
g
s
y
s
tem
s
f
o
r
co
n
s
is
ten
t a
r
o
m
a
ass
ess
m
en
ts
.
E
lectr
o
n
ic
n
o
s
e
(
e
-
n
o
s
e)
s
y
s
tem
s
ad
d
r
ess
th
is
n
ee
d
b
y
co
m
b
in
in
g
g
as
s
en
s
o
r
ar
r
ay
s
with
p
atter
n
r
ec
o
g
n
itio
n
alg
o
r
ith
m
s
to
class
if
y
v
o
latile
c
o
m
p
o
u
n
d
s
ig
n
at
u
r
es
[
6
]
–
[
1
2
]
.
Me
tal
-
o
x
id
e
s
e
m
ico
n
d
u
ct
o
r
(
MO
S)
s
en
s
o
r
s
ar
e
wid
ely
ad
o
p
ted
d
u
e
to
th
eir
s
en
s
itiv
ity
,
lo
w
co
s
t,
a
n
d
co
m
p
atib
ilit
y
with
p
o
r
tab
le
d
ev
ices
[
1
3
]
–
[
1
7
]
.
Ho
we
v
er
,
t
h
eir
r
es
p
o
n
s
es
ar
e
a
f
f
ec
ted
b
y
n
o
is
e,
d
r
if
t,
an
d
n
o
n
lin
ea
r
ch
a
r
ac
ter
i
s
tics
,
wh
ich
r
eq
u
ir
e
r
o
b
u
s
t
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
c
lass
if
icatio
n
m
eth
o
d
s
.
Prio
r
s
t
u
d
ies
h
av
e
ex
p
lo
r
e
d
m
ac
h
in
e
l
ea
r
n
in
g
tech
n
i
q
u
es
s
u
ch
as
k
-
n
ea
r
est
n
eig
h
b
o
r
s
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es,
r
an
d
o
m
f
o
r
est,
XGBo
o
s
t,
an
d
n
e
u
r
al
n
etwo
r
k
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
d
g
e
-
a
w
a
r
e
co
ffee
a
r
o
ma
cla
s
s
ifica
tio
n
u
s
in
g
mu
lti
-
r
ep
r
ese
n
ta
tio
n
…
(
Den
d
a
Dewa
ta
ma
)
2097
[
1
8
]
–
[
2
4
]
.
Alth
o
u
g
h
ef
f
ec
tiv
e
in
co
n
tr
o
lled
en
v
ir
o
n
m
en
t
s
,
th
ese
ap
p
r
o
ac
h
es
ar
e
ty
p
i
ca
lly
ev
alu
ated
o
n
d
esk
to
p
s
y
s
tem
s
an
d
d
o
n
o
t c
o
n
s
id
er
th
e
co
n
s
tr
ain
ts
o
f
r
ea
l
-
wo
r
ld
em
b
e
d
d
ed
d
ep
lo
y
m
en
ts
[
2
5
]
.
R
ec
en
t
ad
v
an
ce
s
in
e
m
b
ed
d
e
d
ar
tific
ial
in
tellig
en
ce
a
n
d
e
d
g
e
co
m
p
u
tin
g
h
a
v
e
en
a
b
led
m
ac
h
in
e
lear
n
in
g
m
o
d
els
to
o
p
er
ate
d
ir
ec
tly
o
n
r
eso
u
r
ce
-
co
n
s
tr
ain
e
d
p
latf
o
r
m
s
s
u
ch
as
J
etso
n
Nan
o
,
FP
GAs,
an
d
m
icr
o
co
n
tr
o
ller
s
[
2
6
]
–
[
2
8
]
.
I
n
s
u
ch
e
n
v
ir
o
n
m
en
ts
,
m
o
d
el
s
elec
tio
n
m
u
s
t
c
o
n
s
id
er
n
o
t
o
n
l
y
th
e
class
if
icatio
n
ac
cu
r
ac
y
b
u
t
also
th
e
co
m
p
u
t
atio
n
al
ef
f
icien
cy
,
in
clu
d
in
g
t
h
e
tr
ain
in
g
tim
e
an
d
m
e
m
o
r
y
u
s
ag
e.
L
ig
h
tweig
h
t
m
o
d
els,
s
u
ch
as
L
ig
h
tGB
M,
p
r
o
v
id
e
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
wit
h
lo
w
m
em
o
r
y
c
o
n
s
u
m
p
tio
n
[
2
9
]
,
[
3
0
]
;
h
o
wev
er
,
th
eir
ef
f
ec
tiv
en
ess
d
ep
en
d
s
o
n
th
e
q
u
ality
o
f
th
e
f
ea
tu
r
e
r
ep
r
esen
tatio
n
.
R
aw
s
en
s
o
r
s
ig
n
als
o
f
ten
co
n
tain
r
ed
u
n
d
an
t
an
d
n
o
is
y
in
f
o
r
m
atio
n
,
lim
itin
g
th
eir
d
is
cr
im
in
ativ
e
ca
p
ab
ilit
y
[
3
1
]
.
R
ep
r
esen
tatio
n
lear
n
in
g
ap
p
r
o
ac
h
es,
in
clu
d
in
g
au
to
en
co
d
er
s
an
d
co
n
v
o
l
u
tio
n
al
n
et
wo
r
k
s
,
ca
n
ca
p
tu
r
e
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
an
d
in
ter
-
s
en
s
o
r
d
ep
e
n
d
en
cies to
i
m
p
r
o
v
e
f
ea
tu
r
e
q
u
ality
[
3
2
]
–
[
3
7
]
.
Desp
ite
th
ese
ad
v
an
ce
s
,
m
o
s
t
ex
is
tin
g
s
tu
d
ies
ev
al
u
ate
a
s
in
g
le
f
ea
tu
r
e
r
ep
r
esen
tatio
n
o
r
f
o
cu
s
p
r
im
ar
ily
o
n
ac
cu
r
ac
y
with
o
u
t
q
u
an
tif
y
in
g
th
e
c
o
m
p
u
tatio
n
al
co
s
t
o
n
th
e
tar
g
et
p
latf
o
r
m
.
C
o
n
s
eq
u
en
tly
,
th
e
tr
ad
e
-
o
f
f
b
etwe
en
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
an
d
em
b
e
d
d
ed
r
eso
u
r
ce
co
n
s
tr
ain
ts
r
em
ain
s
in
s
u
f
f
icien
tly
ex
p
lo
r
e
d
,
th
er
eb
y
lim
itin
g
p
r
ac
tical
d
ep
l
o
y
m
en
t.
T
h
is
s
tu
d
y
ad
d
r
ess
es
th
is
g
ap
b
y
p
r
o
p
o
s
in
g
an
e
d
g
e
-
awa
r
e
ev
alu
atio
n
f
r
am
ewo
r
k
th
at
jo
in
tly
an
al
y
ze
s
ac
cu
r
ac
y
,
tr
ai
n
in
g
tim
e,
an
d
m
em
o
r
y
u
s
ag
e
ac
r
o
s
s
m
u
ltip
le
f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
in
teg
r
at
es
f
iv
e
f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
,
in
clu
d
in
g
b
aselin
e
s
ig
n
als,
a
u
to
en
co
d
er
em
b
ed
d
in
g
s
,
an
d
co
n
v
o
l
u
tio
n
a
l
f
ea
tu
r
es
d
e
r
iv
ed
f
r
o
m
p
s
eu
d
o
-
im
ag
e
tr
a
n
s
f
o
r
m
atio
n
s
,
in
a
u
n
if
ied
L
ig
h
tGB
M
-
b
ased
p
ip
elin
e.
E
x
p
e
r
im
en
ts
wer
e
co
n
d
u
cted
o
n
an
NVI
D
I
A
J
etso
n
Nan
o
u
s
in
g
a
b
alan
ce
d
d
ataset
o
f
1
2
ar
o
m
a
class
es.
A
Par
eto
-
f
r
o
n
t
an
aly
s
is
was
ap
p
lied
to
id
en
tify
th
e
o
p
tim
al
tr
ad
e
-
o
f
f
s
b
etwe
en
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
an
d
co
m
p
u
tatio
n
al
ef
f
icien
cy
,
e
n
ab
lin
g
p
r
ac
tic
al
d
ep
lo
y
m
e
n
t in
em
b
ed
d
e
d
en
v
ir
o
n
m
e
n
ts
.
T
h
e
co
n
tr
i
b
u
tio
n
s
o
f
th
is
s
tu
d
y
ar
e
th
r
ee
f
o
ld
.
−
A
r
ep
r
o
d
u
cib
le
s
en
s
o
r
ar
r
a
y
-
b
ased
f
r
am
ewo
r
k
f
o
r
co
f
f
ee
ar
o
m
a
id
en
tific
atio
n
th
at
in
te
g
r
ates
s
en
s
in
g
,
f
ea
tu
r
e
ex
tr
ac
tio
n
,
an
d
em
b
e
d
d
ed
class
if
icatio
n
−
A
s
y
s
tem
atic
p
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
o
f
f
iv
e
f
ea
tu
r
e
ex
tr
a
ctio
n
tech
n
iq
u
es
co
m
b
i
n
ed
wi
th
a
lig
h
tweig
h
t
g
r
ad
ien
t b
o
o
s
tin
g
class
if
ier
u
n
d
er
r
ea
l e
m
b
ed
d
e
d
co
n
s
tr
ain
ts
.
−
A
Par
eto
-
f
r
o
n
t
an
aly
s
is
was
p
er
f
o
r
m
ed
to
id
en
tif
y
th
e
o
p
t
im
al
b
alan
ce
am
o
n
g
ac
c
u
r
ac
y
,
r
u
n
tim
e,
a
n
d
m
o
d
el
c
o
m
p
lex
ity
,
d
e
m
o
n
s
tr
a
tin
g
th
e
s
u
itab
ilit
y
o
f
a
lig
h
t
weig
h
t
r
esid
u
al
n
etwo
r
k
with
L
ig
h
tGB
M
f
o
r
p
o
r
tab
le
ar
o
m
a
class
if
icatio
n
s
y
s
tem
s
.
2.
M
E
T
H
O
D
2
.
1
.
Co
f
f
ee
s
a
m
ples
a
nd
a
ro
m
a
cl
a
s
s
es
C
o
f
f
ee
s
am
p
les
wer
e
s
elec
ted
to
r
ep
r
esen
t
co
m
m
o
n
I
n
d
o
n
esian
p
r
o
d
u
ctio
n
co
n
d
itio
n
s
,
co
v
er
in
g
b
o
th
Ar
ab
ica
an
d
R
o
b
u
s
ta
v
ar
ieties
f
r
o
m
f
o
u
r
r
e
g
io
n
s
:
Sem
er
u
,
K
awi,
T
ir
to
y
u
d
o
a
n
d
Ged
a
n
g
an
.
Sem
er
u
an
d
Kaw
i
r
ep
r
esen
t
h
i
g
h
-
altitu
d
e
Ar
ab
ic
a,
wh
ile
T
ir
to
y
u
d
o
an
d
Ged
a
n
g
an
r
e
p
r
esen
t
lo
wer
-
altitu
d
e
R
o
b
u
s
ta.
E
ac
h
o
r
ig
in
was
p
r
ep
ar
ed
at
th
r
ee
r
o
asti
n
g
lev
els
(
lig
h
t,
m
e
d
iu
m
,
a
n
d
d
a
r
k
)
,
r
esu
ltin
g
in
1
2
ar
o
m
a
cla
s
s
es,
as
d
ef
in
ed
in
T
ab
le
1
.
T
ab
le
1
.
Def
in
itio
n
o
f
c
o
f
f
ee
a
r
o
m
a
class
es
C
l
a
s
s I
D
C
o
f
f
e
e
O
r
i
g
i
n
A
l
t
i
t
u
d
e
(
md
p
l
)
S
p
e
c
i
e
s
R
o
a
st
Le
v
e
l
La
b
e
l
1
S
e
meru
1
0
0
0
–
1
5
0
0
A
r
a
b
i
c
a
Li
g
h
t
a
S
e
m
-
L
2
S
e
meru
1
0
0
0
–
1
5
0
0
A
r
a
b
i
c
a
M
e
d
i
u
m
a
S
e
m
-
M
3
S
e
meru
1
0
0
0
–
1
5
0
0
A
r
a
b
i
c
a
D
a
r
k
a
S
e
m
-
D
4
Ti
r
t
o
y
u
d
o
1
0
0
–
300
R
o
b
u
st
a
Li
g
h
t
r
Ti
r
-
L
5
Ti
r
t
o
y
u
d
o
1
0
0
–
300
R
o
b
u
st
a
M
e
d
i
u
m
r
Ti
r
-
M
6
Ti
r
t
o
y
u
d
o
1
0
0
–
300
R
o
b
u
st
a
D
a
r
k
r
Ti
r
-
D
7
K
a
w
i
1
0
0
0
–
1
5
0
0
A
r
a
b
i
c
a
Li
g
h
t
a
K
a
w
-
L
8
K
a
w
i
1
0
0
0
–
1
5
0
0
A
r
a
b
i
c
a
M
e
d
i
u
m
a
K
a
w
-
M
9
K
a
w
i
1
0
0
0
–
1
5
0
0
A
r
a
b
i
c
a
D
a
r
k
a
K
a
w
-
D
10
G
e
d
a
n
g
a
n
8
0
0
–
1
2
0
0
R
o
b
u
st
a
Li
g
h
t
r
G
e
d
-
L
11
G
e
d
a
n
g
a
n
8
0
0
–
1
2
0
0
R
o
b
u
st
a
M
e
d
i
u
m
r
G
e
d
-
M
12
G
e
d
a
n
g
a
n
8
0
0
–
1
2
0
0
R
o
b
u
st
a
D
a
r
k
r
G
e
d
-
D
T
o
en
s
u
r
e
co
n
s
is
ten
cy
,
all
s
a
m
p
les
wer
e
s
to
r
ed
in
s
ea
led
c
o
n
tain
er
s
an
d
m
ea
s
u
r
ed
u
n
d
e
r
th
e
s
am
e
co
n
d
itio
n
s
.
Fo
r
ea
c
h
tr
ial,
1
0
g
o
f
f
r
esh
ly
g
r
o
u
n
d
co
f
f
ee
was
p
lace
d
in
th
e
s
am
p
lin
g
c
h
am
b
er
im
m
e
d
iately
af
ter
g
r
in
d
in
g
to
m
i
n
im
ize
th
e
o
x
id
atio
n
.
A
to
tal
o
f
1
,
0
8
0
tr
i
als
wer
e
co
llected
with
a
b
ala
n
ce
d
r
e
p
r
esen
tatio
n
ac
r
o
s
s
all
class
e
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
4
,
Au
g
u
s
t
20
2
6
:
2
0
9
6
-
2
105
2098
2
.
2
.
E
-
no
s
e
ha
rdwa
re
a
nd
em
bedd
ed
pla
t
f
o
rm
T
h
e
e
-
n
o
s
e
s
y
s
tem
co
n
s
is
ts
o
f
a
s
ix
-
ch
an
n
el
MO
S
s
en
s
o
r
ar
r
a
y
,
a
n
E
SP
3
2
m
icr
o
c
o
n
tr
o
ller
f
o
r
ac
q
u
is
itio
n
,
an
d
an
NVI
DI
A
J
etso
n
Nan
o
f
o
r
p
r
o
ce
s
s
in
g
,
as
illu
s
tr
ated
in
Fig
u
r
es
1
an
d
2
.
T
h
e
s
en
s
o
r
ar
r
a
y
in
clu
d
es
MQ
1
3
5
,
MQ
2
,
MQ
3
,
MQ
6
,
MQ
1
3
8
,
a
n
d
MQ
7
,
p
r
o
v
id
in
g
c
o
m
p
lem
e
n
tar
y
s
e
n
s
itiv
ity
to
v
o
latile
co
m
p
o
u
n
d
s
in
c
o
f
f
ee
a
r
o
m
a
[
3
8
]
.
Fig
u
r
e
1
.
E
-
n
o
s
e
s
y
s
tem
ar
ch
it
ec
tu
r
e
Fig
u
r
e
2
.
Ph
y
s
ical
p
r
o
to
ty
p
e
o
f
th
e
e
-
n
o
s
e,
s
h
o
win
g
th
e
s
am
p
lin
g
ch
am
b
er
,
p
u
m
p
s
,
an
d
em
b
e
d
d
ed
h
ar
d
wa
r
e
2
.
3
.
Da
t
a
a
cquis
it
io
n a
nd
pr
epro
ce
s
s
ing
T
h
e
m
ea
s
u
r
em
en
t
s
y
s
tem
em
p
lo
y
s
a
d
u
al
-
ch
a
m
b
er
c
o
n
f
ig
u
r
a
tio
n
co
n
s
is
tin
g
o
f
a
c
o
f
f
ee
c
h
a
m
b
er
an
d
a
s
en
s
o
r
ch
am
b
er
c
o
n
n
ec
ted
b
y
d
iap
h
r
ag
m
p
u
m
p
s
,
as
s
h
o
w
n
in
Fig
u
r
e
2
.
T
h
e
co
m
p
lete
a
r
o
m
a
m
ea
s
u
r
e
m
en
t
p
r
o
to
co
l
an
d
th
e
c
o
r
r
esp
o
n
d
i
n
g
s
en
s
o
r
s
ig
n
al
cu
r
v
es
ar
e
d
ep
icted
in
Fig
u
r
e
3
.
E
ac
h
tr
i
al
f
o
llo
wed
a
f
ix
e
d
f
o
u
r
-
s
tag
e
p
r
o
t
o
co
l:
b
aselin
e
co
n
d
itio
n
in
g
,
ar
o
m
a
e
x
p
o
s
u
r
e
,
s
tead
y
-
s
tate
ac
q
u
is
itio
n
,
a
n
d
f
lu
s
h
in
g
.
B
aselin
e
s
tab
ilizatio
n
was
p
er
f
o
r
m
ed
f
o
r
ap
p
r
o
x
im
ately
9
0
s
u
s
in
g
cl
ea
n
air
.
Ar
o
m
a
ex
p
o
s
u
r
e
was
th
en
in
itiated
,
an
d
th
e
s
en
s
o
r
r
esp
o
n
s
es
g
r
ad
u
ally
in
cr
ea
s
ed
.
Du
r
in
g
t
h
e
s
tead
y
-
s
tate
p
h
ase,
s
tar
tin
g
at
ap
p
r
o
x
i
m
ately
1
1
0
s
,
th
r
e
e
r
ea
d
in
g
s
f
r
o
m
ea
ch
o
f
t
h
e
s
ix
s
en
s
o
r
ch
an
n
els
wer
e
c
o
llected
at
3
s
in
ter
v
als
an
d
av
er
a
g
e
d
to
o
b
tain
a
s
tab
le
s
ix
-
d
im
en
s
io
n
al
f
ea
tu
r
e
v
ec
to
r
.
T
h
e
s
y
s
tem
th
en
r
et
u
r
n
e
d
t
o
th
e
f
l
u
s
h
in
g
s
tag
e
t
o
r
em
o
v
e
th
e
r
esid
u
al
g
ases
b
ef
o
r
e
t
h
e
n
ex
t tr
ial.
Sen
s
o
r
d
ata
wer
e
ac
q
u
ir
ed
b
y
th
e
E
SP
3
2
an
d
d
ig
itized
u
s
in
g
ADS1
1
1
5
co
n
v
e
r
ter
s
,
wh
ich
wer
e
th
en
tr
an
s
m
itted
to
th
e
J
etso
n
Nan
o
f
o
r
s
to
r
a
g
e
an
d
p
r
o
ce
s
s
in
g
.
E
ac
h
tr
ial
was
r
ec
o
r
d
e
d
as
a
s
in
g
le
d
ata
in
s
tan
ce
co
n
s
is
tin
g
o
f
s
ix
s
en
s
o
r
f
ea
tu
r
es
an
d
a
co
r
r
esp
o
n
d
i
n
g
class
l
ab
el.
A
b
alan
ce
d
d
ataset
s
tr
u
ctu
r
e
was
m
ain
tain
e
d
ac
r
o
s
s
th
e
1
2
ar
o
m
a
class
es to
en
s
u
r
e
an
u
n
b
iased
ev
al
u
atio
n
.
Prio
r
to
m
o
d
el
tr
ain
in
g
,
in
co
m
p
lete
r
ec
o
r
d
s
wer
e
r
em
o
v
e
d
.
Min
–
Ma
x
n
o
r
m
aliza
tio
n
is
ap
p
lied
to
ea
ch
f
ea
tu
r
e
d
im
e
n
s
io
n
to
ad
d
r
ess
s
ca
le
d
if
f
er
en
ce
s
b
etwe
en
s
en
s
o
r
s
.
I
n
s
tr
atif
ied
f
iv
e
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
,
n
o
r
m
aliza
tio
n
p
ar
a
m
eter
s
ar
e
co
m
p
u
ted
o
n
th
e
tr
ain
i
n
g
s
p
lit
an
d
ap
p
lied
to
th
e
v
alid
atio
n
s
p
lit
to
p
r
e
v
en
t
th
e
leak
ag
e
o
f
d
ata.
T
h
is
p
r
e
p
r
o
ce
s
s
in
g
p
ip
elin
e
en
s
u
r
es c
o
n
s
is
ten
t d
ata
r
ep
r
esen
tatio
n
an
d
f
air
co
m
p
ar
is
o
n
ac
r
o
s
s
th
e
f
ea
tu
r
e
r
e
p
r
esen
tatio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
d
g
e
-
a
w
a
r
e
co
ffee
a
r
o
ma
cla
s
s
ifica
tio
n
u
s
in
g
mu
lti
-
r
ep
r
ese
n
ta
tio
n
…
(
Den
d
a
Dewa
ta
ma
)
2099
Fig
u
r
e
3
.
Ar
o
m
a
m
ea
s
u
r
e
m
en
t
p
r
o
to
c
o
l a
n
d
s
en
s
o
r
r
esp
o
n
s
e
2
.
4
.
F
e
a
t
ure
re
presenta
t
io
n,
m
o
del t
ra
ini
ng
,
a
nd
ev
a
lua
t
io
n pro
t
o
co
l
Fiv
e
f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
wer
e
ev
alu
ated
with
in
a
u
n
if
i
ed
p
ip
elin
e,
as
illu
s
tr
ated
in
Fig
u
r
e
4
an
d
Alg
o
r
ith
m
1
,
in
clu
d
in
g
b
aselin
e
s
en
s
o
r
s
ig
n
als,
au
to
en
co
d
e
r
em
b
ed
d
i
n
g
s
,
an
d
co
n
v
o
l
u
tio
n
al
f
ea
tu
r
es
d
er
iv
ed
f
r
o
m
p
s
eu
d
o
-
i
m
ag
e
tr
a
n
s
f
o
r
m
atio
n
s
u
s
in
g
Mo
b
ileNetV2
,
R
esNet1
8
,
an
d
a
lig
h
tweig
h
t
r
e
s
id
u
al
n
etwo
r
k
.
T
h
e
p
s
eu
d
o
-
im
a
g
e
ar
r
an
g
es
th
e
s
en
s
o
r
ch
an
n
els
in
to
a
s
tr
u
ctu
r
e
d
g
r
id
t
o
ca
p
tu
r
e
th
e
in
ter
-
s
en
s
o
r
r
elatio
n
s
h
ip
s
an
d
en
ab
le
co
n
v
o
lu
tio
n
al
p
r
o
c
ess
i
n
g
.
E
ac
h
tr
ial
was
n
o
r
m
alize
d
a
n
d
tr
a
n
s
f
o
r
m
e
d
u
s
in
g
th
e
s
el
ec
ted
r
ep
r
esen
tatio
n
.
T
h
e
b
as
elin
e
u
s
es
d
ir
ec
t
s
en
s
o
r
f
ea
tu
r
es,
wh
er
ea
s
th
e
au
to
en
co
d
er
p
r
o
d
u
ce
s
c
o
m
p
ac
t
laten
t
em
b
ed
d
in
g
s
.
C
o
n
v
o
lu
ti
o
n
al
m
o
d
els
ar
e
ap
p
lied
as
f
ix
e
d
f
ea
tu
r
e
ex
tr
ac
to
r
s
with
o
u
t
f
in
e
-
tu
n
in
g
,
an
d
em
b
ed
d
in
g
s
ar
e
o
b
tai
n
ed
f
r
o
m
t
h
e
f
i
n
al
p
o
o
lin
g
la
y
er
.
T
h
e
ex
tr
ac
ted
f
ea
tu
r
es
wer
e
f
latten
ed
an
d
u
s
ed
as
in
p
u
ts
to
L
ig
h
tGB
M,
en
ab
lin
g
a
co
n
tr
o
lled
co
m
p
ar
is
o
n
ac
r
o
s
s
r
ep
r
esen
tat
io
n
ty
p
es.
Fig
u
r
e
4.
B
lo
ck
d
iag
r
am
of
th
e
p
r
o
p
o
s
ed
e
-
n
o
s
e
b
ased
ar
o
m
a
class
if
icatio
n
f
r
am
ewo
r
k
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
4
,
Au
g
u
s
t
20
2
6
:
2
0
9
6
-
2
105
2100
Alg
o
r
ith
m
1.
E
d
g
e
-
awa
r
e
co
f
f
ee
ar
o
m
a
class
if
icatio
n
p
ip
elin
e
Input:
Sensor
signal
matrix
X
from
e
-
nose
array
Output:
Predicted
coffee
aroma
label
ŷ
1:
Acquire
multichannel
gas
response
X
=
{x
₁
,
x
₂
,
…,
x
ₙ
}
2:
Preprocess
signals:
-
Normalize
using
MinMaxScaler
-
Apply
label
encoding
3:
Select
feature
extractor
Eθ
∈
{ResNet18,
MobileNetV2,
Autoencoder,
Lightweight
ResNet}
4:
Compute
feature
vector
f
=
Eθ(X)
5:
Flatten
f
into
1D
numerical
array
6:
Classify
using
LightGBM:
ŷ
=
f_LGBM(f)
7:
Evaluate
performance
metrics
and
inference
time
T
o
en
s
u
r
e
a
f
air
co
m
p
ar
is
o
n
,
all
co
n
f
ig
u
r
atio
n
s
f
o
llo
we
d
an
id
en
tical
tr
ain
in
g
a
n
d
ev
alu
atio
n
p
r
o
to
co
l.
H
y
p
er
p
a
r
am
eter
tu
n
i
n
g
was
p
er
f
o
r
m
ed
u
s
in
g
a
u
n
i
f
o
r
m
s
ea
r
ch
s
tr
ateg
y
with
th
e
s
am
e
s
ea
r
ch
s
p
ac
e
an
d
ev
alu
atio
n
b
u
d
g
et
ac
r
o
s
s
all
f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
,
co
v
er
in
g
k
e
y
p
ar
am
eter
s
s
u
ch
as
th
e
n
u
m
b
er
o
f
esti
m
ato
r
s
,
lear
n
in
g
r
ate,
tr
ee
d
ep
th
,
a
n
d
r
eg
u
la
r
izatio
n
.
T
h
e
f
in
al
h
y
p
er
p
ar
am
eter
s
wer
e
s
elec
ted
b
ased
o
n
th
e
v
alid
atio
n
p
er
f
o
r
m
an
ce
with
in
th
e
s
am
e
s
tr
atif
ied
f
iv
e
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
f
r
am
ewo
r
k
,
e
n
s
u
r
in
g
a
co
n
s
is
ten
t
an
d
r
e
p
r
o
d
u
cib
le
ev
alu
atio
n
.
T
h
e
s
p
ec
if
ic
h
y
p
e
r
p
ar
am
eter
v
alu
es
f
in
alize
d
f
o
r
th
e
L
i
g
h
tGB
M
class
if
ier
ac
r
o
s
s
all
b
aselin
e
an
d
ex
tr
ac
ted
f
ea
t
u
r
es a
r
e
p
r
esen
ted
in
T
ab
le
2
.
T
h
e
m
o
d
e
l
p
e
r
f
o
r
m
a
n
c
e
wa
s
as
s
ess
e
d
u
s
i
n
g
a
c
c
u
r
a
c
y
,
m
ac
r
o
F
1
-
s
c
o
r
e
,
a
n
d
m
a
c
r
o
-
A
UC
.
T
h
e
t
r
a
i
n
i
n
g
t
i
m
e
wa
s
m
e
a
s
u
r
e
d
u
s
i
n
g
t
h
e
Py
t
h
o
n
t
i
m
e
m
o
d
u
l
e
,
w
h
e
r
e
a
s
t
h
e
p
e
a
k
m
e
m
o
r
y
u
s
a
g
e
w
as
r
e
co
r
d
e
d
u
s
i
n
g
a
s
t
h
e
i
n
c
r
e
m
e
n
t
a
l
R
A
M
c
o
n
s
u
m
p
t
i
o
n
,
e
x
c
l
u
d
i
n
g
t
h
e
s
y
s
t
em
o
v
e
r
h
e
a
d
.
T
h
i
s
u
n
i
f
i
e
d
p
r
o
t
o
c
o
l
e
n
s
u
r
e
s
t
h
at
t
h
e
o
b
s
e
r
v
e
d
p
e
r
f
o
r
m
a
n
c
e
d
i
f
f
e
r
e
n
c
e
s
a
r
e
a
tt
r
i
b
u
t
e
d
t
o
f
e
a
t
u
r
e
r
ep
r
e
s
e
n
t
a
ti
o
n
r
a
t
h
e
r
t
h
a
n
d
i
s
c
r
ep
a
n
c
i
e
s
i
n
t
u
n
i
n
g
o
r
e
v
a
l
u
a
t
i
o
n
,
w
h
il
e
s
u
p
p
o
r
t
i
n
g
em
b
e
d
d
e
d
d
e
p
l
o
y
m
e
n
t
t
h
r
o
u
g
h
P
a
r
e
t
o
-
b
a
s
e
d
t
r
a
d
e
-
o
f
f
a
n
a
l
y
s
i
s
.
T
ab
le
2
.
L
ig
h
tGB
M
h
y
p
er
p
a
r
a
m
eter
s
ettin
g
s
f
o
r
ea
ch
f
ea
tu
r
e
r
ep
r
esen
tatio
n
P
a
r
a
me
t
e
r
B
a
se
l
i
n
e
A
u
t
o
e
n
c
o
d
e
r
M
o
b
i
l
e
N
e
t
V
2
R
e
sN
e
t
-
18
Li
g
h
t
w
e
i
g
h
t
R
e
sN
e
t
B
o
o
st
i
n
g
G
B
D
T
G
B
D
T
G
B
D
T
G
B
D
T
G
B
D
T
O
b
j
e
c
t
i
v
e
M
u
l
t
i
c
l
a
ss
M
u
l
t
i
c
l
a
ss
M
u
l
t
i
c
l
a
ss
M
u
l
t
i
c
l
a
ss
M
u
l
t
i
c
l
a
ss
N
u
mb
e
r
o
f
c
l
a
sse
s
12
12
12
12
12
n
_
e
st
i
ma
t
o
r
s
2
0
0
0
1
5
0
1
2
0
1
0
0
1
0
0
Le
a
r
n
i
n
g
r
a
t
e
0
.
0
3
0
.
0
5
0
.
0
1
0
.
1
0
.
1
M
a
x
d
e
p
t
h
–
1
7
5
6
6
N
u
m.
l
e
a
v
e
s
47
D
e
f
a
u
l
t
D
e
f
a
u
l
t
D
e
f
a
u
l
t
D
e
f
a
u
l
t
M
i
n
d
a
t
a
i
n
l
e
a
f
80
D
e
f
a
u
l
t
20
D
e
f
a
u
l
t
D
e
f
a
u
l
t
F
e
a
t
u
r
e
f
r
a
c
t
i
o
n
0
.
8
0
.
9
0
.
8
0
.
8
0
.
8
B
a
g
g
i
n
g
f
r
a
c
t
i
o
n
0
.
6
0
.
9
0
.
8
0
.
8
0
.
8
B
a
g
g
i
n
g
f
r
e
q
u
e
n
c
y
1
–
–
–
–
L1
r
e
g
u
l
a
r
i
z
a
t
i
o
n
(
λ
₁)
0
.
0
1
8
6
–
0
.
1
–
–
L2
r
e
g
u
l
a
r
i
z
a
t
i
o
n
(
λ
₂)
1
.
8
6
3
5
–
0
.
1
–
–
M
a
x
b
i
n
1
2
7
D
e
f
a
u
l
t
D
e
f
a
u
l
t
D
e
f
a
u
l
t
D
e
f
a
u
l
t
Ea
r
l
y
st
o
p
p
i
n
g
Y
e
s (1
0
r
o
u
n
d
s)
No
No
Y
e
s (1
0
r
o
u
n
d
s)
Y
e
s (1
0
r
o
u
n
d
s)
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Cla
s
s
if
ica
t
io
n
perf
o
rm
a
nce
a
nd
re
s
o
urce
-
a
wa
re
a
na
ly
s
is
T
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
was
ev
alu
ated
u
s
in
g
f
iv
e
f
ea
tu
r
e
r
e
p
r
esen
tatio
n
s
tr
ateg
ies
co
m
b
in
ed
with
a
f
ix
ed
L
ig
h
tGB
M
class
if
ier
.
St
r
atif
ied
f
iv
e
-
f
o
ld
c
r
o
s
s
-
v
alid
at
io
n
was
ap
p
lied
,
an
d
th
e
r
esu
l
ts
ar
e
s
u
m
m
ar
ized
in
T
ab
le
3
,
wh
ich
in
clu
d
e
s
b
o
th
th
e
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
an
d
c
o
m
p
u
tatio
n
al
ef
f
icien
cy
.
Al
l
co
n
f
ig
u
r
atio
n
s
ac
h
iev
e
d
h
ig
h
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
,
co
n
f
ir
m
i
n
g
th
at
m
u
ltich
a
n
n
el
MO
S
s
en
s
o
r
r
esp
o
n
s
es
p
r
o
v
id
e
s
tr
o
n
g
d
is
cr
im
in
ativ
e
in
f
o
r
m
atio
n
f
o
r
co
f
f
ee
ar
o
m
a
class
if
icatio
n
.
T
h
e
b
aselin
e
m
o
d
el
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
0
.
9
7
5
9
with
m
in
im
al
tr
ai
n
in
g
tim
e
(
6
.
3
1
s
)
a
n
d
m
e
m
o
r
y
u
s
ag
e
(
0
.
3
4
MB)
,
estab
lis
h
in
g
a
r
eliab
le
an
d
e
f
f
i
cien
t r
ef
er
en
ce
f
o
r
r
eso
u
r
ce
-
c
o
n
s
tr
ain
ed
d
ep
l
o
y
m
en
t.
Featu
r
e
lear
n
in
g
f
u
r
th
e
r
im
p
r
o
v
ed
t
h
e
p
er
f
o
r
m
a
n
ce
.
T
h
e
au
to
en
co
d
er
in
c
r
ea
s
es
th
e
ac
cu
r
ac
y
to
0
.
9
8
5
2
wh
ile
m
ain
tain
in
g
lo
w
m
em
o
r
y
u
s
ag
e
(
0
.
3
3
MB)
b
u
t
in
tr
o
d
u
ce
s
a
s
ig
n
if
ican
tly
h
ig
h
er
tr
ai
n
in
g
tim
e
(
2
2
5
.
1
2
s
)
,
m
a
k
in
g
it
m
o
r
e
s
u
itab
le
f
o
r
o
f
f
lin
e
s
ce
n
a
r
io
s
.
I
n
co
n
tr
ast,
Mo
b
ileNetV2
ex
h
ib
ited
a
lo
wer
p
er
f
o
r
m
an
ce
(
0
.
9
3
6
1
ac
cu
r
ac
y
)
an
d
th
e
h
ig
h
est
co
m
p
u
tatio
n
al
co
s
t
(
6
2
4
.
1
6
s
)
,
in
d
icatin
g
t
h
at
its
ar
ch
itectu
r
e
was n
o
t w
ell
-
alig
n
ed
with
lo
w
-
d
im
en
s
io
n
al
p
s
eu
d
o
-
im
a
g
e
r
e
p
r
esen
tatio
n
s
.
R
esid
u
al
-
b
ased
f
ea
tu
r
e
ex
tr
ac
t
o
r
s
ac
h
iev
e
d
th
e
b
est
p
e
r
f
o
r
m
an
ce
.
R
esNet1
8
r
ea
ch
e
d
a
n
ac
cu
r
ac
y
o
f
0
.
9
9
6
3
b
u
t
r
eq
u
ir
ed
h
ig
h
er
m
em
o
r
y
(
2
.
4
9
MB),
wh
e
r
ea
s
th
e
lig
h
tweig
h
t
r
esid
u
al
n
et
wo
r
k
ac
h
ie
v
ed
th
e
h
ig
h
est ac
cu
r
ac
y
(
0
.
9
9
7
2
)
wit
h
s
ig
n
if
ican
tly
lo
wer
tr
ain
in
g
t
im
e
(
3
3
.
5
3
s
)
an
d
m
e
m
o
r
y
u
s
ag
e
(
0
.
8
3
MB).
T
h
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
d
g
e
-
a
w
a
r
e
co
ffee
a
r
o
ma
cla
s
s
ifica
tio
n
u
s
in
g
mu
lti
-
r
ep
r
ese
n
ta
tio
n
…
(
Den
d
a
Dewa
ta
ma
)
2101
d
em
o
n
s
tr
ates
th
at
r
esid
u
al
c
o
n
n
ec
tio
n
s
ef
f
ec
tiv
ely
ca
p
t
u
r
e
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
wh
ile
m
ain
tain
in
g
th
e
co
m
p
u
tatio
n
al
e
f
f
icien
cy
.
Fro
m
an
e
n
g
in
ee
r
in
g
p
er
s
p
ec
tiv
e,
th
ese
r
esu
lts
in
d
icat
e
th
at
p
er
f
o
r
m
a
n
ce
im
p
r
o
v
e
m
en
ts
ar
e
p
r
im
ar
ily
d
r
iv
e
n
b
y
f
ea
tu
r
e
r
ep
r
esen
tatio
n
r
ath
er
th
a
n
th
e
class
if
ier
co
m
p
lex
ity
.
T
h
e
b
aselin
e
m
o
d
el
is
s
u
itab
le
f
o
r
m
in
im
al
-
r
eso
u
r
ce
s
ce
n
ar
io
s
,
wh
er
ea
s
th
e
lig
h
t
weig
h
t
r
esid
u
al
m
o
d
el
o
f
f
er
s
th
e
b
est
b
ala
n
ce
b
etwe
en
ac
cu
r
ac
y
an
d
e
f
f
icien
cy
,
m
ak
in
g
it th
e
m
o
s
t p
r
ac
tical
ch
o
ice
f
o
r
r
ea
l
-
tim
e
em
b
ed
d
ed
d
ep
lo
y
m
en
t.
T
ab
le
3
.
C
lass
if
icatio
n
p
er
f
o
r
m
an
ce
(
5
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
)
f
o
r
d
if
f
er
e
n
t f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
M
e
t
h
o
d
A
c
c
u
r
a
c
y
M
a
c
r
o
F
1
M
a
c
r
o
A
U
C
Tr
a
i
n
i
n
g
t
i
me
(
s)
M
e
m
o
r
y
u
s
e
d
(
M
B
)
Li
g
h
t
G
B
M
B
a
se
l
i
n
e
0
.
9
7
5
9
0
.
9
7
6
0
0
.
9
9
9
3
6
.
3
1
0
.
3
4
A
u
t
o
e
n
c
o
d
e
r
+
Li
g
h
t
G
B
M
0
.
9
8
5
2
0
.
9
8
5
3
0
.
9
9
9
8
2
2
5
.
1
2
0
.
3
3
M
o
b
i
l
e
N
e
t
V
2
+
Li
g
h
t
G
B
M
0
.
9
3
6
1
0
.
9
3
6
3
0
.
9
9
8
0
6
2
4
.
1
6
0
.
7
3
R
e
sN
e
t
1
8
+
L
i
g
h
t
G
B
M
0
.
9
9
6
3
0
.
9
9
6
3
1
.
0
0
0
0
4
7
.
7
8
2
.
4
9
Li
g
h
t
w
e
i
g
h
t
R
e
sN
e
t
+
L
i
g
h
t
G
B
M
0
.
9
9
7
2
0
.
9
9
7
2
1
.
0
0
0
0
3
3
.
5
3
0
.
8
3
3
.
2
.
T
ra
de
-
o
f
f
a
na
ly
s
is
a
nd
pa
re
t
o
-
ef
f
icient
m
o
del selec
t
io
n
Mo
d
el
s
elec
tio
n
f
o
r
em
b
e
d
d
e
d
co
f
f
ee
ar
o
m
a
class
if
icatio
n
r
eq
u
ir
es
b
alan
cin
g
th
e
ac
cu
r
a
cy
,
tr
ain
in
g
tim
e,
an
d
m
em
o
r
y
u
s
ag
e.
Par
e
to
an
aly
s
is
was
ap
p
lied
u
s
in
g
th
ese
o
b
jectiv
es
o
n
th
e
J
etso
n
Nan
o
,
as
s
h
o
wn
in
Fig
u
r
e
5
,
to
id
e
n
tify
e
f
f
icien
t
co
n
f
ig
u
r
atio
n
s
.
Sp
ec
i
f
ically
,
Fig
u
r
e
5
(
a)
illu
s
tr
ates
th
e
c
o
m
p
r
eh
e
n
s
iv
e
3
D
o
b
jectiv
e
s
p
ac
e,
wh
ile
Fig
u
r
es
5
(
b
)
an
d
5
(
c)
d
etail
th
e
s
p
ec
if
ic
2
D
tr
a
d
e
-
o
f
f
s
o
f
ac
cu
r
ac
y
v
er
s
u
s
r
u
n
tim
e
an
d
ac
cu
r
ac
y
v
e
r
s
u
s
m
o
d
el
d
ep
th
,
r
esp
ec
tiv
ely
.
(
a)
(
b
)
(
c)
Fig
u
r
e
5
.
Par
eto
t
r
ad
e
-
o
f
f
a
n
aly
s
is
o
f
class
if
icatio
n
ac
cu
r
ac
y
v
er
s
u
s
tr
ain
in
g
tim
e
a
n
d
m
em
o
r
y
u
s
ag
e
o
n
J
etso
n
Nan
o
: (
a)
3
D
o
b
jectiv
e
s
p
ac
e
with
Par
eto
-
ef
f
icien
t m
e
th
o
d
s
h
ig
h
lig
h
ted
,
(
b
)
ac
c
u
r
ac
y
v
er
s
u
s
tr
ain
in
g
tim
e,
an
d
(
c
)
ac
cu
r
ac
y
v
er
s
u
s
m
em
o
r
y
u
s
ag
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
4
,
Au
g
u
s
t
20
2
6
:
2
0
9
6
-
2
105
2102
T
h
e
b
aselin
e
L
ig
h
tGB
M
m
o
d
el
r
ep
r
esen
ts
th
e
lo
west
-
co
s
t
s
o
lu
tio
n
with
m
in
im
al
tr
ain
in
g
tim
e
an
d
m
em
o
r
y
u
s
ag
e
as
s
h
o
wn
i
n
Fig
u
r
e
5
(
b
)
an
d
5
(
c)
,
m
ak
in
g
it
s
u
itab
le
f
o
r
h
ig
h
ly
r
e
s
o
u
r
ce
-
co
n
s
tr
ain
e
d
d
ep
lo
y
m
e
n
t.
T
h
e
a
u
to
en
c
o
d
er
im
p
r
o
v
es
ac
c
u
r
ac
y
with
lo
w
m
em
o
r
y
u
s
ag
e
b
u
t
in
cu
r
s
a
h
i
g
h
er
tr
ain
i
n
g
tim
e
,
lim
itin
g
its
u
s
e
to
o
f
f
lin
e
s
ce
n
ar
io
s
.
R
esid
u
al
-
b
ased
r
ep
r
esen
tatio
n
s
p
r
o
v
id
ed
th
e
m
o
s
t
b
alan
ce
d
p
er
f
o
r
m
a
n
ce
.
T
h
e
lig
h
tweig
h
t
r
esid
u
al
n
etwo
r
k
ac
h
iev
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
with
m
o
d
er
ate
r
eso
u
r
ce
u
s
ag
e
,
f
o
r
m
in
g
a
Par
eto
-
ef
f
icien
t
s
o
lu
tio
n
.
C
o
m
p
ar
ed
to
R
esNet1
8
,
it
o
f
f
er
s
a
s
im
ilar
p
er
f
o
r
m
an
ce
with
a
lo
wer
co
m
p
u
tatio
n
al
co
s
t
as
s
h
o
wn
in
Fig
u
r
e
5
(
b
)
.
Mo
b
ileNetV2
is
co
n
s
is
ten
tly
d
o
m
in
ated
,
s
h
o
win
g
lo
wer
ac
cu
r
ac
y
an
d
h
i
g
h
er
c
o
s
t
as
s
h
o
wn
in
Fig
u
r
e
5
(
a)
,
in
d
icatin
g
a
m
is
m
atch
with
lo
w
-
d
im
en
s
io
n
al
s
en
s
o
r
d
ata.
Fro
m
a
d
ep
lo
y
m
en
t
p
er
s
p
ec
tiv
e,
th
e
b
aselin
e
m
o
d
el
is
s
u
itab
le
f
o
r
m
in
im
al
-
r
eso
u
r
ce
s
y
s
tem
s
,
wh
er
ea
s
th
e
lig
h
tweig
h
t
r
esid
u
al
m
o
d
el
p
r
o
v
i
d
es
th
e
b
est b
alan
ce
f
o
r
r
ea
l
-
tim
e
ap
p
l
icatio
n
s
.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
d
em
o
n
s
tr
ates
th
at
f
ea
tu
r
e
r
ep
r
esen
tatio
n
p
l
ay
s
a
cr
itical
r
o
le
in
im
p
r
o
v
in
g
t
h
e
p
er
f
o
r
m
an
ce
o
f
e
-
n
o
s
es
u
n
d
er
em
b
ed
d
e
d
co
n
s
tr
ain
ts
.
W
h
ile
th
e
b
aselin
e
m
o
d
el
p
r
o
v
id
es
ef
f
icien
t
an
d
r
eliab
le
class
if
icatio
n
,
th
e
lear
n
ed
r
ep
r
esen
tatio
n
s
,
p
ar
ticu
lar
ly
th
e
r
esid
u
al
-
b
ased
f
ea
tu
r
es,
s
ig
n
if
i
ca
n
tly
en
h
a
n
ce
th
e
ac
cu
r
ac
y
an
d
s
tab
ilit
y
.
T
h
e
lig
h
tweig
h
t
r
esid
u
al
n
et
wo
r
k
co
m
b
in
ed
with
L
ig
h
tG
B
M
ac
h
iev
es
th
e
b
est
b
alan
ce
b
etwe
en
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
an
d
c
o
m
p
u
tatio
n
al
ef
f
icien
c
y
,
m
a
k
i
n
g
it
th
e
m
o
s
t
s
u
itab
le
ca
n
d
i
d
ate
f
o
r
em
b
e
d
d
ed
d
ep
lo
y
m
e
n
ts
.
T
h
e
Par
eto
an
al
y
s
is
co
n
f
ir
m
ed
t
h
at
o
p
tim
al
p
er
f
o
r
m
a
n
ce
was
o
b
tain
e
d
b
y
b
alan
cin
g
ac
c
u
r
ac
y
,
tr
ain
in
g
tim
e,
an
d
m
em
o
r
y
u
s
ag
e
r
ath
er
t
h
an
in
cr
ea
s
in
g
th
e
m
o
d
el
co
m
p
lex
ity
.
T
h
e
p
r
o
p
o
s
ed
e
d
g
e
-
awa
r
e
ev
a
lu
atio
n
f
r
am
ew
o
r
k
p
r
o
v
id
es
p
r
ac
tical
g
u
id
an
ce
f
o
r
s
elec
tin
g
m
o
d
els
in
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
en
v
ir
o
n
m
en
ts
s
u
ch
as
I
o
T
.
Fu
tu
r
e
wo
r
k
will
f
o
cu
s
o
n
im
p
r
o
v
in
g
th
e
r
o
b
u
s
tn
ess
o
f
th
e
s
en
s
o
r
d
r
if
t a
n
d
en
v
ir
o
n
m
e
n
tal
v
ar
iab
ilit
y
to
en
s
u
r
e
co
n
s
is
ten
t p
er
f
o
r
m
an
ce
in
r
ea
l
-
wo
r
ld
ap
p
licatio
n
s
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
ac
k
n
o
wled
g
e
th
e
in
d
iv
id
u
als
wh
o
p
r
o
v
id
ed
tech
n
ical
an
d
p
r
ac
tical
ass
is
tan
ce
d
u
r
in
g
th
e
d
ev
elo
p
m
e
n
t
an
d
e
v
alu
atio
n
o
f
th
e
e
-
n
o
s
e
s
y
s
tem
an
d
em
b
e
d
d
ed
im
p
le
m
en
tatio
n
.
I
n
p
a
r
ticu
lar
,
we
th
an
k
o
u
r
co
lleag
u
es
an
d
lab
o
r
at
o
r
y
s
taf
f
f
o
r
th
eir
s
u
p
p
o
r
t
in
th
e
s
e
n
s
o
r
s
etu
p
a
n
d
ca
lib
r
atio
n
,
p
r
ep
ar
atio
n
o
f
c
o
f
f
ee
s
am
p
les,
an
d
ass
is
tan
ce
with
d
ata
co
llectio
n
u
n
d
er
c
o
n
tr
o
lle
d
m
ea
s
u
r
em
en
t
c
o
n
d
itio
n
s
.
W
e
also
ac
k
n
o
wled
g
e
th
e
tech
n
ical
s
u
p
p
o
r
t
f
o
r
co
n
f
ig
u
r
in
g
th
e
NVI
DI
A
J
etso
n
N
an
o
e
n
v
ir
o
n
m
en
t
an
d
f
ac
ilit
atin
g
th
e
p
r
elim
in
ar
y
test
in
g
o
f
th
e
o
n
-
d
ev
ice
p
i
p
elin
e.
C
o
n
s
en
t
h
as
b
ee
n
o
b
tain
ed
f
r
o
m
all
in
d
iv
id
u
a
ls
n
am
ed
in
th
is
Ack
n
o
wled
g
m
e
n
ts
s
ec
tio
n
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
s
tate
th
at
n
o
ex
ter
n
al
f
u
n
d
in
g
was in
v
o
lv
ed
i
n
th
e
co
n
d
u
ct
o
f
th
is
r
esear
ch
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Den
d
a
Dew
atam
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
E
r
n
i Y
u
d
an
i
n
g
ty
as
✓
✓
✓
✓
✓
✓
Mu
h
am
m
ad
Fau
za
n
E
d
y
Pu
r
n
o
m
o
✓
✓
✓
✓
✓
✓
Sety
awa
n
Pu
r
n
o
m
o
Sak
ti
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
d
g
e
-
a
w
a
r
e
co
ffee
a
r
o
ma
cla
s
s
ifica
tio
n
u
s
in
g
mu
lti
-
r
ep
r
ese
n
ta
tio
n
…
(
Den
d
a
Dewa
ta
ma
)
2103
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
t
h
o
r
s
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
k
n
o
wn
c
o
m
p
etin
g
f
in
an
cial
in
ter
ests
o
r
p
er
s
o
n
al
r
el
atio
n
s
h
ip
s
th
at
co
u
ld
h
av
e
ap
p
ea
r
ed
t
o
in
f
lu
en
ce
th
e
wo
r
k
r
e
p
o
r
te
d
in
t
h
is
p
ap
er
.
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
No
t
ap
p
licab
le.
T
h
is
s
tu
d
y
d
id
n
o
t
in
v
o
lv
e
h
u
m
an
p
ar
tici
p
an
ts
o
r
th
e
co
llectio
n
o
f
p
e
r
s
o
n
al
o
r
s
en
s
itiv
e
d
ata.
E
T
H
I
CAL AP
P
RO
V
AL
No
t
ap
p
licab
le.
T
h
is
s
tu
d
y
d
i
d
n
o
t
in
v
o
lv
e
h
u
m
an
p
ar
ticip
an
ts
o
r
an
im
al
s
u
b
jects
an
d
th
er
ef
o
r
e
d
i
d
n
o
t r
eq
u
ir
e
eth
ical
ap
p
r
o
v
al.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
i
n
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
aila
b
le
f
r
o
m
th
e
c
o
r
r
esp
o
n
d
in
g
a
u
th
o
r
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
F
.
V
e
z
z
u
l
l
i
,
M
.
L
a
m
b
r
i
,
a
n
d
T
.
B
e
r
t
u
z
z
i
,
“
V
o
l
a
t
i
l
e
c
o
m
p
o
u
n
d
s
i
n
g
r
e
e
n
a
n
d
r
o
a
s
t
e
d
A
r
a
b
i
c
a
s
p
e
c
i
a
l
t
y
c
o
f
f
e
e
:
d
i
s
c
r
i
mi
n
a
t
i
o
n
o
f
o
r
i
g
i
n
s,
p
o
st
-
h
a
r
v
e
s
t
i
n
g
p
r
o
c
e
sses
,
a
n
d
r
o
a
st
i
n
g
l
e
v
e
l
,
”
F
o
o
d
s
,
v
o
l
.
1
2
,
n
o
.
3
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
f
o
o
d
s
1
2
0
3
0
4
8
9
.
[
2
]
N
.
C
a
p
o
r
a
so
,
M
.
B
.
W
h
i
t
w
o
r
t
h
,
a
n
d
I
.
D
.
F
i
s
k
,
“
P
r
e
d
i
c
t
i
o
n
o
f
c
o
f
f
e
e
a
r
o
ma
f
r
o
m
si
n
g
l
e
r
o
a
s
t
e
d
c
o
f
f
e
e
b
e
a
n
s
b
y
h
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
i
n
g
,
”
F
o
o
d
C
h
e
m
i
s
t
ry
,
v
o
l
.
3
7
1
,
n
o
.
S
e
p
t
e
m
b
e
r
2
0
2
1
,
p
.
1
3
1
1
5
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
o
o
d
c
h
e
m.
2
0
2
1
.
1
3
1
1
5
9
.
[
3
]
S
.
C
.
F
r
o
st
,
P
.
W
a
l
k
e
r
,
C
.
M
.
O
r
i
a
n
s
,
a
n
d
A
.
R
o
b
b
a
t
,
“
1
D
/
2
D
g
a
s
c
h
r
o
m
a
t
o
g
r
a
p
h
y
m
a
ss
sp
e
c
t
r
o
m
e
t
r
y
w
i
t
h
s
p
e
c
t
r
a
l
d
e
c
o
n
v
o
l
u
t
i
o
n
,
”
m
o
l
e
c
u
l
e
s
,
v
o
l
.
2
7
,
n
o
.
5
3
2
8
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
mo
l
e
c
u
l
e
s2
7
1
6
5
3
2
8
.
[
4
]
I
.
S
.
N
a
s
u
t
i
o
n
,
D
.
P
.
D
e
l
i
ma,
Z.
Za
i
d
i
y
a
h
,
a
n
d
R
.
F
a
d
h
i
l
,
“
A
l
o
w
c
o
s
t
e
l
e
c
t
r
o
n
i
c
n
o
se
s
y
s
t
e
m
f
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
g
a
y
o
A
r
a
b
i
c
a
c
o
f
f
e
e
r
o
a
st
i
n
g
l
e
v
e
l
s
u
si
n
g
st
e
p
w
i
s
e
l
i
n
e
a
r
d
i
s
c
r
i
m
i
n
a
n
t
a
n
d
k
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
,
”
Ma
t
h
e
m
a
t
i
c
a
l
Mo
d
e
l
l
i
n
g
o
f
En
g
i
n
e
e
ri
n
g
Pro
b
l
e
m
s
,
v
o
l
.
9
,
n
o
.
5
,
p
p
.
1
2
7
1
–
1
2
7
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
8
2
8
0
/
mm
e
p
.
0
9
0
5
1
4
.
[
5
]
P
.
Za
k
i
d
o
u
,
F
.
P
l
a
t
i
,
A
.
M
a
t
sa
k
i
d
o
u
,
E.
M
.
V
a
r
k
a
,
G
.
B
l
e
k
a
s,
a
n
d
A
.
P
a
r
a
sk
e
v
o
p
o
u
l
o
u
,
“
S
i
n
g
l
e
o
r
i
g
i
n
c
o
f
f
e
e
a
r
o
ma
:
F
r
o
m
o
p
t
i
m
i
z
e
d
f
l
a
v
o
r
p
r
o
t
o
c
o
l
s
a
n
d
c
o
f
f
e
e
c
u
st
o
mi
z
a
t
i
o
n
t
o
i
n
st
r
u
me
n
t
a
l
v
o
l
a
t
i
l
e
c
h
a
r
a
c
t
e
r
i
z
a
t
i
o
n
a
n
d
c
h
e
mo
m
e
t
r
i
c
s,
”
M
o
l
e
c
u
l
e
s
,
v
o
l
.
2
6
,
n
o
.
1
5
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
m
o
l
e
c
u
l
e
s
2
6
1
5
4
6
0
9
.
[
6
]
A
.
R
a
b
e
h
i
,
H
.
H
e
l
a
l
,
D
.
Z
a
p
p
a
,
a
n
d
E.
C
o
m
i
n
i
,
“
A
d
v
a
n
c
e
me
n
t
s
a
n
d
p
r
o
sp
e
c
t
s
o
f
e
l
e
c
t
r
o
n
i
c
n
o
s
e
i
n
v
a
r
i
o
u
s
a
p
p
l
i
c
a
t
i
o
n
s
:
a
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s (S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
4
,
n
o
.
1
1
,
p
p
.
1
–
4
6
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
4
1
1
4
5
0
6
.
[
7
]
H
.
R
.
H
o
u
,
Q
.
H
.
M
e
n
g
,
P
.
F
.
Q
i
,
a
n
d
T.
Ji
n
g
,
“
A
h
a
n
d
-
h
e
l
d
e
l
e
c
t
r
o
n
i
c
n
o
se
s
y
s
t
e
m
f
o
r
r
a
p
i
d
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
C
h
i
n
e
se
l
i
q
u
o
r
s,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
s
t
ru
m
e
n
t
a
t
i
o
n
a
n
d
Me
a
s
u
reme
n
t
,
v
o
l
.
7
0
,
p
p
.
1
–
1
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
M
.
2
0
2
1
.
3
1
1
2
7
8
9
.
[
8
]
M
.
I
.
A
.
A
sr
i
,
M
.
N
.
H
a
sa
n
,
M
.
R
.
A
.
F
u
a
a
d
,
Y
.
M
.
Y
u
n
o
s,
a
n
d
M
.
S
.
M
.
A
l
i
,
“
M
E
M
S
g
a
s
s
e
n
so
r
s
:
a
r
e
v
i
e
w
,
”
I
EEE
S
e
n
so
rs
J
o
u
rn
a
l
,
v
o
l
.
2
1
,
n
o
.
1
7
,
p
p
.
1
8
3
8
1
–
1
8
3
9
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
1
.
3
0
9
1
8
5
4
.
[
9
]
A
.
O
.
Tr
i
q
a
d
a
f
i
,
T
.
N
.
Za
f
i
r
a
h
,
H
.
A
.
D
h
a
r
maw
a
n
,
a
n
d
S
.
P
.
S
a
k
t
i
,
“
F
o
u
r
-
c
h
a
n
n
e
l
s
h
i
g
h
-
r
e
s
o
l
u
t
i
o
n
f
r
e
q
u
e
n
c
y
c
o
u
n
t
e
r
f
o
r
Q
C
M
sen
s
o
r
a
r
r
a
y
u
s
i
n
g
g
e
n
e
r
i
c
F
P
G
A
X
C
6
S
LX
9
b
o
a
r
d
,
”
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
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
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
3
/
5
1
8
2
4
5
5
.
[
1
0
]
A
.
D
a
s
a
n
d
R
.
M
a
n
j
u
n
a
t
h
a
,
“
M
o
d
e
l
i
n
g
o
f
g
r
a
p
h
e
n
e
o
x
i
d
e
c
o
a
t
e
d
Q
C
M
s
e
n
s
o
r
f
o
r
e
-
n
o
se
a
p
p
l
i
c
a
t
i
o
n
,
”
S
p
ri
n
g
e
r
Pro
c
e
e
d
i
n
g
s
i
n
Ma
t
e
r
i
a
l
s
,
v
o
l
.
1
8
,
n
o
.
J
u
n
e
,
p
p
.
1
7
9
–
1
8
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
19
-
5
3
9
5
-
8
_
1
4
.
[
1
1
]
A
.
A
.
C
.
I
l
l
a
h
i
,
E.
P
.
D
a
d
i
o
s,
A
.
A
.
B
a
n
d
a
l
a
,
a
n
d
R
.
R
.
P
.
V
i
c
e
r
r
a
,
“
El
e
c
t
r
o
n
i
c
n
o
se
t
e
c
h
n
o
l
o
g
y
a
n
d
a
p
p
l
i
c
a
t
i
o
n
:
a
r
e
v
i
e
w
,
”
2
0
2
1
I
EEE
1
3
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
H
u
m
a
n
o
i
d
,
N
a
n
o
t
e
c
h
n
o
l
o
g
y
,
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
C
o
n
t
ro
l
,
En
v
i
r
o
n
m
e
n
t
,
a
n
d
M
a
n
a
g
e
m
e
n
t
,
H
N
I
C
EM
2
0
2
1
,
p
p
.
1
–
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
H
N
I
C
EM
5
4
1
1
6
.
2
0
2
1
.
9
7
3
1
8
9
0
.
[
1
2
]
J.
W
a
w
r
z
y
n
i
a
k
,
“
A
d
v
a
n
c
e
me
n
t
s
i
n
i
mp
r
o
v
i
n
g
s
e
l
e
c
t
i
v
i
t
y
o
f
me
t
a
l
o
x
i
d
e
s
e
mi
c
o
n
d
u
c
t
o
r
g
a
s
se
n
so
r
s
o
p
e
n
i
n
g
n
e
w
p
e
r
s
p
e
c
t
i
v
e
s
f
o
r
t
h
e
i
r
a
p
p
l
i
c
a
t
i
o
n
i
n
f
o
o
d
i
n
d
u
s
t
r
y
,
”
S
e
n
so
rs
,
v
o
l
.
2
3
,
n
o
.
2
3
,
p
p
.
1
–
3
5
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
3
2
3
9
5
4
8
.
[
1
3
]
P
.
S
i
n
g
h
,
U
.
H
a
b
i
b
a
,
Z.
S
h
a
f
i
,
A
.
N
o
o
r
,
V
.
K
.
P
a
n
d
e
y
,
a
n
d
R
.
S
i
n
g
h
,
“
U
n
d
e
r
st
a
n
d
i
n
g
t
h
e
c
o
n
c
e
p
t
s
o
f
s
mart
e
‐
n
o
se
t
e
c
h
n
o
l
o
g
y
i
n
c
o
m
b
i
n
a
t
i
o
n
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
n
e
w
e
r
a
o
f
f
o
o
d
safe
t
y
:
a
n
a
d
v
a
n
c
e
d
r
e
v
i
e
w
,
”
F
o
o
d
S
a
f
e
t
y
a
n
d
H
e
a
l
t
h
,
v
o
l
.
3
,
n
o
.
4
,
p
p
.
5
1
8
–
5
3
4
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
2
/
f
s
h
3
.
7
0
0
2
9
.
[
1
4
]
W
.
Z
h
a
n
g
e
t
a
l
.
,
“
D
e
s
i
g
n
a
n
d
c
o
n
s
t
r
u
c
t
i
o
n
o
f
e
n
z
y
me
-
b
a
s
e
d
e
l
e
c
t
r
o
c
h
e
m
i
c
a
l
g
a
s
s
e
n
s
o
r
s,
”
Mo
l
e
c
u
l
e
s
,
v
o
l
.
2
9
,
n
o
.
1
,
p
p
.
2
–
1
8
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
m
o
l
e
c
u
l
e
s
2
9
0
1
0
0
0
5
.
[
1
5
]
H
.
N
a
z
e
mi
,
A
.
J
o
se
p
h
,
J.
P
a
r
k
,
a
n
d
A
.
Ema
d
i
,
“
A
d
v
a
n
c
e
d
mi
c
r
o
-
a
n
d
n
a
n
o
-
g
a
s
se
n
s
o
r
t
e
c
h
n
o
l
o
g
y
:
A
r
e
v
i
e
w
,
”
S
e
n
so
rs
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
9
,
n
o
.
6
,
p
p
.
1
–
2
3
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
s
1
9
0
6
1
2
8
5
.
[
1
6
]
A
.
A
u
r
o
r
a
,
“
A
l
g
o
r
i
t
h
mi
c
c
o
r
r
e
c
t
i
o
n
o
f
M
O
S
g
a
s s
e
n
s
o
r
f
o
r
a
m
b
i
e
n
t
t
e
m
p
e
r
a
t
u
r
e
a
n
d
r
e
l
a
t
i
v
e
h
u
m
i
d
i
t
y
f
l
u
c
t
u
a
t
i
o
n
s
,
”
I
EE
E
S
e
n
so
rs
J
o
u
rn
a
l
,
v
o
l
.
2
2
,
n
o
.
1
5
,
p
p
.
1
5
0
5
4
–
1
5
0
6
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
2
.
3
1
8
5
1
7
6
.
[
1
7
]
A
.
G
.
P
a
t
i
l
,
B
.
P
r
a
m
a
n
i
c
k
,
a
n
d
A
.
M
a
d
h
u
k
a
r
,
“
M
O
S
b
a
s
e
d
g
a
s
se
n
so
r
s
f
o
r
mo
n
i
t
o
r
i
n
g
o
f
a
i
r
p
o
l
l
u
t
i
o
n
:
a
r
e
v
i
e
w
,
”
I
EEE
S
e
n
so
rs
J
o
u
rn
a
l
,
v
o
l
.
2
5
,
n
o
.
6
,
p
p
.
9
2
5
0
–
9
2
6
2
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
5
.
3
5
3
1
8
8
8
.
[
1
8
]
T.
T
o
h
a
r
u
d
i
n
e
t
a
l
.
,
“
B
o
o
st
i
n
g
a
l
g
o
r
i
t
h
m
t
o
h
a
n
d
l
e
u
n
b
a
l
a
n
c
e
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
P
M
2
.
5
c
o
n
c
e
n
t
r
a
t
i
o
n
l
e
v
e
l
s
b
y
o
b
serv
i
n
g
met
e
o
r
o
l
o
g
i
c
a
l
p
a
r
a
m
e
t
e
r
s
i
n
Ja
k
a
r
t
a
-
I
n
d
o
n
e
si
a
u
si
n
g
A
d
a
B
o
o
s
t
,
X
G
B
o
o
s
t
,
C
a
t
B
o
o
st
,
a
n
d
Li
g
h
t
G
B
M
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
n
o
.
A
p
r
i
l
,
p
p
.
3
5
6
8
0
–
3
5
6
9
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
6
5
0
1
9
.
[
1
9
]
M
.
S
o
u
i
,
N
.
M
a
n
so
u
r
i
,
R
.
A
l
h
a
m
a
d
,
M
.
K
e
s
se
n
t
i
n
i
,
a
n
d
K
.
G
h
e
d
i
r
a
,
“
N
S
G
A
-
I
I
a
s
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
a
n
d
A
d
a
B
o
o
s
t
c
l
a
ss
i
f
i
e
r
f
o
r
C
O
V
I
D
-
1
9
p
r
e
d
i
c
t
i
o
n
u
si
n
g
p
a
t
i
e
n
t
’
s
sy
m
p
t
o
ms
,
”
N
o
n
l
i
n
e
a
r
D
y
n
a
m
i
c
s
,
v
o
l
.
1
0
6
,
n
o
.
2
,
p
p
.
1
4
5
3
–
1
4
7
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
7
1
-
0
2
1
-
0
6
5
0
4
-
1.
[
2
0
]
L.
D
e
m
a
r
c
h
i
,
A
.
K
a
n
i
a
,
W
.
C
i
e
z
k
o
w
sk
i
,
H
.
P
i
ó
r
k
o
w
sk
i
,
Z.
O
św
i
e
c
i
msk
a
-
P
i
a
s
k
o
,
a
n
d
J.
C
h
o
r
m
a
ń
s
k
i
,
“
R
e
c
u
r
si
v
e
f
e
a
t
u
r
e
e
l
i
mi
n
a
t
i
o
n
a
n
d
r
a
n
d
o
m
f
o
r
e
st
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
n
a
t
u
r
a
2
0
0
0
g
r
a
ssl
a
n
d
s
i
n
l
o
w
l
a
n
d
r
i
v
e
r
v
a
l
l
e
y
s
o
f
p
o
l
a
n
d
b
a
se
d
o
n
a
i
r
b
o
r
n
e
h
y
p
e
r
s
p
e
c
t
r
a
l
a
n
d
Li
D
A
R
d
a
t
a
f
u
s
i
o
n
,
”
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
2
,
n
o
.
1
1
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
2
1
1
1
8
4
2
.
[
2
1
]
S
.
O
j
h
a
e
t
a
l
.
,
“
A
m
e
t
h
o
d
t
o
e
n
h
a
n
c
e
p
r
i
v
a
c
y
p
r
e
ser
v
a
t
i
o
n
i
n
c
l
o
u
d
st
o
r
a
g
e
t
h
r
o
u
g
h
a
t
h
r
e
e
-
l
a
y
e
r
sc
h
e
m
e
f
o
r
c
o
m
p
u
t
a
t
i
o
n
a
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
4
,
Au
g
u
s
t
20
2
6
:
2
0
9
6
-
2
105
2104
i
n
t
e
l
l
i
g
e
n
c
e
i
n
f
o
g
c
o
m
p
u
t
i
n
g
,
”
Me
t
h
o
d
sX
,
v
o
l
.
1
3
,
n
o
.
N
o
v
e
m
b
e
r
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
x
.
2
0
2
4
.
1
0
3
0
5
3
.
[
2
2
]
J.
A
.
B
.
D
e
l
mo
,
M
.
V
V
i
l
l
a
r
i
c
a
,
a
n
d
A
.
A
.
V
i
n
l
u
a
n
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
c
o
f
f
e
e
v
a
r
i
e
t
y
u
si
n
g
e
l
e
c
t
r
o
n
i
c
n
o
se
,
”
2
0
2
2
I
EEE
1
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
l
l
o
q
u
i
u
m
o
n
S
i
g
n
a
l
Pro
c
e
ssi
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s,
C
S
PA
2
0
2
2
-
Pr
o
c
e
e
d
i
n
g
,
n
o
.
M
a
y
,
p
p
.
2
4
8
–
2
5
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
C
S
P
A
5
5
0
7
6
.
2
0
2
2
.
9
7
8
2
0
5
6
.
[
2
3
]
D
.
A
u
l
i
a
,
R
.
S
a
r
n
o
,
S
.
C
.
H
i
d
a
y
a
t
i
,
a
n
d
M
.
R
i
v
a
i
,
“
O
p
t
i
m
i
z
a
t
i
o
n
o
f
t
h
e
e
l
e
c
t
r
o
n
i
c
n
o
s
e
s
e
n
so
r
a
r
r
a
y
f
o
r
a
st
h
ma
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m,”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
n
o
.
J
u
l
y
,
p
p
.
7
4
9
2
4
–
7
4
9
3
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
9
1
4
5
1
.
[
2
4
]
A
.
M
.
F
a
j
r
i
n
,
M
.
N
i
sw
a
r
,
a
n
d
A
.
W
.
P
a
u
n
d
u
,
“
I
mp
l
e
me
n
t
a
t
i
o
n
o
f
m
o
d
i
f
i
e
d
k
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
a
l
g
o
r
i
t
h
m
i
n
e
l
e
c
t
r
o
n
i
c
n
o
s
e
s
y
st
e
m
t
o
d
e
t
e
c
t
g
a
s
t
r
o
e
so
p
h
a
g
e
a
l
r
e
f
l
u
x
d
i
s
e
a
se
,
”
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
S
e
m
i
n
a
r
o
n
I
n
t
e
l
l
i
g
e
n
t
T
e
c
h
n
o
l
o
g
y
a
n
d
I
t
s
Ap
p
l
i
c
a
t
i
o
n
s:
L
e
v
e
r
a
g
i
n
g
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
t
o
A
c
h
i
e
v
e
S
u
s
t
a
i
n
a
b
l
e
D
e
v
e
l
o
p
m
e
n
t
G
o
a
l
s,
I
S
I
T
I
A
2
0
2
3
-
Pr
o
c
e
e
d
i
n
g
,
p
p
.
6
2
6
–
6
3
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
I
T
I
A
5
9
0
2
1
.
2
0
2
3
.
1
0
2
2
1
1
1
3
.
[
2
5
]
M
.
A
.
M
o
h
si
n
,
S
.
N
.
S
h
a
h
r
o
u
z
i
,
a
n
d
D
.
G
.
P
e
r
e
r
a
,
“
C
o
m
p
o
si
n
g
e
f
f
i
c
i
e
n
t
c
o
mp
u
t
a
t
i
o
n
a
l
m
o
d
e
l
s
f
o
r
r
e
a
l
-
t
i
me
p
r
o
c
e
ssi
n
g
o
n
n
e
x
t
-
g
e
n
e
r
a
t
i
o
n
e
d
g
e
-
c
o
m
p
u
t
i
n
g
p
l
a
t
f
o
r
ms,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
2
4
9
0
5
–
2
4
9
3
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
6
5
6
5
2
.
[
2
6
]
P
.
M
a
h
a
d
e
v
a
p
p
a
,
R
.
K
.
M
u
r
u
g
e
sa
n
,
R
.
A
l
-
a
mr
i
,
R
.
T
h
a
b
i
t
,
A
.
H
.
A
l
-
G
h
u
s
h
a
mi
,
a
n
d
G
.
A
l
k
a
w
s
i
,
“
A
sec
u
r
e
e
d
g
e
c
o
mp
u
t
i
n
g
mo
d
e
l
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
I
D
S
t
o
d
e
t
e
c
t
a
n
d
i
so
l
a
t
e
i
n
t
r
u
d
e
r
s,
”
M
e
t
h
o
d
sX
,
v
o
l
.
1
2
,
n
o
.
Ja
n
u
a
r
y
,
p
.
1
0
2
5
9
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
x
.
2
0
2
4
.
1
0
2
5
9
7
.
[
2
7
]
A
.
G
a
r
c
i
a
-
P
e
r
e
z
,
R
.
M
i
ñ
ó
n
,
A
.
I
.
To
r
r
e
-
B
a
s
t
i
d
a
,
a
n
d
E.
Z
u
l
u
e
t
a
-
G
u
e
r
r
e
r
o
,
“
A
n
a
l
y
s
i
n
g
e
d
g
e
c
o
m
p
u
t
i
n
g
d
e
v
i
c
e
s
f
o
r
t
h
e
d
e
p
l
o
y
me
n
t
o
f
e
m
b
e
d
d
e
d
A
I
,
”
S
e
n
so
rs
,
v
o
l
.
2
3
,
n
o
.
2
3
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
2
3
9
4
9
5
.
[
2
8
]
C
.
X
u
e
t
a
l
.
,
“
T
h
e
c
a
se
f
o
r
F
P
G
A
-
b
a
se
d
e
d
g
e
c
o
m
p
u
t
i
n
g
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
Mo
b
i
l
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
1
,
n
o
.
7
,
p
p
.
2
6
1
0
–
2
6
1
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
T
M
C
.
2
0
2
0
.
3
0
4
1
7
8
1
.
[
2
9
]
C
.
H
.
Ta
i
,
T
.
Y
.
Li
a
o
,
S
.
P
.
C
h
e
n
,
a
n
d
M
.
H
.
C
h
u
n
g
,
“
S
l
e
e
p
s
t
a
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
l
i
g
h
t
g
r
a
d
i
e
n
t
b
o
o
s
t
m
a
c
h
i
n
e
:
e
x
p
l
o
r
i
n
g
f
e
a
t
u
r
e
i
m
p
a
c
t
i
n
d
e
p
r
e
s
si
v
e
a
n
d
h
e
a
l
t
h
y
p
a
r
t
i
c
i
p
a
n
t
s,”
Bi
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pro
c
e
ss
i
n
g
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
8
8
,
n
o
.
P
A
,
p
.
1
0
5
6
4
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
2
3
.
1
0
5
6
4
7
.
[
3
0
]
R
.
B
i
d
w
e
,
S
.
M
i
sh
r
a
,
S
.
B
a
j
a
j
,
a
n
d
K
.
K
o
t
e
c
h
a
,
“
L
e
v
e
r
a
g
i
n
g
h
y
b
r
i
d
m
o
d
e
l
o
f
C
o
n
v
N
e
x
t
B
a
s
e
a
n
d
Li
g
h
t
G
B
M
f
o
r
e
a
r
l
y
A
S
D
d
e
t
e
c
t
i
o
n
v
i
a
e
y
e
-
g
a
z
e
a
n
a
l
y
s
i
s,”
M
e
t
h
o
d
sX
,
v
o
l
.
1
4
,
n
o
.
J
a
n
u
a
r
y
,
p
.
1
0
3
1
6
6
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
x
.
2
0
2
5
.
1
0
3
1
6
6
.
[
3
1
]
J.
H
u
a
n
g
a
n
d
W
.
C
h
e
n
,
“
A
s
t
u
d
y
o
n
c
a
t
e
g
o
r
y
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
a
s
e
d
o
n
L
i
g
h
t
G
B
M
f
o
r
s
i
g
n
a
l
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
k
-
m
e
a
n
s
c
l
u
st
e
r
i
n
g
,
”
2
0
2
3
I
EEE
5
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
Po
w
e
r
,
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
i
n
g
a
n
d
S
y
s
t
e
m
s
,
I
C
PI
C
S
2
0
2
3
,
p
p
.
8
5
8
–
8
6
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
P
I
C
S
5
8
3
7
6
.
2
0
2
3
.
1
0
2
3
5
5
2
2
.
[
3
2
]
J.
L
i
a
o
e
t
a
l
.
,
“
A
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
m
e
t
h
o
d
f
o
r
i
mag
e
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
R
e
sN
e
t
a
r
c
h
i
t
e
c
t
u
r
e
,
”
D
i
g
i
t
a
l
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
:
A
Re
v
i
e
w
J
o
u
r
n
a
l
,
v
o
l
.
1
6
0
,
n
o
.
1
0
5
0
3
6
,
p
p
.
1
–
1
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
s
p
.
2
0
2
5
.
1
0
5
0
3
6
.
[
3
3
]
Y
.
W
u
,
H
.
H
u
a
n
g
,
Z
.
L
i
,
a
n
d
S
.
Z
h
a
n
g
,
“
C
B
A
M
-
R
e
s
N
e
t
:
a
l
i
g
h
t
w
e
i
g
h
t
R
e
s
N
e
t
n
e
t
w
o
r
k
f
o
c
u
s
i
n
g
o
n
t
i
m
e
d
o
m
a
i
n
f
e
a
t
u
r
e
s
f
o
r
e
n
d
-
to
-
e
n
d
d
e
e
p
f
a
k
e
s
p
e
e
c
h
d
e
t
e
c
t
i
o
n
,
”
E
l
e
c
t
r
o
n
i
c
s
(
S
w
i
t
z
e
r
l
a
n
d
)
,
v
o
l
.
1
4
,
n
o
.
1
2
,
p
p
.
1
–
2
0
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
4
1
2
2
4
5
6
.
[
3
4
]
S
.
R
y
u
,
H
.
C
h
o
i
,
H
.
Le
e
,
a
n
d
H
.
K
i
m,
“
C
o
n
v
o
l
u
t
i
o
n
a
l
a
u
t
o
e
n
c
o
d
e
r
b
a
s
e
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
c
l
u
s
t
e
r
i
n
g
f
o
r
c
u
s
t
o
m
e
r
l
o
a
d
a
n
a
l
y
si
s
,
”
I
E
EE
T
r
a
n
sa
c
t
i
o
n
s
o
n
P
o
w
e
r S
y
st
e
m
s
,
v
o
l
.
3
5
,
n
o
.
2
,
p
p
.
1
0
4
8
–
1
0
6
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
TPW
R
S
.
2
0
1
9
.
2
9
3
6
2
9
3
.
[
3
5
]
E.
R
.
A
r
d
e
l
e
a
n
,
A
.
C
o
p
o
r
î
i
e
,
A
.
M
.
I
c
h
i
m,
M
.
D
î
n
ş
o
r
e
a
n
u
,
a
n
d
R
.
C
.
M
u
r
e
şa
n
,
“
A
s
t
u
d
y
o
f
a
u
t
o
e
n
c
o
d
e
r
s
a
s
a
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
t
e
c
h
n
i
q
u
e
f
o
r
sp
i
k
e
s
o
r
t
i
n
g
,
”
PL
o
S
O
N
E
,
v
o
l
.
1
8
,
n
o
.
3
M
a
r
c
h
,
p
p
.
1
–
2
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
8
2
8
1
0
.
[
3
6
]
P
.
P
r
e
ma
a
n
d
V
.
V
R
a
mal
i
n
g
a
m,
“
F
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
e
x
c
e
l
l
e
n
c
e
:
a
t
t
e
n
t
i
o
n
M
o
b
i
l
e
N
e
t
a
n
d
t
a
c
t
i
c
a
l
u
n
i
t
s
e
a
r
c
h
f
u
si
o
n
f
o
r
r
o
b
u
s
t
sat
e
l
l
i
t
e
i
ma
g
e
c
l
a
s
si
f
i
c
a
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
t
h
e
I
n
d
i
a
n
S
o
c
i
e
t
y
o
f
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
5
3
,
n
o
.
1
1
,
p
p
.
3
9
6
7
–
3
9
8
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
5
2
4
-
0
2
5
-
0
2
1
7
5
-
2.
[
3
7
]
A
.
S
i
v
a
su
b
r
a
m
a
n
i
a
n
,
M
.
D
e
v
i
se
t
t
y
,
a
n
d
P
.
B
h
a
v
u
k
a
m,
“
F
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
a
n
o
mal
y
d
e
t
e
c
t
i
o
n
u
s
i
n
g
d
i
f
f
e
r
e
n
t
a
u
t
o
e
n
c
o
d
e
r
s
f
o
r
mo
d
e
l
i
n
g
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
ms
,
”
Ar
a
b
i
a
n
J
o
u
r
n
a
l
f
o
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
4
9
,
n
o
.
9
,
p
p
.
1
3
0
6
1
–
1
3
0
7
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
3
6
9
-
0
2
4
-
0
8
9
5
1
-
5.
[
3
8
]
D
.
D
e
w
a
t
a
ma
,
E
.
Y
u
d
a
n
i
n
g
t
y
a
s,
M
.
F
.
E.
P
u
r
n
o
m
o
,
a
n
d
S
.
P
.
S
a
k
t
i
,
“
H
y
b
r
i
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
f
o
r
o
p
t
i
mi
z
i
n
g
s
e
n
s
o
r
a
r
r
a
y
r
e
d
u
c
t
i
o
n
i
n
c
o
f
f
e
e
a
r
o
m
a
e
l
e
c
t
r
o
n
i
c
n
o
s
e
s
y
s
t
e
ms,
”
J
o
u
r
n
a
l
o
f
R
o
b
o
t
i
c
s
a
n
d
C
o
n
t
r
o
l
(
J
RC
)
,
v
o
l
.
6
,
n
o
.
5
,
p
.
2
0
2
5
,
2
0
2
5
,
d
o
i
:
1
0
.
1
8
1
9
6
/
j
r
c
.
v
6
i
5
.
2
8
4
7
0
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
De
n
d
a
De
wa
ta
m
a
is
a
d
o
c
to
ra
l
stu
d
e
n
t
in
th
e
De
p
a
rtm
e
n
t
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
a
t
Un
i
v
e
rsitas
Bra
wijay
a
a
n
d
a
lec
tu
re
r
a
t
P
o
li
tek
n
ik
Ne
g
e
ri
M
a
lan
g
.
His
re
se
a
rc
h
fo
c
u
se
s
o
n
a
rti
ficia
l
in
telli
g
e
n
c
e
a
n
d
e
m
b
e
d
d
e
d
sy
ste
m
s,
p
a
rti
c
u
larly
in
te
g
ra
ti
n
g
m
a
c
h
in
e
lea
rn
in
g
with
re
so
u
rc
e
-
c
o
n
stra
i
n
e
d
se
n
so
r
p
latfo
rm
s.
He
c
o
n
tri
b
u
ted
to
th
e
st
u
d
y
’s
fra
m
e
wo
r
k
d
e
sig
n
,
s
o
ftwa
re
d
e
v
e
lo
p
m
e
n
t,
e
x
p
e
rime
n
ts,
d
a
ta
a
n
a
ly
sis,
a
n
d
m
a
n
u
sc
rip
t
p
re
p
a
ra
ti
o
n
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
e
n
d
a
.
d
e
wa
tam
a
@p
o
li
n
e
m
a
.
a
c
.
id
,
d
e
n
d
a
d
e
wa
tam
a
@s
tu
d
e
n
t.
u
b
.
a
c
.
id
.
Er
n
i
Yud
a
n
in
g
t
y
a
s
a
lec
tu
re
r
in
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
a
t
Un
iv
e
rsitas
Bra
wijay
a
.
He
r
a
c
a
d
e
m
ic
a
n
d
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
c
o
n
tr
o
l
sy
ste
m
s
a
n
d
b
io
m
e
d
ica
l
i
n
stru
m
e
n
tati
o
n
,
wit
h
a
fo
c
u
s
o
n
th
e
a
p
p
li
c
a
ti
o
n
o
f
in
telli
g
e
n
t
a
l
g
o
rit
h
m
s
a
n
d
c
o
n
tro
l
stra
teg
ies
in
e
n
g
i
n
e
e
rin
g
a
n
d
b
io
m
e
d
ica
l
m
e
a
su
re
m
e
n
t
sy
ste
m
s.
S
h
e
h
a
s
e
x
p
e
rien
c
e
i
n
su
p
e
rv
isi
n
g
a
p
p
li
e
d
re
se
a
rc
h
p
r
o
jec
ts
a
n
d
e
n
s
u
rin
g
m
e
t
h
o
d
o
l
o
g
ica
l
ri
g
o
r
in
e
x
p
e
rime
n
tal
stu
d
ies
.
In
th
is
wo
r
k
,
sh
e
c
o
n
tri
b
u
ted
to
t
h
e
c
o
n
c
e
p
t
u
a
l
a
n
d
m
e
th
o
d
o
lo
g
ica
l
d
e
v
e
lo
p
m
e
n
t
o
f
th
e
p
ro
p
o
se
d
a
p
p
ro
a
c
h
,
p
r
o
v
i
d
e
d
re
se
a
rc
h
re
so
u
rc
e
s,
a
n
d
s
u
p
e
rv
ise
d
th
e
re
se
a
rc
h
p
ro
c
e
ss
.
S
h
e
a
lso
p
a
rti
c
ip
a
ted
in
re
v
iew
in
g
a
n
d
e
d
i
ti
n
g
t
h
e
m
a
n
u
sc
rip
t
t
o
e
n
su
re
sc
i
e
n
ti
fic
c
larity
,
c
o
n
siste
n
c
y
,
a
n
d
c
o
m
p
l
ian
c
e
with
p
u
b
li
c
a
ti
o
n
sta
n
d
a
rd
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
e
rn
i@u
b
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
d
g
e
-
a
w
a
r
e
co
ffee
a
r
o
ma
cla
s
s
ifica
tio
n
u
s
in
g
mu
lti
-
r
ep
r
ese
n
ta
tio
n
…
(
Den
d
a
Dewa
ta
ma
)
2105
Mu
h
a
m
m
a
d
F
a
u
z
a
n
Ed
y
Pu
r
n
o
m
o
is
a
le
c
tu
re
r
in
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
a
t
Un
i
v
e
rsitas
Bra
wijay
a
.
He
h
a
s
e
x
p
e
rti
se
in
se
n
so
r,
c
o
m
p
u
ter
sc
ien
c
e
,
a
n
ten
n
a
s
a
n
d
p
r
o
p
a
g
a
ti
o
n
,
m
icro
wa
v
e
e
n
g
i
n
e
e
rin
g
,
ra
d
a
r,
a
n
d
n
a
v
ig
a
ti
o
n
sy
ste
m
s.
His
a
c
a
d
e
m
ic
a
c
ti
v
it
ies
i
n
v
o
lv
e
su
p
p
o
r
ti
n
g
e
x
p
e
rime
n
tal
re
se
a
rc
h
th
r
o
u
g
h
m
e
th
o
d
o
lo
g
ica
l
a
ss
istan
c
e
,
re
so
u
rc
e
p
r
o
v
isi
o
n
,
a
n
d
sy
ste
m
s
u
p
e
rv
isi
o
n
.
His
b
a
c
k
g
r
o
u
n
d
i
n
e
l
e
c
tro
m
a
g
n
e
ti
c
sy
ste
m
s
a
n
d
sig
n
a
l
p
r
o
p
a
g
a
ti
o
n
c
o
n
tri
b
u
tes
t
o
t
h
e
u
n
d
e
rsta
n
d
i
n
g
o
f
se
n
so
r
b
e
h
a
v
i
o
r
a
n
d
m
e
a
su
re
m
e
n
t
re
li
a
b
il
it
y
.
I
n
th
is
stu
d
y
,
h
e
c
o
n
tri
b
u
te
d
t
o
th
e
m
e
th
o
d
o
l
o
g
ic
a
l
a
sp
e
c
ts
o
f
th
e
re
se
a
rc
h
,
su
p
p
o
rted
e
x
p
e
rime
n
tal
imp
lem
e
n
tatio
n
,
p
ro
v
id
e
d
re
se
a
rc
h
re
so
u
rc
e
s,
a
n
d
p
a
rti
c
ip
a
ted
in
re
v
iew
in
g
a
n
d
e
d
it
in
g
th
e
m
a
n
u
s
c
rip
t
to
e
n
s
u
re
tec
h
n
ica
l
a
c
c
u
ra
c
y
a
n
d
r
o
b
u
stn
e
ss
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
fa
u
z
a
n
e
p
@u
b
.
a
c
.
id
.
S
e
ty
a
wa
n
Pu
r
n
o
m
o
S
a
k
ti
is a p
ro
fe
ss
o
r
a
n
d
t
h
e
p
rima
ry
p
ro
m
o
to
r
o
f
th
e
d
o
c
to
ra
l
p
ro
g
ra
m
in
th
e
De
p
a
rtme
n
t
o
f
E
lec
tri
c
a
l
En
g
i
n
e
e
rin
g
a
t
Un
i
v
e
rsitas
Bra
wijay
a
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
se
n
so
r
i
n
stru
m
e
n
tatio
n
,
m
e
a
su
re
m
e
n
t
sy
ste
m
s,
a
n
d
fu
n
c
ti
o
n
a
l
m
a
teria
ls.
He
e
m
p
h
a
siz
e
s
th
e
d
e
sig
n
,
i
n
teg
ra
ti
o
n
,
a
n
d
su
p
e
r
v
isio
n
o
f
a
p
p
li
e
d
e
n
g
in
e
e
rin
g
re
se
a
rc
h
in
v
o
l
v
i
n
g
se
n
sin
g
tec
h
n
o
lo
g
ies
a
n
d
i
n
t
e
ll
ig
e
n
t
sy
ste
m
s.
He
h
a
s
e
x
p
e
rien
c
e
in
c
o
o
r
d
i
n
a
ti
n
g
m
u
lt
id
isc
ip
li
n
a
r
y
re
se
a
rc
h
p
ro
j
e
c
ts
a
n
d
g
u
id
i
n
g
re
se
a
rc
h
tea
m
s
to
e
n
su
re
stru
c
t
u
re
d
,
re
p
ro
d
u
c
ib
le,
a
n
d
m
e
th
o
d
o
lo
g
ic
a
ll
y
so
u
n
d
o
u
tco
m
e
s.
In
th
is
p
a
p
e
r,
h
e
c
o
n
tr
ib
u
ted
t
o
th
e
c
o
n
c
e
p
tu
a
li
z
a
ti
o
n
a
n
d
m
e
th
o
d
o
l
o
g
ica
l
p
lan
n
in
g
o
f
t
h
e
stu
d
y
,
su
p
e
rv
ise
d
th
e
o
v
e
ra
ll
re
se
a
rc
h
p
ro
c
e
ss
,
m
a
n
a
g
e
d
p
r
o
jec
t
a
d
m
in
istratio
n
,
a
n
d
p
a
rti
c
i
p
a
ted
in
re
v
iew
in
g
a
n
d
e
d
it
i
n
g
th
e
m
a
n
u
sc
rip
t
to
e
n
su
r
e
a
li
g
n
m
e
n
t
with
re
se
a
rc
h
o
b
jec
ti
v
e
s
a
n
d
p
u
b
li
c
a
ti
o
n
sta
n
d
a
rd
s.
He
se
rv
e
s
a
s
th
e
c
o
rre
sp
o
n
d
in
g
a
u
th
o
r
fo
r
th
is
m
a
n
u
sc
rip
t
a
n
d
is
re
sp
o
n
s
ib
le
fo
r
a
ll
c
o
rre
sp
o
n
d
e
n
c
e
re
late
d
to
th
e
s
u
b
m
issio
n
,
re
v
isi
o
n
,
a
n
d
p
u
b
li
c
a
ti
o
n
p
ro
c
e
ss
e
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
k
ti
@u
b
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.