T
E
L
KO
M
NIK
A
, V
ol
.
17
,
No.
2
,
A
pril
20
19
,
pp
.7
71
~
7
80
IS
S
N: 1
69
3
-
6
93
0
,
accr
ed
ited
F
irst
Gr
ad
e b
y K
em
en
r
istekdikti,
Decr
ee
No: 2
1/E/
K
P
T
/20
18
DOI:
10.12928/TE
LK
OM
N
IK
A
.v
1
3
i
2
.
11787
77
1
Rec
ei
v
ed
A
ug
us
t
23
,
20
1
8;
Rev
i
s
ed
Nov
e
mb
er 2
, 2
0
1
8;
A
c
c
ep
t
ed
N
ov
em
be
r
2
4,
20
18
MOS
ga
s sen
so
r
of
m
eat
fresh
n
ess anal
y
s
is o
n
E
-
no
s
e
Bu
d
i G
u
n
aw
an
1
,
S
alman
A
l
f
a
r
is
i
*
2
,
G
u
n
anj
ar
S
at
r
io
3
,
A
r
i
ef Sud
a
r
maji
4
,
M
al
v
in
5
, Kr
is
ya
r
ang
g
a
6
1
,
3
El
e
c
tri
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
Fa
c
u
l
ty
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
rs
i
ta
s
M
u
ri
a
Ku
d
u
s
,
G
o
n
d
a
n
g
m
a
n
i
s
PO
.
BO
X
5
3
Ba
e
5
9
3
2
4
Ku
d
u
s
,
Cen
tr
a
l
J
a
v
a
,
I
n
d
o
n
e
s
i
a
2
In
d
u
s
tri
a
l
En
g
i
n
e
e
ri
n
g
,
Fa
c
u
l
t
y
o
f
En
g
i
n
e
e
ri
n
g
,
Un
i
v
e
rs
i
ta
s
M
u
ri
a
Ku
d
u
s
,
G
o
n
d
a
n
g
m
a
n
i
s
PO
.
BO
X
5
3
Ba
e
5
9
3
2
4
Ku
d
u
s
,
Cen
tr
a
l
J
a
v
a
,
I
n
d
o
n
e
s
i
a
4
,5
,6
Ag
ri
c
u
l
tu
ra
l
En
g
i
n
e
e
ri
n
g
,
F
a
c
u
l
ty
o
f
Ag
ri
c
u
l
tu
re
,
Un
i
v
e
rs
i
t
a
s
J
e
n
d
e
ra
l
S
o
e
d
i
rm
a
n
G
re
n
d
e
n
g
,
Pu
rw
o
k
e
rto
,
Ba
n
y
u
m
a
s
,
5
3
1
2
3
,
Cen
tra
l
J
a
v
a
,
In
d
o
n
e
s
i
a
*
Corre
s
p
o
n
d
n
g
a
u
t
h
o
r,
e
-
m
a
i
l
:
s
a
l
m
a
n
.
a
l
f
a
ri
s
i
@um
k
.a
c
.i
d
Ab
strac
t
Th
e
h
i
g
h
d
e
m
a
n
d
o
f
m
e
a
t
c
a
u
s
e
s
th
e
s
e
l
l
e
r
m
i
x
th
e
fre
s
h
a
n
d
n
o
t
-
fre
s
h
m
e
a
t
.
E
l
e
c
tro
n
i
c
n
o
s
e
was
u
s
e
d
to
d
e
te
c
t
th
e
q
u
a
l
i
t
y
o
f
th
e
m
e
a
t
q
u
i
c
k
l
y
a
n
d
a
c
c
u
ra
te
l
y
.
T
h
i
s
r
e
s
e
a
rc
h
i
s
p
ro
p
o
s
e
d
t
o
te
s
t
a
n
d
a
n
a
l
y
z
e
th
e
s
e
n
s
i
ti
v
i
t
y
o
f
M
O
S
s
e
n
s
o
r
i
n
t
h
e
e
l
e
c
tro
n
i
c
n
o
s
e
a
n
d
s
i
m
u
l
a
te
i
t
u
s
i
n
g
M
a
tl
a
b
to
i
d
e
n
t
i
fy
m
e
a
t
c
l
a
s
s
i
fi
c
a
ti
o
n
u
s
i
n
g
n
e
u
ra
l
n
e
two
rk
.
Te
s
t
p
a
ra
m
e
t
e
rs
b
a
s
e
d
o
n
In
d
o
n
e
s
i
a
n
Nat
i
o
n
a
l
Sta
n
d
a
r
d
(SNI
3932
-
2
0
0
8
)
r
e
q
u
i
r
e
m
e
n
t
o
n
th
e
q
u
a
l
i
ty
o
f
c
a
r
c
a
s
s
a
n
d
m
e
a
t
.
In
th
i
s
s
i
m
u
l
a
ti
o
n
,
th
e
n
u
m
b
e
r
o
f
n
e
u
r
o
n
s
i
n
th
e
h
i
d
d
e
n
l
a
y
e
r
was
v
a
r
i
e
d
t
o
fi
n
d
th
e
m
o
s
t
a
c
c
u
r
a
te
i
d
e
n
ti
fi
c
a
ti
o
n
.
T
h
e
s
e
n
s
i
t
i
v
i
ty
a
n
a
l
y
s
i
s
o
f
th
e
M
O
S
s
e
n
s
o
r
wa
s
c
o
n
d
u
c
te
d
b
y
t
e
s
t
i
n
g
th
e
m
e
a
t
s
a
m
p
l
e
a
ro
m
a
,
c
a
l
c
u
l
a
te
t
h
e
s
e
n
s
i
ti
v
i
t
y
,
i
d
e
n
t
i
f
y
t
h
e
fo
rm
a
ti
o
n
o
f
i
n
p
u
t
,
h
i
d
d
e
n
l
a
y
e
r,
o
u
tp
u
ts
,
a
n
d
s
i
m
u
l
a
t
e
t
h
e
r
e
s
u
l
t
o
f
t
h
e
v
a
ri
e
d
fo
rm
a
ti
o
n
.
Th
e
n
,
f
o
u
n
d
t
h
e
n
u
m
b
e
r
o
f
th
e
m
o
s
t
o
p
t
i
m
a
l
n
e
u
ro
n
s
.
T
h
e
re
s
u
l
t
o
f
t
h
e
d
a
ta
t
ra
i
n
i
n
g
wi
l
l
b
e
a
p
p
l
i
e
d
to
th
e
r
e
a
l
i
n
s
tru
m
e
n
t
.
Key
w
ords
:
m
a
tl
a
b
,
m
e
a
t,
m
e
t
a
l
o
x
i
d
e
s
e
m
i
c
o
n
d
u
c
to
r
,
n
e
u
ra
l
n
e
two
r
k
,
s
i
m
u
l
a
t
i
o
n
Copy
righ
t
©
2
0
1
9
Uni
v
e
rsi
t
a
s
Ahm
a
d
D
a
hl
a
n.
All
rig
ht
s
r
e
s
e
rve
d
.
1.
Int
r
o
d
u
ctio
n
Meat
i
s
on
e
of
the
m
os
t
c
on
s
um
ed
m
ea
l
s
b
y
th
e
pe
op
l
e
aroun
d
the
w
orl
d.
T
he
hi
gh
de
m
an
d
of
m
ea
t
i
s
r
el
ate
d
to
m
ea
t
s
torage
c
o
nd
i
ti
on
s
af
ter
c
utt
i
ng
tha
t
af
f
ec
ts
the
q
ua
l
i
t
y
of
m
ea
t
.
E
s
ti
m
ati
on
of
m
ea
t
qu
a
l
i
t
y
i
s
us
u
al
l
y
ba
s
e
d
on
the
s
en
s
e
of
s
m
el
l
or
hu
m
an
v
i
s
i
on
t
ha
t
al
l
o
w
s
the
oc
c
urr
en
c
e
of
ne
gl
i
ge
nc
e
[1]
.
T
he
f
r
es
hn
es
s
l
ev
e
l
of
m
ea
t
i
s
us
ua
l
l
y
us
ed
to
d
ec
i
d
e
weth
er
t
he
m
ea
t
i
s
c
on
s
um
ab
l
e
or
no
t
[2]
.
T
he
qu
a
l
i
t
y
i
de
nt
i
f
i
c
ati
on
of
f
r
es
h
m
ea
t
r
eq
ui
r
es
a
nu
m
be
r
of
l
ab
orator
y
tes
t
s
ac
c
ordi
ng
to
S
N
I
c
l
as
s
i
f
i
c
ati
on
,
na
m
el
y
;
t
he
n
um
b
er
of
ba
c
teri
a,
c
ol
or, h
ardnes
s
, m
oi
s
ture c
on
te
nt
[3
]
.
T
he
hi
gh
d
em
an
d
f
or
m
ea
t
c
au
s
es
the
s
el
l
er
m
i
x
the
f
r
es
h
m
ea
t
w
i
t
h
th
e
de
c
a
y
e
d
on
es
(
no
t
-
f
r
es
h
m
ea
t
)
.
T
he
pu
r
p
os
e
i
s
a
hi
g
he
r
prof
i
t
al
t
h
ou
gh
tha
t
i
s
i
l
l
eg
a
l
a
nd
i
t
ha
r
m
s
f
or
the
c
on
s
um
ers
[4
]
.
Dete
r
m
i
ni
n
g
th
e
s
af
et
y
of
m
ea
t
i
s
c
on
du
c
t
ed
b
y
q
ua
nt
i
f
y
i
ng
v
ol
at
i
l
e
organ
i
c
c
o
m
po
un
d
as
s
oc
i
ate
d
wi
th
the
gro
wth
of
m
i
c
r
oo
r
ga
ni
s
m
s
[
5
].
It
i
s
h
ard
to
k
no
w
e
as
i
l
y
th
e
qu
al
i
t
y
of
the
m
ea
t
on
the
m
ar
k
et
be
c
au
s
e
th
e
m
ea
t
m
us
t
be
tes
ted
i
n
th
e
l
a
bo
r
at
or
y
an
d
a
l
s
o
ti
m
e
c
on
s
um
i
ng
,
f
or
tha
t
r
ea
s
o
n
s
,
t
he
el
ec
tr
on
i
c
no
s
e
c
ou
p
l
ed
w
i
th
di
f
f
erent
t
y
pe
of
s
e
ns
or
arr
a
y
s
i
s
us
ed
.
A
n
art
i
f
i
c
i
al
i
nte
l
l
i
ge
n
c
e
progr
am
i
s
n
ee
d
ed
t
o
c
r
ea
te
th
at
i
ns
tr
um
en
t
ne
ed
s
to
i
d
en
t
i
f
y
th
e
c
l
as
s
i
f
i
c
ati
on
of
the
m
ea
t
on
the
m
ar
k
et
an
d
ne
ural
ne
t
wor
k
i
s
on
e
of
c
o
m
m
on
us
ed
progr
am
s
[
6
]
.
T
he
el
ec
tr
o
ni
c
no
s
e
i
s
a
n
i
ns
tr
um
en
t
tha
t
h
av
e
be
e
n
de
v
e
l
op
ed
i
n
wi
de
l
y
r
an
gi
ng
t
o
di
a
gn
os
e
s
e
v
er
al
ob
j
ec
t
s
u
c
h
as
f
oo
d
i
nd
us
tr
y
an
d
ag
r
i
c
ul
t
ure
[7
]
.
T
he
el
ec
tr
on
i
c
no
s
e
h
as
be
e
n
ap
p
l
i
e
d
i
n
s
e
v
era
l
s
t
ud
i
es
,
s
uc
h
as
to
de
t
erm
i
ne
the
qu
a
l
i
t
y
of
c
off
ee
un
de
r
r
oa
s
ti
ng
[8]
,
w
i
ne
c
l
as
s
i
f
i
c
ati
on
[9
]
,
d
ete
c
t
i
on
of
m
atu
r
i
t
y
of
f
r
ui
t
[10]
,
br
ea
d
ba
k
i
ng
arom
a
[11]
,
an
d
e
v
a
l
ua
te
t
h
e
op
ti
m
al
ha
r
v
es
t
da
te
of
ap
p
l
es
[12]
.
T
he
r
e
are
t
w
o
t
y
p
e
s
of
el
ec
tr
on
i
c
n
os
e,
t
ho
s
e
are
di
r
ec
t
a
nd
i
nd
i
r
ec
t.
Ind
i
r
ec
t
m
ea
ns
s
u
c
h
as
qu
an
ti
ati
v
e
a
na
l
y
s
i
s
ba
s
ed
on
i
ns
tr
um
en
tal
d
ete
c
ti
on
,
w
h
i
l
e
di
r
ec
t
de
t
ec
ti
on
us
i
ng
s
en
s
or
y
ol
f
ac
tom
er
y
an
d
i
t
i
s
i
n
c
l
ud
i
ng
m
ol
ec
ul
ar
t
ec
hn
o
l
o
gi
es
,
s
uc
h
as
po
l
y
m
eras
e
c
ha
i
n
r
ea
c
ti
on
(
P
CR)
,
f
l
uo
r
en
c
s
en
c
e
i
n
-
s
i
t
u
h
y
br
i
d
i
z
ati
on
(
F
IS
H)
a
nd
en
z
y
m
e
-
l
i
nk
ed
i
m
m
un
os
orbent
as
s
a
y
(
E
LI
S
A
)
[
13
-
15
]
.
T
w
o
m
ai
n
c
om
po
ne
nts
of
the
el
ec
tr
o
ni
c
no
s
e
i
s
a
s
en
s
i
n
g
s
y
s
tem
an
d
a
r
ec
o
gn
i
z
i
n
g
pa
tte
r
n
s
y
s
tem
.
S
en
s
i
ng
s
y
s
t
em
tha
t
c
ou
p
l
ed
w
i
t
h
a
nu
m
be
r
of
arr
a
y
s
or
s
e
qu
e
nc
es
f
r
o
m
the
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N: 16
93
-
6
93
0
T
E
L
KO
M
NIK
A
V
ol
.
17
,
No.
2
,
A
pril
20
19
:
77
1
~
7
80
772
di
f
f
erent
el
em
en
ts
,
s
uc
h
as
c
he
m
i
c
al
s
en
s
ors
,
whi
c
h
i
s
ea
c
h
el
em
en
t
m
ea
s
ure
the
di
f
f
erent
qu
a
l
i
t
y
of
the
c
he
m
i
c
al
s
te
s
ted
[1
6
]
.
W
he
n
ga
s
s
am
pl
es
are
s
pr
ea
d
ac
r
os
s
the
s
en
s
or
y
arr
a
y
s
,
the
n
t
he
o
do
r
m
ol
ec
ul
es
i
nd
uc
es
the
p
h
y
s
i
c
oc
he
m
i
c
al
c
ha
ng
es
to
th
e
s
e
ns
i
ng
m
ate
r
i
a
l
s
.
T
he
c
i
r
c
ui
t
w
i
l
l
be
m
od
ul
ate
th
e s
i
gn
a
l
a
nd
the
pa
tt
ern
c
an
be
us
ed
t
o c
l
as
s
i
f
y
t
he
arom
a
[17
]
.
A
ne
ural
n
et
w
ork
i
s
a
ne
t
wor
k
o
f
a
s
m
al
l
group
of
proc
es
s
i
ng
p
aradi
gm
s
w
hi
c
h
m
od
e
l
e
d
hu
m
an
ne
ural
s
y
s
tem
s
to
no
n
-
l
i
n
ea
r
s
tat
i
s
t
i
c
s
m
od
el
i
ng
da
t
a.
A
n
eu
r
a
l
ne
t
wor
k
ha
s
a
s
et
of
i
nte
r
c
on
ne
c
te
d
pa
r
a
l
l
el
a
l
g
orit
hm
s
[18]
.
A
ne
ur
al
ne
t
w
ork
i
s
an
a
da
p
ti
v
e
an
d
c
a
p
ab
l
e
s
y
s
t
em
to
s
ol
v
e
pro
bl
em
s
ba
s
ed
on
t
he
i
nf
orm
ati
on
thr
ou
g
h
t
he
ne
t
w
ork
.
A
ne
ural
ne
t
wor
k
i
s
m
os
tl
y
us
e
d
as
a
s
pe
c
i
f
i
c
ap
p
l
i
c
at
i
on
,
s
uc
h
as
da
ta
c
l
as
s
i
f
i
c
ati
on
or
pa
tte
r
n
r
ec
o
gn
i
ti
on
thr
ou
gh
l
e
arni
n
g
proc
es
s
[19]
.
A
ne
ural
n
et
wor
k
ha
s
al
r
ea
d
y
tr
ai
ne
d
t
o
r
ec
og
n
i
z
e
the
g
a
s
the
n
q
ui
c
k
l
y
i
d
en
t
i
f
y
t
he
od
or of
ga
s
b
ec
au
s
e
the
r
e
c
og
ni
t
i
o
n p
r
oc
es
s
ac
tu
al
l
y
i
nv
o
l
v
es
on
l
y
pro
pa
g
ati
on
pr
oc
es
s
[20]
.
Ma
tr
i
x
l
a
bo
r
ato
r
y
,
us
ua
l
l
y
c
al
l
e
d
as
Ma
tl
a
b,
i
s
a
n
u
m
eric
al
c
o
m
pu
tat
i
on
an
d
a
na
l
y
s
i
s
de
s
i
g
ne
d
i
n
a
dv
an
c
e
progr
am
m
i
ng
l
an
g
ua
g
e
us
i
ng
th
e
c
ha
r
ac
ter
i
s
ti
c
s
a
nd
t
he
f
or
m
of
a
m
atri
x
.
Ma
tl
ab
i
s
a
c
om
m
erc
i
al
produc
t
of
Ma
th
wor
k
.In
c
c
o
m
pa
n
y
w
h
i
c
h
d
ev
el
o
pe
d
b
y
us
i
ng
C
+
+
l
an
gu
a
ge
a
nd
as
s
em
bl
er
f
or
the
ba
s
i
c
f
un
c
ti
on
s
of
Ma
t
l
ab
.
G
en
era
l
l
y
,
Ma
t
l
a
b
i
s
us
ed
f
or
m
ath
e
m
ati
c
s
an
d
c
o
m
pu
ta
ti
on
,
al
g
orit
hm
de
v
el
o
pm
en
t,
m
od
el
i
n
g,
s
i
m
ul
ati
o
n,
an
d
prot
ot
y
pe
c
r
ea
ti
o
n
,
da
t
a
an
a
l
y
s
i
s
,
ex
pl
orat
i
o
n,
v
i
s
ua
l
i
z
at
i
o
n,
an
d
G
r
ap
hi
c
Us
er
Int
erf
ac
e
(
G
UI)
.
Ma
tl
ab
h
as
s
o
m
e
pa
r
ti
c
ul
ar
f
un
c
ti
on
s
a
nd
v
ar
i
ou
s
m
eth
od
s
to
s
ol
v
e
an
y
pro
bl
em
s
w
hi
c
h
c
ate
go
r
i
z
ed
i
n
the
too
l
bo
x
[2
1]
.
I
n
th
i
s
r
es
ea
r
c
h,
Ma
t
l
a
b
i
s
us
e
d
to
s
i
m
ul
ate
the
r
es
ul
t
of
v
ar
y
i
n
g
f
orm
ati
on
of
i
np
ut
,
l
a
y
er an
d o
utp
ut
us
i
ng
grap
hi
c
us
er i
nte
r
f
ac
e (G
UI)
.
Me
ta
l
ox
i
d
e
s
em
i
c
on
d
uc
to
r
(
MO
S
)
w
i
d
el
y
us
ed
t
o
m
a
k
e
arr
a
y
f
or
od
or
s
en
s
i
ng
,
bu
t
m
an
y
of
the
m
s
ho
w
s
ga
s
s
en
s
i
ti
v
i
t
y
un
de
r
s
u
i
ta
bl
e
c
on
d
i
ti
on
[
22
,
23
].
T
he
b
as
i
c
prin
c
i
pl
e
of
m
eta
l
ox
i
de
s
em
i
c
on
du
c
tor
(
MO
S
)
s
en
s
or
whe
n
th
e
c
on
c
en
tr
at
i
o
n
of
ox
y
g
en
i
s
0
%
c
on
c
en
tr
a
ti
o
an
d
t
he
tem
p
erature
of
ti
n
di
ox
i
de
(
S
nO
2
)
m
ate
r
i
al
r
ea
c
he
s
400
o
C
,
the
el
ec
tr
on
s
wi
l
l
be
ac
r
os
s
he
gre
en
bo
u
nd
ar
y
.
I
n
c
l
e
an
a
i
r
,
d
on
or
el
ec
tr
o
ns
i
n
ti
n
di
ox
i
de
(
S
nO
2
)
are
at
r
ac
ted
to
war
d
ox
y
ge
n
whi
c
h
i
s
prev
en
t
i
n
g
e
l
ec
tr
i
c
c
urr
en
t
f
l
o
w
.
If
t
he
s
en
s
or
ex
po
s
e
d
b
y
r
ed
uc
i
ng
ga
s
,
the
s
urf
ac
e
de
ns
i
t
y
of
ab
s
or
be
d
ox
y
ge
n
de
c
r
ea
s
e
d
b
ec
au
s
e
the
r
e
ac
ti
o
n
of
r
ed
uc
i
ng
ga
s
.
T
he
el
ec
tr
o
ns
w
i
l
l
b
e
e
as
y
t
o
f
l
o
w
i
n
ti
n
di
ox
i
de
a
nd
i
ts
al
l
o
w
i
ng
c
urr
en
t
to
f
l
o
w
f
r
ee
l
y
thro
ug
h
th
e
s
en
s
or.
T
he
c
he
m
i
c
al
r
ea
c
ti
on
s
f
r
om
the
ga
s
an
d
t
he
ad
s
orb
e
d
ox
y
g
en
on
t
he
s
u
r
f
ac
e
of
the
ti
n
ox
i
de
l
a
y
er
ar
e
v
ari
ed
,
t
ho
s
e
de
p
en
d
o
n
the
r
ea
c
ti
v
i
t
y
of
the
s
en
s
i
n
g
m
a
teri
a
l
an
d
th
e
tem
pe
r
atu
r
e
c
on
d
i
ti
on
of
t
he
s
en
s
or.
T
he
ga
s
c
on
c
en
tr
at
i
on
i
n
t
he
a
i
r
c
an
b
e
de
t
ec
ted
b
y
m
ea
s
urin
g t
he
c
h
an
g
e o
f
th
e res
i
s
tan
c
e
of
th
e m
eta
l
ox
i
de
s
em
i
c
on
du
c
t
or gas
s
en
s
or
[24]
.
B
as
ed
on
t
he
pro
bl
em
ab
ov
e,
t
hi
s
r
es
ea
r
c
h
propos
e
d
to
i
d
en
t
i
f
y
l
e
v
e
l
of
m
ea
t
f
r
e
s
hn
es
s
b
y
us
i
ng
t
he
MO
S
s
en
s
or
t
y
p
es
T
G
S
26
0
0,
T
G
S
26
0
2,
T
G
S
26
20
,
MQ
1
35
,
T
G
S
18
3.
T
he
n,
ne
ural
ne
t
w
ork
m
eth
od
wi
l
l
be
us
ed
to
i
n
de
nt
i
f
y
th
e
r
es
ul
t
of
MO
S
s
en
s
or,
ne
ura
l
n
et
wor
k
m
eth
od
wi
l
l
be
c
r
ea
t
ed
on
Ma
t
l
a
b.
T
he
f
un
c
i
on
of
n
eu
r
a
l
n
et
w
ork
m
eth
od
i
s
to
tes
t
the
m
ea
t
s
a
m
pl
e
arom
a
to
ob
t
ai
n
th
e
r
es
i
s
tan
c
e
r
ati
o.
T
he
r
es
ul
t
of
th
i
s
r
es
ea
r
c
h
i
s
the
m
os
t
op
ti
m
al
nu
m
be
r
of
ne
u
r
o
ns
f
or thi
s
de
tec
t
or s
y
s
tem
s
.
2.
Re
se
a
r
ch M
eth
o
d
T
he
m
eth
od
us
ed
i
s
an
i
n
di
r
ec
t
m
eth
od
.
T
he
aro
m
a
of
the
m
ea
t
w
as
tak
en
by
us
i
ng
i
nj
ec
ti
o
n
tu
be
t
he
n
pu
t
i
t
i
nto
th
e
tes
t
i
ng
c
h
am
be
r
.
In
the
t
es
ti
n
g
c
ha
m
be
r
,
the
r
e
are
f
i
v
e
ga
s
s
en
s
ors
of
m
eta
l
ox
i
de
s
e
m
i
c
on
du
c
tor
t
y
p
e,
whi
c
h
wi
l
l
v
erif
y
t
he
s
am
pl
e
aro
m
a
ex
ac
tl
y
an
d
s
i
m
ul
tan
eo
us
l
y
.
T
he
da
t
a
r
ea
d
b
y
t
he
s
en
s
or
w
i
l
l
b
e
ac
qu
i
r
ed
b
y
th
e
da
t
a
ac
q
ui
s
i
t
i
on
.
E
ac
h
di
f
f
erent
s
a
m
pl
e
w
i
l
l
a
l
s
o
r
es
ul
t
a
d
i
f
f
erent
pa
tte
r
ns
.
T
ho
s
e
pa
tte
r
ns
w
i
l
l
b
e
l
e
arned
b
y
us
i
ng
a
ne
ura
l
ne
t
w
ork
w
i
th
t
he
d
e
term
i
ne
d
target
,
th
at
i
s
t
he
c
l
as
s
i
f
i
c
ati
o
n
of
m
ea
t
f
r
es
hn
es
s
of
ea
c
h
s
en
s
or
2.1
.
D
ata Co
ll
ec
t
ion
T
he
s
tep
s
of
da
ta
c
ol
l
ec
t
i
o
n
an
d
s
am
pl
e
m
ea
s
ure
m
en
t
i
s
s
ho
w
n
i
n
F
i
gu
r
e
1
.
T
he
da
t
a
c
ol
l
ec
t
i
on
i
s
s
tarted
b
y
e
nte
r
i
n
g
the
s
am
pl
e
i
nt
o
a
v
i
a
l
bo
tt
l
e
a
nd
en
d
wi
t
h
no
r
m
al
i
z
at
i
on
.
T
he
da
ta
us
ed
i
s
th
e
s
e
n
s
i
ti
v
i
t
y
of
the
av
erage
s
en
s
or
ou
tp
ut
t
o
th
e
c
l
ea
n
a
i
r
an
d
the
ga
s
s
a
m
pl
e i
n rea
l
-
ti
m
e.
T
he
s
en
s
i
ti
v
i
t
y
of
th
e res
p
on
s
e s
e
ns
or us
ed
e
qu
ati
on
as
f
ol
l
o
w
s
;
=
⁄
(
1)
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NIK
A
IS
S
N: 1
69
3
-
6
93
0
M
O
S
g
as
s
en
s
or
of
me
at
fr
es
hn
es
s
an
al
y
s
i
s
o
n E
-
n
os
e
(
B
u
d
i
G
u
na
w
an
)
773
W
h
ere
Ro
i
s
the
s
e
ns
or
r
es
po
ns
e
t
o
th
e
c
l
e
an
a
i
r
(
r
ef
erenc
e)
an
d
R
g
i
s
th
e
s
en
s
or
r
es
po
ns
e
to
the
s
am
pl
e
i
n
oh
m
un
i
ts
.
MO
S
t
y
p
e
s
e
ns
or
s
en
s
i
n
g
e
l
em
en
t
i
s
m
ad
e
of
ti
n
ox
i
d
e
m
ate
r
i
al
(
S
nO
2)
w
he
r
e
Ro
i
s
the
s
en
s
or
r
es
po
ns
e
to
c
l
ea
n
a
i
r
(
r
e
f
erenc
e)
an
d
Rg
i
s
th
e
s
en
s
o
r
r
es
po
ns
e
to
t
he
s
am
pl
e
i
n
oh
m
un
i
t.
In
th
i
s
c
as
e,
the
m
ea
t
aro
m
a
i
s
the
r
ed
uc
er
ga
s
s
o
tha
t
th
e
r
es
i
s
tan
c
e
i
s
al
wa
y
s
c
h
an
g
ed
ac
c
ord
i
ng
to
g
as
c
on
c
en
tr
ati
o
n.
E
n
t
e
r
t
h
e
s
a
m
p
l
e
i
n
t
o
a
1
0
g
r
a
m
v
i
a
l
b
o
t
t
l
e
M
e
a
s
u
r
i
n
g
R
o
f
o
r
2
m
i
n
u
t
e
s
T
u
r
n
o
n
t
h
e
a
i
r
p
u
m
p
M
e
a
s
u
r
i
n
g
R
g
f
o
r
2
m
i
n
u
t
e
s
N
o
r
m
a
l
i
z
e
t
h
e
s
e
n
s
o
r
w
i
t
h
a
i
r
a
n
d
s
i
l
i
c
a
g
e
l
f
o
r
3
0
m
i
n
u
t
e
s
-
1
h
o
u
r
I
n
j
e
c
t
a
s
a
m
p
l
e
s
c
e
n
t
i
n
t
o
t
h
e
c
h
a
m
b
e
r
T
u
r
n
o
f
f
t
h
e
a
i
r
p
u
m
p
F
i
gu
r
e
1
.
T
he
s
tep
of
da
ta
c
ol
l
ec
ti
o
n
a
nd
s
am
pl
e m
ea
s
urem
en
t
2.
2
.
D
ata
A
cqu
i
sitio
n
Data
ac
qu
i
s
i
ti
on
i
s
c
on
d
uc
t
ed
as
o
do
r
d
ete
c
t
i
on
s
y
s
te
m
.
Har
dw
are
un
i
t
i
s
de
s
i
g
n
ed
f
or
ac
qu
i
r
i
ng
the
r
es
po
ns
e
of
s
en
s
ors
.
T
he
da
ta
ac
qu
i
s
i
t
i
on
d
es
i
g
n
of
th
e
s
am
pl
e
m
ea
s
urem
en
t
i
s
s
ho
w
n
i
n
F
i
g
ure
2
.
T
he
da
ta
a
c
qu
i
s
i
ti
on
us
e
d
5
t
y
p
es
of
MO
S
s
e
ns
ors
,
i
e
;
T
G
S
26
00
,
T
G
S
26
02
,
T
G
S
26
20
,
T
G
S
81
3
an
d
MQ
1
35
.
T
he
pa
r
am
ete
r
us
ed
i
n
the
c
l
as
s
i
f
i
c
ati
on
f
ol
l
o
wi
ng
S
NI r
u
l
e
39
3
2:2
0
08
, s
uc
h a
s
; th
e n
um
be
r
of
ba
c
teri
a,
c
ol
or,
s
tr
i
c
t
ne
s
s
an
d
w
at
er c
on
te
nt
.
F
i
gu
r
e
2
.
T
he
d
a
ta
ac
qu
i
s
i
ti
on
d
es
i
gn
of
th
e s
am
pl
e m
ea
s
urem
en
t
2.3
.
N
eura
l Netw
o
r
k S
t
r
u
c
t
u
r
e De
s
ign
In
th
i
s
s
tud
y
,
n
eu
r
a
l
n
et
wor
k
s
tr
uc
ture
de
s
i
gn
e
d
b
y
us
i
ng
th
e
f
or
m
ati
on
o
f
5
-
1
-
2
(
5
i
np
ut
,
1
hi
d
de
n
l
a
y
e
r
,
da
n
2
ou
tpu
t)
.
T
he
f
or
m
ati
on
f
i
gu
r
e
is
s
ho
wn
i
n
F
i
gu
r
e
3
.
Th
e
i
np
ut
of
thi
s
s
tr
uc
ture
are
T
G
S
26
0
0,
T
G
S
26
02
,
T
G
S
26
20
,
T
G
S
81
3
an
d
MQ
13
5.
T
he
ou
tp
ut
of
ne
ura
l
ne
t
w
ork
s
tr
uc
ture
de
s
i
gn
a
r
e
c
on
s
i
s
t
of
tw
o
ou
t
pu
ts
where
i
t
i
s
i
nd
i
c
ate
t
he
m
ea
t
f
r
es
hn
es
s
.
F
un
c
ti
o
n o
f
ac
ti
v
at
i
o
n u
s
ed
i
n h
i
d
de
n
l
a
y
er
i
s
s
i
gm
oi
d b
i
ne
r
a
nd
t
he
ou
t
pu
t
i
s
l
i
ni
er.
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N: 16
93
-
6
93
0
T
E
L
KO
M
NIK
A
V
ol
.
17
,
No.
2
,
A
pril
20
19
:
77
1
~
7
80
774
T
G
S
2
6
0
2
T
G
S
2
6
2
0
M
Q
1
3
5
T
G
S
8
1
3
T
G
S
2
6
0
0
u
n
f
r
e
s
h
f
r
e
s
h
I
N
P
U
T
H
I
D
D
E
N
L
A
Y
E
R
O
U
T
P
U
T
w
e
i
g
h
t
s
w
e
i
g
h
t
s
.
.
.
.
O
u
t
1
O
u
t
2
F
o
r
w
a
r
d
p
r
o
p
a
g
a
t
i
o
n
B
a
c
k
p
r
o
p
a
g
a
t
i
o
n
S
y
n
a
p
s
e
S
y
n
a
p
s
e
F
i
gu
r
e
3
.
T
he
m
ul
ti
l
a
y
er
pe
r
c
ep
tr
on
s
tr
uc
ture
of
th
e
de
s
i
gn
ed
n
eu
r
a
l
n
et
w
ork
T
he
proc
es
s
of
l
ea
r
ni
n
g
wi
th
ba
c
k
propag
ati
on
a
l
g
orit
h
m
i
n
the
arti
f
i
c
i
a
l
n
eu
r
a
l
n
e
twork
us
ed
e
qu
at
i
o
n
s
(
2
)
to
(
1
2
)
[
25
]
.
1)
S
tep
s
i
n f
or
w
ard
i
ng
are:
a)
Nor
m
al
i
z
e t
he
i
np
ut
a
nd
de
s
i
r
ed
ou
tpu
t
(
w
i
t
hi
n
th
e
r
an
ge
0
-
1)
.
b)
W
ei
gh
ti
ng
v
al
ue
r
a
nd
om
l
y
t
o (
-
1
)
un
t
i
l
(
+1
)
c)
i
ni
ti
a
l
i
z
i
ng
of
bi
as
v
a
l
ue
(
1
)
d)
F
i
nd
t
he
s
um
an
d s
i
gm
oi
d f
or
a Hi
dd
en
l
ay
er
a
nd
O
ut
p
ut
l
ay
er
i)
Hi
dd
en
La
y
er
,
S
um
v
al
u
e
:
N
0
i
.
j
i
i
j
V
X
Z
(
2
)
wi
th
N =
tot
al
s
y
na
ps
e l
a
y
er
2 (hi
dd
e
n l
a
y
er)
,
S
i
gm
oi
d
v
al
u
e
:
bi
a
s
Zj
j
e
Z
1
1
'
(
3
)
ii)
O
utp
ut
La
y
er
,
S
um
v
al
ue
:
M
0
i
j
'.
k
j
k
W
Z
Y
(
4
)
wi
th
M
=
tot
al
s
y
na
ps
e
l
a
y
e
r
3
,
S
i
gm
oi
d
v
al
ue
:
b
i
a
s
Yk
k
e
Y
1
1
'
(
5
)
2)
S
tep
s
i
n
ba
c
k
w
ard s
te
ps
ar
e:
a)
Cal
c
u
l
ate
th
e
ou
t
pu
t
err
or (
)
.
O
utp
u
t
err
or=
O
u
tpu
t
l
a
y
er
3
-
de
s
i
r
e
d
ou
t
pu
t
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NIK
A
IS
S
N: 1
69
3
-
6
93
0
M
O
S
g
as
s
en
s
or
of
me
at
fr
es
hn
es
s
an
al
y
s
i
s
o
n E
-
n
os
e
(
B
u
d
i
G
u
na
w
an
)
775
2
'
2
1
)
(
k
k
k
Y
d
M
S
E
E
r
r
(
6
)
'
'
k
k
k
k
k
Y
d
dY
d
E
r
r
(
7
)
b)
Cal
c
u
l
ate
th
e
hi
dd
en
err
or (
)
jk
L
k
k
j
k
k
k
j
j
j
j
k
k
k
j
k
O
W
dZ
dY
dY
d
E
r
r
E
r
r
dZ
dZ
dZ
dY
dY
d
E
r
r
dZ
d
E
r
r
1
'
'
'
)
1
(
'
'
j
j
j
O
Z
Z
E
r
r
(
8
)
c)
Upda
t
i
n
g
w
e
i
g
ht
f
or
wei
gh
t
on
H
i
dd
en
-
O
utp
ut
l
a
y
er
'
j
k
jk
k
k
k
jk
k
jk
Z
dW
dY
dY
d
E
r
r
dW
d
E
r
r
W
jk
jk
jk
W
W
W
(
9
)
d)
Upda
t
i
n
g
b
i
as
v
al
ue
on
t
he
ou
tp
ut
l
a
y
er
1
'
'
k
k
k
k
k
k
k
k
d
b
i
a
s
dY
dY
d
E
r
r
d
b
i
a
s
d
E
r
r
b
i
a
s
k
k
k
b
i
a
s
b
i
a
s
b
i
a
s
(
10
)
e)
Upda
t
i
n
g
w
e
i
g
ht
f
or
wei
gh
t
on
In
pu
t
-
H
i
dd
en
l
a
y
er
i
O
ij
j
j
j
ij
j
ij
X
dV
daZ
dZ
d
E
r
r
dV
d
E
r
r
V
'
'
ij
ij
ij
V
V
V
(1
1
)
f)
Upda
t
i
n
g b
i
as
on
th
e h
i
dd
e
n l
a
y
er
1
'
'
O
j
j
j
j
j
j
j
d
b
ia
s
dZ
dZ
d
E
r
r
d
b
ia
s
d
E
r
r
b
ia
s
j
j
j
b
i
a
s
b
i
a
s
b
i
a
s
(1
2
)
W
h
ere:
i
,j
,
k
: Res
pe
c
t
i
v
el
y
n
eu
r
on
nu
m
be
r
of
i
np
ut,
hi
dd
e
n,
a
nd
o
u
tpu
t
l
a
y
ers
X
i
: In
p
ut
-
i
o
n i
np
ut
l
a
y
er
V
i
,j
:
W
ei
gh
t o
f
i
n
pu
t
-
h
i
d
de
n
l
a
y
er
Z
j
: S
um
m
i
ng
r
es
ul
t
on
ne
uro
n
-
j
at
hi
dd
e
n l
a
y
er
Z
j
`
: A
c
ti
v
at
i
o
n res
ul
t o
n
ne
uro
n
-
j
a
y
h
i
d
de
n
l
a
y
er
W
j,
k
:
W
ei
gh
t o
f
hi
dd
e
n
-
ou
t
pu
t
l
a
y
e
r
Y
j
: S
um
m
i
ng
r
es
ul
t
on
ne
uro
n
-
j
at
ou
t
pu
t
l
a
y
er
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N: 16
93
-
6
93
0
T
E
L
KO
M
NIK
A
V
ol
.
17
,
No.
2
,
A
pril
20
19
:
77
1
~
7
80
776
Y
j
`
: A
c
ti
v
at
i
o
n res
ul
t o
n
ne
uro
n
-
j
a
y
o
utp
u
t l
a
y
er
0
: In
i
t
i
a
l
l
ea
r
n
i
n
g rate
: L
ea
r
n
i
n
g rate
i
t
erati
on
-
n
0
: Con
s
ta
nta
l
e
arni
ng
r
at
e
0
: Hi
d
de
n
err
or
: O
utp
ut
err
or
∆
: Upd
ati
ng
c
ha
ng
e
of
wei
gh
t o
n
hi
d
de
n
-
ou
tp
ut
l
a
y
er
∆
: Upd
ati
ng
c
ha
ng
e
of
wei
gh
t o
n
i
np
ut
-
hi
dd
en
l
a
y
er
∆
: Upd
ati
ng
c
ha
ng
e
of
bi
as
a
t o
ut
pu
t
l
a
y
er
∆
: Upd
ati
ng
c
ha
ng
e
of
bi
as
a
t h
i
dd
e
n l
a
y
er
T
he
tr
ai
ni
ng
i
s
do
ne
b
y
gi
v
i
ng
v
ari
ati
on
s
on
the
nu
m
be
r
of
ne
urons
i
n
t
he
hi
dd
e
n
l
a
y
er,
wi
th
th
e
qu
an
t
i
t
y
4,
8,
a
nd
16
.
T
ho
s
e
v
ari
ati
on
s
i
s
us
e
d
to
en
l
arge
t
he
d
i
m
en
s
i
on
of
r
ec
og
ni
ti
o
n
pa
tte
r
n
.
F
r
om
tho
s
e
v
ar
i
ati
on
s
w
i
l
l
b
e
f
ou
nd
th
e
n
um
be
r
of
th
e
m
os
t
op
ti
m
al
n
e
urons
a
nd
t
he
r
es
ul
t o
f
th
e
da
t
a t
r
a
i
n
i
ng
wi
l
l
be
a
pp
l
i
e
d i
n t
h
e rea
l
i
ns
tr
um
en
t.
3.
Re
sult
s
a
nd
D
isc
u
s
sio
n
T
he
da
ta
ac
qu
i
s
i
ti
on
s
y
s
te
m
f
or
s
a
m
pl
e
m
ea
s
ure
m
e
nt
ha
s
be
e
n
m
ad
e
as
s
ho
wn
i
n
F
i
gu
r
e
4
.
T
he
s
am
pl
e
of
m
ea
t
us
ed
i
s
10
gram
s
.
O
n
thi
s
ac
q
ui
s
i
ti
o
n
d
ata
proc
e
s
s
,
ardui
n
o
i
s
c
on
ne
c
te
d
t
o
CO
M
11
the
n
the
t
he
s
am
pl
i
ng
c
al
c
u
l
at
i
o
n
ba
s
el
i
ne
w
i
l
l
b
e
a
na
l
y
z
e
d
.
T
hi
s
proc
es
s
i
s
c
on
du
c
t
ed
i
n f
oo
d
tec
hn
o
l
og
y
l
ab
orator
y
.
D
es
c
r
i
pti
on
:
1 =
s
i
l
i
c
a g
e
l
f
or nor
m
al
i
z
ati
on
of
th
e
s
en
s
or
2 =
i
n
pu
t
pu
m
p t
o d
r
ai
n a
i
r
i
nto
t
he
c
ha
m
be
r
3 =
ou
t
pu
t
pu
m
p t
o f
l
o
w
a
i
r
ou
t
4 =
A
r
du
i
n
o m
eg
a 2
56
0
5 =
c
h
am
be
r
w
i
th
s
en
s
or
arr
a
y
s
MOS
6 =
r
u
bb
er
i
n
l
et
to
i
nj
ec
t a
r
o
m
a
f
r
o
m
th
e s
a
m
pl
e
7 =
ad
a
pto
r
A
C
-
DC
F
i
gu
r
e
4
.
T
he
da
ta
ac
qu
i
s
i
ti
on
s
y
s
tem
f
or s
a
m
pl
e m
ea
s
urem
en
t
T
he
p
ara
m
ete
r
s
of
thi
s
s
am
pl
e
are
tes
ted
in
ag
r
i
c
u
l
tu
r
e
l
ab
orat
or
y
to
f
i
n
d
o
ut
the
c
r
i
teri
a
of
fr
es
h
an
d
no
t
-
f
r
es
h
m
e
at
as
a
r
ef
erenc
e
tr
a
i
ni
ng
target.
B
as
ed
on
I
nd
o
ne
s
i
an
Na
ti
o
na
l
S
tan
da
r
d
(
S
NI
39
3
2
-
20
08
)
r
eq
ui
r
em
en
t
o
n
th
e
q
ua
l
i
t
y
of
c
arc
as
s
an
d
m
ea
t,
the
m
ea
t
i
s
c
l
as
s
i
f
i
ed
as
f
r
es
h
of
th
e
n
um
be
r
of
ba
c
teri
a
l
es
th
en
0.4
6
x
10
6
Cf
u/g
.
T
he
de
t
ai
l
s
r
es
ul
t
of
th
e
tes
ted
s
am
pl
e p
aram
ete
r
i
s
s
ho
w
n
i
n
T
ab
l
e
1
.
T
ab
l
e
1.
F
r
es
h
ne
s
s
C
l
as
s
i
f
i
c
ati
on
of
M
eat
f
r
o
m
La
bo
r
at
or
y
T
es
ts
No
Tes
t
P
a
r
a
m
e
t
e
r
s
Tes
t
E
q
u
ip
men
t
F
r
e
s
h
N
o
t
-
f
r
e
s
h
1
n
u
m
b
e
r
o
f
b
a
c
t
e
r
ia
c
u
p
c
o
u
n
t
met
h
o
d
(
TP
C
)
0
,
4
6
x
1
0
6
C
f
u
/
g
1
,
1
8
x
1
0
6
C
f
u
/
g
2
c
o
lor
c
o
lor
r
e
a
d
e
r
L
2
8
.
5
a
0
.
2
b
7
.
1
L
3
9
.
6
a
3
.
5
b
1
1
.
9
3
s
t
r
i
c
t
n
e
s
s
p
e
n
e
t
r
o
m
e
t
e
r
1
4
0
g
r
1
5
5
g
r
4
w
a
t
e
r
c
o
n
t
e
n
t
D
igit
a
l
w
e
igh
e
r
1
0
.
0
3
g
r
8
.
8
8
5
g
r
F
i
gu
r
e
5
s
ho
w
s
t
ha
t
the
da
ta
us
ed
f
or
i
ni
t
i
a
l
s
i
m
ul
ati
o
n
i
s
2
2
da
ta
a
nd
ea
c
h
s
en
s
or
ha
s
di
f
f
erent
s
en
s
i
t
i
v
i
t
y
ac
c
ordi
ng
t
o
i
ts
c
ha
r
ac
te
r
i
s
ti
c
s
.
O
n
the
r
ep
eti
t
i
o
n
1
-
1
1
s
h
o
w
s
the
s
en
s
or
s
en
s
i
ti
v
i
t
y
was
s
tab
l
e
be
c
a
us
e
the
c
on
di
t
i
o
n
of
m
ea
t
s
am
pl
es
i
s
s
ti
l
l
g
oo
d
(
u
nd
er
4
ho
urs
)
w
hi
l
e
on
the
r
ep
e
ti
t
i
o
n
12
-
22
s
ho
wed
the
c
om
pa
r
i
s
on
s
en
s
i
ti
v
i
t
y
be
t
wee
n
the
ba
s
e
l
i
ne
a
nd
the
s
am
pl
e
arom
a
ha
v
e
bi
g
ge
r
nu
m
be
r
be
c
au
s
e
th
e
c
on
di
ti
on
of
m
ea
t
s
a
m
pl
es
be
gi
n
to
d
ec
a
y
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NIK
A
IS
S
N: 1
69
3
-
6
93
0
M
O
S
g
as
s
en
s
or
of
me
at
fr
es
hn
es
s
an
al
y
s
i
s
o
n E
-
n
os
e
(
B
u
d
i
G
u
na
w
an
)
777
(
ov
er
6
ho
ur
s)
.
G
UI
on
Ma
tl
ab
i
s
us
e
d
to
s
i
m
ul
at
e
th
e
r
es
ul
t
of
i
de
nt
i
f
i
c
ati
on
.
T
h
e
s
i
m
ul
ati
o
n
i
s
c
on
du
c
te
d
af
ter
the
ac
k
qu
i
s
i
ti
o
n
da
t
a
s
a
v
ed
as
l
o
ad
d
ata
.
T
he
n
t
he
tr
a
i
n
i
ng
c
a
n
be
r
un
af
ter
the
da
ta
i
n
pu
t c
om
pl
ete
l
y
. T
he
de
ta
i
l
di
s
p
l
a
y
a
nd
i
np
ut
of
G
UI o
f
th
i
s
s
tud
y
s
h
o
w
s
i
n
F
i
gu
r
e
6
.
F
i
gu
r
e
5
.
S
en
s
i
ti
v
i
t
y
of
MOS g
as
s
e
ns
or
F
i
gu
r
e
6
.
G
UI s
i
m
ul
ati
o
n
s
o
n M
at
l
a
b
T
he
r
es
ul
ts
of
the
tr
ai
ni
ng
proc
es
s
i
s
s
ho
w
n
i
n
F
i
gu
r
e
7
w
he
r
e
the
v
ar
i
at
i
on
nu
m
be
r
of
ne
uro
ns
i
n
the
hi
dd
e
n
l
a
y
er
s
ho
w
th
at
the
ac
c
urac
y
of
thi
s
tr
ai
ni
n
g
i
s
10
0%
where
the
w
r
on
g
da
ta
i
s
0.
T
ota
l
d
ata
us
e
d
a
r
e
22
.
T
he
r
es
ul
t
of
th
i
s
tr
ai
ni
n
g
m
ea
ns
tha
t
the
r
ec
o
gn
i
z
i
ng
a
pa
t
tern
of
aro
m
as
f
r
o
m
the
f
i
f
th
s
en
s
or
s
en
s
i
ti
v
i
t
y
t
o
w
ards
t
he
c
on
d
i
ti
on
s
of
the
f
r
es
h
an
d
n
ot
-
f
r
es
h m
ea
t
up
to
10
0%.
F
i
gu
r
e
7
.
T
he
r
es
ul
t o
f
th
r
e
e v
aria
t
i
o
ns
of
ne
urons
nu
m
be
r
trai
ni
ng
proc
es
s
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N: 16
93
-
6
93
0
T
E
L
KO
M
NIK
A
V
ol
.
17
,
No.
2
,
A
pril
20
19
:
77
1
~
7
80
778
T
he
ne
x
t
tr
ai
n
i
n
g
tes
t
i
s
c
on
du
c
t
ed
b
y
us
i
ng
10
s
ets
of
da
ta
to
f
i
nd
t
he
m
os
t
op
ti
m
al
ne
uro
n
n
um
be
r
f
or
ea
c
h
s
en
s
or.
T
he
s
ou
r
c
e
of
da
t
a
i
s
l
oc
a
ted
on
ard
ui
n
o.
T
he
da
ta
i
s
l
oa
de
d
an
d
r
u
n
th
e
t
es
t
i
ng
.
T
he
n
um
be
r
of
ne
urons
v
ar
i
at
i
on
us
ed
i
n
t
hi
s
s
tud
i
ar
e
4,
8
,
an
d
16
.
T
he
r
es
ul
t
of
tes
ti
n
g
b
y
us
i
n
g
4
ne
ur
on
s
i
s
s
ho
wn
i
n
T
ab
l
e
2,
8
ne
urons
i
s
s
ho
wn
i
n
T
ab
l
e
3,
an
d
16
n
eu
r
on
s
i
s
s
ho
w
n
i
n
T
ab
l
e 4
.
B
as
ed
o
n
tab
l
e,
t
he
r
es
ul
ts
of
tes
ti
ng
wi
t
h
4
ne
u
r
on
s
i
n
the
h
i
dd
en
l
a
y
er
wi
th
1
0
ti
m
es
tes
ti
n
g
f
ou
nd
t
ha
t
7
m
ea
t
on
c
l
as
s
i
f
i
c
at
i
on
and
3
m
ea
t
on
not
-
f
r
es
h
c
l
as
s
i
f
i
c
ati
on
.
B
ut,
th
i
s
tes
ti
n
g
ha
s
2
err
or
i
de
nti
f
i
c
ati
on
wi
th
t
he
p
erc
en
ta
ge
of
s
uc
c
es
s
r
ate
i
s
80
%.
T
he
err
or
i
de
nti
f
i
tas
i
on
are
i
n t
es
ti
n
g
nu
m
b
er 7 an
d
9.
T
he
r
es
ul
ts
of
tes
ti
ng
wi
th
8
ne
urons
i
n
t
he
hi
d
de
n
l
a
y
er
w
i
t
h
1
0
ti
m
es
tes
ti
n
g
f
ou
nd
th
at
5
m
ea
t
on
f
r
es
h
m
ea
t
c
l
as
s
i
f
i
c
ati
on
an
d
5
m
ea
t
on
no
t
-
f
r
es
h
c
l
as
s
i
f
i
c
ati
on
.
T
he
r
e
wer
e
no
err
or
i
de
nti
f
i
c
at
i
on
on
t
hi
s
t
es
ti
n
g
proc
es
s
.
T
he
pe
r
c
en
ta
ge
of
s
uc
c
es
s
r
ate
i
s
10
0%.
T
he
d
eta
i
l
r
es
u
l
t
of
th
i
s
te
s
ti
ng
i
s
s
ho
w
n
i
n
T
ab
l
e 3
.
T
he
r
es
ul
ts
of
tes
ti
ng
w
i
t
h
16
n
eu
r
on
s
i
n
t
he
h
i
d
de
n
l
a
y
er
wi
th
10
ti
m
es
tes
ti
ng
f
ou
nd
tha
t
6
m
ea
t
o
n
f
r
es
h
m
ea
t
c
l
as
s
i
f
i
c
ati
on
an
d
4
m
ea
t
on
no
t
-
f
r
es
h
c
l
as
s
i
f
i
c
at
i
o
n.
T
he
r
e
we
r
e
1
err
or
i
d
en
t
i
f
i
c
ati
on
.
T
he
t
he
p
erc
en
ta
ge
of
s
uc
c
es
s
r
ate
i
s
9
0%.
T
he
err
or
i
de
n
ti
f
i
c
ati
o
n
r
es
ul
t
are i
s
i
n t
es
t
i
n
g n
um
be
r
8.
T
he
r
es
ul
t o
f
te
s
ti
ng
i
s
s
ho
wn i
n T
ab
l
e
4.
T
ab
l
e
2.
T
he
R
es
ul
t
o
f
Data
T
es
t
i
ng
w
i
t
h 4
Neuro
ns
No
TGS
2
6
0
0
TGS
2
6
0
2
TGS
2
6
2
0
M
Q
1
3
5
TGS
8
1
3
Ou
t
p
u
t
Ou
t
p
u
t
C
la
s
s
1
0
.
9
8
9
1
.
0
8
1
1
0
.
9
9
8
0
.
9
9
8
[
1
;
0
]
Fr
e
s
h
2
0
.
9
9
8
1
.
1
0
3
1
.
0
0
3
1
.
0
0
6
1
.
0
1
4
[
1
;
0
]
Fr
e
s
h
3
0
.
9
8
9
1
.
0
7
9
0
.
9
9
9
0
.
9
9
6
1
[
1
;
0
]
Fr
e
s
h
4
1
.
0
1
5
1
.
0
5
8
1
.
0
2
3
1
.
0
0
6
1
.
0
0
4
[
1
;
0
]
Fr
e
s
h
5
1
.
0
2
2
1
.
0
3
2
1
.
0
4
3
0
.
9
9
8
1
.
0
1
5
[
1
;
0
]
Fr
e
s
h
6
1
.
7
0
2
0
.
9
8
2
1
.
5
6
4
1
.
4
2
7
1
.
7
7
1
[
0
;
1
]
N
o
t
Fr
e
s
h
7
1
.
1
6
0
.
9
7
6
1
.
1
1
.
1
0
5
1
.
1
7
5
[
1
;
0
]
Fr
e
s
h
8
3
.
9
3
9
1
.
1
3
8
3
.
8
9
4
3
.
1
0
9
5
.
1
4
4
[
0
;
1
]
N
o
t
Fr
e
s
h
9
0
.
5
7
1
1
.
2
4
0
.
6
5
9
0
.
6
5
9
0
.
5
1
4
[
1
;
0
]
Fr
e
s
h
10
1
.
9
1
3
1
.
2
4
6
1
.
8
7
1
1
.
7
4
3
2
.
1
0
6
[
0
;
1
]
N
o
t
Fr
e
s
h
T
ab
l
e
3.
T
he
R
es
ul
t
of
Data
T
es
ti
ng
w
i
t
h 8
Neuro
ns
No
TGS
2
6
0
0
TGS
2
6
0
2
TGS
2
6
2
0
M
Q
1
3
5
TGS
8
1
3
Ou
t
p
u
t
Ou
t
p
u
t
C
la
s
s
1
0
.
9
8
9
1
.
0
8
1
1
0
.
9
9
8
0
.
9
9
8
[
1
;
0
]
Fr
e
s
h
2
0
.
9
9
8
1
.
1
0
3
1
.
0
0
3
1
.
0
0
6
1
.
0
1
4
[
1
;
0
]
Fr
e
s
h
3
0
.
9
8
9
1
.
0
7
9
0
.
9
9
9
0
.
9
9
6
1
[
1
;
0
]
Fr
e
s
h
4
1
.
0
1
5
1
.
0
5
8
1
.
0
2
3
1
.
0
0
6
1
.
0
0
4
[1
;
0
]
Fr
e
s
h
5
1
.
0
2
2
1
.
0
3
2
1
.
0
4
3
0
.
9
9
8
1
.
0
1
5
[
1
;
0
]
Fr
e
s
h
6
1
.
7
0
2
0
.
9
8
2
1
.
5
6
4
1
.
4
2
7
1
.
7
7
1
[
0
;
1
]
N
o
t
Fr
e
s
h
7
1
.
1
6
0
.
9
7
6
1
.
1
1
.
1
0
5
1
.
1
7
5
[
0
;
1
]
N
o
t
Fr
e
s
h
8
3
.
9
3
9
1
.
1
3
8
3
.
8
9
4
3
.
1
0
9
5
.
1
4
4
[
0
;
1
]
N
o
t
Fr
e
s
h
9
0
.
5
7
1
1
.
2
4
0
.
6
5
9
0
.
6
5
9
0
.
5
1
4
[
0
;
1
]
N
o
t
Fr
e
s
h
10
1
.
9
1
3
1
.
2
4
6
1
.
8
7
1
1
.
7
4
3
2
.
1
0
6
[
0
;
1
]
N
o
t
Fr
e
s
h
T
ab
l
e
4.
T
he
R
es
ul
t
of
Data
T
es
ti
ng
w
i
t
h 1
6 Ne
urons
No
TGS
2
6
0
0
TGS
2
6
0
2
TGS
2
6
2
0
M
Q
1
3
5
TGS
8
1
3
Ou
t
p
u
t
Ou
t
p
u
t
C
la
s
s
1
0
.
9
8
9
1
.
0
8
1
1
0
.
9
9
8
0
.
9
9
8
[
1
;
0
]
Fr
e
s
h
2
0
.
9
9
8
1
.
1
0
3
1
.
0
0
3
1
.
0
0
6
1
.
0
1
4
[
1
;
0
]
Fr
e
s
h
3
0
.
9
8
9
1
.
0
7
9
0
.
9
9
9
0
.
9
9
6
1
[
1
;
0
]
Fr
e
s
h
4
1
.
0
1
5
1
.
0
5
8
1
.
0
2
3
1
.
0
0
6
1
.
0
0
4
[
1
;
0
]
Fr
e
s
h
5
1
.
0
2
2
1
.
0
3
2
1
.
0
4
3
0
.
9
9
8
1
.
0
1
5
[
1
;
0
]
Fr
e
s
h
6
1
.
7
0
2
0
.
9
8
2
1
.
5
6
4
1
.
4
2
7
1
.
7
7
1
[
0
;
1
]
N
o
t
Fr
e
s
h
7
1
.
1
6
0
.
9
7
6
1
.
1
1
.
1
0
5
1
.
1
7
5
[
1
;
0
]
Fr
e
s
h
8
3
.
9
3
9
1
.
1
3
8
3
.
8
9
4
3
.
1
0
9
5
.
1
4
4
[
0
;
1
]
N
o
t
Fr
e
s
h
9
0
.
5
7
1
1
.
2
4
0
.
6
5
9
0
.
6
5
9
0
.
5
1
4
[
0
;
1
]
N
o
t
Fr
e
s
h
10
1
.
9
1
3
1
.
2
4
6
1
.
8
7
1
1
.
7
4
3
2
.
1
0
6
[
0
;
1
]
N
o
t
Fr
e
s
h
4.
Co
n
clus
ion
A
n
a
na
l
y
s
i
s
of
f
i
v
e
v
ari
ed
s
en
s
ors
ex
po
s
ed
b
y
r
ed
u
c
i
ng
g
as
of
m
ea
t
s
a
m
pl
e
arom
a
(
bo
th
f
r
es
h
m
ea
t
a
nd
not
-
f
r
es
h
m
ea
t
)
was
c
on
du
c
te
d.
T
he
tr
a
i
n
i
ng
proc
es
s
i
d
en
ti
f
i
e
d
5
-
1
-
2
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NIK
A
IS
S
N: 1
69
3
-
6
93
0
M
O
S
g
as
s
en
s
or
of
me
at
fr
es
hn
es
s
an
al
y
s
i
s
o
n E
-
n
os
e
(
B
u
d
i
G
u
na
w
an
)
779
f
or
m
ati
on
pa
tt
ern
(
5
i
n
pu
ts
,
1
hi
d
de
n
l
a
y
er,
an
d
2
ou
t
pu
ts
i
n
ac
c
orda
nc
e
w
i
t
h
th
e
target
c
od
e)
wi
th
t
he
v
aria
ti
o
n
of
ne
uro
n
nu
m
be
r
i
n
the
h
i
d
de
n
l
a
y
e
r
qu
an
t
i
t
y
4,
8,
1
6
to
f
o
un
d
th
e
m
os
t
op
ti
m
al
w
e
i
g
ht
a
nd
b
i
as
v
a
l
ue
s
f
or
tes
ti
ng
.
T
he
tr
ai
ni
ng
proc
es
s
ha
s
b
ee
n
c
on
du
c
te
d
us
i
ng
v
ar
y
nu
m
be
r
of
ne
urons
i
n
t
he
hi
d
de
n
l
a
y
er
of
4,
8,
an
d
16
w
i
th
2
2
da
tas
ets
of
i
np
u
t
th
at
c
o
n
s
i
s
ted
of
1
1
d
ata
of
f
r
es
h
m
ea
t
arom
a
an
d
11
da
t
a
of
no
t
-
f
r
es
h
m
ea
t
arom
a.
T
he
r
es
ul
t
prov
es
ne
ural
n
et
w
ork
m
eth
od
c
an
de
t
ec
t
the
f
r
es
hn
es
s
of
m
ea
t
w
i
th
a
a
c
c
urac
y
was
10
0%
.
It
i
s
f
o
un
d
t
ha
t
t
he
n
et
w
ork
i
s
pe
r
f
ec
tl
y
f
or
m
ed
.
B
as
ed
o
n
t
he
s
i
m
ul
ati
o
n
r
es
ul
t,
b
y
us
i
ng
4,
8
an
d
1
6
n
eu
r
o
ns
i
n
th
e
hi
d
de
n
l
a
y
e
r
,
the
v
al
ue
s
pe
r
c
en
ta
ge
of
s
uc
c
es
s
f
ul
de
tec
t
i
on
w
ere
80
%
,
1
00
%
an
d
9
0%.
I
t
c
an
be
c
o
nc
l
ud
ed
t
ha
t
th
e
op
ti
m
al
n
um
be
r
of
ne
urons
f
or thi
s
de
tec
t
i
on
s
y
s
tem
i
s
8.
A
c
kno
w
ledg
men
t
s
T
he
r
es
ea
r
c
h
i
s
f
un
de
d
b
y
Di
r
ec
torat
e
of
r
es
ea
r
c
h
an
d
c
om
m
un
i
t
y
s
erv
i
c
es
Di
r
e
c
torate
G
en
eral
of
S
tr
en
gth
e
ni
ng
r
es
ea
r
c
h
an
d
de
v
e
l
op
m
en
t
Mi
n
i
s
tr
y
of
Res
ea
r
c
h,
te
c
hn
ol
og
y
an
d
hi
g
he
r
ed
uc
a
ti
o
n
In
ac
c
ordanc
e
wi
th
th
e
l
ett
er
of
the
c
on
tr
ac
t
Res
ea
r
c
h
Num
be
r
:
00
8/
K
6/
K
M/
S
P
2H/res
e
arc
h
/20
1
7
.
Ref
er
en
ce
s
[1
]
Pe
rm
e
n
k
e
s
.
4
1
.
B
a
l
a
n
c
e
d
N
u
tri
ti
o
n
G
u
i
d
e
l
i
n
e
s
(
i
n
I
n
d
o
n
e
s
i
a
Pe
d
o
m
a
n
G
i
z
i
Se
i
m
b
a
n
g
)
.
J
a
k
a
rt
a
:
M
e
n
te
ri
Ke
s
e
h
a
ta
n
Re
p
u
b
l
i
k
I
n
d
o
n
e
s
i
a
;
2
0
1
4
.
[2
]
G
u
o
P,
Ba
o
M
.
Res
e
a
r
c
h
a
n
d
Rea
l
i
z
a
ti
o
n
o
f
Han
d
-
h
e
l
d
M
o
b
i
l
e
Ba
c
o
n
D
e
te
c
ti
o
n
Ba
s
e
d
o
n
Ne
u
ra
l
Net
work
P
a
tt
e
rn
Rec
o
g
n
i
ti
o
n
.
Chi
n
e
s
e
Con
t
ro
l
a
n
d
D
e
c
i
s
i
o
n
Con
f
e
re
n
c
e
.
Y
i
n
c
h
u
a
n
.
2
0
1
6
:
2
018
-
2
0
2
1
.
[3
]
S
ta
n
d
a
r
N
a
s
i
o
n
a
l
I
n
d
o
n
e
s
i
a
.
3932.
Q
u
a
l
i
ty
o
f
C
a
rc
a
s
s
a
n
d
Be
e
f
(i
n
In
d
o
n
e
s
i
a
M
u
tu
K
a
rk
a
s
d
a
n
Dag
i
n
g
S
a
p
i
)
.
J
a
k
a
rt
a
:
Ba
d
a
n
Sta
n
d
a
d
i
s
a
s
i
Na
s
i
o
n
a
l
;
2
0
0
8
.
[4
]
Zu
l
fi
FI
.
Id
e
n
ti
f
i
c
a
ti
o
n
o
f
L
o
c
a
l
Be
e
f
L
e
v
e
l
o
f
Fre
s
h
n
e
s
s
Us
i
n
g
Col
o
r
Fe
a
tu
re
Ex
tra
c
ti
o
n
Ba
s
e
d
o
n
M
a
tl
a
b
G
UI
(i
n
In
d
o
n
e
s
i
a
:
Id
e
n
ti
f
i
k
a
s
i
T
i
n
g
k
a
t
Ke
s
e
g
a
ra
n
D
a
g
i
n
g
Sa
p
i
L
o
k
a
l
M
e
n
g
g
u
n
a
k
a
n
Ek
s
tra
k
s
i
Fi
tu
r
W
a
rn
a
B
e
rb
a
s
i
s
Gui
M
a
tl
a
b
)
.
Und
e
rg
ra
d
u
a
t
e
T
h
e
s
i
s
.
L
a
m
p
u
n
g
:
Uni
v
e
r
s
i
t
a
s
L
a
m
pung
;
2017
.
[5
]
M
a
y
r
D,
Hart
u
n
g
e
n
E,
M
a
rk
T
,
M
a
rg
e
s
i
n
R,
Sc
h
i
n
n
e
r
F.
Det
e
rm
i
n
a
t
i
o
n
o
f
T
h
e
Sp
o
i
l
a
g
e
Sta
tu
s
o
f
M
e
a
t
b
y
Aro
m
a
Det
e
c
ti
o
n
Us
i
n
g
Pro
to
n
-
Tra
n
s
f
er
-
Re
a
c
t
i
o
n
M
a
s
s
-
Sp
e
c
to
m
e
tr
y
.
Pro
c
e
e
d
i
n
g
o
f
T
h
e
10
th
W
e
u
rm
a
n
F
l
a
v
o
u
r Re
s
e
a
r
c
h
Sy
m
p
o
s
i
u
m
.
B
e
a
u
n
c
e
.
2
0
0
2
:
757
-
760
.
[6
]
Sa
m
i
j
a
y
a
n
i
O
N,
As
th
a
ri
n
i
D.
Ap
p
l
i
c
a
ti
o
n
o
f
Pre
-
Pra
c
ti
c
a
l
S
i
m
u
l
a
ti
o
n
M
e
th
o
d
s
Us
i
n
g
G
ra
p
h
i
c
Us
e
r
In
te
rfa
c
e
(G
UI)
a
n
d
FDAT
O
O
L
,
M
a
tl
a
b
(i
n
In
d
o
n
e
s
i
a
:
Pe
n
e
ra
p
a
n
M
e
to
d
e
Si
m
u
l
a
s
i
Pra
-
Pra
k
ti
k
u
m
M
e
n
g
g
u
n
a
k
a
n
G
ra
p
h
i
c
U
s
e
r
I
n
te
rfa
c
e
(G
UI)
d
a
n
FDAT
O
O
L
,
M
a
tl
a
b
)
.
J
u
r
n
a
l
A
l
-
A
z
h
a
r
In
d
o
n
e
s
i
a
Se
r
i
Sa
i
n
s
d
a
n
T
e
k
n
o
l
o
g
i
.
2
0
1
2
;
1
:
186
-
1
9
1
.
[
7
]
Carm
o
n
a
EN,
Sb
e
rv
e
g
l
i
e
ri
V,
Po
n
z
o
n
i
A,
G
a
l
s
ty
a
n
V,
Za
p
p
a
D,
Pu
l
v
i
re
n
t
i
A,
Com
i
n
i
E.
D
e
te
c
t
i
o
n
o
f
fo
o
d
a
n
d
s
k
i
n
p
a
t
h
o
g
e
n
m
i
c
ro
b
i
o
ta
b
y
m
e
a
n
s
o
f
a
n
e
l
e
c
tr
o
n
i
c
n
o
s
e
b
a
s
e
d
o
n
m
e
ta
l
o
x
i
d
e
c
h
e
m
i
re
s
i
s
to
r
s
.
Se
n
s
o
r
s
a
n
d
A
c
tu
a
t
o
rs
B
:
C
h
e
m
i
c
a
l
.
2
0
1
7
;
2
3
8
:
1
2
2
4
-
1
2
3
0
.
[8
]
Ki
m
KH,
Pa
r
k
SY
.
A
Com
p
a
r
a
ti
v
e
An
a
l
y
s
i
s
o
f
M
a
l
o
d
o
r
Sa
m
p
l
e
s
Be
tw
e
e
n
Dir
e
c
t
(O
l
f
a
c
t
o
m
e
ry
)
a
n
d
In
d
i
re
c
t
(I
n
s
tr
u
m
e
n
ta
l
) M
e
th
o
d
s
.
Atm
o
s
p
h
e
ri
c
En
v
i
r
o
n
m
e
n
t
.
2
0
0
8
;
42
:
5
0
6
1
-
5070
.
[9
]
Rad
i
,
Riv
a
i
M
,
Pu
rn
o
m
o
M
H.
Stu
d
y
o
n
El
e
c
tro
n
i
c
-
No
s
e
-
Ba
s
e
d
Q
u
a
l
i
ty
M
o
n
i
to
ri
n
g
Sy
s
t
e
m
fo
r
Cof
fe
e
u
n
d
e
r Ro
a
s
t
i
n
g
.
J
o
u
rn
a
l
o
f
C
i
r
c
u
i
t,
Sy
s
te
m
,
a
n
d
Co
p
u
te
r
s
.
2
0
1
6
;
25
:
1
-
19
.
[1
0
]
L
o
z
a
n
o
J
,
Sa
n
to
s
J
P
,
Su
á
re
z
J
I,
Cab
e
l
l
o
s
M
,
Arro
y
o
T
,
Horr
i
l
l
o
C.
Au
to
m
a
t
i
c
Se
n
s
o
r
Sy
s
te
m
fo
r
T
h
e
Con
ti
n
o
u
s
An
a
l
y
s
i
s
o
f
T
h
e
Ev
o
l
u
ti
o
n
o
f
W
i
n
e
.
Am
e
ri
c
a
n
J
o
u
rn
a
l
o
f
En
o
l
o
g
y
a
n
d
Vi
ti
c
u
l
tu
re
.
2
0
1
5
;
66
:
148
-
1
5
5
.
[1
1
]
Po
n
z
o
n
i
A,
Dep
a
r
i
A,
Fa
l
a
s
c
o
n
i
M
,
Com
i
n
i
E,
Fl
a
m
m
i
n
i
A,
M
a
ri
o
l
i
D,
T
a
ro
n
i
A,
Sb
e
rv
e
g
l
i
e
ri
G
.
Bre
a
d
Ba
k
i
n
g
Aro
m
a
s
D
e
te
c
ti
o
n
b
y
L
o
w
-
Cos
t
El
e
c
tro
n
i
c
No
s
e
.
S
e
n
s
o
r
s
Ac
t
u
a
to
r
s
B
:
Ch
e
m
i
c
a
l
.
2
0
0
8
.
1
3
0
:
100
-
1
0
4
.
[1
2
]
L
e
b
ru
n
M
,
Pl
o
tt
o
A,
G
o
o
d
n
e
r
K,
Duc
a
m
p
M
N,
Ba
l
d
w
i
n
E.
Di
s
c
ri
m
i
n
a
ti
o
n
o
f
M
a
n
g
g
o
Fru
i
t
M
a
tu
ri
ty
b
y
Vo
l
a
ti
l
e
s
Us
i
n
g
T
h
e
El
e
c
tr
o
n
i
c
No
s
e
a
n
d
G
a
s
Chro
m
a
t
o
g
ra
p
h
y
.
Po
s
th
a
rv
e
s
t
B
i
o
l
o
g
y
a
n
d
T
e
c
h
n
o
l
o
g
y
.
2008
;
48
:
122
-
131
.
[1
3
]
Sa
e
v
e
l
s
S,
L
a
m
e
rty
n
J
,
Be
r
n
a
AZ,
V
e
ra
v
e
rb
e
k
e
EA,
Di
Na
ta
l
e
S
,
Ni
c
o
l
ï
BM
.
El
e
c
tr
o
n
i
c
Nos
e
A
s
A
Non
-
Des
tr
u
c
t
i
v
e
T
o
o
l
T
o
E
v
a
l
u
a
te
T
h
e
O
ti
m
a
l
Harv
e
s
t
Da
te
o
f
Ap
p
l
e
s
.
Po
s
t
h
a
r
v
e
s
t
Bi
o
l
o
g
y
a
n
d
Te
c
h
n
o
l
o
g
y
.
2
0
0
3
;
30
:
3
-
14
.
[1
4
]
Nis
h
i
k
,
Is
o
b
e
SL
,
Zh
u
Y
,
Ki
y
a
m
a
R.
Fl
u
o
re
s
c
e
n
c
e
-
B
a
s
e
d
B
i
o
a
s
s
a
s
y
fo
r
T
h
e
Det
e
c
ti
o
n
a
n
d
Ev
a
l
u
a
ti
o
n
o
f
Fo
o
d
M
a
te
ri
a
l
s
.
Se
n
s
o
r
s
.
2
0
1
5
;
15
:
2
5
8
3
1
-
2
5
8
6
7
.
[1
5
]
Nas
s
u
th
A,
Po
l
l
a
ri
E,
Hel
m
e
c
z
y
K,
Ste
w
a
rt
S,
Ko
f
a
l
v
i
SA.
I
m
p
ro
v
e
d
RN
A
Ex
tra
c
ti
o
n
a
n
d
O
n
e
-
tu
b
e
RT
-
PCR
As
s
a
y
fo
r
Si
m
u
l
ta
n
e
o
u
s
De
te
c
ti
o
n
o
f
Co
n
tro
l
Pl
a
n
t
RN
A
Pl
u
s
Se
v
e
re
a
l
Vi
r
u
s
e
s
i
n
Pl
a
n
t
E
x
tra
c
ts
.
J
o
u
rn
a
l
o
f
Vi
ro
l
o
g
i
c
a
l
M
e
th
o
d
s
.
2
0
0
0
;
90
:
37
-
49
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N: 16
93
-
6
93
0
T
E
L
KO
M
NIK
A
V
ol
.
17
,
No.
2
,
A
pril
20
19
:
77
1
~
7
80
780
[1
6
]
Zh
o
u
HQ
,
L
i
S,
Hua
n
g
Y
H,
L
i
u
Y
,
Ba
u
e
r
R,
Pe
n
g
L
,
T
a
o
O
,
Y
a
n
SR,
Y
a
n
Y
H.
Rap
i
d
Id
e
n
ti
fi
c
a
ti
o
n
o
f
As
te
rc
e
a
e
Pl
a
n
ts
W
i
th
Im
p
ro
v
e
d
RBF
-
ANN
Cla
s
s
i
fi
c
a
ti
o
n
M
o
d
e
l
s
Ba
s
e
d
O
n
M
O
S
Se
n
s
o
r
E
-
Nos
e
.
Ev
i
d
e
n
c
e
-
B
a
s
e
d
Co
m
p
l
e
m
e
n
t
a
ry
a
n
d
A
l
t
e
rn
a
t
i
v
e
M
e
d
i
c
i
n
e
.
2
0
1
4
;
2
0
1
4
:
1
-
6
.
[1
7
]
Cui
S,
L
i
n
g
P,
Zh
u
H,
Ke
e
n
e
r
HM
.
Pl
a
n
t
T
e
s
t
Det
e
c
t
i
o
n
Us
i
n
g
a
n
Arti
fi
c
i
a
l
Nos
e
Sy
s
te
m
:
A
Rev
i
e
w
.
Se
n
s
o
r
s
.
2
0
1
8
;
18
:
1
-
18
.
[1
8
]
Be
rn
a
A.
M
e
ta
l
O
x
i
d
e
Se
n
s
o
rs
fo
r
El
e
c
tro
n
i
c
Nos
e
s
a
n
d
T
h
e
i
r
Ap
p
l
i
c
a
t
i
o
n
to
F
o
o
d
A
n
a
l
y
s
i
s
.
Se
n
s
o
rs
.
2010
;
10
:
3882
-
3
9
1
0
.
[1
9
]
Hag
a
n
M
T,
Dem
u
th
HB
,
Be
a
l
e
M
H. Ne
u
ra
l
Ne
tw
o
rk
De
s
i
g
n
.
O
k
l
a
h
o
m
a
.
1
9
9
5
.
[
20
]
Riv
a
i
M
,
Bu
d
i
m
a
n
F,
Pu
rw
a
n
to
D,
Si
m
a
m
o
ra
J
.
M
e
a
t
Fre
s
h
n
e
s
s
I
d
e
n
t
i
fi
c
a
ti
o
n
Sy
s
te
m
Us
i
n
g
G
a
s
Se
n
s
o
r
Arr
a
y
a
n
d
Col
o
r
Se
n
s
o
r
i
n
Con
j
u
n
c
ti
o
n
W
i
th
Ne
u
ra
l
Net
w
o
rk
Pa
tt
e
rn
Rec
o
g
n
i
ti
o
n
.
J
o
u
rn
a
l
o
f
Th
e
o
ri
ti
c
a
l
a
n
d
Ap
p
l
i
e
d
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
.
2
0
1
8
;
96
:
3
8
6
1
-
3
8
7
2
.
[2
1
]
Cah
y
o
n
o
B.
T
h
e
U
s
e
o
f
So
ft
w
a
re
M
a
tri
x
L
a
b
o
ra
to
ry
(M
a
tl
a
b
)
i
n
L
i
n
e
a
r
A
l
g
e
b
r
a
i
c
L
e
a
rn
i
n
g
(
i
n
In
d
o
n
e
s
i
a
:
Pe
n
g
g
u
n
a
a
n
So
ft
w
a
re
M
a
tri
x
L
a
b
o
ra
to
ry
(M
a
tl
a
b
)
Dal
a
m
Pe
m
b
e
l
a
j
a
ra
n
Al
j
a
b
a
r
L
i
n
i
e
r
)
.
Ph
e
n
o
m
e
n
o
n
.
2
0
1
3
;
1:
45
-
62
.
[2
2
]
Ka
n
a
d
e
A,
Sh
a
l
i
g
ra
m
A.
Re
v
i
e
w
o
n
M
O
S
G
a
s
Se
n
s
o
r Ba
s
e
d
E
-
Nos
e
s
a
n
d
T
h
e
i
r Ap
p
l
i
c
a
ti
o
n
s
t
o
F
o
o
d
An
a
l
y
s
i
s
.
I
n
te
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
R
e
s
e
a
rc
h
i
n
E
l
e
c
tri
c
a
l
,
El
e
c
tro
n
i
c
s
a
n
d
I
n
s
tr
u
m
e
n
ta
ti
o
n
En
g
i
n
e
e
ri
n
g
.
2
0
1
6
;
5(
7
)
:
6
4
6
5
-
6473
.
[2
3
]
G
a
rd
n
e
r
J
W
,
Ba
rt
l
e
tt
PN.
El
e
c
t
ro
n
i
c
No
s
e
s
:
Pr
i
n
c
i
p
l
e
s
a
n
d
A
p
p
l
i
c
a
ti
o
n
.
IOP
Pu
b
l
i
s
h
i
n
g
.
2
0
0
0
.
[2
4
]
Fi
g
a
ro
.c
o
.j
p
.
O
p
e
ra
t
i
n
g
p
ri
n
c
i
p
l
e
‐
M
O
S
-
ty
p
e
g
a
s
s
e
n
s
o
r
2
0
1
8
.
h
tt
p
:/
/w
ww
.f
i
g
a
ro
.c
o
.j
p
/
e
n
/t
e
c
h
n
i
c
a
l
i
n
fo
/p
r
i
n
c
i
p
l
e
/m
o
s
-
ty
p
e
.h
t
m
l
(
A
c
c
e
s
s
e
d
Ap
r
i
l
2
2
,
2
0
1
8
)
[2
5
]
G
u
n
a
w
a
n
B,
Riv
a
i
M
,
J
u
w
o
n
o
H.
Cha
ra
c
t
e
ri
z
a
ti
o
n
o
f
Po
l
y
m
e
ri
c
Che
m
i
r
e
s
i
s
to
r
s
fo
r
G
a
s
Se
n
s
o
r.
TEL
KO
M
NIKA
Te
l
e
c
o
m
m
u
n
i
c
a
ti
o
n
Co
m
p
u
ti
n
g
E
l
e
c
tr
o
n
i
c
s
a
n
d
Co
n
tr
o
l
.
2
0
1
2
;
10:
275
-
2
8
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.