I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l
I
nte
llig
ence
(
I
J
-
AI
)
Vo
l.
14
,
No
.
4
,
A
u
g
u
s
t 2
0
2
5
,
p
p
.
2
7
1
3
~
2
7
2
3
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
4
.
p
p
2
7
1
3
-
2
7
2
3
2713
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Bro
iler meats
ten
derness
pr
edictio
n using
nea
r i
nfra
red
spectros
co
py
a
g
a
inst
no
n
-
lin
ea
r pre
dictive mo
delling
Ra
s
hid
a
h G
ha
za
li,
H
er
lin
a
Abdu
l R
a
h
im
,
Sy
a
hid
a
h Nu
ra
ni Z
ulk
if
li
D
e
p
a
r
t
me
n
t
o
f
C
o
n
t
r
o
l
a
n
d
M
e
c
h
a
t
r
o
n
i
c
s,
F
a
c
u
l
t
y
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
s
i
t
i
T
e
k
n
o
l
o
g
i
M
a
l
a
y
si
a
,
S
k
u
d
a
i
J
o
h
o
r
,
M
a
l
a
y
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l 2
3
,
2
0
2
4
R
ev
is
ed
J
u
n
1
2
,
2
0
2
5
Acc
ep
ted
J
u
l 1
0
,
2
0
2
5
Ne
a
r
in
fra
re
d
(
NIR
)
sp
e
c
tro
sc
o
p
y
is
a
n
o
n
-
in
v
a
siv
e
a
n
a
ly
ti
c
a
l
tec
h
n
i
q
u
e
k
n
o
w
n
f
o
r
it
s
a
b
i
li
ty
t
o
a
ss
e
ss
th
e
q
u
a
li
ty
a
tt
rib
u
tes
o
f
m
e
a
t
p
r
o
d
u
c
ts.
Ho
we
v
e
r,
th
e
li
n
e
a
r
m
o
d
e
ls
u
t
il
iz
e
d
,
p
a
rti
a
l
lea
st
sq
u
a
re
(P
LS
)
a
n
d
p
rin
c
ip
a
l
c
o
m
p
o
n
e
n
t
re
g
re
ss
io
n
(P
CR)
a
c
h
iev
e
d
u
n
sa
ti
sfa
c
to
ry
p
e
rfo
rm
a
n
c
e
s
o
f
m
e
a
t
p
h
y
sic
a
l
a
tt
ri
b
u
tes
p
re
d
ictio
n
.
He
n
c
e
,
in
th
is
re
se
a
rc
h
,
fo
r
it
s
in
h
e
re
n
t
a
d
v
a
n
tag
e
s
in
m
o
d
e
ll
in
g
n
o
n
li
n
e
a
r
sy
ste
m
,
a
rti
ficia
l
n
e
u
ra
l
n
e
tw
o
rk
(AN
N)
is
a
u
g
m
e
n
ted
t
o
t
h
e
c
o
m
p
o
n
e
n
ts
o
f
P
CR
a
n
d
P
L
S
.
Th
r
o
u
g
h
th
e
a
u
g
m
e
n
tatio
n
,
t
h
e
p
ri
n
c
ip
a
l
c
o
m
p
o
n
e
n
t
n
e
u
ra
l
n
e
two
r
k
(P
CNN
)
a
n
d
late
n
t
v
a
riab
le
n
e
u
ra
l
n
e
two
rk
(LVNN
)
m
o
d
e
ls
a
re
d
e
v
e
lo
p
e
d
.
F
ro
m
t
h
e
re
su
lt
s
o
b
tai
n
e
d
,
it
sh
o
ws
t
h
a
t
P
CNN
a
n
d
LVNN
su
c
c
e
ss
fu
ll
y
su
rp
a
ss
e
d
th
e
ir
re
sp
e
c
ti
v
e
li
n
e
a
r
v
e
rsio
n
s
o
f
P
CR
a
n
d
P
L
S
b
y
7
0
%
h
ig
h
e
r
s
h
e
a
r
f
o
rc
e
p
re
d
ictio
n
p
e
rf
o
rm
a
n
c
e
s.
Th
e
LVNN
p
ro
v
e
d
to
a
c
h
iev
e
t
h
e
b
e
st p
r
e
d
ictio
n
i
n
b
re
a
st me
a
t
with
ro
o
t
m
e
a
n
sq
u
a
re
e
rro
r
o
f
p
re
d
ictio
n
(RM
S
E
P
)
o
f
0
.
0
7
6
9
k
g
a
n
d
c
o
e
fficie
n
t
o
f
d
e
term
in
a
ti
o
n
(
R
P
2
)
o
f
0
.
8
2
0
1
wh
il
st
fo
r
d
ru
m
stick
s,
RM
S
EP
=
0
.
1
4
9
4
k
g
a
n
d
R
P
2
=
0
.
8
6
0
6
.
NIR
sp
e
c
tro
sc
o
p
y
t
e
c
h
n
o
l
o
g
y
in
teg
ra
ted
with
m
a
c
h
in
e
lea
rn
in
g
y
iel
d
s
a
p
ro
m
isin
g
n
o
n
-
i
n
v
a
siv
e
tec
h
n
iq
u
e
in
p
re
d
ictin
g
t
h
e
sh
e
a
r
fo
rc
e
o
f
in
t
a
c
t
ra
w b
ro
il
e
r
m
e
a
t.
K
ey
w
o
r
d
s
:
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
Me
at
ten
d
er
n
ess
Nea
r
in
f
r
ar
e
d
s
p
ec
tr
o
s
co
p
y
Par
tial le
a
s
t sq
u
ar
e
Prin
cip
al
co
m
p
o
n
en
t r
e
g
r
ess
io
n
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
:
Her
lin
a
Ab
d
u
l Rah
im
Dep
ar
tm
en
t o
f
C
o
n
tr
o
l a
n
d
M
ec
h
atr
o
n
ics,
Facu
lty
o
f
E
lectr
i
ca
l E
n
g
in
ee
r
in
g
,
Un
iv
e
r
s
iti T
ek
n
o
lo
g
i
Ma
lay
s
ia
Sk
u
d
ai
J
o
h
o
r
,
Ma
lay
s
ia
E
m
ail: h
er
lin
a@
u
tm
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
B
r
o
iler
s
ar
e
k
n
o
wn
f
o
r
th
eir
h
ig
h
p
r
o
tein
c
o
n
ten
t,
n
u
tr
iti
o
n
al
v
al
u
e,
r
a
p
id
g
r
o
wth
,
an
d
d
iv
e
r
s
e
p
r
o
ce
s
s
ed
p
r
o
d
u
cts.
Ho
wev
er
,
ce
r
tain
r
elig
io
n
s
o
r
r
ac
es
f
o
r
b
id
th
e
co
n
s
u
m
p
tio
n
o
f
m
ea
t
,
s
u
ch
as
b
ee
f
an
d
p
o
r
k
[
1
]
,
[
2
]
,
as
a
s
o
u
r
ce
o
f
p
r
o
tein
.
Gen
er
ally
,
in
a
ty
p
ical
co
n
s
u
m
er
’
s
p
er
ce
p
ti
o
n
,
ten
d
e
r
n
ess
i
s
an
im
p
o
r
tan
t
q
u
ality
attr
ib
u
te
wh
ich
is
d
e
f
in
ed
b
y
th
e
ea
s
e
o
f
m
asti
ca
tio
n
.
Fro
m
liter
atu
r
e,
th
e
m
ea
t
is
i
n
d
icate
d
as
‘
ten
d
e
r
’
wh
en
s
m
all
s
h
ea
r
f
o
r
ce
v
alu
e
is
o
b
tain
ed
,
m
ea
n
wh
ile
m
ea
t
is
co
n
s
id
er
ed
‘
to
u
g
h
’
wh
en
lar
g
er
s
h
ea
r
f
o
r
c
e
v
alu
es
ar
e
o
b
tain
ed
[
3
]
,
[
4
]
.
Nu
m
er
o
u
s
tech
n
iq
u
es
h
av
e
b
ee
n
u
s
ed
to
ass
es
s
m
ea
t
ten
d
er
n
ess
in
p
o
u
ltry
,
in
clu
d
in
g
in
s
tr
u
m
e
n
tal
ap
p
r
o
a
ch
es
s
u
ch
as
th
e
Al
lo
-
Kr
am
er
,
Me
u
llen
et
-
Owe
n
R
az
o
r
s
h
ea
r
f
o
r
ce
(
MO
R
SF
)
,
s
lice
s
h
ea
r
f
o
r
ce
(
SS
F),
an
d
W
ar
n
er
-
B
r
atzle
r
s
h
ea
r
f
o
r
ce
(
W
B
S
F)
m
eth
o
d
s
.
Ho
wev
er
,
th
ese
m
eth
o
d
s
ar
e
in
v
asiv
e,
d
estru
ctiv
e,
a
n
d
tim
e
-
co
n
s
u
m
in
g
,
r
eq
u
ir
in
g
ex
ten
s
iv
e
ca
lib
r
atio
n
a
n
d
s
am
p
le
p
r
ep
ar
atio
n
.
T
y
p
ically
,
ef
f
ec
tiv
e
ev
alu
atio
n
o
f
p
r
o
d
u
ct
q
u
ality
in
t
h
e
f
o
o
d
an
d
ag
r
ic
u
ltu
r
e
s
ec
to
r
s
is
ca
r
r
ied
o
u
t
u
tili
zin
g
n
ea
r
in
f
r
ar
ed
(
NI
R
)
s
p
ec
tr
o
s
co
p
y
.
NI
R
s
p
ec
tr
o
s
co
p
y
ca
n
b
e
u
s
ed
with
o
u
t
ca
u
s
in
g
h
ar
m
in
a
c
o
n
s
tan
t
way
to
an
aly
ze
th
e
ch
em
ical,
p
h
y
s
ical,
an
d
s
en
s
o
r
y
f
ea
tu
r
es
o
f
m
ea
t p
r
o
d
u
cts [
3
]
,
[
5
]
,
[
6
]
.
Op
tical
in
s
tr
u
m
en
ts
co
n
n
ec
ted
to
co
m
p
u
ter
s
p
r
o
v
id
e
f
ast
d
ata
c
o
llectio
n
th
at
e
n
ab
les
ev
alu
atio
n
o
f
m
ea
t
q
u
ality
,
d
esp
it
e
b
ein
g
lim
ited
to
a
s
m
all
s
elec
ted
s
u
r
f
ac
e
ar
ea
f
o
r
s
am
p
lin
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
7
1
3
-
2
7
2
3
2714
Prin
cip
al
co
m
p
o
n
en
t
r
e
g
r
ess
io
n
(
PC
R
)
an
d
p
ar
tial
least
s
q
u
ar
es
(
PLS)
ar
e
b
o
t
h
lin
ea
r
m
u
ltiv
ar
iate
m
o
d
els
th
at
h
ea
v
ily
r
ely
o
n
r
ed
u
cin
g
d
ata
th
r
o
u
g
h
d
e
r
iv
in
g
a
s
m
all
n
u
m
b
er
o
f
o
r
th
o
g
o
n
al
co
m
p
o
n
e
n
ts
o
r
s
co
r
es,
in
s
tead
o
f
u
s
in
g
th
e
e
n
tire
s
p
ec
tr
al
d
ata
f
o
r
r
eg
r
ess
io
n
an
al
y
s
is
[
7
]
,
[
8
]
.
T
h
e
in
f
o
r
m
atio
n
is
b
r
o
k
en
d
o
wn
in
to
s
co
r
es
an
d
lo
a
d
in
g
s
,
wh
ich
ca
n
p
r
ev
en
t
c
o
llin
ea
r
ity
p
r
o
b
lem
s
am
o
n
g
v
ar
ia
b
les.
B
o
th
m
o
d
els
ca
n
h
an
d
le
m
u
ltip
le
v
a
r
iab
les
th
at
ex
ce
ed
th
e
n
u
m
b
er
o
f
s
am
p
le
s
b
y
co
m
p
r
ess
in
g
an
d
r
ed
u
ci
n
g
th
e
d
im
en
s
io
n
o
f
s
p
ec
tr
al
d
ata.
PC
R
b
r
ea
k
s
d
o
wn
s
p
ec
tr
al
v
ar
iab
les
in
to
p
r
in
cip
al
co
m
p
o
n
en
ts
(
PC
s
)
,
wh
i
le
PLS
b
r
ea
k
s
d
o
wn
b
o
th
s
p
ec
tr
al
an
d
r
ef
e
r
en
ce
v
a
r
iab
les in
to
laten
t v
ar
iab
les
(
L
Vs)
.
Nu
m
er
o
u
s
r
esear
ch
es
h
av
e
e
m
p
lo
y
ed
lin
ea
r
m
u
ltiv
ar
iate
an
aly
s
is
alo
n
g
s
id
e
NI
R
s
p
ec
tr
o
s
co
p
y
t
o
f
o
r
ec
ast
ch
em
ical
co
m
p
o
n
e
n
ts
s
u
ch
as
p
r
o
tein
,
in
tr
am
u
s
cu
lar
f
at,
an
d
m
o
is
tu
r
e
in
p
o
u
ltr
y
[
5
]
–
[
7
]
,
[
9
]
–
[
1
4
]
.
Nev
er
th
eless
,
lin
ea
r
an
al
y
s
is
d
em
o
n
s
tr
ated
in
a
d
eq
u
ate
p
er
f
o
r
m
an
ce
wh
e
n
p
r
ed
ictin
g
p
h
y
s
ical
p
ar
am
eter
s
lik
e
p
H,
co
lo
r
,
te
n
d
er
n
ess
,
a
n
d
wate
r
-
h
o
ld
in
g
ca
p
ac
ity
(
W
HC
)
i
n
p
r
o
tein
-
b
ased
f
o
o
d
s
.
I
n
th
e
r
esear
ch
co
n
d
u
cte
d
b
y
L
ia
o
et
a
l
.
[
1
5
]
,
em
p
lo
y
in
g
v
is
ib
le
-
NI
R
s
p
ec
tr
a
an
d
a
PLS
m
o
d
el
y
ield
e
d
im
p
r
ess
iv
e
co
ef
f
icien
ts
o
f
d
eter
m
in
atio
n
(
R
2
=0
.
8
2
)
wh
en
f
o
r
ec
asti
n
g
in
tact
p
o
r
k
q
u
ality
ch
ar
ac
ter
is
tics
s
u
ch
as
in
tr
am
u
s
cu
lar
f
at,
p
r
o
tein
,
a
n
d
wate
r
.
On
t
h
e
o
th
e
r
h
a
n
d
,
t
h
e
t
o
p
m
o
d
el
d
i
d
n
o
t
h
a
v
e
s
u
f
f
ic
ien
t
p
r
ed
ict
iv
e
p
o
we
r
f
o
r
s
h
e
ar
f
o
r
ce
m
ea
s
u
r
e
m
e
n
t
.
E
v
e
n
th
o
u
g
h
all
p
ar
am
ete
r
s
i
n
t
h
e
ca
l
ib
r
a
tio
n
a
n
d
v
al
id
ati
o
n
s
ets
s
h
o
wed
a
n
i
n
c
r
e
ase
i
n
p
r
e
d
ic
ti
o
n
a
cc
u
r
ac
y
u
p
t
o
0
.
7
,
th
e
s
h
e
ar
f
o
r
c
e
i
n
t
h
e
v
ali
d
at
i
o
n
s
e
t
h
a
d
l
o
w
e
r
a
cc
u
r
ac
y
(
R
2
=0
.
2
7
8
,
r
o
o
t
m
ea
n
s
q
u
a
r
e
er
r
o
r
o
f
p
r
e
d
i
cti
o
n
(
R
MSE
P
)
=
0
.
3
6
0
)
t
h
a
n
t
h
e
c
ali
b
r
ati
o
n
s
et
.
Ma
r
c
h
i
et
a
l
.
[
1
6
]
u
tili
z
e
d
a
PLS
m
o
d
el
f
o
r
s
h
e
ar
f
o
r
c
e
p
r
ed
icti
o
n
,
h
o
we
v
er
th
e
c
r
o
s
s
-
v
ali
d
a
ti
o
n
o
u
tc
o
m
es
(
R
2
=
0
.
1
7
,
r
o
o
t
m
e
an
s
q
u
a
r
e
d
er
r
o
r
o
f
cr
o
s
s
-
v
ali
d
a
ti
o
n
(
R
MSE
C
V
)
=
3
.
1
8
)
w
er
e
d
e
em
ed
i
n
a
d
e
q
u
a
t
e.
E
x
p
a
n
d
in
g
t
h
e
s
ca
n
n
i
n
g
a
r
e
as
o
f
m
ea
t
s
a
m
p
les
co
u
l
d
p
o
t
en
tia
ll
y
e
n
h
a
n
ce
th
e
p
r
e
d
ic
ti
o
n
d
u
e
t
o
t
h
e
i
n
f
lu
en
ce
o
f
s
m
a
ll
s
ca
n
n
i
n
g
a
r
e
as
o
n
in
ac
c
u
r
at
e
s
h
e
a
r
f
o
r
ce
p
r
e
d
ic
ti
o
n
.
B
a
r
b
in
et
a
l
.
[
1
7
]
f
aile
d
t
o
a
cc
u
r
at
el
y
p
r
ed
ict
ch
i
ck
en
m
e
at
t
en
d
e
r
n
ess
co
m
p
a
r
e
d
t
o
p
H,
c
o
l
o
r
,
a
n
d
W
HC
d
u
e
to
a
n
i
n
a
d
eq
u
ate
l
in
ea
r
m
o
d
eli
n
g
a
n
al
y
s
is
t
h
at
c
o
u
ld
n
o
t
ac
co
u
n
t
f
o
r
t
h
e
c
o
m
p
le
x
ity
o
f
m
e
at
te
x
t
u
r
e
att
r
i
b
u
tes
.
I
n
t
h
e
m
ea
n
t
im
e,
a
n
u
m
b
e
r
o
f
s
t
u
d
i
es
u
t
ili
zi
n
g
li
n
e
ar
m
o
d
eli
n
g
d
is
c
o
v
er
e
d
q
u
i
te
s
at
is
f
ac
t
o
r
y
o
u
tc
o
m
es
in
f
o
r
e
ca
s
t
in
g
t
h
e
te
n
d
e
r
n
ess
o
f
b
e
ef
a
n
d
p
o
r
k
,
wit
h
R
-
v
al
u
es
r
a
n
g
i
n
g
f
r
o
m
0
.
5
3
t
o
0
.
7
4
.
Nev
er
t
h
el
ess
,
s
t
u
d
i
es o
n
b
ee
f
,
p
o
u
ltr
y
,
p
o
r
k
,
a
n
d
l
am
b
h
a
v
e
s
h
o
wn
u
n
s
a
tis
f
ac
to
r
y
p
r
e
d
i
cti
o
n
o
u
tc
o
m
es
i
n
li
n
e
ar
m
u
lti
v
a
r
i
ate
a
n
al
y
s
is
,
wi
th
a
cc
u
r
ac
ies
u
n
d
e
r
0
.
5
w
h
en
es
tim
at
in
g
te
n
d
e
r
n
ess
b
ase
d
o
n
NI
R
s
p
e
ct
r
al
d
at
a.
W
h
ile
PC
R
an
d
PLS
m
o
d
els
ca
n
d
ec
r
ea
s
e
h
ig
h
-
d
im
en
s
io
n
al
in
p
u
ts
an
d
r
em
o
v
e
c
o
llin
ea
r
ity
,
th
ey
ca
n
n
o
t
a
d
d
r
ess
n
o
n
lin
ea
r
ities
p
r
esen
t
in
th
e
d
ata.
No
n
lin
e
ar
ities
in
s
p
ec
tr
al
s
ig
n
als
m
a
y
r
esu
lt
f
r
o
m
lig
h
t
s
ca
tter
in
g
ef
f
ec
ts
in
u
n
alter
ed
m
ea
t
s
am
p
les
[
1
8
]
.
Mo
r
eo
v
er
,
f
ac
to
r
s
s
u
ch
as
p
r
o
tein
co
n
ten
t
an
d
m
u
s
cle
s
tr
u
ctu
r
e,
as
well
as
co
n
n
ec
tiv
e
ti
s
s
u
e,
af
f
ec
t
q
u
alities
lik
e
ten
d
er
n
ess
,
co
lo
r
,
p
H,
an
d
wat
er
h
o
ld
in
g
ca
p
ac
ity
o
f
m
ea
t
[
1
9
]
.
No
n
li
n
ea
r
ca
lib
r
atio
n
m
o
d
e
ls
ar
e
n
ec
ess
ar
y
b
e
ca
u
s
e
lin
ea
r
m
u
ltiv
ar
iate
m
o
d
els
ca
n
n
o
t
ca
p
tu
r
e
th
ese
n
o
n
lin
ea
r
ities
.
T
h
e
in
cr
e
ased
in
ter
est
in
v
ar
io
u
s
f
ield
s
,
n
o
tab
ly
in
ag
r
ic
u
ltu
r
e
an
d
f
o
o
d
in
d
u
s
tr
y
,
is
d
u
e
to
th
e
ca
p
ab
ilit
y
o
f
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN
)
in
m
o
d
e
lin
g
h
ig
h
l
y
n
o
n
l
in
ea
r
d
ata
[
2
0
]
.
R
esear
ch
er
s
h
av
e
in
v
esti
g
ated
h
y
b
r
i
d
m
o
d
els
th
at
h
ar
n
es
s
b
o
th
lin
ea
r
an
d
n
o
n
lin
ea
r
m
eth
o
d
s
to
tack
le
th
is
is
s
u
e.
Me
th
o
d
s
s
u
ch
as
p
r
in
cip
al
co
m
p
o
n
e
n
t
n
e
u
r
al
n
etwo
r
k
(
PC
NN)
an
d
laten
t
v
ar
iab
le
n
e
u
r
al
n
etwo
r
k
(
L
VNN)
u
tili
ze
th
e
r
esu
lts
f
r
o
m
PC
R
an
d
PLS
as
in
p
u
ts
in
to
an
ANN.
T
h
is
m
e
r
g
es
th
e
d
ata
r
ed
u
ctio
n
s
k
ills
o
f
lin
ea
r
m
o
d
els
with
th
e
n
o
n
lin
ea
r
m
o
d
elin
g
s
tr
en
g
th
o
f
ANNs,
ad
d
r
ess
in
g
th
e
lim
itatio
n
s
o
f
in
d
iv
id
u
al
m
et
h
o
d
s
lik
e
n
o
n
lin
ea
r
ity
,
r
ed
u
n
d
a
n
t
s
p
ec
tr
al
b
an
d
s
,
an
d
wav
elen
g
th
s
elec
tio
n
is
s
u
es
[
2
1
]
.
R
esear
ch
h
as
in
d
icate
d
th
at
h
y
b
r
id
m
o
d
els
lik
e
L
VNN
ar
e
ef
f
ec
tiv
e
in
d
ea
lin
g
wi
th
r
ed
u
n
d
an
c
y
an
d
n
o
n
lin
ea
r
ity
in
s
p
ec
tr
al
d
ata
to
esti
m
ate
m
in
er
al
ab
u
n
d
an
c
e
o
n
th
e
m
o
o
n
'
s
s
u
r
f
ac
e,
p
er
f
o
r
m
in
g
b
etter
th
a
n
s
tan
d
alo
n
e
PLS a
n
d
g
en
etic
al
g
o
r
ith
m
(
GA
)
-
PLS m
o
d
els
[
2
2
]
.
T
h
e
o
b
jectiv
e
o
f
th
is
r
esear
ch
is
to
ev
alu
ate
th
e
ef
f
ec
tiv
en
ess
o
f
af
f
o
r
d
ab
le
p
o
r
ta
b
le
s
p
ec
tr
o
s
co
p
y
in
p
r
ed
ictin
g
th
e
ten
d
er
n
ess
o
f
b
r
o
iler
m
ea
t
ea
r
ly
o
n
,
b
y
an
aly
zi
n
g
NI
R
s
p
ec
tr
a
f
r
o
m
b
r
ea
s
t
m
ea
t
an
d
d
r
u
m
s
tick
s
u
s
in
g
b
o
th
lin
ea
r
(
PC
R
an
d
PLS)
an
d
n
o
n
lin
ea
r
(
PC
NN
an
d
L
VNN)
m
o
d
els.
T
h
is
r
esear
ch
also
ex
am
in
ed
th
e
u
tili
za
tio
n
o
f
two
d
i
v
e
r
s
e
s
u
b
s
et
wav
elen
g
th
in
ter
v
als
(
i.e
.
6
6
2
–
1
,
0
0
5
n
m
an
d
7
0
0
–
1
,
0
0
5
n
m
)
.
Ad
d
itio
n
ally
,
it
co
n
tr
asted
th
r
ee
d
is
tin
ct
s
p
ec
tr
al
p
r
e
-
p
r
o
ce
s
s
in
g
m
eth
o
d
s
(
i.e
.
ze
r
o
o
r
d
er
,
f
ir
s
t
o
r
d
er
,
an
d
s
ec
o
n
d
o
r
d
er
Sav
itzk
y
-
Go
lay
d
e
r
iv
ativ
es).
2.
M
E
T
H
O
D
2
.
1
.
Sa
m
ple a
nd
da
t
a
co
l
lect
io
n
R
o
s
s
b
r
o
iler
s
wer
e
u
til
ized
in
th
is
s
tu
d
y
an
d
wer
e
r
aised
in
a
co
m
m
er
cial
co
o
p
with
a
ca
p
ac
ity
o
f
2
,
2
0
0
b
r
o
iler
s
p
er
co
o
p
o
n
a
f
ar
m
in
L
en
tan
g
,
Du
n
g
u
n
,
T
er
en
g
g
an
u
,
Ma
lay
s
ia.
T
h
e
b
r
o
il
er
s
wer
e
g
iv
en
Hu
at
L
ai
Feed
m
ill
Sd
n
.
B
er
h
ad
's
co
m
m
er
cial
p
ellets
f
o
r
th
eir
m
ea
ls
.
On
d
ay
3
9
,
twen
ty
-
s
ev
en
b
r
o
iler
s
wer
e
ch
o
s
en
at
r
an
d
o
m
an
d
t
r
an
s
p
o
r
ted
to
th
e
b
r
o
iler
p
r
o
ce
s
s
in
g
p
lan
t.
T
h
e
s
am
p
le
s
ize
i
s
d
eter
m
in
ed
u
s
in
g
r
ec
o
m
m
en
d
atio
n
s
an
d
r
eso
u
r
c
e
eq
u
atio
n
ap
p
r
o
ac
h
o
u
tlin
ed
in
ea
r
lier
s
tu
d
ies
[
2
3
]
,
[
2
4
]
.
T
h
e
ef
f
ec
tiv
en
ess
o
f
d
ata
an
aly
s
is
r
elies
h
ea
v
ily
o
n
th
e
ch
o
ice
o
f
s
am
p
le
s
izes.
C
h
o
o
s
in
g
a
s
am
p
le
s
ize
w
ith
a
s
m
all
n
u
m
b
er
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
B
r
o
iler
mea
ts
ten
d
ern
ess
p
r
ed
ictio
n
u
s
in
g
N
I
R
s
p
ec
tr
o
s
co
p
y
a
g
a
in
s
t
n
o
n
-
lin
ea
r
…
(
R
a
s
h
id
a
h
Gh
a
z
a
li)
2715
an
im
als
ca
n
r
esu
lt
in
s
u
b
s
ta
n
tial
d
if
f
er
en
ce
s
in
th
e
r
aw
d
ata
co
llected
.
Nev
er
t
h
eless
,
ex
ce
s
s
iv
e
waste
o
f
an
im
als
,
alo
n
g
with
eth
ical
c
o
n
ce
r
n
s
,
p
o
s
es a
p
r
o
b
lem
f
o
r
e
x
ten
s
iv
e
s
am
p
le
s
izes.
T
h
e
ch
ick
e
n
s
wer
e
h
o
u
s
ed
i
n
cr
ates
co
n
tai
n
in
g
n
in
e
c
h
i
ck
en
s
ea
ch
d
u
r
in
g
lair
ag
e
b
e
f
o
r
e
b
ein
g
s
lau
g
h
ter
ed
an
d
p
r
o
ce
s
s
ed
ac
c
o
r
d
in
g
t
o
th
e
r
eg
u
latio
n
s
o
u
tli
n
ed
in
Ma
lay
s
ian
Stan
d
ar
d
1
,
5
0
0
:2
,
0
0
9
f
o
r
h
alal
f
o
o
d
p
r
o
d
u
ctio
n
,
p
r
ep
a
r
atio
n
,
h
an
d
lin
g
,
an
d
s
to
r
a
g
e
[
2
5
]
.
T
h
e
p
ec
to
r
alis
m
ajo
r
m
u
s
cles
o
n
th
e
lef
t
s
id
e
a
n
d
th
e
p
air
o
f
d
r
u
m
s
tick
s
wer
e
e
x
tr
ac
ted
f
r
o
m
ea
ch
p
r
e
p
ar
ed
ca
r
ca
s
s
,
th
en
ch
illed
an
d
d
eli
v
er
ed
to
Un
iv
er
s
iti
Pu
tr
a
Ma
lay
s
ia
in
Ser
d
an
g
,
M
alay
s
ia
at
a
tem
p
er
atu
r
e
o
f
-
20
°C
b
y
a
s
p
ec
ialized
c
o
ld
lo
g
is
tics
s
er
v
ice.
T
h
e
ch
illed
s
p
ec
im
en
s
wer
e
k
ep
t
i
n
a
f
r
ee
ze
r
at
-
20
°C
in
a
Me
at
Scien
ce
L
ab
o
r
ato
r
y
,
p
ar
t
o
f
th
e
Dep
a
r
tm
en
t
o
f
An
im
al
Scien
ce
at
th
e
Facu
lty
o
f
Ag
r
icu
lt
u
r
e,
Un
iv
e
r
s
iti Pu
tr
a
Ma
lay
s
ia,
lo
ca
ted
in
Ser
d
a
n
g
,
Ma
lay
s
ia.
B
ef
o
r
e
th
e
d
ay
o
f
d
ata
co
llec
tio
n
,
a
to
tal
o
f
n
in
e
b
r
ea
s
t
m
ea
t
p
iece
s
an
d
n
in
e
p
air
s
o
f
d
r
u
m
s
tick
s
wer
e
th
awe
d
o
v
er
n
ig
h
t
at
a
te
m
p
er
atu
r
e
o
f
4
°C
f
o
r
1
2
h
o
u
r
s
.
B
ec
au
s
e
m
u
s
cle
h
eter
o
g
en
e
ity
ca
n
lead
to
h
ig
h
v
ar
iab
ilit
y
in
s
h
ea
r
f
o
r
ce
m
e
asu
r
em
en
ts
o
b
tain
ed
f
r
o
m
th
e
s
am
e
m
u
s
cle,
s
ix
s
am
p
les
wer
e
co
llected
f
r
o
m
b
r
ea
s
t
m
ea
t
an
d
th
r
ee
s
am
p
les
wer
e
co
llected
f
r
o
m
d
r
u
m
s
tick
s
.
T
h
e
u
n
co
o
k
e
d
ch
ick
en
b
r
ea
s
t
p
i
ec
es
f
r
o
m
ea
ch
b
r
o
iler
ca
r
ca
s
s
wer
e
s
lic
ed
in
to
r
ec
tan
g
le
s
tr
ip
s
m
ea
s
u
r
in
g
1
0
m
m
th
ick
×
1
0
m
m
wid
e
×
2
0
m
m
lo
n
g
with
th
eir
a
x
is
alig
n
ed
p
ar
all
el
to
th
e
m
u
s
cle
f
ib
er
s
[
2
6
]
–
[
2
8
]
.
T
h
e
d
r
u
m
s
tick
s
wer
e
b
o
n
eless
b
ef
o
r
e
b
ein
g
s
liced
to
th
e
s
am
e
s
ize.
A
s
a
r
esu
lt,
a
to
tal
o
f
1
0
8
s
am
p
les
o
f
b
r
ea
s
t
m
ea
t
an
d
d
r
u
m
s
tick
s
wer
e
p
r
ep
ar
ed
in
o
n
e
d
a
y
.
E
v
er
y
m
ea
t
s
a
m
p
le
s
tr
ip
was
p
lace
d
in
f
r
o
n
t
o
f
a
N
I
R
r
ef
lectio
n
p
r
o
b
e
t
o
g
ath
e
r
s
p
ec
tr
u
m
d
ata,
af
ter
wh
ich
th
e
s
h
ea
r
f
o
r
ce
o
f
th
e
s
tr
ip
s
was te
s
ted
with
th
e
Vo
lo
k
ev
ich
J
aw
tex
tu
r
e
an
aly
s
er
.
I
n
o
r
d
er
to
r
e
d
u
ce
th
e
tim
e
g
ap
b
etwe
en
th
e
two
p
r
o
ce
s
s
es a
n
d
p
r
ev
en
t m
o
is
tu
r
e
lo
s
s
,
m
ea
t a
g
in
g
,
an
d
d
is
co
lo
r
ati
o
n
,
s
h
ea
r
f
o
r
ce
was
m
ea
s
u
r
ed
r
ig
h
t
af
ter
ac
q
u
i
r
in
g
th
e
s
p
ec
tr
u
m
[
5
]
.
T
h
e
p
r
o
ce
s
s
o
f
o
b
tain
in
g
s
am
p
les
w
as
r
ep
ea
ted
f
o
r
th
e
f
o
llo
win
g
two
d
ay
s
.
I
n
to
tal,
3
2
4
s
am
p
les
o
f
b
r
ea
s
t
m
ea
t
an
d
d
r
u
m
s
tick
s
wer
e
co
llected
o
v
er
a
s
p
an
o
f
th
r
ee
d
ay
s
f
o
r
s
p
ec
tr
o
s
co
p
ic
an
d
s
h
e
ar
f
o
r
ce
a
n
aly
s
is
.
2
.
2
.
Sp
ec
t
ro
s
co
py
m
ea
s
urem
ent
A
s
m
all,
af
f
o
r
d
ab
le
h
a
n
d
h
el
d
v
is
ib
le
-
s
h
o
r
t
-
wav
e
i
n
f
r
ar
e
d
(
VI
S
-
SW
NI
R
)
s
p
ec
tr
o
m
eter
d
ev
ice,
th
e
Oce
an
Op
tics
USB
4
0
0
0
m
in
ia
tu
r
e
f
ib
r
e
o
p
tic
s
p
ec
tr
o
m
eter
(
6
5
0
to
1
,
3
1
8
n
m
)
,
m
a
n
u
f
ac
tu
r
ed
b
y
OR
NE
T
Sd
n
.
T
h
e
d
ev
ice
f
r
o
m
a
co
m
p
an
y
i
n
Ma
lay
s
ia
was
u
tili
ze
d
to
g
ath
er
r
ef
lecta
n
ce
s
p
ec
tr
a
f
r
o
m
th
e
s
u
r
f
ac
e
o
f
ea
ch
b
r
o
iler
m
ea
t
s
am
p
le
with
o
u
t
in
v
asiv
e
m
eth
o
d
s
.
T
h
e
lig
h
t
s
o
u
r
ce
em
p
l
o
y
ed
was
a
T
u
n
g
s
ten
h
alo
g
e
n
lig
h
t
(LS
-
1
,
Oce
an
Op
tics
,
USA)
,
with
a
wav
elen
g
th
r
an
g
e
s
p
an
n
in
g
f
r
o
m
3
6
0
to
2
,
0
0
0
n
m
.
A
f
ib
er
o
p
tic
r
ef
lecta
n
ce
p
r
o
b
e
(
R
4
0
0
-
7
-
VI
S/NIR,
Oce
an
Op
tic
s
,
USA)
was e
m
p
lo
y
ed
to
s
en
d
lig
h
t th
at
was r
ef
lecte
d
f
r
o
m
th
e
s
u
r
f
ac
e
o
f
th
e
m
ea
t
to
an
i
n
ter
n
al
d
etec
to
r
.
T
h
e
o
p
tical
f
ib
er
p
r
o
b
e
in
clu
d
es
two
co
n
n
e
ctio
n
s
:
o
n
e
f
o
r
th
e
lig
h
t
s
o
u
r
ce
an
d
o
n
e
f
o
r
d
ata
co
llectio
n
.
I
n
o
r
d
er
to
m
ea
s
u
r
e
d
if
f
u
s
e
r
ef
lectio
n
,
th
e
f
i
b
er
o
p
tic
p
r
o
b
e
was
p
lace
d
v
er
tically
at
a
9
0
°
an
g
le,
p
o
s
itio
n
ed
5
m
m
a
b
o
v
e
t
h
e
s
u
r
f
ac
e
o
f
t
h
e
u
n
c
o
o
k
e
d
b
r
o
iler
m
ea
t strip
s
[
29]
.
T
h
e
s
etu
p
f
o
r
m
ea
s
u
r
in
g
VI
S
-
SW
NI
R
s
p
ec
tr
o
s
co
p
y
is
s
h
o
wn
in
Fig
u
r
e
1
.
E
v
er
y
d
a
y
,
d
ar
k
an
d
wh
ite
r
ef
er
en
ce
s
wer
e
ac
q
u
ir
ed
b
y
s
witch
in
g
o
f
f
th
e
lig
h
t
s
o
u
r
ce
an
d
ca
p
tu
r
in
g
a
s
p
ec
tr
u
m
f
r
o
m
a
wh
ite
d
if
f
u
s
e
r
ef
lecta
n
ce
s
tan
d
ar
d
(
W
S
-
1
,
Oce
an
Op
tics
,
USA)
f
o
r
o
p
ti
ca
l
r
ef
er
en
ce
.
T
h
e
s
p
ec
tr
o
m
e
ter
co
n
n
ec
ted
to
a
lap
to
p
co
m
p
u
ter
with
th
e
Sp
ec
tr
a
Su
ite
®
s
o
f
twar
e
(
Oce
an
Op
tics
,
USA)
f
o
r
ca
p
tu
r
in
g
s
p
ec
tr
al
d
ata.
T
h
e
r
ef
lecta
n
ce
s
p
ec
tr
u
m
o
f
a
b
r
o
iler
m
ea
t
s
am
p
le
was
o
b
tain
e
d
u
s
in
g
an
av
er
ag
e
o
f
5
co
n
s
ec
u
tiv
e
s
ca
n
s
.
T
o
im
p
r
o
v
e
t
h
e
s
ig
n
al
-
to
-
n
o
is
e
r
a
tio
o
f
th
e
o
b
tain
ed
s
p
ec
tr
u
m
,
i
t
was
s
m
o
o
th
ed
u
s
in
g
a
b
o
x
c
a
r
v
alu
e
o
f
6
0
.
T
h
e
o
b
tain
ed
s
p
ec
tr
al
d
ata
was
s
av
ed
o
n
th
e
lap
to
p
an
d
a
n
aly
ze
d
u
s
in
g
MA
T
L
AB
s
im
u
latio
n
s
o
f
twar
e
(
MA
T
L
AB
® Ve
r
s
io
n
7
.
1
2
.
0
.
6
3
5
(
R
2
0
1
6
a)
)
.
Fig
u
r
e
1
.
T
h
e
illu
s
tr
atio
n
o
f
VI
S
-
SW
NI
R
s
p
ec
tr
o
s
co
p
y
m
ea
s
u
r
em
en
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
7
1
3
-
2
7
2
3
2716
2
.
3
.
Sh
ea
r
f
o
rc
e
m
e
a
s
urem
e
nt
T
h
e
s
h
ea
r
f
o
r
ce
was
m
ea
s
u
r
ed
with
th
e
h
elp
o
f
a
co
m
p
u
ter
-
aid
ed
tex
tu
r
e
an
aly
s
er
T
A
s
y
s
tem
.
HD
p
lu
s
TA
(
Stab
le
Mic
r
o
Sy
s
tem
s
,
UK)
eq
u
ip
p
ed
with
a
Vo
lo
d
k
ev
ich
J
aw
s
et
(
s
tain
less
s
teel
p
r
o
b
e
r
esem
b
lin
g
an
in
ciso
r
)
.
T
h
e
tex
tu
r
e
an
aly
s
er
was
s
et
u
p
with
co
m
p
r
ess
io
n
f
o
r
test
m
o
d
e,
p
r
e
-
test
,
test
an
d
p
o
s
t
-
test
s
p
ee
d
s
o
f
0
.
2
cm
/s
ec
,
a
0
.
5
cm
d
is
tan
ce
,
an
d
au
to
tr
ig
g
er
ty
p
e
ca
lib
r
atio
n
.
E
v
er
y
b
r
o
iler
s
tr
ip
s
am
p
le
was
co
m
p
r
ess
ed
an
d
s
h
ea
r
ed
o
n
ce
at
th
e
ce
n
ter
,
p
er
p
en
d
ic
u
lar
to
th
e
m
u
s
cle
f
ib
er
s
'
lo
n
g
itu
d
in
al
o
r
ie
n
tatio
n
[
2
7
]
.
T
h
e
h
ig
h
est
r
ec
o
r
d
e
d
s
h
ea
r
f
o
r
c
e
was
m
ea
s
u
r
ed
in
k
ilo
g
r
am
s
(
k
g
)
.
I
n
o
r
d
er
to
p
r
ev
en
t
b
u
ild
-
u
p
o
f
r
esid
u
es
th
at
co
u
ld
af
f
ec
t
m
e
asu
r
em
en
t
ac
cu
r
ac
y
,
th
e
te
x
tu
r
e
an
aly
s
er
'
s
s
lo
t
an
d
s
teel
p
r
o
b
e
wer
e
tak
en
o
u
t
an
d
clea
n
ed
af
ter
ev
er
y
8
s
tr
ip
s
test
ed
.
T
h
er
ef
o
r
e,
th
e
s
lo
t
an
d
s
teel
p
r
o
b
e
wer
e
r
ein
s
talled
an
d
th
e
tex
tu
r
e
an
aly
s
er
u
n
d
er
wen
t
r
ec
alib
r
ati
o
n
af
ter
e
v
er
y
1
8
m
ea
s
u
r
em
e
n
ts
.
T
h
e
m
eth
o
d
s
wer
e
ca
r
r
ied
o
u
t
m
u
ltip
le
tim
es
wh
ile
g
ath
er
in
g
d
ata
o
n
s
h
ea
r
f
o
r
ce
o
f
b
r
o
iler
m
ea
t
s
am
p
les.
T
h
e
in
f
o
r
m
atio
n
g
at
h
er
ed
wa
s
s
to
r
ed
in
an
E
x
ce
l
d
o
cu
m
e
n
t a
n
d
a
n
aly
ze
d
u
s
in
g
MA
T
L
AB
s
im
u
latio
n
s
o
f
twar
e.
2
.
4
.
P
re
-
pro
ce
s
s
ing
T
h
e
s
p
ec
tr
o
m
eter
u
tili
ze
d
a
T
C
D1
3
0
4
AP
ch
ar
g
e
-
co
u
p
led
d
ev
ice
(
CCD
)
lin
ea
r
im
ag
e
s
en
s
o
r
f
r
o
m
T
o
s
h
ib
a,
J
ap
an
,
to
co
v
e
r
a
r
a
n
g
e
f
r
o
m
6
5
0
to
1
,
3
1
8
n
m
.
Nev
er
th
eless
,
th
e
C
C
D
s
en
s
o
r
co
u
l
d
n
'
t
d
etec
t
an
y
wav
elen
g
th
s
b
ey
o
n
d
1
,
1
0
0
n
m
,
an
d
th
er
e
was
s
ig
n
if
ican
t
n
o
i
s
e
p
r
esen
t
at
b
o
th
en
d
s
o
f
th
e
ca
p
tu
r
ed
s
p
ec
tr
u
m
.
T
h
er
ef
o
r
e,
a
to
tal
o
f
1
,
7
4
1
wa
v
elen
g
th
s
wer
e
k
e
p
t,
o
f
f
er
in
g
s
p
ec
tr
al
d
ata
r
an
g
in
g
f
r
o
m
ab
o
u
t 6
6
2
t
o
1
,
0
0
5
n
m
.
Mo
r
eo
v
er
,
th
e
in
co
n
s
is
ten
cy
in
th
e
in
ter
v
al
b
etwe
en
two
n
eig
h
b
o
r
in
g
wav
elen
g
th
s
was
attr
ib
u
ted
to
th
e
an
alo
g
-
to
-
d
ig
ital
co
n
v
er
s
io
n
a
n
d
th
e
r
e
d
u
ce
d
ef
f
icien
cy
o
f
t
h
e
s
p
ec
tr
o
m
eter
'
s
g
r
atin
g
.
An
av
er
ag
in
g
m
eth
o
d
was u
s
ed
to
ad
ju
s
t th
e
s
p
ec
tr
al
d
ata
in
ter
v
al
to
1
n
m
.
I
n
o
r
d
er
to
elim
in
ate
u
n
wa
n
ted
s
ig
n
als
r
esu
ltin
g
f
r
o
m
lig
h
t
s
ca
tter
in
g
an
d
r
a
n
d
o
m
n
o
is
es,
th
e
d
if
f
u
s
e
r
ef
lecta
n
ce
s
p
ec
tr
a
a
n
d
s
h
ea
r
f
o
r
ce
m
ea
s
u
r
em
e
n
ts
th
at
wer
e
r
ec
o
r
d
ed
u
n
d
e
r
wen
t
p
r
e
-
p
r
o
ce
s
s
in
g
d
ata
p
r
o
ce
d
u
r
es.
Po
s
s
ib
le
o
u
tlier
s
am
p
les
wer
e
s
u
b
s
eq
u
e
n
tly
p
in
p
o
in
ted
au
to
n
o
m
o
u
s
ly
u
s
in
g
e
x
ter
n
all
y
s
tu
d
en
tized
r
esid
u
als
with
th
e
h
elp
o
f
a
PC
R
m
o
d
el
a
n
d
leav
e
-
o
n
e
-
o
u
t
cr
o
s
s
-
v
alid
atio
n
.
T
h
e
e
x
ter
n
a
lly
s
tu
d
en
tized
r
esid
u
al
was
ca
l
cu
lated
u
s
in
g
th
e
v
ar
ian
ce
b
etwe
en
th
e
f
o
r
ec
asted
an
d
a
ctu
al
b
r
o
iler
m
ea
t
ten
d
er
n
ess
.
Sam
p
les
wh
er
e
r
e
s
id
u
al
v
alu
es
wer
e
h
ig
h
er
th
a
n
1
.
9
7
6
,
th
e
cr
itical
v
alu
es
o
f
th
e
t
-
d
is
tr
ib
u
tio
n
,
wer
e
co
n
s
id
er
ed
o
u
tlier
s
an
d
e
lim
in
ated
,
r
esu
ltin
g
in
th
e
ex
cl
u
s
io
n
o
f
1
6
%
o
f
b
r
ea
s
t
m
ea
t
s
am
p
les
an
d
1
5
.
4
%
o
f
d
r
u
m
s
tick
s
am
p
les.
I
n
T
ab
le
1
,
th
e
s
h
ea
r
f
o
r
ce
v
a
lu
es
f
o
r
b
r
ea
s
t
m
ea
t
a
n
d
d
r
u
m
s
tick
s
ar
e
lis
ted
,
with
p
o
te
n
tial
o
u
tlier
s
r
em
o
v
ed
u
s
in
g
ex
ter
n
ally
s
tu
d
en
tized
r
esid
u
al.
I
n
s
o
f
t
m
ea
t
s
am
p
l
es,
th
e
tex
tu
r
e
an
aly
s
er
r
eq
u
ir
es
less
s
h
ea
r
f
o
r
ce
to
p
ier
ce
t
h
e
m
ea
t
th
an
in
to
u
g
h
e
r
m
ea
t.
T
h
is
in
d
ica
tes
th
at
s
o
f
t
m
ea
t
h
as
a
lo
wer
s
h
ea
r
f
o
r
ce
v
alu
e
,
wh
ile
h
ar
d
e
r
m
ea
t
h
as
a
h
ig
h
er
s
h
ea
r
f
o
r
ce
v
al
u
e.
A
d
d
itio
n
ally
,
th
e
av
er
a
g
e,
lo
west,
a
n
d
h
ig
h
est
s
h
ea
r
f
o
r
ce
v
ar
iab
ilit
y
f
o
r
b
r
ea
s
t
m
ea
t
was
s
ig
n
if
ican
tly
s
m
aller
co
m
p
ar
ed
to
th
e
d
r
u
m
s
tick
s
.
B
r
ea
s
t
m
ea
t
is
m
o
r
e
ten
d
er
an
d
h
as lo
wer
s
h
ea
r
f
o
r
ce
co
m
p
ar
ed
to
d
r
u
m
s
tick
s
.
T
ab
le
1
.
T
h
e
r
ef
er
e
n
ce
s
h
ea
r
f
o
r
ce
v
alu
es o
f
r
etain
ed
b
r
o
iler
b
r
ea
s
t m
ea
t a
n
d
d
r
u
m
s
tick
s
s
am
p
les
M
e
a
t
t
y
p
e
s
N
o
.
o
f
sa
mp
l
e
s
M
e
a
n
±
S
D
(
k
g
)
R
a
n
g
e
(
k
g
)
B
r
e
a
s
t
m
e
a
t
1
3
6
0
.
7
1
5
±
0
.
1
7
3
0
.
3
0
t
o
1
.
1
5
D
r
u
msti
c
k
s
1
3
7
1
.
0
4
5
±
0
.
3
6
4
0
.
2
7
t
o
1
.
8
4
2
.
4
.
1
.
Sp
ec
t
ra
l pre
-
pro
ce
s
s
in
g
a
nd
ca
lib
ra
t
io
n
T
h
e
ab
s
o
r
b
an
ce
s
p
ec
tr
a
we
r
e
d
iv
id
e
d
in
t
o
two
d
if
f
e
r
en
t
wav
elen
g
t
h
r
a
n
g
es,
VI
S
-
SW
NI
R
(
6
6
2
to
1
,
0
0
5
n
m
)
an
d
SW
NI
R
(
7
0
0
to
1
,
0
0
5
n
m
)
,
an
d
an
aly
ze
d
with
th
r
ee
m
ath
em
atica
l
tech
n
iq
u
es
(
ze
r
o
-
o
r
d
er
,
f
ir
s
t
-
o
r
d
er
,
an
d
s
ec
o
n
d
-
o
r
d
er
Sav
itzk
y
-
G
o
lay
(
SG)
d
er
iv
ativ
e)
to
in
v
esti
g
ate
if
m
o
r
e
ac
cu
r
ate
m
o
d
els
co
u
l
d
b
e
cr
ea
ted
f
o
r
p
ar
ticu
lar
tr
aits
(
b
r
ea
s
t
m
ea
t
an
d
d
r
u
m
s
tick
s
)
b
y
f
o
c
u
s
in
g
o
n
s
p
ec
if
ic
s
p
ec
tr
u
m
r
an
g
es
r
ath
e
r
th
an
th
e
e
n
tire
s
p
ec
tr
u
m
[
3
0
]
,
[
3
1
]
.
T
h
e
p
ar
am
eter
s
f
o
r
SG
f
ilter
in
g
in
clu
d
e
t
h
e
d
er
iv
ati
v
e
o
r
d
er
,
p
o
ly
n
o
m
ial
o
r
d
er
,
an
d
f
ilter
l
en
g
th
.
T
h
e
v
alu
e
o
f
th
e
d
er
i
v
ativ
e
o
r
d
er
was
c
h
o
s
en
as
D
O=
0
,
1
,
an
d
2
,
w
h
ile
th
e
p
o
ly
n
o
m
ial
o
r
d
er
was
s
elec
ted
as
PO=1
,
2
,
an
d
3
.
A
clea
r
ex
p
lan
atio
n
o
f
th
e
ap
p
r
o
p
r
iate
f
ilter
len
g
th
is
n
ec
ess
ar
y
to
m
ain
tain
th
e
r
eso
lu
tio
n
o
f
th
e
d
er
iv
ativ
e
s
ig
n
al
[
3
0
]
.
Mo
n
te
C
ar
lo
cr
o
s
s
-
v
alid
atio
n
(
MCC
V)
wa
s
u
tili
ze
d
to
v
alid
ate
t
h
e
p
r
ec
is
io
n
o
f
th
e
PC
R
m
o
d
el
in
c
o
r
p
o
r
atin
g
v
a
r
io
u
s
p
r
e
-
p
r
o
ce
s
s
ed
s
p
ec
tr
al
d
ata,
f
ilter
len
g
th
,
an
d
n
u
m
b
er
o
f
PC
s
[
3
0
]
.
MCC
V,
also
k
n
o
wn
as
r
ep
ea
ted
r
a
n
d
o
m
s
u
b
s
am
p
li
n
g
o
r
h
o
ld
o
u
t
with
r
an
d
o
m
r
esam
p
lin
g
,
is
a
s
tr
ai
g
h
tf
o
r
war
d
b
u
t
ef
f
i
cien
t
m
eth
o
d
f
o
r
f
i
n
d
in
g
o
p
tim
al
p
ar
am
eter
s
an
d
p
r
ed
ictio
n
er
r
o
r
.
I
t
o
f
f
er
s
m
o
r
e
d
ep
en
d
a
b
le
r
esu
lts
th
an
leav
e
-
one
-
o
u
t
cr
o
s
s
-
v
alid
atio
n
(
L
OOCV
)
wh
en
d
ea
lin
g
with
a
s
m
all
d
ata
s
et.
T
h
e
SG
d
er
iv
ativ
e
c
o
ef
f
icien
t
s
wer
e
p
r
o
d
u
ce
d
u
s
in
g
MA
T
L
AB
s
im
u
latio
n
s
o
f
twar
e's
b
u
ilt
-
in
m
atr
ix
r
o
u
tin
es
f
u
n
ctio
n
,
s
g
o
lay
f
ilt,
in
MA
T
L
AB
v
er
s
io
n
R
2
0
1
6
a
[
3
2
]
.
On
e
h
u
n
d
r
e
d
d
ata
s
ets
wer
e
cr
ea
ted
with
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
B
r
o
iler
mea
ts
ten
d
ern
ess
p
r
ed
ictio
n
u
s
in
g
N
I
R
s
p
ec
tr
o
s
co
p
y
a
g
a
in
s
t
n
o
n
-
lin
ea
r
…
(
R
a
s
h
id
a
h
Gh
a
z
a
li)
2717
v
ar
io
u
s
ar
r
a
n
g
em
en
ts
an
d
M
C
C
V
wa
s
co
n
d
u
cted
u
s
in
g
2
-
f
o
ld
Ven
etian
b
lin
d
cr
o
s
s
v
ali
d
atio
n
.
T
h
is
m
eth
o
d
wa
s
u
tili
ze
d
an
d
cited
f
r
o
m
C
h
ia
et
a
l.
[
3
0
]
.
T
h
e
R
MSE
C
V
was
ca
lcu
lated
to
as
s
ess
an
d
co
n
tr
ast
th
e
PC
R
p
er
f
o
r
m
an
ce
o
n
v
ar
io
u
s
p
r
e
-
p
r
o
ce
s
s
ed
s
p
ec
tr
al
d
ata,
with
f
ilter
len
g
th
r
an
g
in
g
f
r
o
m
5
to
3
1
n
m
i
n
2
n
m
in
cr
em
en
ts
an
d
n
u
m
b
er
o
f
PC
s
r
an
g
in
g
f
r
o
m
1
to
1
5
PC
s.
T
h
e
r
esu
lts
o
f
PC
R
in
f
in
d
in
g
th
e
b
est
n
u
m
b
er
o
f
f
ilter
len
g
th
s
f
o
r
ze
r
o
,
f
ir
s
t
an
d
s
ec
o
n
d
o
r
d
er
SG
d
er
iv
ativ
es
o
n
VI
S
-
SW
NI
R
an
d
SW
NI
R
s
p
ec
tr
a
r
e
g
io
n
s
ar
e
s
u
m
m
ar
ized
in
T
ab
le
2
.
T
h
e
b
r
ea
s
t
m
ea
t
h
a
d
a
R
MSE
C
V=
0
.
8
2
with
f
ilter
le
n
g
th
=2
1
at
6
PC
s
,
ac
h
iev
ed
b
y
th
e
s
ec
o
n
d
-
o
r
d
er
d
e
r
iv
ativ
e
o
f
SW
NI
R
r
eg
io
n
,
wh
ich
was
s
m
aller
th
an
th
e
ze
r
o
-
o
r
d
er
an
d
f
ir
s
t
-
o
r
d
e
r
d
er
iv
a
tiv
es,
in
clu
d
in
g
VI
S
-
SW
NI
R
r
eg
io
n
.
I
n
co
n
tr
ast,
th
e
d
r
u
m
s
tick
s
s
am
p
le
h
ad
t
h
e
lo
west
R
MSE
C
V
v
alu
e
o
f
0
.
8
0
an
d
f
ilter
len
g
th
o
f
2
1
at
1
0
PC
s
f
o
r
th
e
s
ec
o
n
d
-
o
r
d
er
d
e
r
iv
ativ
e
o
f
VI
S
-
SW
NI
R
r
eg
io
n
.
T
ab
le
2
f
u
r
th
er
d
em
o
n
s
tr
ates
th
at
u
tili
zin
g
s
ec
o
n
d
-
o
r
d
er
d
e
r
iv
ativ
e
p
r
e
-
p
r
o
ce
s
s
in
g
in
PC
R
r
esu
lts
in
b
etter
R
MSE
C
V
p
er
f
o
r
m
an
c
e
with
a
d
ec
r
ea
s
ed
n
u
m
b
e
r
o
f
PC
f
ac
to
r
s
co
m
p
a
r
ed
to
u
s
in
g
ze
r
o
-
o
r
d
er
an
d
f
ir
s
t
-
o
r
d
er
d
er
iv
ativ
es.
T
o
m
ai
n
tain
th
e
p
r
ec
is
io
n
o
f
th
e
d
e
r
iv
ativ
e
s
ig
n
als,
it
was
n
o
ticed
th
at
a
g
r
ea
ter
-
o
r
d
e
r
d
er
iv
ativ
e
n
ec
ess
itates
a
len
g
th
ier
f
ilter
d
u
e
to
th
e
lik
elih
o
o
d
o
f
n
o
is
e
am
p
lific
atio
n
d
u
r
in
g
th
e
esti
m
atio
n
p
r
o
ce
s
s
.
W
h
en
lo
o
k
in
g
at
th
e
b
r
ea
s
t
m
ea
t
SW
N
I
R
r
eg
io
n
an
d
d
r
u
m
s
tick
s
VI
S
-
SW
NI
R
r
eg
io
n
,
th
e
f
ilter
len
g
th
r
e
q
u
ir
e
d
to
s
m
o
o
th
o
u
t
n
o
is
e
i
n
th
e
s
ec
o
n
d
-
o
r
d
er
d
er
iv
ativ
e
is
lar
g
e
r
th
a
n
th
at
n
ee
d
ed
f
o
r
t
h
e
ze
r
o
-
o
r
d
er
an
d
f
ir
s
t
-
o
r
d
e
r
d
er
iv
ativ
es.
As
a
r
esu
lt,
th
e
m
o
s
t
ac
cu
r
ate
way
to
esti
m
ate
t
h
e
s
h
ea
r
f
o
r
ce
o
f
d
r
u
m
s
tick
s
in
v
o
lv
ed
u
s
in
g
th
e
v
is
ib
le
s
p
ec
tr
u
m
.
On
th
e
o
th
er
h
an
d
,
wh
en
it
ca
m
e
to
b
r
ea
s
t
m
ea
t,
th
e
b
es
t
ap
p
r
o
ac
h
was
to
ex
clu
d
e
th
e
v
is
ib
le
s
p
ec
tr
u
m
an
d
u
s
e
s
ec
o
n
d
-
o
r
d
e
r
d
er
i
v
ativ
e
SG
p
r
e
-
p
r
o
ce
s
s
in
g
with
a
f
ilter
len
g
th
o
f
2
1
n
m
f
o
r
th
e
b
est r
e
s
u
lt
s.
T
ab
le
2
.
R
esu
lts
o
f
PC
R
m
o
d
els b
ased
o
n
d
if
f
e
r
en
t p
r
etr
ea
tm
en
ts
u
s
in
g
VI
S
-
SW
NI
R
an
d
SW
NI
R
r
an
g
es
M
e
a
t
t
y
p
e
S
p
e
c
t
r
a
r
e
g
i
o
n
Pre
-
p
r
o
c
e
ssi
n
g
F
i
l
t
e
r
l
e
n
g
t
h
(
n
m)
P
r
i
n
c
i
p
a
l
c
o
mp
o
n
e
n
t
s
R
o
o
t
me
a
n
sq
u
a
r
e
e
r
r
o
r
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
B
r
e
a
s
t
m
e
a
t
V
I
S
-
S
W
N
I
R
(
6
6
2
t
o
1
0
0
5
n
m)
Ze
r
o
o
r
d
e
r
d
e
r
i
v
a
t
i
v
e
5
13
0
.
8
5
F
i
r
st
o
r
d
e
r
d
e
r
i
v
a
t
i
v
e
9
10
0
.
8
4
S
e
c
o
n
d
o
r
d
e
r
d
e
r
i
v
a
t
i
v
e
29
8
0
.
8
4
S
W
N
I
R
(
7
0
0
t
o
1
0
0
5
n
m)
Ze
r
o
o
r
d
e
r
d
e
r
i
v
a
t
i
v
e
11
10
0
.
8
5
F
i
r
st
o
r
d
e
r
d
e
r
i
v
a
t
i
v
e
19
8
0
.
8
4
S
e
c
o
n
d
o
r
d
e
r
d
e
r
i
v
a
t
i
v
e
21
6
0
.
8
2
D
r
u
msti
c
k
s
V
I
S
-
S
W
N
I
R
(
6
6
2
t
o
1
0
0
5
n
m)
Ze
r
o
o
r
d
e
r
d
e
r
i
v
a
t
i
v
e
15
11
0
.
8
2
F
i
r
st
o
r
d
e
r
d
e
r
i
v
a
t
i
v
e
17
10
0
.
8
2
S
e
c
o
n
d
o
r
d
e
r
d
e
r
i
v
a
t
i
v
e
21
10
0
.
8
0
S
W
N
I
R
(
7
0
0
t
o
1
0
0
5
n
m)
Ze
r
o
o
r
d
e
r
d
e
r
i
v
a
t
i
v
e
5
11
0
.
8
3
F
i
r
st
o
r
d
e
r
d
e
r
i
v
a
t
i
v
e
27
8
0
.
8
7
S
e
c
o
n
d
o
r
d
e
r
d
e
r
i
v
a
t
i
v
e
11
10
0
.
8
3
I
n
d
r
u
m
s
tick
s
,
PC
R
s
h
o
wed
g
r
ea
ter
en
h
a
n
ce
m
en
t
in
s
h
ea
r
f
o
r
ce
ass
ess
m
en
t
wh
en
in
clu
d
in
g
th
e
v
is
ib
le
r
eg
io
n
,
m
ea
s
u
r
i
n
g
b
et
wee
n
6
6
2
to
7
0
0
n
m
,
co
m
p
a
r
ed
to
b
r
ea
s
t
m
ea
t,
r
e
g
ar
d
les
s
o
f
SG
d
er
iv
ativ
e
f
u
n
ctio
n
o
r
d
er
.
T
h
is
is
d
u
e
to
th
e
h
i
g
h
er
m
y
o
g
lo
b
i
n
co
n
ten
t
in
d
r
u
m
s
tick
m
u
s
cles
co
m
p
ar
ed
to
b
r
ea
s
t
m
ea
t
m
u
s
cles.
T
h
e
d
r
u
m
s
tick
,
b
ei
n
g
a
co
m
p
o
n
en
t
o
f
th
e
leg
m
u
s
cles,
co
n
s
is
ts
o
f
a
h
ig
h
er
am
o
u
n
t
o
f
d
elica
te
m
u
s
cle
f
ib
er
s
u
s
ed
p
r
im
ar
il
y
f
o
r
e
v
er
y
d
ay
ac
tio
n
s
lik
e
walk
in
g
[
3
3
]
.
T
h
er
e
f
o
r
e,
a
h
ig
h
e
r
a
m
o
u
n
t
o
f
m
y
o
g
lo
b
in
is
n
ec
ess
ar
y
to
d
ir
ec
t
o
x
y
g
en
d
eliv
e
r
y
to
th
e
wo
r
k
in
g
m
u
s
cle
[
3
4
]
.
Fu
r
th
e
r
m
o
r
e,
t
h
e
h
i
g
h
m
y
o
g
l
o
b
i
n
c
o
n
te
n
t
is
t
h
e
ca
u
s
e
o
f
t
h
e
r
e
d
d
is
h
h
u
e
i
n
d
r
u
m
s
ti
ck
m
ea
t.
C
o
n
s
e
q
u
e
n
tl
y
,
a
h
ig
h
l
ev
el
o
f
m
y
o
g
l
o
b
i
n
co
n
t
en
t
a
id
s
i
n
u
ti
lizi
n
g
th
e
v
is
ib
le
an
d
SW
NI
R
wa
v
el
e
n
g
t
h
s
,
s
p
ec
i
f
i
ca
ll
y
b
etw
ee
n
6
6
2
an
d
1
,
0
0
5
n
m
,
f
o
r
ev
alu
atin
g
d
r
u
m
s
tick
ten
d
e
r
n
e
s
s
.
I
n
co
n
tr
ast,
ju
s
t
th
e
SW
NI
R
ar
ea
b
etwe
en
7
0
0
a
n
d
1
,
0
0
5
n
m
wav
elen
g
t
h
s
is
u
s
ed
to
ev
al
u
ate
th
e
s
h
ea
r
f
o
r
c
e
o
f
b
r
ea
s
t m
ea
t.
Fig
u
r
e
2
d
is
p
lay
s
th
e
av
er
ag
e
s
ec
o
n
d
-
o
r
d
er
d
er
iv
ativ
e
a
b
s
o
r
b
an
ce
s
p
ec
tr
u
m
f
o
r
b
r
ea
s
t
m
ea
t
an
d
d
r
u
m
s
tick
s
am
p
les
o
b
tain
e
d
f
r
o
m
m
ea
s
u
r
em
en
ts
.
T
h
e
s
ec
o
n
d
ar
y
d
er
i
v
ativ
e
s
h
o
ws
a
s
ig
n
if
ican
t
d
ec
r
ea
s
e
i
n
th
e
v
is
ib
le
s
p
ec
tr
al
r
an
g
e,
en
ab
lin
g
th
e
d
is
tin
ctio
n
o
f
o
v
er
lap
p
in
g
p
ea
k
s
an
d
u
n
co
v
e
r
in
g
m
o
r
e
in
ten
s
e
an
d
d
ef
in
ed
p
ea
k
s
with
a
r
ed
u
ce
d
b
an
d
wid
th
.
T
h
e
s
ec
o
n
d
-
o
r
d
e
r
SG
d
er
iv
ativ
e
s
h
o
ws
h
ig
h
er
p
r
o
f
icien
cy
th
an
ze
r
o
an
d
f
ir
s
t
d
er
iv
ativ
es
b
y
o
f
f
er
i
n
g
r
o
b
u
s
t
s
ig
n
als
with
e
x
ten
s
iv
e
d
a
ta
a
f
ter
elim
in
atin
g
b
ase
lin
e
s
h
if
t
an
d
s
lo
p
e
ef
f
ec
ts
[
1
2
]
.
T
h
e
f
o
r
m
s
o
f
th
e
NI
R
s
p
ec
tr
a
ap
p
ea
r
alik
e,
h
o
wev
er
v
ar
iatio
n
s
in
th
e
s
p
ec
tr
al
in
f
o
r
m
atio
n
o
f
wh
ite
m
ea
t a
n
d
r
e
d
m
ea
t in
b
r
ea
s
t a
n
d
d
r
u
m
s
tick
s
ca
n
b
e
n
o
ticed
at
s
p
ec
if
ic
wav
elen
g
th
s
.
Fig
u
r
e
2
s
h
o
ws
th
at
th
e
v
is
ib
le
r
eg
io
n
o
n
ly
a
p
p
lies
to
d
r
u
m
s
tick
s
,
wh
ich
h
a
v
e
a
h
ig
h
er
co
n
ten
t
o
f
m
y
o
g
lo
b
in
co
n
s
titu
en
ts
co
m
p
ar
ed
to
b
r
ea
s
t m
ea
t sam
p
les.
T
h
r
ee
p
r
o
m
in
en
t p
ea
k
s
with
h
ig
h
ab
s
o
r
b
an
ce
i
n
th
e
v
is
ib
le
s
p
ec
tr
u
m
at
6
6
2
to
7
0
0
n
m
ar
e
lin
k
ed
to
th
e
lev
els
o
f
m
y
o
g
lo
b
in
in
m
ea
t
a
n
d
t
h
e
d
if
f
er
e
n
t
f
o
r
m
s
o
f
m
y
o
g
lo
b
in
th
at
d
eter
m
i
n
e
m
e
at
co
lo
r
[
3
5
]
,
[
3
6
]
.
T
h
e
ab
s
o
r
p
tio
n
p
ea
k
s
f
r
o
m
7
0
0
to
7
7
5
n
m
r
ep
r
esen
t
th
e
v
ib
r
atio
n
s
o
f
C
-
H
th
ir
d
o
v
er
to
n
es
r
elate
d
to
f
at
o
r
lip
i
d
,
a
n
d
O
-
H
th
ir
d
o
v
er
t
o
n
es
r
elate
d
t
o
th
e
wate
r
c
o
n
ten
t
o
f
m
ea
t
s
am
p
les
[
3
5
]
.
Peak
s
in
th
e
r
an
g
e
o
f
7
7
5
to
8
5
0
n
m
co
r
r
esp
o
n
d
to
th
e
th
ir
d
h
ar
m
o
n
ics
o
f
N
-
H
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
7
1
3
-
2
7
2
3
2718
s
tr
etch
in
g
,
wh
ich
ar
e
a
co
m
p
o
n
en
t
o
f
th
e
m
o
lecu
lar
b
o
n
d
s
f
o
u
n
d
i
n
p
r
o
tein
s
.
T
h
e
d
is
tin
ct
ab
s
o
r
p
tio
n
p
ea
k
s
in
th
e
8
5
0
t
o
9
5
0
n
m
r
a
n
g
e
ar
e
r
elate
d
to
t
h
e
in
t
r
am
u
s
cu
la
r
f
at
lev
els
[
1
7
]
,
[
1
9
]
,
in
d
ica
tin
g
th
e
s
tr
etch
in
g
v
ib
r
atio
n
o
f
C
-
H
th
ir
d
s
o
v
e
r
to
n
es.
Ad
d
itio
n
ally
,
th
e
ab
s
o
r
b
a
n
ce
p
ea
k
s
in
th
e
r
an
g
e
o
f
9
5
0
to
1
,
005
n
m
co
u
ld
b
e
attr
ib
u
ted
to
th
e
p
r
esen
ce
o
f
O
-
H
s
ec
o
n
d
o
v
er
to
n
e
s
tr
etch
in
g
an
d
s
ec
o
n
d
o
v
er
to
n
e
N
-
H
s
tr
etch
in
g
[
3
7
]
.
Fig
u
r
e
2
.
T
h
e
av
er
a
g
e
s
ec
o
n
d
-
o
r
d
er
d
er
iv
ativ
e
a
b
s
o
r
b
an
ce
s
p
ec
tr
a
f
o
r
b
r
ea
s
t m
ea
t a
n
d
d
r
u
m
s
tick
s
2
.
5
.
Da
t
a
a
na
ly
s
is
T
ab
le
3
p
r
esen
ts
th
e
d
escr
ip
ti
v
e
s
tatis
tics
o
f
th
e
ca
lib
r
atio
n
an
d
test
in
g
d
ata
s
ets
f
o
r
b
o
th
b
r
ea
s
t
m
ea
t
an
d
d
r
u
m
s
tick
s
.
I
n
o
r
d
er
to
ev
al
u
ate
th
e
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
o
d
els,
th
e
d
ata
wa
s
d
iv
id
ed
r
an
d
o
m
ly
in
to
a
ca
lib
r
atio
n
s
et
(
co
m
p
r
i
s
in
g
2
/3
o
f
th
e
d
ata)
a
n
d
a
te
s
tin
g
s
et
(
co
m
p
r
is
in
g
1
/3
o
f
t
h
e
d
ata)
u
s
in
g
th
e
h
o
ld
-
o
u
t
cr
o
s
s
v
alid
atio
n
tech
n
iq
u
e.
T
h
e
ca
lib
r
atio
n
s
et
was
u
tili
ze
d
f
o
r
co
n
s
tr
u
ctin
g
th
e
p
r
ed
ictiv
e
m
o
d
els,
wh
ile
th
e
test
in
g
s
ets
wer
e
u
s
ed
f
o
r
ass
ess
in
g
th
e
p
r
e
d
ictiv
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
els.
I
n
o
r
d
er
to
p
r
ev
e
n
t
o
v
er
f
itti
n
g
i
n
th
e
PC
R
an
d
PLS
eq
u
atio
n
s
,
MCC
V
was
co
n
d
u
cted
with
a
ca
lib
r
atio
n
s
et
s
p
lit
in
to
5
0
%
f
o
r
tr
a
in
in
g
an
d
5
0
%
f
o
r
v
alid
ati
o
n
.
T
h
e
n
u
m
b
er
o
f
PC
an
d
L
V
s
elec
ted
was
b
ased
o
n
ac
h
iev
in
g
th
e
l
o
west
R
MSE
C
V
v
alu
es,
a
s
f
u
r
th
er
r
ed
u
ctio
n
in
er
r
o
r
was
m
i
n
im
al.
T
h
e
o
p
tim
izatio
n
o
f
v
ar
io
u
s
f
ac
to
r
s
in
co
n
s
tr
u
ctin
g
n
o
n
lin
ea
r
m
o
d
el
s
(
PC
N
N
an
d
L
VNN)
was
f
i
n
e
-
tu
n
ed
u
s
in
g
th
e
MCC
V
m
eth
o
d
,
in
clu
d
in
g
th
e
h
id
d
en
n
eu
r
o
n
co
u
n
t,
lear
n
in
g
r
ate,
m
o
m
en
t
u
m
,
an
d
ep
o
ch
q
u
an
tity
.
T
ab
le
3
.
C
alib
r
atio
n
a
n
d
test
in
g
s
tatis
tic
s
f
o
r
s
h
ea
r
f
o
r
ce
attr
i
b
u
te
M
e
a
t
t
y
p
e
s
S
a
mp
l
e
s
e
t
s
S
a
mp
l
e
n
u
mb
e
r
S
h
e
a
r
f
o
r
c
e
(
k
g
)
M
i
n
M
a
x
M
e
a
n
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
(SD)
B
r
e
a
s
t
m
e
a
t
C
a
l
i
b
r
a
t
i
o
n
t
e
s
t
i
n
g
91
0
.
3
0
1
.
0
2
0
.
7
2
0
9
0
.
1
6
9
0
45
0
.
3
0
1
.
1
5
0
.
7
0
2
9
0
.
1
8
3
3
To
t
a
l
1
3
6
0
.
3
0
1
.
1
5
0
.
7
1
5
0
0
.
1
7
3
4
D
r
u
msti
c
k
s
C
a
l
i
b
r
a
t
i
o
n
92
0
.
3
0
1
.
8
4
1
.
0
6
2
4
0
.
3
4
4
8
Te
st
i
n
g
45
0
.
2
7
1
.
7
4
1
.
0
3
6
4
0
.
4
0
4
6
To
t
a
l
1
3
7
0
.
2
7
1
.
8
4
1
.
0
4
5
0
0
.
3
6
4
2
T
h
e
p
r
e
d
ictiv
e
ca
p
a
b
ilit
ies
o
f
ca
lib
r
atio
n
m
o
d
els
wer
e
ass
ess
ed
u
s
in
g
R
C
2
an
d
R
P
2
f
o
r
ca
li
b
r
atio
n
a
n
d
p
r
ed
ictio
n
,
r
esp
ec
tiv
ely
.
R
MS
E
C
an
d
R
MSE
P,
alo
n
g
with
r
atio
o
f
p
er
f
o
r
m
an
ce
to
d
e
v
iatio
n
(
R
PD
)
,
wer
e
also
u
s
ed
to
ev
alu
ate
th
e
m
o
d
els.
R
PD
is
ca
lcu
lated
b
y
d
iv
id
in
g
th
e
s
tan
d
ar
d
d
e
v
iatio
n
(
SD)
o
f
r
ef
e
r
en
ce
v
alu
e
s
f
r
o
m
th
e
p
r
e
d
ictio
n
s
et
b
y
th
e
R
MSE
P.
B
ec
au
s
e
i
t
lack
s
d
im
en
s
io
n
s
,
R
PD
is
b
ein
g
u
s
ed
m
o
r
e
o
f
te
n
f
o
r
q
u
ick
ly
ass
ess
in
g
a
ca
lib
r
atio
n
m
o
d
el
in
NI
R
s
p
ec
tr
o
s
co
p
y
.
R
PD
v
alu
es
o
v
er
3
a
r
e
s
ee
n
as
b
en
ef
icial
f
o
r
q
u
ality
co
n
tr
o
l
task
s
b
u
t
ar
e
ch
allen
g
in
g
t
o
ac
h
iev
e;
2
.
5
to
2
.
9
ar
e
co
n
s
id
er
ed
ac
ce
p
t
ab
le
f
o
r
s
cr
ee
n
i
n
g
;
2
.
0
to
2
.
4
ar
e
v
iewe
d
as
in
ad
e
q
u
ate
an
d
o
n
ly
s
u
itab
le
f
o
r
b
a
s
ic
s
cr
ee
n
in
g
,
wh
ile
v
alu
es
b
e
twee
n
1
.
5
an
d
2
ar
e
s
o
lely
f
o
r
in
d
icatin
g
q
u
ality
[
7
]
.
2
.
5
.
1
.
Art
if
icia
l neura
l net
wo
rk
T
h
e
r
esear
ch
u
tili
ze
d
a
th
r
ee
-
lay
er
f
ee
d
f
o
r
war
d
b
ac
k
p
r
o
p
a
g
atio
n
n
eu
r
al
n
etwo
r
k
with
th
e
L
ev
en
b
er
g
-
Ma
r
q
u
ar
d
t
alg
o
r
ith
m
,
in
co
r
p
o
r
atin
g
tan
-
s
ig
m
o
id
an
d
p
u
r
elin
tr
a
n
s
f
er
f
u
n
ctio
n
s
in
th
e
h
id
d
en
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
B
r
o
iler
mea
ts
ten
d
ern
ess
p
r
ed
ictio
n
u
s
in
g
N
I
R
s
p
ec
tr
o
s
co
p
y
a
g
a
in
s
t
n
o
n
-
lin
ea
r
…
(
R
a
s
h
id
a
h
Gh
a
z
a
li)
2719
o
u
tp
u
t
lay
er
s
,
co
r
r
esp
o
n
d
in
g
ly
.
I
n
th
e
PC
NN
m
o
d
el,
in
p
u
t
n
eu
r
o
n
s
wer
e
th
e
b
est
PC
s
co
r
es
f
r
o
m
PC
R
,
an
d
in
th
e
L
VNN
m
o
d
el,
in
p
u
t
n
eu
r
o
n
s
wer
e
th
e
b
est
L
V
s
co
r
es
f
r
o
m
PLS
r
eg
r
ess
io
n
.
T
h
e
o
u
tp
u
t
lay
er
co
n
s
is
ted
o
f
o
n
e
n
eu
r
o
n
t
h
at
r
ep
r
esen
te
d
th
e
p
r
ed
icted
s
h
ea
r
f
o
r
ce
(
SF
)
p
ar
am
eter
.
T
h
e
in
p
u
t
(
PC
s
o
r
L
Vs)
an
d
tar
g
e
t
(
m
ea
s
u
r
ed
SF
)
d
ata
wer
e
b
o
th
n
o
r
m
alize
d
to
a
r
an
g
e
o
f
-
1
to
+1
u
s
in
g
th
e
m
ap
m
in
m
ax
f
u
n
ctio
n
in
MA
T
L
A
B
[
3
8
]
,
an
d
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
p
ar
am
eter
s
we
r
e
s
av
ed
t
o
r
e
-
s
ca
le
th
e
p
r
e
d
icted
o
u
tp
u
ts
b
ac
k
to
th
eir
o
r
ig
in
al
s
ca
le.
T
h
e
b
ac
k
p
r
o
p
ag
atio
n
t
r
ain
in
g
al
g
o
r
ith
m
,
tr
ain
lm
,
was
u
tili
ze
d
alo
n
g
with
a
MCC
V
tech
n
iq
u
e
to
o
p
tim
ize
f
o
u
r
n
etwo
r
k
p
ar
am
e
ter
s
(
h
id
d
en
n
e
u
r
o
n
s
,
lear
n
in
g
r
ate,
m
o
m
en
tu
m
r
ate,
an
d
n
u
m
b
er
o
f
e
p
o
ch
s
)
o
n
th
e
ca
lib
r
atio
n
d
ata
s
et
[
3
9
]
,
s
p
lit
in
to
tr
ai
n
in
g
an
d
v
alid
atio
n
s
u
b
s
ets.
T
h
e
b
est
n
etwo
r
k
s
t
r
u
ctu
r
e
was
ch
o
s
en
b
y
lo
o
k
in
g
at
th
e
lo
west
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
o
n
th
e
v
alid
atio
n
s
u
b
s
et,
an
d
t
h
e
im
p
r
o
v
ed
n
etwo
r
k
was
s
u
b
s
eq
u
en
tly
tr
ain
e
d
u
s
in
g
t
h
e
co
m
p
lete
ca
lib
r
atio
n
d
ataset
an
d
test
ed
with
a
d
if
f
e
r
en
t te
s
tin
g
d
ataset.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
L
inea
r
mo
del
I
n
o
r
d
er
to
o
p
tim
ize
th
e
n
u
m
b
er
o
f
PC
s
an
d
L
Vs,
th
e
P
C
R
a
n
d
PLS m
o
d
els wa
s
ex
am
in
ed
u
s
in
g
PC
s
an
d
L
Vs
r
an
g
in
g
f
r
o
m
1
to
1
5
.
T
h
e
ch
a
n
g
es
o
f
R
MSE
C
V
an
d
R
MSE
C
in
d
icate
s
th
at
PC
R
ac
h
iev
ed
th
e
o
p
tim
al
p
er
f
o
r
m
an
ce
b
y
h
av
in
g
6
PC
s
an
d
1
0
PC
s
,
r
esp
ec
tiv
ely
.
B
o
th
m
o
d
els
co
m
p
r
o
m
is
ed
u
n
d
e
r
-
f
itti
n
g
a
n
d
o
v
er
-
f
itti
n
g
r
esu
lts
f
o
r
b
r
e
ast
m
ea
t
an
d
d
r
u
m
s
tic
k
s
.
T
h
e
R
MSE
C
V
o
f
PLS
m
o
d
els
r
ad
ically
d
ec
r
ea
s
ed
ap
p
r
o
ac
h
in
g
th
e
lo
west
er
r
o
r
at
3
L
Vs
an
d
5
L
Vs
f
o
r
b
r
ea
s
t
m
ea
t
an
d
d
r
u
m
s
tick
s
,
r
esp
ec
tiv
ely
.
T
h
e
o
p
tim
al
n
u
m
b
er
o
f
PC
s
an
d
L
Vs
o
b
t
ain
ed
was
ev
alu
ated
u
s
in
g
th
e
p
r
ed
ictio
n
s
et.
B
ased
o
n
t
h
e
p
r
ed
ictio
n
r
esu
lt
s
s
u
m
m
ar
is
ed
in
T
ab
le
4
,
th
e
P
L
S
m
o
d
el
ac
h
iev
e
d
b
etter
r
es
u
lts
th
an
PC
R
,
r
esu
ltin
g
a
f
ewe
r
n
u
m
b
e
r
o
f
L
Vs.
Fo
r
in
s
tan
ce
,
PLS
(
R
P
2
=0
.
4
9
5
9
,
R
MSE
P=0
.
2
8
8
0
)
f
o
r
d
r
u
m
s
tick
s
attain
ed
s
l
ig
h
tly
h
ig
h
er
p
er
f
o
r
m
an
ce
s
th
an
PC
R
(
R
P
2
=0
.
4
4
6
7
,
R
MSE
P=0
.
3
0
1
3
)
with
o
n
ly
5
L
Vs
o
v
er
1
0
PC
s
d
ata
s
e
t.
Ho
wev
er
,
th
e
ca
lib
r
atio
n
(
R
C
2
)
an
d
p
r
e
d
ictio
n
(
R
P
2
)
ac
c
u
r
ac
ie
s
f
r
o
m
b
o
th
PC
R
an
d
PLS m
o
d
els f
o
r
b
r
ea
s
t m
ea
t a
n
d
d
r
u
m
s
tick
s
ar
e
s
til
l
u
n
d
er
th
e
0
.
8
tar
g
et
ac
cu
r
ac
y
.
B
o
th
m
o
d
els
o
n
ly
m
an
ag
e
d
to
esti
m
ate
th
e
b
r
ea
s
t
m
ea
t
an
d
d
r
u
m
s
tick
s
at
th
e
p
r
ed
ictio
n
ac
c
u
r
ac
y
(
R
P
2
)
o
f
0
.
3
7
an
d
0
.
5
0
,
r
esp
ec
tiv
el
y
.
T
ab
le
4
.
Per
f
o
r
m
an
ce
o
f
lin
ea
r
an
d
n
o
n
-
lin
ea
r
m
o
d
els in
p
r
ed
ictin
g
s
h
ea
r
f
o
r
ce
v
alu
es o
n
b
r
ea
s
t m
ea
t a
n
d
d
r
u
m
s
tick
s
tr
aits
M
e
a
t
t
y
p
e
s
M
o
d
e
l
s
P
C
/
LV
I
n
p
u
t
n
o
d
e
s
P
a
r
a
me
t
e
r
s
R
C
2
R
M
S
E
C
R
P
2
R
M
S
EP
S
l
o
p
e
I
n
t
e
r
c
e
p
t
R
P
D
N
e
u
r
o
n
LR
MC
Ep
o
c
h
s
B
r
e
a
s
t
m
eat
P
C
R
6
0
.
3
7
9
6
0
.
1
3
2
4
0
.
3
6
5
0
0
.
1
4
5
0
0
.
4
1
0
.
4
2
1
.
2
6
P
LS
3
0
.
3
9
9
9
0
.
1
3
0
2
0
.
3
8
1
8
0
.
1
4
3
9
0
.
4
5
0
.
3
8
1
.
2
7
P
C
N
N
6
6
0
.
1
0
.
8
5
0
0
0
.
8
2
3
3
0
.
0
7
0
7
0
.
7
9
7
7
0
.
0
8
1
5
0
.
8
0
.
1
4
2
.
2
4
LV
N
N
3
9
0
.
9
0
.
4
4
0
0
0
.
8
4
2
5
0
.
0
6
6
7
0
.
8
2
0
1
0
.
0
7
6
9
0
.
8
2
0
.
1
3
2
.
3
8
D
r
u
m
st
i
c
k
s
P
C
R
10
0
.
4
5
0
2
0
.
2
5
4
3
0
.
4
4
6
7
0
.
3
0
1
3
0
.
4
3
0
.
5
6
1
.
3
4
P
LS
5
0
.
5
1
2
9
0
.
2
3
9
3
0
.
4
9
5
9
0
.
2
8
8
0
0
.
4
6
0
.
5
3
1
.
4
0
P
C
N
N
10
4
0
.
6
1
.
0
5
0
0
0
.
8
5
2
5
0
.
1
3
1
7
0
.
8
3
6
5
0
.
1
6
1
8
0
.
8
4
0
.
1
7
2
.
5
0
LV
N
N
5
6
0
.
3
0
.
8
3
0
0
0
.
8
8
1
3
0
.
1
1
8
2
0
.
8
6
0
6
0
.
1
4
9
4
0
.
8
6
0
.
1
5
2
.
7
1
3
.
2
.
No
nli
nea
r
m
o
dels
3
.
2
.
1
.
T
he
o
ptim
um
P
CNN
des
ig
n
I
n
s
tead
o
f
u
tili
zin
g
th
e
co
m
p
le
te
ab
s
o
r
b
a
n
ce
s
p
ec
tr
al
d
ata,
th
e
PC
NN
u
tili
ze
d
th
e
o
p
tim
al
P
C
s
s
co
r
es
d
er
iv
ed
f
r
o
m
PC
R
as
in
p
u
ts
f
o
r
ANN.
Fo
r
b
r
ea
s
t
m
ea
t,
th
e
b
est
n
u
m
b
er
o
f
in
p
u
t
n
o
d
es
is
6
,
wh
ile
f
o
r
d
r
u
m
s
tick
s
it is
1
0
.
T
h
e
q
u
an
ti
ty
o
f
h
i
d
d
en
n
eu
r
o
n
af
f
e
cts th
e
co
n
n
ec
tio
n
s
b
etwe
en
in
p
u
ts
an
d
o
u
t
p
u
ts
an
d
ca
n
ch
an
g
e
b
ased
o
n
th
e
p
a
r
ticu
lar
p
r
o
b
le
m
b
ein
g
r
esear
ch
e
d
.
U
s
in
g
an
ex
ce
s
s
iv
e
am
o
u
n
t
o
f
n
eu
r
o
n
s
in
t
h
e
ANN
ca
n
lead
to
o
v
er
f
itti
n
g
,
wh
e
r
e
th
e
m
o
d
el
m
em
o
r
izes
th
e
tr
ai
n
in
g
d
ata
in
s
tead
o
f
m
ak
in
g
a
cc
u
r
ate
p
r
ed
ictio
n
s
.
T
h
e
b
est
n
u
m
b
er
o
f
h
id
d
en
n
eu
r
o
n
s
f
o
r
b
r
ea
s
t
m
ea
t
an
d
d
r
u
m
s
tick
s
wer
e
f
o
u
n
d
to
b
e
6
an
d
4
,
r
esp
ec
tiv
ely
,
b
ased
o
n
th
e
s
m
allest M
SE
v
alu
e.
B
o
th
th
e
lear
n
in
g
r
ate
an
d
m
o
m
en
tu
m
r
ate
in
f
lu
e
n
ce
th
e
s
tab
ilit
y
an
d
co
n
v
er
g
e
n
ce
o
f
th
e
ANN
m
o
d
el.
Nev
er
t
h
eless
,
if
th
e
lea
r
n
in
g
an
d
m
o
m
en
tu
m
r
ates
ar
e
to
o
s
m
all,
it
will
r
esu
lt
in
a
s
l
u
g
g
is
h
co
n
v
er
g
i
n
g
p
r
o
ce
s
s
,
wh
er
ea
s
ex
ce
s
s
iv
ely
h
ig
h
v
alu
es
ca
n
ca
u
s
e
n
etwo
r
k
in
s
tab
ilit
y
an
d
tr
ain
in
g
d
iv
er
g
en
ce
.
I
n
th
is
r
esear
ch
,
th
e
lear
n
in
g
r
ate
an
d
m
o
m
en
tu
m
r
ate
wer
e
ad
j
u
s
te
d
with
in
th
e
r
an
g
e
o
f
0
.
1
to
0
.
9
.
T
h
e
b
est
lear
n
in
g
r
ate
is
0
.
1
f
o
r
b
r
ea
s
t
m
ea
t
an
d
0
.
6
f
o
r
d
r
u
m
s
tick
s
.
T
h
e
m
o
m
en
tu
m
r
ate'
s
im
p
ac
t
d
ec
r
ea
s
es
s
lo
wly
o
v
er
tim
e.
At
m
o
m
en
tu
m
lev
els
o
f
0
.
8
a
n
d
1
.
0
,
th
e
n
etwo
r
k
ac
h
iev
e
d
th
e
lo
west
MSE
f
o
r
b
r
ea
s
t
m
ea
t
an
d
d
r
u
m
s
tick
s
,
r
esp
ec
tiv
ely
.
T
h
e
am
o
u
n
t
o
f
ep
o
ch
s
o
r
tr
ain
in
g
c
y
cles
p
lay
s
a
v
ital
r
o
le
in
d
eter
m
in
in
g
th
e
ac
cu
r
ac
y
o
f
n
etwo
r
k
m
o
d
els.
B
o
th
th
e
b
r
e
ast
m
ea
t
an
d
d
r
u
m
s
tick
h
ad
th
e
lo
west
MSE
at
5
0
0
iter
atio
n
s
.
On
ce
all
n
etwo
r
k
p
ar
am
eter
s
wer
e
estab
lis
h
ed
,
th
e
PC
N
N
co
u
ld
f
o
r
ec
ast
t
h
e
s
am
p
les.
T
ab
le
4
s
u
m
m
a
r
izes
th
e
o
p
tim
ized
p
ar
am
eter
s
'
to
p
o
lo
g
y
i
n
co
n
s
tr
u
ctin
g
th
e
PC
NN
m
o
d
el
an
d
t
h
e
r
eg
r
ess
io
n
o
u
tco
m
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
7
1
3
-
2
7
2
3
2720
3
.
2
.
2
.
T
he
o
ptim
um
la
t
ent
v
a
ria
ble neura
l net
wo
rk
d
esig
n
I
n
ad
d
itio
n
to
u
tili
zin
g
th
e
PC
s
o
b
tain
ed
f
r
o
m
PC
R
,
th
e
o
p
tim
al
L
Vs
d
er
iv
ed
f
r
o
m
PL
S
h
av
e
also
b
ee
n
u
s
ed
as
in
p
u
ts
f
o
r
ANN.
T
h
e
p
r
o
ce
s
s
f
o
r
cr
ea
tin
g
t
h
e
b
est
L
VNN
m
o
d
el
clo
s
ely
r
esem
b
led
th
at
o
f
th
e
PC
NN
m
o
d
el.
Fo
r
b
r
ea
s
t
m
e
at,
th
e
id
ea
l
n
u
m
b
er
o
f
L
Vs
as
i
n
p
u
t
n
o
d
es
is
3
,
wh
ile
f
o
r
d
r
u
m
s
tick
s
it
is
5
.
T
h
e
b
est
n
u
m
b
er
o
f
h
i
d
d
en
n
e
u
r
o
n
s
f
o
r
m
in
im
izin
g
MSE
in
b
r
ea
s
t
m
ea
t
was
9
,
wh
er
ea
s
f
o
r
d
r
u
m
s
tick
s
it
was
6
.
Acc
o
r
d
in
g
to
th
e
m
in
im
u
m
MSE
v
alu
e,
th
e
b
est
lear
n
in
g
r
ate
an
d
m
o
m
e
n
tu
m
r
ate
f
o
r
b
r
ea
s
t
m
ea
t
ar
e
0.
9
an
d
0
.
4
,
an
d
f
o
r
d
r
u
m
s
tick
s
ar
e
0
.
9
a
n
d
0
.
3
,
r
esp
ec
tiv
e
ly
.
Me
an
wh
ile,
th
e
id
ea
l
n
u
m
b
er
o
f
e
p
o
ch
s
f
o
r
b
r
ea
s
t
m
ea
t
an
d
d
r
u
m
s
tick
s
h
a
s
b
ee
n
s
et
at
4
0
0
an
d
3
0
0
.
T
h
e
o
p
tim
ized
p
ar
am
eter
s
t
o
p
o
lo
g
y
f
o
r
b
u
ild
in
g
th
e
L
VNN
m
o
d
el
an
d
t
h
e
r
eg
r
ess
io
n
o
u
tc
o
m
e
ar
e
o
u
tl
in
ed
i
n
T
a
b
le
4
.
3
.
3
.
P
re
dict
io
n
o
f
bro
iler
brea
s
t
m
ea
t
a
nd
drum
s
t
ick
s
s
hea
r
f
o
rc
e
v
a
lue
T
ab
le
4
s
u
m
m
ar
izes
t
h
e
n
o
n
-
lin
ea
r
p
r
ed
ictio
n
o
u
tco
m
es
f
o
r
b
r
ea
s
t
m
ea
t
an
d
d
r
u
m
s
tick
s
,
lis
tin
g
th
e
in
ter
ce
p
t,
r
eg
r
ess
io
n
eq
u
atio
n
s
lo
p
e,
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
,
as
well
as
th
e
c
alib
r
atio
n
(
R
C
2
)
an
d
p
r
ed
ictio
n
(
R
P
2
)
co
ef
f
icien
ts
o
f
d
eter
m
in
atio
n
f
o
r
all
m
o
d
els.
T
h
e
in
ter
ce
p
t
an
d
s
lo
p
e
i
n
d
icate
th
e
lev
el
o
f
lin
ea
r
ity
b
etwe
en
s
h
ea
r
f
o
r
ce
v
alu
es
an
d
NI
R
s
p
ec
tr
o
s
co
p
y
co
n
ce
n
t
r
atio
n
v
al
u
es.
A
m
o
d
el'
s
lin
ea
r
ity
is
a
d
ep
en
d
a
b
le
p
r
e
d
icto
r
o
f
its
q
u
ality
o
f
f
it b
ec
a
u
s
e
it p
r
o
v
i
d
es p
r
ec
is
e
q
u
an
titativ
e
an
aly
s
is
.
W
h
ile
PLS
m
ad
e
ad
v
an
ce
m
e
n
ts
in
co
m
p
ar
is
o
n
to
PC
R
,
b
o
t
h
m
eth
o
d
s
s
h
o
we
d
in
s
u
f
f
icien
t
ac
cu
r
ac
y
in
p
r
ed
ictin
g
b
r
ea
s
t
m
ea
t
(
0
.
3
7
to
0
.
4
0
)
an
d
d
r
u
m
s
tick
(
0
.
4
5
to
0
.
5
1
)
q
u
alities
.
Desp
ite
ac
h
iev
in
g
g
o
o
d
r
esu
lts
with
o
p
tim
al
PC
s
an
d
L
Vs,
th
e
lo
w
p
r
ec
is
io
n
,
R
2
,
a
n
d
h
ig
h
R
MSE
in
b
o
th
ca
lib
r
atio
n
an
d
test
d
atasets
s
h
o
wed
th
at
th
e
p
r
e
d
ictiv
e
p
o
wer
o
f
PC
R
an
d
PLS
was
lim
ited
,
as
e
v
id
en
c
ed
b
y
t
h
e
u
n
e
q
u
al
d
is
tr
ib
u
tio
n
o
f
eq
u
ality
lin
e
test
s
am
p
les.
T
h
is
im
p
lies
th
at
th
e
m
o
d
el
m
a
y
h
av
e
b
ee
n
ad
ju
s
ted
to
ac
c
o
u
n
t
f
o
r
th
e
in
h
e
r
en
t
n
o
is
e
o
r
er
r
o
r
in
th
e
d
ata,
o
r
th
er
e
co
u
ld
h
av
e
b
ee
n
n
o
n
-
lin
ea
r
elem
en
ts
in
th
e
s
p
ec
tr
u
m
-
s
h
ea
r
f
o
r
ce
r
elatio
n
s
h
ip
th
at
wer
e
n
o
t
ac
cu
r
ately
ca
p
tu
r
e
d
b
y
th
e
lin
e
ar
m
o
d
els.
B
ased
o
n
p
r
ev
io
u
s
r
esear
ch
,
lin
ea
r
m
o
d
els
s
ee
m
to
p
r
o
v
i
d
e
in
ad
e
q
u
ate
ev
alu
atio
n
o
f
m
ea
t
ten
d
er
n
ess
u
s
in
g
NI
R
s
p
ec
tr
al
d
at
a.
Var
y
in
g
p
ar
ticle
s
izes
in
m
ea
t
r
esu
lt
in
lig
h
t
-
s
ca
tter
in
g
ef
f
ec
t,
ca
u
s
i
n
g
n
o
n
lin
ea
r
ity
in
in
f
o
r
m
atio
n
.
Ad
d
itio
n
ally
,
th
e
R
PD
v
alu
e
r
an
g
in
g
f
r
o
m
1
.
2
6
to
1
.
4
0
o
b
tain
ed
f
r
o
m
th
e
lin
ea
r
m
o
d
els
is
d
ee
m
ed
in
s
u
f
f
icien
t
f
o
r
th
e
u
s
e
o
f
VI
S
-
SW
NI
R
s
p
ec
tr
o
s
co
p
y
in
f
o
r
ec
asti
n
g
s
h
ea
r
f
o
r
ce
v
al
u
es,
as
R
PD
v
alu
es
<2
.
0
ar
e
n
o
t
ad
v
is
ed
f
o
r
q
u
ality
co
n
tr
o
l o
r
g
r
a
d
in
g
a
p
p
licatio
n
s
.
T
h
e
L
VNN
an
d
PC
NN
m
o
d
e
ls
ac
h
iev
ed
p
r
ed
ictio
n
ac
cu
r
a
cies
ab
o
v
e
0
.
8
,
ex
ce
p
t
f
o
r
b
r
ea
s
t
m
ea
t
PC
NN
p
r
ed
ictio
n
(
R
P
2
=0
.
8
0
)
.
No
n
lin
ea
r
m
o
d
els
o
u
t
p
er
f
o
r
m
ed
lin
ea
r
m
o
d
els
in
h
an
d
lin
g
co
m
p
le
x
n
o
n
lin
ea
r
in
f
o
r
m
atio
n
with
in
s
p
ec
tr
al
d
ata.
Usi
n
g
PC
s
an
d
L
Vs
h
elp
s
to
d
ec
r
ea
s
e
th
e
to
tal
am
o
u
n
t
o
f
in
p
u
t
n
o
d
es
in
ANN
an
d
elim
in
ates
i
s
s
u
es
th
at
ca
n
o
cc
u
r
wh
en
u
s
in
g
PC
R
,
PLS
,
o
r
ANN
s
ep
ar
ately
.
T
h
e
L
VNN
an
d
PC
NN
g
o
t
r
i
d
o
f
r
ep
etitiv
e,
p
ar
allel
in
f
o
r
m
atio
n
f
o
u
n
d
in
s
p
ec
tr
al
d
ata,
d
ec
r
ea
s
ed
d
ata
s
to
r
a
g
e
an
d
tr
ain
in
g
tim
e
r
eq
u
ir
ed
to
r
ea
c
h
co
n
v
er
g
en
ce
,
an
d
en
h
an
ce
d
th
e
ANN
m
o
d
el'
s
g
en
er
aliza
tio
n
ca
p
ab
ilit
y
.
Fu
r
th
er
m
o
r
e
,
PC
NN
an
d
L
VNN
m
o
d
els
ac
h
iev
ed
a
p
r
ed
ictio
n
ac
cu
r
ac
y
th
at
was
ar
o
u
n
d
7
0
%
h
ig
h
er
th
an
th
eir
lin
ea
r
co
u
n
ter
p
a
r
ts
,
PC
R
an
d
PLS.
T
h
e
R
PD
v
alu
es
f
o
r
P
C
N
N
an
d
L
VNN
in
b
r
ea
s
t
m
e
at
an
d
d
r
u
m
s
tick
s
,
r
an
g
in
g
f
r
o
m
2
.
2
4
to
2
.
7
1
,
i
n
d
icate
th
at
VI
S
-
SW
NI
R
s
p
ec
tr
o
s
co
p
y
co
m
b
i
n
ed
with
n
o
n
lin
ea
r
m
o
d
els
is
s
u
itab
le
f
o
r
s
cr
ee
n
in
g
p
u
r
p
o
s
es
[
7
]
.
T
h
is
is
an
ticip
ated
b
ec
au
s
e
ANN
r
esu
lts
w
ill
o
u
tp
er
f
o
r
m
lin
ea
r
m
o
d
els
f
o
r
h
ig
h
l
y
n
o
n
lin
ea
r
d
atasets
.
T
h
e
L
V
-
NN
h
ad
th
e
h
ig
h
est
R
MSE
P
an
d
p
r
ed
ictio
n
ac
cu
r
ac
y
,
R
P
2
,
am
o
n
g
p
r
ed
ictiv
e
m
o
d
els,
with
PC
NN,
PLS,
an
d
PC
R
tr
ailin
g
f
o
r
b
r
ea
s
t
m
ea
t
a
n
d
d
r
u
m
s
tick
s
.
T
h
e
L
VNN
m
o
d
el
ac
h
iev
ed
a
co
e
f
f
icien
t
o
f
d
et
er
m
in
atio
n
g
r
ea
ter
th
an
0
.
8
f
o
r
b
o
th
ca
lib
r
atio
n
an
d
test
in
g
in
b
r
ea
s
t
m
ea
t
(
R
C
2
=0
.
8
4
2
5
,
R
P
2
=
0
.
8
2
0
1
)
a
n
d
d
r
u
m
s
tick
s
(
R
C
2
=0
.
8
8
1
3
,
R
P
2
=0
.
8
6
0
6
)
,
d
em
o
n
s
tr
atin
g
ex
ce
l
len
t p
er
f
o
r
m
an
ce
.
4.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
h
as
ef
f
ec
tiv
el
y
co
n
f
ir
m
ed
th
e
tr
u
s
two
r
th
i
n
ess
o
f
af
f
o
r
d
a
b
le
an
d
p
o
r
t
ab
le
NI
R
s
p
ec
tr
o
s
co
p
y
with
a
s
h
o
r
t r
an
g
e
an
d
lo
w
in
ten
s
ity
.
T
h
is
was
d
o
n
e
b
y
cr
ea
tin
g
a
n
o
n
lin
ea
r
p
r
ed
ictio
n
s
y
s
tem
to
p
r
ed
ict
th
e
ten
d
e
r
n
ess
o
f
r
aw
b
r
o
iler
b
r
ea
s
t
m
ea
t
a
n
d
d
r
u
m
s
tick
s
with
o
u
t
th
e
n
ee
d
f
o
r
in
v
asiv
e
m
eth
o
d
s
.
T
h
e
L
VNN
ap
p
ea
r
s
to
h
av
e
a
s
h
o
r
ter
tr
ain
i
n
g
tim
e
th
an
PC
N
N
d
u
e
t
o
h
a
v
in
g
f
ewe
r
i
n
p
u
t
n
o
d
es,
wh
ile
also
o
u
tp
er
f
o
r
m
in
g
PC
NN.
T
h
es
e
f
in
d
i
n
g
s
s
u
g
g
est
th
at
L
V
NN
is
s
u
p
er
io
r
to
PC
NN
i
n
ter
m
s
o
f
s
av
i
n
g
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
an
d
r
ed
u
cin
g
tr
ai
n
in
g
tim
e,
as
well
as
in
h
an
d
lin
g
n
o
n
lin
ea
r
ities
,
r
ed
u
n
d
an
cies,
an
d
co
llin
ea
r
ity
in
in
p
u
t
s
p
ec
tr
al
d
ata.
B
ased
o
n
o
v
er
all
p
e
r
f
o
r
m
an
ce
,
th
e
m
o
d
els
ca
n
b
e
r
a
n
k
ed
in
ascen
d
in
g
o
r
d
er
as
PC
R
,
PLS,
PC
N
N,
an
d
L
VNN.
Alter
n
ativ
ely
,
th
e
s
ec
o
n
d
-
o
r
d
er
SG
d
er
iv
ativ
e
p
r
o
v
id
e
d
v
alu
a
b
le
in
s
ig
h
ts
b
y
r
em
o
v
in
g
b
aselin
e
s
h
if
t
an
d
s
lo
p
e
ef
f
ec
ts
,
en
h
an
cin
g
s
p
ec
tr
al
r
eso
l
u
tio
n
,
an
d
d
is
tin
g
u
is
h
in
g
o
v
er
lap
p
i
n
g
p
ea
k
s
f
o
r
clea
r
er
an
d
m
o
r
e
d
is
tin
ct
p
ea
k
s
co
m
p
ar
ed
to
ze
r
o
-
o
r
d
er
o
r
f
i
r
s
t
-
o
r
d
er
SG
d
er
iv
ativ
e
p
r
ep
r
o
ce
s
s
in
g
.
T
h
e
r
esu
lts
s
h
o
w
th
at
o
n
ly
th
e
wav
elen
g
th
f
r
o
m
6
6
2
to
7
0
0
n
m
in
th
e
v
is
ib
le
r
eg
io
n
g
av
e
ac
cu
r
ate
d
ata
f
o
r
ass
ess
in
g
d
r
u
m
s
tick
s
s
h
ea
r
f
o
r
ce
.
T
h
er
ef
o
r
e,
th
e
d
r
u
m
s
tick
s
ar
e
p
r
ed
ict
ed
u
s
in
g
th
e
v
is
ib
le
an
d
SW
NI
R
r
eg
io
n
s
,
wh
ich
h
av
e
wav
elen
g
th
s
b
etwe
en
6
6
2
an
d
1
,
0
0
5
n
m
.
Nev
e
r
th
eless
,
p
r
ed
icto
r
s
f
o
r
th
e
b
r
ea
s
t m
ea
t sam
p
les i
n
clu
d
e
th
e
SW
NI
R
r
eg
io
n
with
wav
elen
g
th
b
etwe
en
7
0
0
an
d
1
,
0
0
5
n
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
B
r
o
iler
mea
ts
ten
d
ern
ess
p
r
ed
ictio
n
u
s
in
g
N
I
R
s
p
ec
tr
o
s
co
p
y
a
g
a
in
s
t
n
o
n
-
lin
ea
r
…
(
R
a
s
h
id
a
h
Gh
a
z
a
li)
2721
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
wis
h
to
th
an
k
th
e
Un
iv
er
s
iti
T
ec
h
n
o
lo
g
i
Ma
lay
s
ia
(
UT
M)
f
o
r
f
in
an
cin
g
th
i
s
r
esear
ch
with
g
r
an
t
v
o
te
n
o
.
2
2
H0
1
.
T
h
e
s
taf
f
o
f
Un
iv
er
s
ity
L
a
b
o
r
ato
r
y
Ma
n
ag
em
e
n
t
Un
it
(
UPMU)
d
eser
v
es
a
s
p
ec
ial
th
an
k
s
f
o
r
th
eir
g
e
n
er
o
u
s
ass
is
tan
ce
in
ass
ess
in
g
lab
o
r
ato
r
y
e
q
u
ip
m
en
t.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was f
u
n
d
e
d
b
y
Un
iv
er
s
iti T
ek
n
o
lo
g
i M
ala
y
s
ia
(
UT
M)
u
n
d
er
Vo
te
No
.
(
2
2
H0
1
)
.
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
R
ash
id
ah
Gh
az
ali
✓
✓
✓
✓
✓
✓
✓
Her
lin
a
Ab
d
u
l Rah
im
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Sy
ah
id
ah
Nu
r
a
n
i
Z
u
lk
if
li
✓
✓
✓
✓
✓
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
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
all
in
d
iv
id
u
als in
c
lu
d
ed
in
t
h
is
s
tu
d
y
.
DATA AV
AI
L
AB
I
L
I
T
Y
Data
av
ailab
ilit
y
is
n
o
t
ap
p
li
ca
b
le
to
th
is
p
ap
er
as
n
o
n
e
w
d
ata
wer
e
cr
ea
ted
o
r
an
aly
ze
d
in
th
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
I
.
A
b
d
u
r
o
f
i
,
M
.
M
.
I
smai
l
,
H
.
A
.
W
.
K
a
m
a
l
,
a
n
d
B
.
H
.
G
a
b
d
o
,
“
Ec
o
n
o
m
i
c
a
n
a
l
y
si
s
o
f
b
r
o
i
l
e
r
p
r
o
d
u
c
t
i
o
n
i
n
P
e
n
i
n
su
l
a
r
M
a
l
a
y
s
i
a
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
Fo
o
d
R
e
se
a
rc
h
J
o
u
r
n
a
l
,
v
o
l
.
2
4
,
n
o
.
4
,
p
p
.
1
3
8
7
–
1
3
9
2
,
2
0
1
7
.
[
2
]
M
.
P
e
t
r
a
c
c
i
,
S
.
M
u
d
a
l
a
l
,
A
.
B
o
n
f
i
g
l
i
o
,
a
n
d
C
.
C
a
v
a
n
i
,
“
O
c
c
u
r
r
e
n
c
e
o
f
w
h
i
t
e
st
r
i
p
i
n
g
u
n
d
e
r
c
o
mm
e
r
c
i
a
l
c
o
n
d
i
t
i
o
n
s
a
n
d
i
t
s
i
m
p
a
c
t
o
n
b
r
e
a
st
m
e
a
t
q
u
a
l
i
t
y
i
n
b
r
o
i
l
e
r
c
h
i
c
k
e
n
s
,
”
P
o
u
l
t
ry
S
c
i
e
n
c
e
,
v
o
l
.
9
2
,
n
o
.
6
,
p
p
.
1
6
7
0
–
1
6
7
5
,
J
u
n
.
2
0
1
3
,
d
o
i
:
1
0
.
3
3
8
2
/
p
s.
2
0
1
2
-
0
3
0
0
1
.
[
3
]
R
.
R
.
G
a
n
g
i
d
i
a
n
d
A
.
P
r
o
c
t
o
r
,
“
C
h
a
p
t
e
r
8
-
me
a
t
a
n
d
m
e
a
t
p
r
o
d
u
c
t
s,
”
i
n
I
n
f
r
a
re
d
S
p
e
c
t
r
o
s
c
o
p
y
f
o
r
F
o
o
d
Q
u
a
l
i
t
y
A
n
a
l
y
si
s
a
n
d
C
o
n
t
r
o
l
,
1
st
e
d
.
,
N
e
w
Y
o
r
k
,
U
n
i
t
e
d
S
t
a
t
e
s
:
A
c
a
d
e
m
i
c
P
r
e
ss
,
2
0
0
9
,
p
p
.
1
8
1
–
2
1
4
.
[
4
]
Y
.
C
h
e
n
e
t
a
l
.
,
“
D
i
f
f
e
r
e
n
c
e
s
i
n
p
h
y
s
i
c
o
c
h
e
m
i
c
a
l
a
n
d
n
u
t
r
i
t
i
o
n
a
l
p
r
o
p
e
r
t
i
e
s
o
f
b
r
e
a
st
a
n
d
t
h
i
g
h
m
e
a
t
f
r
o
m
c
r
o
ssb
r
e
d
c
h
i
c
k
e
n
s,
c
o
mm
e
r
c
i
a
l
b
r
o
i
l
e
r
s,
a
n
d
sp
e
n
t
h
e
n
s,”
As
i
a
n
-
A
u
st
r
a
l
a
s
i
a
n
J
o
u
rn
a
l
o
f
A
n
i
m
a
l
S
c
i
e
n
c
e
s
,
v
o
l
.
2
9
,
n
o
.
6
,
p
p
.
8
5
5
–
8
6
4
,
2
0
1
6
,
d
o
i
:
1
0
.
5
7
1
3
/
a
j
a
s.
1
5
.
0
8
4
0.
[
5
]
N
.
P
r
i
e
t
o
,
R
.
R
o
e
h
e
,
P
.
La
v
í
n
,
G
.
B
a
t
t
e
n
,
a
n
d
S
.
A
n
d
r
é
s,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
n
e
a
r
i
n
f
r
a
r
e
d
r
e
f
l
e
c
t
a
n
c
e
s
p
e
c
t
r
o
sc
o
p
y
t
o
p
r
e
d
i
c
t
m
e
a
t
a
n
d
m
e
a
t
p
r
o
d
u
c
t
s
q
u
a
l
i
t
y
:
a
r
e
v
i
e
w
,
”
Me
a
t
S
c
i
e
n
c
e
,
v
o
l
.
8
3
,
n
o
.
2
,
p
p
.
1
7
5
–
1
8
6
,
2
0
0
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
e
a
t
sc
i
.
2
0
0
9
.
0
4
.
0
1
6
.
[
6
]
M
.
P
r
e
v
o
l
n
i
k
,
M
.
Č
a
n
d
e
k
-
P
o
t
o
k
a
r
,
a
n
d
D
.
Š
k
o
r
j
a
n
c
,
“
A
b
i
l
i
t
y
o
f
N
I
R
sp
e
c
t
r
o
s
c
o
p
y
t
o
p
r
e
d
i
c
t
me
a
t
c
h
e
m
i
c
a
l
c
o
m
p
o
si
t
i
o
n
a
n
d
q
u
a
l
i
t
y
-
a
r
e
v
i
e
w
,
”
C
z
e
c
h
J
o
u
r
n
a
l
o
f
An
i
m
a
l
S
c
i
e
n
c
e
,
v
o
l
.
4
9
,
n
o
.
1
1
,
p
p
.
5
0
0
–
5
1
0
,
2
0
0
4
,
d
o
i
:
1
0
.
1
7
2
2
1
/
4
3
3
7
-
c
j
a
s.
[
7
]
N
.
P
r
i
e
t
o
,
O
.
P
a
w
l
u
c
z
y
k
,
M
.
E.
R
.
D
u
g
a
n
,
a
n
d
J.
L
.
A
a
l
h
u
s,
“
A
r
e
v
i
e
w
o
f
t
h
e
p
r
i
n
c
i
p
l
e
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
o
f
n
e
a
r
-
i
n
f
r
a
r
e
d
sp
e
c
t
r
o
sc
o
p
y
t
o
c
h
a
r
a
c
t
e
r
i
z
e
mea
t
,
f
a
t
,
a
n
d
me
a
t
p
r
o
d
u
c
t
s
,
”
Ap
p
l
i
e
d
S
p
e
c
t
r
o
sc
o
p
y
,
v
o
l
.
7
1
,
n
o
.
7
,
p
p
.
1
4
0
3
–
1
4
2
6
,
Ju
l
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
7
7
/
0
0
0
3
7
0
2
8
1
7
7
0
9
2
9
9
.
[
8
]
M
.
B
.
R
o
mí
a
a
n
d
M
.
A
.
B
e
r
n
à
r
d
e
z
,
“
M
u
l
t
i
v
a
r
i
a
t
e
c
a
l
i
b
r
a
t
i
o
n
f
o
r
q
u
a
n
t
i
t
a
t
i
v
e
a
n
a
l
y
s
i
s,
”
I
n
f
r
a
re
d
S
p
e
c
t
ro
s
c
o
p
y
f
o
r
Fo
o
d
Q
u
a
l
i
t
y
An
a
l
y
si
s
a
n
d
C
o
n
t
r
o
l
,
p
p
.
5
1
–
8
2
,
2
0
0
8
,
d
o
i
:
1
0
.
1
0
1
6
/
B
9
7
8
-
0
-
12
-
3
7
4
1
3
6
-
3
.
0
0
0
0
3
-
1.
[
9
]
F
.
L
i
u
e
t
a
l
.
,
“
D
e
t
e
r
mi
n
a
t
i
o
n
o
f
a
c
e
t
o
l
a
c
t
a
t
e
s
y
n
t
h
a
s
e
a
c
t
i
v
i
t
y
a
n
d
p
r
o
t
e
i
n
c
o
n
t
e
n
t
o
f
o
i
l
se
e
d
r
a
p
e
(
Br
a
ssi
c
a
n
a
p
u
s
L
.
)
l
e
a
v
e
s
u
s
i
n
g
v
i
s
i
b
l
e
/
n
e
a
r
-
i
n
f
r
a
r
e
d
s
p
e
c
t
r
o
sc
o
p
y
,
”
An
a
l
y
t
i
c
a
C
h
i
m
i
c
a
Ac
t
a
,
v
o
l
.
6
2
9
,
n
o
.
1
–
2
,
p
p
.
5
6
–
6
5
,
N
o
v
.
2
0
0
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
c
a
.
2
0
0
8
.
0
9
.
0
2
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
7
1
3
-
2
7
2
3
2722
[
1
0
]
L.
S
.
W
a
t
a
n
a
b
e
,
Y
.
R
.
B
o
v
o
l
e
n
t
a
,
V
.
R
.
A
.
Ju
n
i
o
r
,
D
.
F
.
B
a
r
b
i
n
,
T.
B
.
M
a
d
e
i
r
a
,
a
n
d
S
.
L
.
N
i
x
d
o
r
f
,
“
I
n
v
e
s
t
i
g
a
t
i
o
n
o
f
N
I
R
s
p
e
c
t
r
a
p
r
e
-
p
r
o
c
e
ssi
n
g
me
t
h
o
d
s
c
o
m
b
i
n
e
d
w
i
t
h
m
u
l
t
i
v
a
r
i
a
t
e
r
e
g
r
e
ss
i
o
n
f
o
r
d
e
t
e
r
mi
n
a
t
i
o
n
o
f
m
o
i
s
t
u
r
e
i
n
p
o
w
d
e
r
e
d
i
n
d
u
st
r
i
a
l
e
g
g
,
”
Ac
t
a
S
c
i
e
n
t
i
a
r
u
m
-
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
4
0
,
2
0
1
8
,
d
o
i
:
1
0
.
4
0
2
5
/
a
c
t
a
s
c
i
t
e
c
h
n
o
l
.
v
4
0
i
1
.
3
0
1
3
3
.
[
1
1
]
J.
H
.
Q
u
e
t
a
l
.
,
“
A
p
p
l
i
c
a
t
i
o
n
s
o
f
n
e
a
r
-
i
n
f
r
a
r
e
d
sp
e
c
t
r
o
s
c
o
p
y
i
n
f
o
o
d
safe
t
y
e
v
a
l
u
a
t
i
o
n
a
n
d
c
o
n
t
r
o
l
:
a
r
e
v
i
e
w
o
f
r
e
c
e
n
t
r
e
s
e
a
r
c
h
a
d
v
a
n
c
e
s,”
C
ri
t
i
c
a
l
R
e
v
i
e
w
s
i
n
Fo
o
d
S
c
i
e
n
c
e
a
n
d
N
u
t
r
i
t
i
o
n
,
v
o
l
.
5
5
,
n
o
.
1
3
,
p
p
.
1
9
3
9
–
1
9
5
4
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
8
0
/
1
0
4
0
8
3
9
8
.
2
0
1
3
.
8
7
1
6
9
3
.
[
1
2
]
B
.
M
.
N
i
c
o
l
a
ï
e
t
a
l
.
,
“
N
o
n
d
e
st
r
u
c
t
i
v
e
mea
s
u
r
e
m
e
n
t
o
f
f
r
u
i
t
a
n
d
v
e
g
e
t
a
b
l
e
q
u
a
l
i
t
y
b
y
mea
n
s
o
f
N
I
R
sp
e
c
t
r
o
s
c
o
p
y
:
a
r
e
v
i
e
w
,
”
Po
st
h
a
rv
e
st
Bi
o
l
o
g
y
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
4
6
,
n
o
.
2
,
p
p
.
9
9
–
118
,
2
0
0
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
o
st
h
a
r
v
b
i
o
.
2
0
0
7
.
0
6
.
0
2
4
.
[
1
3
]
M
.
d
.
N
.
B
o
n
i
n
e
t
a
l
.
,
“
P
r
e
d
i
c
t
i
n
g
t
h
e
sh
e
a
r
v
a
l
u
e
a
n
d
i
n
t
r
a
m
u
sc
u
l
a
r
f
a
t
i
n
mea
t
f
r
o
m
N
e
l
l
o
r
e
c
a
t
t
l
e
u
s
i
n
g
V
i
s
-
N
I
R
sp
e
c
t
r
o
s
c
o
p
y
,
”
Me
a
t
S
c
i
e
n
c
e
,
v
o
l
.
1
6
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
a
t
s
c
i
.
2
0
2
0
.
1
0
8
0
7
7
.
[
1
4
]
G
.
K
r
e
p
p
e
r
e
t
a
l
.
,
“
D
e
t
e
r
m
i
n
a
t
i
o
n
o
f
f
a
t
c
o
n
t
e
n
t
i
n
c
h
i
c
k
e
n
h
a
m
b
u
r
g
e
r
s
u
si
n
g
N
I
R
sp
e
c
t
r
o
s
c
o
p
y
a
n
d
t
h
e
s
u
c
c
e
ssi
v
e
p
r
o
j
e
c
t
i
o
n
s
a
l
g
o
r
i
t
h
m
f
o
r
i
n
t
e
r
v
a
l
s
e
l
e
c
t
i
o
n
i
n
P
LS
r
e
g
r
e
ssi
o
n
(
i
S
P
A
-
P
LS)
,
”
S
p
e
c
t
r
o
c
h
i
m
i
c
a
A
c
t
a
-
Pa
r
t
A:
Mo
l
e
c
u
l
a
r
a
n
d
Bi
o
m
o
l
e
c
u
l
a
r
S
p
e
c
t
ro
s
c
o
p
y
,
v
o
l
.
1
8
9
,
p
p
.
3
0
0
–
3
0
6
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
saa
.
2
0
1
7
.
0
8
.
0
4
6
.
[
1
5
]
Y
.
T.
Li
a
o
,
Y
.
X
.
F
a
n
,
a
n
d
F
.
C
h
e
n
g
,
“
O
n
-
l
i
n
e
p
r
e
d
i
c
t
i
o
n
o
f
f
r
e
s
h
p
o
r
k
q
u
a
l
i
t
y
u
si
n
g
v
i
s
i
b
l
e
/
n
e
a
r
-
i
n
f
r
a
r
e
d
r
e
f
l
e
c
t
a
n
c
e
sp
e
c
t
r
o
sc
o
p
y
,
”
M
e
a
t
S
c
i
e
n
c
e
,
v
o
l
.
8
6
,
n
o
.
4
,
p
p
.
9
0
1
–
9
0
7
,
2
0
1
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
a
t
s
c
i
.
2
0
1
0
.
0
7
.
0
1
1
.
[
1
6
]
M
.
D
.
M
a
r
c
h
i
,
M
.
P
e
n
a
s
a
,
M
.
B
a
t
t
a
g
i
n
,
E.
Z
a
n
e
t
t
i
,
C
.
P
u
l
i
c
i
,
a
n
d
M
.
C
a
ssan
d
r
o
,
“
F
e
a
s
i
b
i
l
i
t
y
o
f
t
h
e
d
i
r
e
c
t
a
p
p
l
i
c
a
t
i
o
n
o
f
n
e
a
r
-
i
n
f
r
a
r
e
d
r
e
f
l
e
c
t
a
n
c
e
s
p
e
c
t
r
o
sc
o
p
y
o
n
i
n
t
a
c
t
c
h
i
c
k
e
n
b
r
e
a
st
s
t
o
p
r
e
d
i
c
t
m
e
a
t
c
o
l
o
r
a
n
d
p
h
y
s
i
c
a
l
t
r
a
i
t
s
,
”
Po
u
l
t
ry
S
c
i
e
n
c
e
,
v
o
l
.
9
0
,
n
o
.
7
,
p
p
.
1
5
9
4
–
1
5
9
9
,
2
0
1
1
,
d
o
i
:
1
0
.
3
3
8
2
/
p
s
.
2
0
1
0
-
0
1
2
3
9
.
[
1
7
]
D
.
F
.
B
a
r
b
i
n
e
t
a
l
.
,
“
P
r
e
d
i
c
t
i
o
n
o
f
c
h
i
c
k
e
n
q
u
a
l
i
t
y
a
t
t
r
i
b
u
t
e
s
b
y
n
e
a
r
i
n
f
r
a
r
e
d
sp
e
c
t
r
o
s
c
o
p
y
,
”
F
o
o
d
C
h
e
m
i
st
ry
,
v
o
l
.
1
6
8
,
p
p
.
5
5
4
–
5
6
0
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
o
o
d
c
h
e
m
.
2
0
1
4
.
0
7
.
1
0
1
.
[
1
8
]
L.
J
.
J
a
n
i
k
,
D
.
C
o
z
z
o
l
i
n
o
,
R
.
D
a
m
b
e
r
g
s,
W
.
C
y
n
k
a
r
,
a
n
d
M
.
G
i
s
h
e
n
,
“
Th
e
p
r
e
d
i
c
t
i
o
n
o
f
t
o
t
a
l
a
n
t
h
o
c
y
a
n
i
n
c
o
n
c
e
n
t
r
a
t
i
o
n
i
n
r
e
d
-
g
r
a
p
e
h
o
m
o
g
e
n
a
t
e
s
u
si
n
g
v
i
si
b
l
e
-
n
e
a
r
-
i
n
f
r
a
r
e
d
sp
e
c
t
r
o
sc
o
p
y
a
n
d
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
An
a
l
y
t
i
c
a
C
h
i
m
i
c
a
Ac
t
a
,
v
o
l
.
5
9
4
,
n
o
.
1
,
p
p
.
1
0
7
–
1
1
8
,
2
0
0
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
c
a
.
2
0
0
7
.
0
5
.
0
1
9
.
[
1
9
]
J.
M
.
B
a
l
a
g
e
,
M
.
R
.
M
a
z
o
n
,
D
.
S
.
A
n
t
o
n
e
l
o
,
K
.
E
.
Z
.
N
u
b
i
a
t
o
,
D
.
J
.
B
r
i
g
i
d
a
,
a
n
d
L
.
S
i
l
v
a
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
v
i
s
i
b
l
e
/
n
e
a
r
i
n
f
r
a
r
e
d
sp
e
c
t
r
o
c
o
p
y
t
o
b
e
e
f
l
o
n
g
i
ss
i
m
u
s
t
e
n
d
e
r
n
e
ss
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
a
s
e
d
o
n
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
i
n
6
1
st
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
g
ress
o
f
Me
a
t
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
2
0
1
5
,
n
o
.
2
3
-
2
8
t
h
A
u
g
u
st
.
[
2
0
]
R
.
M
.
B
a
l
a
b
i
n
,
R
.
Z.
S
a
f
i
e
v
a
,
a
n
d
E
.
I
.
Lo
ma
k
i
n
a
,
“
C
o
mp
a
r
i
s
o
n
o
f
l
i
n
e
a
r
a
n
d
n
o
n
l
i
n
e
a
r
c
a
l
i
b
r
a
t
i
o
n
mo
d
e
l
s
b
a
s
e
d
o
n
n
e
a
r
i
n
f
r
a
r
e
d
(
N
I
R
)
sp
e
c
t
r
o
s
c
o
p
y
d
a
t
a
f
o
r
g
a
s
o
l
i
n
e
p
r
o
p
e
r
t
i
e
s p
r
e
d
i
c
t
i
o
n
,
”
C
h
e
m
o
m
e
t
r
i
c
s a
n
d
I
n
t
e
l
l
i
g
e
n
t
L
a
b
o
ra
t
o
ry
S
y
st
e
m
s
,
v
o
l
.
8
8
,
n
o
.
2
,
p
p
.
1
8
3
–
1
8
8
,
2
0
0
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
h
e
m
o
l
a
b
.
2
0
0
7
.
0
4
.
0
0
6
.
[
2
1
]
M
.
N
.
E.
M
o
h
d
I
d
r
u
s
a
n
d
K
.
S
.
C
h
i
a
,
“
A
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
p
a
r
t
i
a
l
l
e
a
s
t
s
q
u
a
r
e
i
n
p
r
e
d
i
c
t
i
n
g
b
l
o
o
d
h
e
m
o
g
l
o
b
i
n
u
si
n
g
ne
ar
-
i
n
f
r
a
r
e
d
sp
e
c
t
r
u
m
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
6
,
n
o
.
2
,
p
p
.
7
0
1
–
7
0
8
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
1
6
.
i
2
.
p
p
7
0
1
-
7
0
8
.
[
2
2
]
S
.
Li
,
L.
Li
,
R
.
M
i
l
l
i
k
e
n
,
a
n
d
K
.
S
o
n
g
,
“
H
y
b
r
i
d
i
z
a
t
i
o
n
o
f
p
a
r
t
i
a
l
l
e
a
st
s
q
u
a
r
e
s
a
n
d
n
e
u
r
a
l
n
e
t
w
o
r
k
m
o
d
e
l
s
f
o
r
q
u
a
n
t
i
f
y
i
n
g
l
u
n
a
r
su
r
f
a
c
e
mi
n
e
r
a
l
s
,
”
I
c
a
r
u
s
,
v
o
l
.
2
2
1
,
n
o
.
1
,
p
p
.
2
0
8
–
2
2
5
,
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
c
a
r
u
s.
2
0
1
2
.
0
7
.
0
2
3
.
[
2
3
]
W
.
N
.
A
r
i
f
i
n
a
n
d
W
.
M
.
Z
a
h
i
r
u
d
d
i
n
,
“
S
a
mp
l
e
si
z
e
c
a
l
c
u
l
a
t
i
o
n
i
n
a
n
i
mal
st
u
d
i
e
s
u
s
i
n
g
r
e
s
o
u
r
c
e
e
q
u
a
t
i
o
n
a
p
p
r
o
a
c
h
,
”
M
a
l
a
y
s
i
a
n
J
o
u
rn
a
l
o
f
Me
d
i
c
a
l
S
c
i
e
n
c
e
s
,
v
o
l
.
2
4
,
n
o
.
5
,
p
p
.
1
0
1
–
1
0
5
,
2
0
1
7
,
d
o
i
:
1
0
.
2
1
3
1
5
/
mj
ms2
0
1
7
.
2
4
.
5
.
1
1
.
[
2
4
]
J.
C
h
a
r
a
n
a
n
d
N
.
K
a
n
t
h
a
r
i
a
,
“
H
o
w
t
o
c
a
l
c
u
l
a
t
e
sam
p
l
e
s
i
z
e
i
n
a
n
i
ma
l
s
t
u
d
i
e
s?
,
”
J
o
u
rn
a
l
o
f
P
h
a
rm
a
c
o
l
o
g
y
a
n
d
Ph
a
rm
a
c
o
t
h
e
r
a
p
e
u
t
i
c
s
,
v
o
l
.
4
,
n
o
.
4
,
p
p
.
3
0
3
–
3
0
6
,
2
0
1
3
,
d
o
i
:
1
0
.
4
1
0
3
/
0
9
7
6
-
5
0
0
X
.
1
1
9
7
2
6
.
[
2
5
]
D
e
p
a
r
t
me
n
t
o
f
I
sl
a
m
i
c
D
e
v
e
l
o
p
m
e
n
t
M
a
l
a
y
si
a
,
“
M
a
l
a
y
s
i
a
n
p
r
o
t
o
c
o
l
f
o
r
t
h
e
h
a
l
a
l
m
e
a
t
a
n
d
p
o
u
l
t
r
y
p
r
o
d
u
c
t
i
o
n
s,
”
M
y
e
h
a
l
a
l
,
2
0
1
1
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
m
y
e
h
a
l
a
l
.
h
a
l
a
l
.
g
o
v
.
m
y
/
p
o
r
t
a
l
-
h
a
l
a
l
/
v
1
/
i
ma
g
e
s/
p
d
f
/
p
r
o
t
o
c
o
l
%
2
0
h
a
l
a
l
%
2
0
me
a
t
%2
0
p
o
u
l
t
r
y
.
p
d
f
[
2
6
]
L.
C
.
C
a
v
i
t
t
,
G
.
W
.
Y
o
u
m
,
J.
F
.
M
e
u
l
l
e
n
e
t
,
C
.
M
.
O
w
e
n
s,
a
n
d
R
.
X
i
o
n
g
,
“
P
r
e
d
i
c
t
i
o
n
o
f
p
o
u
l
t
r
y
mea
t
t
e
n
d
e
r
n
e
ss
u
si
n
g
r
a
z
o
r
b
l
a
d
e
sh
e
a
r
,
A
l
l
o
-
K
r
a
m
e
r
sh
e
a
r
,
a
n
d
sarc
o
mere
l
e
n
g
t
h
,
”
J
o
u
r
n
a
l
o
f
Fo
o
d
S
c
i
e
n
c
e
,
v
o
l
.
6
9
,
n
o
.
1
,
2
0
0
4
,
d
o
i
:
1
0
.
1
1
1
1
/
j
.
1
3
6
5
-
2
6
2
1
.
2
0
0
4
.
t
b
1
7
8
7
9
.
x
.
[
2
7
]
M
.
S
.
S
a
l
w
a
n
i
,
A
.
Q
.
S
a
z
i
l
i
,
L
.
Zu
l
k
i
f
l
i
,
Z
.
N
i
z
a
m,
a
n
d
W
.
Z
.
Ed
h
a
m
,
“
Ef
f
e
c
t
s
o
f
h
e
a
d
-
o
n
l
y
e
l
e
c
t
r
i
c
a
l
s
t
u
n
n
i
n
g
o
n
t
h
e
p
h
y
si
c
o
-
c
h
e
mi
c
a
l
c
h
a
r
a
c
t
e
r
i
st
i
c
s
a
n
d
d
e
s
mi
n
d
e
g
r
a
d
a
t
i
o
n
o
f
b
r
o
i
l
e
r
b
r
e
a
st
m
u
sc
l
e
s
a
t
d
i
f
f
e
r
e
n
t
t
i
me
p
o
st
m
o
r
t
e
m,”
J
o
u
r
n
a
l
o
f
A
n
i
m
a
l
a
n
d
Ve
t
e
ri
n
a
r
y
A
d
v
a
n
c
e
s
,
v
o
l
.
1
1
,
n
o
.
1
4
,
p
p
.
2
4
0
9
–
2
4
1
6
,
2
0
1
2
,
d
o
i
:
1
0
.
3
9
2
3
/
j
a
v
a
a
.
2
0
1
2
.
2
4
0
9
.
2
4
1
6
.
[
2
8
]
N
.
R
.
L
a
m
b
e
,
E.
A
.
N
a
v
a
j
a
s,
L
.
B
ü
n
g
e
r
,
A
.
V
.
F
i
sh
e
r
,
R
.
R
o
e
h
e
,
a
n
d
G
.
S
i
mm
,
“
P
r
e
d
i
c
t
i
o
n
o
f
l
a
mb
c
a
r
c
a
ss
c
o
m
p
o
s
i
t
i
o
n
a
n
d
m
e
a
t
q
u
a
l
i
t
y
u
si
n
g
c
o
m
b
i
n
a
t
i
o
n
s
o
f
p
o
st
-
m
o
r
t
e
m
me
a
su
r
e
me
n
t
s
,
”
M
e
a
t
S
c
i
e
n
c
e
,
v
o
l
.
8
1
,
n
o
.
4
,
p
p
.
7
1
1
–
7
1
9
,
2
0
0
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
e
a
t
sc
i
.
2
0
0
8
.
1
0
.
0
2
5
.
[
2
9
]
O
c
e
a
n
O
p
t
i
c
s
I
n
c
.
,
“
N
o
n
-
i
n
v
a
s
i
v
e
r
e
f
l
e
c
t
i
o
n
m
e
a
s
u
r
e
m
e
n
t
s
o
f
t
h
e
s
k
i
n
,
a
s
s
e
s
s
i
n
g
s
a
m
p
l
i
n
g
d
e
p
t
h
b
y
u
s
i
n
g
s
k
i
n
s
u
r
r
o
g
a
t
e
s
o
v
e
r
v
i
e
w
,
”
K
T
e
c
h
K
f
t
,
p
p
.
1
-
7
,
2
0
1
2
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
r
k
t
e
c
h
.
h
u
/
d
o
k
u
m
e
n
t
a
c
i
o
k
/
O
c
e
a
n
O
p
t
i
c
s
/
A
p
p
l
i
c
a
t
i
o
n
_
n
o
t
e
/
s
k
i
n
_
k
p
.
p
d
f
[
3
0
]
K
.
S
.
C
h
i
a
,
H
.
A
.
R
a
h
i
m,
a
n
d
R
.
A
.
R
a
h
i
m
,
“
E
v
a
l
u
a
t
i
o
n
o
f
c
o
mm
o
n
p
r
e
-
p
r
o
c
e
ss
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
v
i
s
i
b
l
e
(
V
I
S
)
a
n
d
s
h
o
r
t
w
a
v
e
n
e
a
r
i
n
f
r
a
r
e
d
(
S
W
N
I
R
)
sp
e
c
t
r
o
sc
o
p
y
i
n
s
o
l
u
b
l
e
s
o
l
i
d
s
c
o
n
t
e
n
t
(
S
S
C
)
a
ssessme
n
t
,
”
Bi
o
s
y
st
e
m
s
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
1
5
,
n
o
.
1
,
p
p
.
8
2
–
8
8
,
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
i
o
s
y
st
e
ms
e
n
g
.
2
0
1
3
.
0
2
.
0
0
8
.
[
3
1
]
J.
C
a
f
f
e
r
k
y
e
t
a
l
.
,
“
I
n
v
e
s
t
i
g
a
t
i
n
g
t
h
e
u
se
o
f
v
i
s
i
b
l
e
a
n
d
n
e
a
r
i
n
f
r
a
r
e
d
s
p
e
c
t
r
o
sco
p
y
t
o
p
r
e
d
i
c
t
se
n
so
r
y
a
n
d
t
e
x
t
u
r
e
a
t
t
r
i
b
u
t
e
s
o
f
b
e
e
f
M.
l
o
n
g
i
ss
i
m
u
s t
h
o
ra
c
i
s
e
t
l
u
m
b
o
r
u
m
,
”
M
e
a
t
S
c
i
e
n
c
e
,
v
o
l
.
1
5
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
a
t
s
c
i
.
2
0
1
9
.
1
0
7
9
1
5
.
[
3
2
]
M
.
Č
l
u
p
e
k
,
P
.
M
a
t
ě
j
k
a
,
a
n
d
K
.
V
o
l
k
a
,
“
N
o
i
s
e
r
e
d
u
c
t
i
o
n
i
n
R
a
ma
n
s
p
e
c
t
r
a
:
F
i
n
i
t
e
i
m
p
u
l
se
r
e
s
p
o
n
s
e
f
i
l
t
r
a
t
i
o
n
v
e
r
s
u
s
S
a
v
i
t
z
k
y
-
G
o
l
a
y
s
mo
o
t
h
i
n
g
,
”
J
o
u
rn
a
l
o
f
Ra
m
a
n
S
p
e
c
t
ro
s
c
o
p
y
,
v
o
l
.
3
8
,
n
o
.
9
,
p
p
.
1
1
7
4
–
1
1
7
9
,
2
0
0
7
,
d
o
i
:
1
0
.
1
0
0
2
/
j
r
s.
1
7
4
7
.
[
3
3
]
J.
J
a
c
o
b
,
“
C
h
a
p
t
e
r
3
-
C
h
i
c
k
e
n
a
n
a
t
o
my
a
n
d
p
h
y
si
o
l
o
g
y
,
”
i
n
A
v
i
a
n
Mu
s
c
u
l
a
r
S
y
st
e
m
,
2
0
1
4
,
p
p
.
1
–
2
4
,
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
y
u
mp
u
.
c
o
m/
e
n
/
d
o
c
u
me
n
t
/
v
i
e
w
/
1
1
2
8
2
2
5
1
/
c
h
a
p
t
e
r
-
3
-
c
h
i
c
k
e
n
-
a
n
a
t
o
m
y
-
a
n
d
-
p
h
y
s
i
o
l
o
g
y
.
[
3
4
]
J.
Ja
c
o
b
a
n
d
T.
P
e
sca
t
o
r
e
,
“
A
v
i
a
n
m
u
scu
l
a
r
s
y
st
e
m,
”
C
o
o
p
e
r
a
t
i
v
e
Ex
t
e
n
s
i
o
n
S
e
r
v
i
c
e
,
p
p
.
1
–
6
,
2
0
1
5
.
[
3
5
]
Y
.
L
i
u
,
B
.
G
.
L
y
o
n
,
W
.
R
.
W
i
n
d
h
a
m
,
C
.
E.
R
e
a
l
i
n
i
,
T.
D
.
D
.
P
r
i
n
g
l
e
,
a
n
d
S
.
D
u
c
k
e
t
t
,
“
P
r
e
d
i
c
t
i
o
n
o
f
c
o
l
o
r
,
t
e
x
t
u
r
e
,
a
n
d
s
e
n
s
o
r
y
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
o
f
b
e
e
f
s
t
e
a
k
s
b
y
v
i
si
b
l
e
a
n
d
n
e
a
r
i
n
f
r
a
r
e
d
r
e
f
l
e
c
t
a
n
c
e
s
p
e
c
t
r
o
s
c
o
p
y
.
A
f
e
a
si
b
i
l
i
t
y
s
t
u
d
y
,
”
M
e
a
t
S
c
i
e
n
c
e
,
v
o
l
.
6
5
,
n
o
.
3
,
p
p
.
1
1
0
7
–
1
1
1
5
,
2
0
0
3
,
d
o
i
:
1
0
.
1
0
1
6
/
S
0
3
0
9
-
1
7
4
0
(
0
2
)
0
0
3
2
8
-
5.
[
3
6
]
L.
W
.
M
a
ma
n
i
-
L
i
n
a
r
e
s,
C
.
G
a
l
l
o
,
a
n
d
D
.
A
l
o
m
a
r
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
c
a
t
t
l
e
,
l
l
a
ma
a
n
d
h
o
r
se
m
e
a
t
b
y
n
e
a
r
i
n
f
r
a
r
e
d
r
e
f
l
e
c
t
a
n
c
e
o
r
t
r
a
n
sf
l
e
c
t
a
n
c
e
s
p
e
c
t
r
o
sc
o
p
y
,
”
Me
a
t
S
c
i
e
n
c
e
,
v
o
l
.
9
0
,
n
o
.
2
,
p
p
.
3
7
8
–
3
8
5
,
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
e
a
t
sc
i
.
2
0
1
1
.
0
8
.
0
0
2
.
[
3
7
]
R
.
R
i
o
v
a
n
t
o
,
M
.
D
.
M
a
r
c
h
i
,
M
.
C
a
ss
a
n
d
r
o
,
a
n
d
M
.
P
e
n
a
sa
,
“
U
s
e
o
f
n
e
a
r
i
n
f
r
a
r
e
d
t
r
a
n
s
mi
t
t
a
n
c
e
s
p
e
c
t
r
o
sc
o
p
y
t
o
p
r
e
d
i
c
t
f
a
t
t
y
a
c
i
d
c
o
m
p
o
si
t
i
o
n
o
f
c
h
i
c
k
e
n
mea
t
,
”
F
o
o
d
C
h
e
m
i
st
ry
,
v
o
l
.
1
3
4
,
n
o
.
4
,
p
p
.
2
4
5
9
–
2
4
6
4
,
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
o
o
d
c
h
e
m
.
2
0
1
2
.
0
4
.
0
3
8
.
[
3
8
]
L.
J
.
J
a
n
i
k
,
S
.
T.
F
o
r
r
e
s
t
e
r
,
a
n
d
A
.
R
a
w
so
n
,
“
Th
e
p
r
e
d
i
c
t
i
o
n
o
f
s
o
i
l
c
h
e
mi
c
a
l
a
n
d
p
h
y
s
i
c
a
l
p
r
o
p
e
r
t
i
e
s
f
r
o
m
mi
d
-
i
n
f
r
a
r
e
d
sp
e
c
t
r
o
sc
o
p
y
a
n
d
c
o
mb
i
n
e
d
p
a
r
t
i
a
l
l
e
a
s
t
-
sq
u
a
r
e
s
r
e
g
r
e
ssi
o
n
a
n
d
n
e
u
r
a
l
n
e
t
w
o
r
k
s
(
P
LS
-
N
N
)
a
n
a
l
y
si
s,
”
C
h
e
m
o
m
e
t
r
i
c
s
a
n
d
I
n
t
e
l
l
i
g
e
n
t
L
a
b
o
r
a
t
o
r
y
S
y
st
e
m
s
,
v
o
l
.
9
7
,
n
o
.
2
,
p
p
.
1
7
9
–
1
8
8
,
2
0
0
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
h
e
m
o
l
a
b
.
2
0
0
9
.
0
4
.
0
0
5
.
[
3
9
]
A
.
M
.
M
o
u
a
z
e
n
,
B
.
K
u
a
n
g
,
J.
D
.
B
a
e
r
d
e
ma
e
k
e
r
,
a
n
d
H
.
R
a
mo
n
,
“
C
o
mp
a
r
i
so
n
a
m
o
n
g
p
r
i
n
c
i
p
a
l
c
o
mp
o
n
e
n
t
,
p
a
r
t
i
a
l
l
e
a
s
t
s
q
u
a
r
e
s
a
n
d
b
a
c
k
p
r
o
p
a
g
a
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
a
l
y
ses
f
o
r
a
c
c
u
r
a
c
y
o
f
m
e
a
s
u
r
e
men
t
o
f
s
e
l
e
c
t
e
d
s
o
i
l
p
r
o
p
e
r
t
i
e
s
w
i
t
h
v
i
si
b
l
e
a
n
d
n
e
a
r
i
n
f
r
a
r
e
d
s
p
e
c
t
r
o
sc
o
p
y
,
”
G
e
o
d
e
rm
a
,
v
o
l
.
1
5
8
,
n
o
.
1
–
2
,
p
p
.
2
3
–
3
1
,
2
0
1
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
e
o
d
e
r
m
a
.
2
0
1
0
.
0
3
.
0
0
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.