I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
15
,
No
.
2
,
A
p
r
il
2
0
2
6
,
p
p
.
1
2
4
7
~
1
2
6
0
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
2
.
p
p
1
2
4
7
-
1
2
6
0
1247
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
G
ene
tic
a
lg
o
rith
m
-
ba
sed chic
ken
ma
nure weigh
t
pr
ediction
sy
stem develo
pm
ent
Rida
H
ud
a
y
a
1
,
Septr
ia
nd
i W
ira
y
o
g
a
2
,
M
o
ec
ha
mm
a
d Sa
r
o
s
a
2
,
M
uh
a
m
m
a
d Yus
uf
3
,
Arm
a
nd
a
Dwi
P
ra
y
ug
o
4
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
P
o
l
i
t
e
k
n
i
k
N
e
g
e
r
i
B
a
n
d
u
n
g
,
B
a
n
d
u
n
g
,
I
n
d
o
n
e
s
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
P
o
l
i
t
e
k
n
i
k
N
e
g
e
r
i
M
a
l
a
n
g
,
M
a
l
a
n
g
,
I
n
d
o
n
e
s
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
h
e
m
i
st
r
y
,
F
a
c
u
l
t
y
o
f
M
a
t
h
e
m
a
t
i
c
s
a
n
d
N
a
t
u
r
a
l
S
c
i
e
n
c
e
s,
U
n
i
v
e
r
s
i
t
a
s
P
a
d
j
a
d
j
a
r
a
n
,
S
u
m
e
d
a
n
g
,
I
n
d
o
n
e
s
i
a
4
D
e
p
a
r
t
me
n
t
o
f
B
i
o
m
e
d
i
c
a
l
S
c
i
e
n
c
e
s
,
F
a
c
u
l
t
y
o
f
M
e
d
i
c
i
n
e
,
U
n
i
v
e
r
si
t
a
s
P
a
d
j
a
d
j
a
r
a
n
,
S
u
m
e
d
a
n
g
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
21
,
2
0
2
4
R
ev
is
ed
J
an
7
,
2
0
2
6
Acc
ep
ted
J
an
25
,
2
0
2
6
Th
is r
e
se
a
rc
h
p
re
se
n
ts d
e
sig
n
a
n
d
imp
lem
e
n
tatio
n
o
f
i
n
tern
e
t
o
f
th
i
n
g
s (Io
T)
-
b
a
se
d
m
o
n
it
o
rin
g
a
n
d
p
re
d
ictiv
e
sy
ste
m
fo
r
e
v
a
lu
a
ti
n
g
c
h
ick
e
n
m
a
n
u
re
we
ig
h
t
a
n
d
e
n
v
iro
n
m
e
n
tal
c
o
n
d
it
io
n
s
in
p
o
u
lt
r
y
h
o
u
si
n
g
.
Th
e
p
ro
p
o
se
d
sy
ste
m
in
teg
ra
tes
M
Q
-
1
3
7
se
n
so
r
fo
r
a
m
m
o
n
ia
d
e
tec
ti
o
n
,
DH
T2
2
se
n
so
r
fo
r
tem
p
e
ra
tu
re
a
n
d
h
u
m
i
d
it
y
m
e
a
su
re
m
e
n
t,
a
n
d
lo
a
d
c
e
ll
m
o
d
u
les
f
o
r
m
a
n
u
r
e
we
ig
h
t
m
o
n
it
o
ri
n
g
.
All
se
n
so
r
d
a
ta
a
re
tran
sm
it
ted
in
re
a
l
ti
m
e
to
c
lo
u
d
p
latfo
rm
,
e
n
a
b
li
n
g
c
o
n
ti
n
u
o
u
s
e
n
v
iro
n
m
e
n
tal
a
ss
e
ss
m
e
n
t.
A
3
0
-
d
a
y
e
x
p
e
rime
n
tal
stu
d
y
wa
s
c
o
n
d
u
c
ted
u
sin
g
two
c
o
n
t
ro
ll
e
d
c
h
ic
k
e
n
d
r
u
m
m
o
d
e
ls,
e
a
c
h
c
o
n
t
a
i
n
in
g
1
5
b
ro
il
e
r
c
h
ick
e
n
s
a
n
d
p
ro
v
id
e
d
wit
h
d
iff
e
re
n
t
fe
e
d
ty
p
e
s
t
o
o
b
se
rv
e
v
a
riatio
n
s
i
n
m
a
n
u
re
p
r
o
d
u
c
ti
o
n
a
n
d
a
ir
q
u
a
l
it
y
.
S
e
n
s
o
r
c
a
li
b
ra
ti
o
n
re
su
lt
s
i
n
d
ica
te
h
i
g
h
a
c
c
u
ra
c
y
,
with
a
v
e
ra
g
e
e
rro
r
o
f
0
.
3
1
%
fo
r
a
m
m
o
n
ia
re
a
d
in
g
s
a
n
d
0
.
1
0
%
fo
r
m
a
n
u
re
we
ig
h
t
m
e
a
su
re
m
e
n
t.
Ex
p
e
rime
n
tal
fi
n
d
i
n
g
s
s
h
o
w
t
h
a
t
fe
e
d
ty
p
e
A
g
e
n
e
ra
tes
lo
we
r
m
a
n
u
re
we
ig
h
t,
re
d
u
c
e
d
a
m
m
o
n
ia
c
o
n
c
e
n
tratio
n
,
a
n
d
m
o
re
sta
b
le
tem
p
e
ra
tu
re
c
o
n
d
i
ti
o
n
s
c
o
m
p
a
re
d
to
fe
e
d
ty
p
e
B,
su
g
g
e
stin
g
imp
r
o
v
e
d
fe
e
d
e
fficie
n
c
y
a
n
d
b
e
tt
e
r
o
v
e
ra
ll
c
h
ick
e
n
h
e
a
lt
h
.
A
ge
n
e
ti
c
a
lg
o
ri
th
m
(G
A)
wa
s
e
m
p
lo
y
e
d
to
o
p
ti
m
ize
re
g
re
ss
io
n
m
o
d
e
l
p
re
d
ictin
g
m
a
n
u
re
we
i
g
h
t
u
si
n
g
a
m
m
o
n
ia
c
o
n
c
e
n
tratio
n
a
n
d
tem
p
e
ra
tu
re
a
s
in
p
u
t
fe
a
tu
re
s.
Th
e
G
A
-
o
p
ti
m
i
z
e
d
m
o
d
e
l
a
c
h
iev
e
d
stro
n
g
p
re
d
icti
v
e
p
e
r
fo
rm
a
n
c
e
,
with
r
o
o
t
m
e
a
n
sq
u
a
re
e
rro
r
(
RM
S
E
)
o
f
0
.
3
5
8
g
a
n
d
c
o
e
fficie
n
t
o
f
d
e
term
in
a
ti
o
n
(
R
2
)
v
a
lu
e
o
f
0
.
9
9
2
.
T
h
e
re
su
lt
s
d
e
m
o
n
stra
te
th
a
t
p
ro
p
o
se
d
sy
ste
m
p
ro
v
id
e
s
re
li
a
b
le,
sc
a
lab
le,
a
n
d
d
a
ta
-
d
riv
e
n
so
l
u
ti
o
n
f
o
r
sm
a
rt
p
o
u
lt
ry
m
o
n
i
to
ri
n
g
a
n
d
e
a
rl
y
h
e
a
lt
h
d
e
tec
ti
o
n
.
K
ey
w
o
r
d
s
:
E
n
v
ir
o
n
m
en
tal
s
en
s
in
g
Gen
etic
alg
o
r
ith
m
I
n
ter
n
et
o
f
th
in
g
s
Ma
n
u
r
e
weig
h
t
p
r
ed
ictio
n
MQ
-
1
3
7
s
en
s
o
r
Po
u
ltry
m
o
n
ito
r
in
g
Sm
ar
t f
ar
m
in
g
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
:
Sep
tr
ian
d
i Wi
r
ay
o
g
a
Dep
ar
tm
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
,
Po
litek
n
ik
Neg
er
i M
a
lan
g
Ma
lan
g
,
E
ast J
av
a,
I
n
d
o
n
esia
E
m
ail:
y
o
g
a.
s
ep
tr
ian
d
i@
p
o
lin
em
a.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
I
n
m
o
d
e
r
n
an
im
al
h
u
s
b
an
d
r
y
,
m
ain
tain
in
g
ch
ick
e
n
h
ea
lth
is
ess
en
tia
l
f
o
r
ac
h
iev
in
g
ef
f
icien
t
an
d
s
u
cc
ess
f
u
l
p
r
o
d
u
ctio
n
.
Hea
lth
y
ch
ick
en
s
g
r
o
w
o
p
tim
ally
an
d
p
r
o
d
u
ce
h
ig
h
-
q
u
ality
m
ea
t
an
d
eg
g
s
,
r
e
d
u
cin
g
co
s
ts
r
elate
d
to
d
is
ea
s
e
m
an
ag
em
en
t
an
d
tr
ea
tm
e
n
t.
T
h
er
ef
o
r
e,
r
e
g
u
lar
an
d
tim
ely
h
e
alth
m
o
n
ito
r
in
g
is
cr
u
cial.
Ho
wev
er
,
s
m
all
to
m
e
d
iu
m
-
s
ca
le
f
ar
m
s
o
f
ten
r
ely
o
n
m
an
u
al
m
o
n
ito
r
in
g
,
wh
ich
i
n
cr
ea
s
es
th
e
r
is
k
o
f
d
elay
ed
d
etec
tio
n
o
f
h
ea
lth
p
r
o
b
lem
s
.
T
h
is
h
ig
h
lig
h
ts
th
e
n
ee
d
f
o
r
a
n
au
to
m
ated
s
y
s
tem
ca
p
ab
le
o
f
m
o
n
ito
r
in
g
liv
esto
ck
co
n
d
itio
n
s
ac
cu
r
ately
an
d
q
u
ic
k
ly
[
1
]
–
[
6
]
.
On
e
im
p
o
r
tan
t
b
u
t
o
f
ten
o
v
e
r
lo
o
k
ed
p
ar
am
eter
is
th
e
weig
h
t
o
f
ch
ic
k
en
f
ec
es.
Fece
s
weig
h
t
ca
n
s
er
v
e
as
a
s
ig
n
if
ican
t
in
d
icat
o
r
o
f
d
ig
esti
v
e
h
ea
lth
.
A
n
o
ti
ce
ab
le
in
cr
ea
s
e
o
r
d
ec
r
ea
s
e
m
ay
s
ig
n
al
d
ig
esti
v
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.
15
,
No
.
2
,
Ap
r
il
20
26
:
1
2
4
7
-
1
2
6
0
1248
d
is
o
r
d
er
s
o
r
o
t
h
er
h
ea
lth
is
s
u
es
[
7
]
–
[
1
1
]
.
Feed
co
n
s
u
m
p
tio
n
is
an
o
th
er
k
ey
in
d
icato
r
clo
s
ely
r
elate
d
to
g
r
o
wth
.
E
f
f
icien
t
f
ee
d
in
tak
e
s
u
p
p
o
r
ts
o
p
tim
al
d
ev
elo
p
m
e
n
t,
wh
ile
r
ed
u
ce
d
co
n
s
u
m
p
tio
n
m
a
y
in
d
icate
ea
r
ly
s
ig
n
s
o
f
illn
ess
o
r
s
tr
ess
[
1
2
]
,
[
1
3
]
.
T
h
u
s
,
m
o
n
ito
r
in
g
b
o
th
f
ec
es
weig
h
t
an
d
f
ee
d
co
n
s
u
m
p
tio
n
i
s
v
ital
f
o
r
ef
f
ec
tiv
e
p
o
u
ltry
h
ea
lth
m
an
a
g
e
m
en
t.
R
ec
en
t
ad
v
an
ce
m
en
ts
in
th
e
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
h
av
e
l
ed
to
its
ad
o
p
tio
n
in
v
ar
io
u
s
in
d
u
s
tr
ial
s
ec
to
r
s
,
in
clu
d
in
g
an
im
al
h
u
s
b
an
d
r
y
.
I
o
T
en
a
b
les
au
to
m
ate
d
m
o
n
it
o
r
in
g
th
r
o
u
g
h
in
ter
n
et
-
co
n
n
ec
ted
s
en
s
o
r
s
,
allo
win
g
r
ea
l
-
tim
e
d
ata
c
o
llectio
n
[
1
4
]
–
[
1
8
]
.
Usi
n
g
I
o
T
,
d
at
a
o
n
f
ec
es
weig
h
t
an
d
f
ee
d
c
o
n
s
u
m
p
tio
n
ca
n
b
e
co
n
tin
u
o
u
s
ly
g
ath
er
e
d
an
d
a
n
aly
ze
d
,
p
r
o
v
id
in
g
v
alu
a
b
le
in
s
ig
h
ts
f
o
r
f
ar
m
m
an
ag
e
m
en
t.
T
h
is
tech
n
o
lo
g
y
also
allo
ws
f
ar
m
er
s
to
m
o
n
ito
r
ch
ick
en
co
n
d
itio
n
s
r
em
o
tely
an
d
d
etec
t
h
ea
lth
is
s
u
es
ea
r
l
y
,
en
ab
lin
g
tim
ely
in
ter
v
en
tio
n
s
[
1
9
]
–
[
2
2
]
.
Ma
ch
in
e
lear
n
in
g
(
ML
)
alg
o
r
ith
m
s
f
u
r
th
er
en
h
an
ce
th
e
an
al
y
s
is
o
f
I
o
T
s
en
s
o
r
d
ata.
B
y
lear
n
in
g
p
atter
n
s
f
r
o
m
f
ec
es
weig
h
t
an
d
f
ee
d
c
o
n
s
u
m
p
t
io
n
,
th
ese
alg
o
r
ith
m
s
ca
n
p
r
e
d
ict
ch
ick
en
h
ea
lth
s
tatu
s
with
g
r
ea
ter
ac
cu
r
ac
y
[
2
3
]
–
[
2
7
]
.
I
r
r
eg
u
lar
p
atter
n
s
m
ay
in
d
icate
in
f
ec
tio
n
s
o
r
u
n
s
u
itab
le
en
v
ir
o
n
m
en
ta
l
co
n
d
itio
n
s
,
s
u
ch
as
ex
ce
s
s
iv
e
h
ea
t
o
r
h
u
m
id
ity
[
2
8
]
,
[
2
9
]
.
T
h
is
tr
an
s
f
o
r
m
s
th
e
s
y
s
t
em
f
r
o
m
a
s
im
p
le
m
o
n
ito
r
in
g
to
o
l in
t
o
a
p
r
ed
ictiv
e
an
d
p
r
ev
e
n
tiv
e
s
o
lu
tio
n
.
T
h
e
p
u
r
p
o
s
e
o
f
th
is
r
esear
ch
is
to
d
ev
elo
p
an
I
o
T
-
b
ased
m
o
n
ito
r
in
g
s
y
s
tem
th
at
m
e
asu
r
es
th
e
r
ea
l
-
tim
e
weig
h
t
o
f
c
h
ick
en
f
ec
es
an
d
f
ee
d
c
o
n
s
u
m
p
tio
n
.
T
h
e
s
y
s
tem
will
in
teg
r
ate
ML
to
en
a
b
le
ea
r
ly
d
etec
tio
n
o
f
p
o
ten
tial
h
ea
lth
i
s
s
u
es.
B
y
an
aly
zin
g
s
en
s
o
r
d
a
ta
o
n
a
cl
o
u
d
p
latf
o
r
m
,
it
aim
s
to
im
p
r
o
v
e
f
ar
m
m
an
ag
em
en
t
e
f
f
icien
cy
,
r
ed
u
ce
d
is
ea
s
e
r
is
k
s
,
an
d
o
p
tim
ize
p
o
u
ltry
p
r
o
d
u
ctio
n
[
3
0
]
–
[
3
3
]
.
I
n
I
n
d
o
n
esia,
th
e
ad
o
p
tio
n
o
f
I
o
T
in
th
e
li
v
esto
ck
s
ec
to
r
r
em
ain
s
r
elativ
ely
n
ew
a
n
d
f
ac
es
ch
allen
g
es,
s
u
ch
as
h
ig
h
in
itial
in
v
estme
n
t c
o
s
ts
an
d
lim
ited
in
ter
n
et
in
f
r
astru
ctu
r
e
[
3
4
]
,
[
3
5
]
.
No
n
eth
eless
,
in
cr
ea
s
in
g
d
e
m
an
d
s
f
o
r
ef
f
icien
cy
h
av
e
en
co
u
r
ag
e
d
in
ter
est
in
th
ese
tech
n
o
lo
g
ies,
p
ar
ticu
lar
ly
am
o
n
g
f
a
r
m
er
s
s
ee
k
in
g
to
s
ca
le
th
eir
o
p
er
atio
n
s
.
Go
v
er
n
m
e
n
t
an
d
r
esear
ch
in
s
titu
tio
n
s
ar
e
also
b
eg
in
n
in
g
to
p
r
o
m
o
te
in
n
o
v
atio
n
to
s
tr
en
g
th
en
f
o
o
d
s
ec
u
r
ity
an
d
s
u
p
p
o
r
t th
e
g
r
o
wth
o
f
th
e
n
atio
n
al
liv
esto
ck
in
d
u
s
tr
y
[
3
6
]
.
2.
M
E
T
H
O
D
T
o
d
ev
el
o
p
t
h
is
s
y
s
tem
,
it
is
ess
en
tial
to
u
n
d
er
s
tan
d
f
o
u
r
k
ey
c
o
m
p
o
n
en
ts
:
ch
ick
e
n
m
an
u
r
e
ch
ar
ac
ter
is
tics
,
air
p
ar
ticle
d
et
ec
to
r
s
f
o
r
m
an
u
r
e,
th
e
I
o
T
,
an
d
ML
.
On
ce
th
ese
co
m
p
o
n
e
n
t
s
ar
e
u
n
d
er
s
to
o
d
,
a
s
y
s
tem
ca
n
b
e
d
esig
n
ed
to
m
o
n
ito
r
a
n
d
r
e
g
u
late
air
q
u
a
lity
at
th
e
ca
s
e
s
tu
d
y
s
ite.
T
h
e
s
y
s
tem
will
th
en
u
n
d
er
g
o
a
3
0
-
d
a
y
test
in
g
p
er
io
d
to
ev
alu
ate
s
en
s
o
r
ac
c
u
r
ac
y
an
d
d
ata
q
u
ality
.
T
h
is
ev
alu
atio
n
will
h
elp
d
eter
m
in
e
t
h
e
s
y
s
tem
’
s
ef
f
ec
tiv
en
ess
in
m
o
n
ito
r
i
n
g
f
ee
d
q
u
a
lity
an
d
o
v
e
r
all
ch
ic
k
en
h
ea
lth
,
en
s
u
r
in
g
t
h
at
th
e
s
en
s
o
r
s
p
r
o
v
id
e
r
eliab
le
d
ata
f
o
r
f
ar
m
m
an
ag
e
m
en
t.
2
.
1
.
Chick
en
m
a
nu
re
C
h
ick
en
m
an
u
r
e
is
a
waste
p
r
o
d
u
ct
o
f
ch
ick
en
m
etab
o
lis
m
,
co
n
s
is
tin
g
o
f
u
n
d
ig
ested
f
o
o
d
r
esid
u
es,
u
r
in
e,
an
d
o
th
er
m
etab
o
lic
b
y
-
p
r
o
d
u
cts.
I
t
p
lay
s
an
im
p
o
r
ta
n
t
r
o
le
in
p
o
u
ltry
h
ea
lt
h
ass
ess
m
en
t
b
ec
au
s
e
it
s
co
m
p
o
s
itio
n
a
n
d
q
u
a
n
tity
p
r
o
v
id
e
v
al
u
ab
le
in
s
ig
h
ts
i
n
to
th
e
ch
ick
en
s
’
o
v
e
r
all
co
n
d
itio
n
.
Facto
r
s
s
u
ch
as
d
iet,
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
,
an
d
d
ig
esti
v
e
h
ea
lth
d
ir
ec
tly
in
f
lu
en
ce
th
e
co
n
ten
t a
n
d
weig
h
t o
f
m
an
u
r
e.
On
e
m
ajo
r
co
n
ce
r
n
with
m
an
u
r
e
ac
cu
m
u
latio
n
in
ch
ic
k
en
co
o
p
s
is
th
e
i
n
cr
ea
s
e
in
am
m
o
n
ia
lev
els
ca
u
s
ed
b
y
th
e
b
r
ea
k
d
o
wn
o
f
n
itro
g
en
i
n
th
e
m
an
u
r
e.
Am
m
o
n
ia
is
p
r
o
d
u
ce
d
th
r
o
u
g
h
th
e
d
e
co
m
p
o
s
itio
n
o
f
u
r
ic
ac
id
,
a
n
itro
g
e
n
-
r
ich
co
m
p
o
u
n
d
in
ch
ick
en
waste.
Un
d
er
wa
r
m
an
d
m
o
is
t
co
n
d
itio
n
s
,
m
ic
r
o
o
r
g
a
n
is
m
s
b
r
ea
k
d
o
wn
u
r
ic
ac
id
an
d
r
elea
s
e
am
m
o
n
ia
as
a
b
y
-
p
r
o
d
u
ct.
T
h
is
g
as
is
to
x
ic
an
d
p
o
s
es
s
ig
n
if
i
ca
n
t
h
ea
lth
r
is
k
s
to
ch
ick
en
s
[
3
7
]
,
[
3
8
]
.
Hig
h
am
m
o
n
ia
lev
els
ca
n
ir
r
i
tate
th
e
r
esp
ir
ato
r
y
tr
ac
t,
ey
es
,
an
d
s
k
in
,
in
cr
ea
s
in
g
t
h
e
lik
e
lih
o
o
d
o
f
r
esp
ir
ato
r
y
in
f
ec
tio
n
s
.
Pro
lo
n
g
ed
ex
p
o
s
u
r
e
wea
k
en
s
th
e
im
m
u
n
e
s
y
s
tem
,
m
ak
in
g
ch
ick
e
n
s
m
o
r
e
s
u
s
ce
p
tib
le
to
d
is
ea
s
es
s
u
ch
as
ch
r
o
n
ic
r
esp
ir
ato
r
y
d
is
ea
s
e
an
d
b
ac
ter
ial
in
f
ec
tio
n
s
,
wh
ile
also
r
ed
u
ci
n
g
p
r
o
d
u
ctiv
ity
[
3
9
]
.
E
x
ce
s
s
iv
e
am
m
o
n
ia
f
u
r
th
er
d
e
g
r
ad
es
air
q
u
ality
,
lead
in
g
to
l
o
wer
g
r
o
wth
r
ates
an
d
d
ec
r
ea
s
ed
eg
g
p
r
o
d
u
ctio
n
.
T
h
er
ef
o
r
e,
ef
f
ec
tiv
e
m
an
ag
em
en
t
an
d
m
o
n
ito
r
in
g
o
f
m
an
u
r
e
ac
cu
m
u
latio
n
a
n
d
am
m
o
n
ia
l
ev
els
ar
e
ess
en
tial
f
o
r
m
ain
tain
i
n
g
ch
ic
k
en
h
ea
lth
an
d
p
r
o
d
u
ctiv
ity
.
2
.
2
.
M
Q
-
1
3
7
s
ens
o
r
T
h
e
MQ
-
1
3
7
s
en
s
o
r
is
a
g
as
s
en
s
o
r
u
s
ed
in
eq
u
ip
m
en
t
to
d
etec
t
am
m
o
n
ia
g
as
in
e
v
er
y
d
ay
life
,
in
d
u
s
tr
y
,
o
r
ca
r
s
[
4
0
]
–
[
4
2
]
.
T
h
e
f
ea
tu
r
e
o
f
th
is
MQ
-
1
3
7
g
as
s
en
s
o
r
is
th
at
it
h
as
h
ig
h
s
en
s
itiv
ity
to
d
etec
t
am
m
o
n
ia
,
is
s
tab
le,
an
d
h
as
a
lo
n
g
life
.
T
h
is
s
en
s
o
r
u
s
es
a
h
ea
ter
p
o
wer
s
u
p
p
l
y
o
f
5
V
A
C
/D
C
an
d
a
cir
cu
i
t
p
o
wer
s
u
p
p
ly
o
f
5
V
DC
,
with
a
with
a
m
ea
s
u
r
em
en
t
d
is
tan
ce
o
f
5
-
5
0
0
p
p
m
to
ef
f
ec
tiv
e
ly
m
ea
s
u
r
e
ca
r
b
o
n
d
io
x
id
e
g
as.
I
n
th
is
r
esear
ch
,
th
e
MQ
-
1
3
7
s
en
s
o
r
will
b
e
u
s
ed
,
w
h
ich
ca
n
d
etec
t
co
m
b
u
s
tio
n
r
esid
u
es.
Fig
u
r
e
1
s
h
o
ws
th
e
s
en
s
i
tiv
ity
v
alu
e
o
f
MQ
-
1
3
7
to
o
th
er
g
ases
.
Fig
u
r
e
2
.
s
h
o
ws
th
e
cir
cu
it
o
f
th
e
MQ
-
7
u
s
ed
.
T
o
f
in
d
o
u
t th
e
r
elatio
n
s
h
ip
b
e
twee
n
co
m
p
o
n
en
ts
an
d
d
etec
tio
n
,
it is
d
escr
ib
ed
in
(
1
).
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
Gen
etic
a
lg
o
r
ith
m
-
b
a
s
ed
c
h
icke
n
ma
n
u
r
e
w
eig
h
t p
r
ed
ictio
n
s
ystem
d
ev
elo
p
men
t
(
R
id
a
Hu
d
a
ya
)
1249
=
√
100
−
1
.
53
(
1
)
W
h
er
e
y
is
th
e
d
esire
d
clea
n
ai
r
s
tan
d
ar
d
(
i
n
p
p
m
)
,
th
e
n
af
ter
g
ettin
g
th
e
x
v
alu
e
p
r
o
ce
ed
t
o
(
2
).
=
×
−
(
2
)
W
h
er
e
is
th
e
r
esis
tan
ce
to
th
e
s
en
s
o
r
,
is
th
e
in
p
u
t
v
o
ltag
e
to
th
e
s
en
s
o
r
,
is
th
e
lo
ad
r
esis
tan
ce
in
t
h
e
cir
cu
it,
an
d
is
th
e
o
u
tp
u
t
v
o
ltag
e
o
f
th
e
cir
cu
it.
Af
ter
ca
lcu
latin
g
with
(
1
)
an
d
(
2
)
,
it
is
co
n
tin
u
ed
to
ca
lcu
late
th
e
v
alu
e
o
f
wh
ich
is
a
co
m
p
ar
is
o
n
r
esis
tan
ce
f
o
r
n
o
r
m
al
co
n
d
itio
n
s
o
f
clea
n
air
wh
ich
is
th
e
r
ef
er
en
ce
in
(
3
).
=
(
3
)
So
th
at
af
ter
th
e
v
alu
es o
f
an
d
ar
e
o
b
tain
e
d
,
th
e
y
ca
n
o
n
ly
m
ea
s
u
r
e
th
e
ch
a
n
g
es in
th
e
air
th
at
o
cc
u
r
.
Fig
u
r
e
1
.
MQ
-
1
3
7
s
en
s
iv
ity
g
r
ap
h
ic
Fig
u
r
e
2
.
MQ
-
1
3
7
s
en
s
o
r
cir
c
u
it
2
.
3
.
I
nte
rnet
o
f
t
hin
g
s
co
mm
un
ica
t
io
ns
T
h
e
I
o
T
is
a
co
n
ce
p
t
in
wh
ic
h
d
ev
ices
tr
an
s
m
it
d
ata
o
v
e
r
a
n
etwo
r
k
with
o
u
t
r
eq
u
ir
i
n
g
h
u
m
an
-
to
-
h
u
m
an
o
r
h
u
m
an
-
to
-
co
m
p
u
te
r
in
ter
ac
tio
n
.
T
h
e
ter
m
“
I
o
T
”
was
in
tr
o
d
u
ce
d
i
n
1
9
9
9
b
y
Kev
in
Ash
to
n
,
co
f
o
u
n
d
er
an
d
ex
ec
u
tiv
e
d
ir
e
cto
r
o
f
th
e
Au
to
-
I
D
C
en
ter
at
MI
T
.
Ho
wev
er
,
th
e
d
ev
elo
p
m
en
t
o
f
I
o
T
b
e
g
an
lo
n
g
b
ef
o
r
e
th
at.
On
e
ea
r
ly
ex
am
p
le
is
th
e
C
o
ca
-
C
o
la
m
ac
h
in
e
at
C
ar
n
eg
ie
Me
llo
n
Un
iv
er
s
ity
in
th
e
ea
r
ly
1
9
8
0
s
,
wh
ic
h
b
ec
am
e
t
h
e
f
ir
s
t
in
ter
n
et
-
co
n
n
ec
ted
d
ev
ice.
Pr
o
g
r
am
m
e
r
s
co
u
ld
ac
ce
s
s
it
r
e
m
o
tely
to
ch
ec
k
its
s
tatu
s
an
d
d
ete
r
m
in
e
wh
eth
er
co
ld
d
r
i
n
k
s
wer
e
av
ailab
le
with
o
u
t
v
is
itin
g
th
e
m
ac
h
in
e
in
p
er
s
o
n
[
4
3
]
,
[
4
4
]
.
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.
15
,
No
.
2
,
Ap
r
il
20
26
:
1
2
4
7
-
1
2
6
0
1250
Fig
u
r
e
3
illu
s
tr
ates
an
I
o
T
s
y
s
tem
u
s
in
g
wir
eless
co
m
m
u
n
icatio
n
to
s
en
d
m
ea
s
u
r
em
e
n
t
d
ata
to
a
clo
u
d
d
atab
ase
f
o
r
s
to
r
a
g
e.
W
ir
eles
s
co
m
m
u
n
icatio
n
r
ef
e
r
s
to
th
e
tr
an
s
f
er
o
f
d
ata
b
etwe
en
two
o
r
m
o
r
e
l
o
ca
tio
n
s
with
o
u
t
a
n
elec
tr
ical
co
n
d
u
cto
r
.
I
ts
r
an
g
e
ca
n
v
ar
y
f
r
o
m
a
f
ew
m
eter
s
,
s
u
ch
as
in
telev
is
io
n
r
em
o
te
co
n
tr
o
ls
,
to
th
o
u
s
an
d
s
o
r
ev
e
n
m
illi
o
n
s
o
f
k
ilo
m
ete
r
s
in
d
ee
p
-
s
p
ac
e
r
ad
io
tr
an
s
m
is
s
io
n
s
.
W
ir
eles
s
co
m
m
u
n
i
ca
tio
n
en
co
m
p
ass
es
d
ev
ices
s
u
ch
as
p
e
r
s
o
n
al
d
i
g
ital
ass
is
tan
t
s
(
PDAs
)
,
ce
ll
p
h
o
n
es,
wir
eless
n
etwo
r
k
s
,
an
d
v
a
r
io
u
s
ty
p
es
o
f
f
i
x
ed
,
m
o
b
ile,
an
d
p
o
r
tab
le
two
-
way
r
ad
io
s
.
T
h
e
2
.
4
GHz
b
an
d
is
wid
ely
u
s
ed
f
o
r
m
an
y
ap
p
licatio
n
s
[
4
5
]
–
[
4
7
]
,
with
o
n
e
o
f
th
e
m
o
s
t
c
o
m
m
o
n
b
ei
n
g
wir
eless
n
etwo
r
k
ac
ce
s
s
f
o
r
u
s
er
s
wh
o
m
o
v
e
b
etwe
en
lo
ca
tio
n
s
.
An
o
th
e
r
m
ajo
r
ap
p
licatio
n
is
m
o
b
ile
n
e
two
r
k
s
co
n
n
ec
te
d
v
ia
s
atellite.
Fig
u
r
e
3
.
I
n
ter
n
et
o
f
th
in
g
s
s
ch
em
atic
2
.
4
.
M
a
chine le
a
rning
ML
is
th
e
p
r
o
ce
s
s
o
f
cr
ea
tin
g
a
m
ath
em
atica
l
m
o
d
el
to
m
ak
e
p
r
ed
ictio
n
s
o
r
d
ec
is
io
n
s
u
s
in
g
tr
ain
in
g
d
ata,
wh
ich
ar
e
s
am
p
le
d
ata
s
ets
[
4
8
]
,
[
4
9
]
.
As
a
s
u
b
f
ield
o
f
ar
tific
ial
in
tellig
en
ce
(
AI
)
,
ML
f
o
cu
s
es
o
n
d
ev
elo
p
in
g
alg
o
r
ith
m
s
th
at
an
aly
ze
d
ata
to
g
en
er
ate
p
r
e
d
ictio
n
s
[
5
0
]
,
[
5
1
]
.
T
h
ese
alg
o
r
ith
m
s
lear
n
f
r
o
m
th
e
d
ata
to
im
p
r
o
v
e
th
eir
p
er
f
o
r
m
an
ce
o
v
er
tim
e.
An
ML
alg
o
r
i
th
m
is
tr
ain
ed
with
a
d
ataset,
wh
ich
is
th
en
u
s
ed
to
class
if
y
o
r
p
r
ed
ict
o
u
tc
o
m
es
b
ased
o
n
th
e
d
ata.
Fig
u
r
e
1
s
h
o
ws
a
g
en
er
al
s
tr
u
ctu
r
e
o
f
h
o
w
th
e
lear
n
in
g
m
o
d
el
f
u
n
ctio
n
s
,
wh
ile
Fig
u
r
e
2
illu
s
tr
ates
th
e
p
r
o
ce
s
s
o
f
class
if
y
in
g
s
am
p
le
(
test
)
d
ata
b
ased
o
n
th
e
tr
ain
ed
d
ataset.
ML
alg
o
r
ith
m
s
ca
n
b
e
ca
teg
o
r
ized
in
to
th
r
ee
m
ain
ty
p
es b
ased
o
n
th
eir
lear
n
in
g
m
e
th
o
d
s
.
Su
p
er
v
is
ed
,
u
n
s
u
p
er
v
is
ed
,
an
d
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
ar
e
th
e
th
r
ee
d
is
tin
ct
ca
teg
o
r
ies
in
to
wh
ich
ML
alg
o
r
ith
m
s
f
all
b
ased
o
n
th
eir
ab
ilit
ies
to
lear
n
.
Un
d
e
r
th
e
s
u
p
er
v
is
ed
lear
n
i
n
g
ca
teg
o
r
y
,
r
eg
r
ess
io
n
m
o
d
el
s
an
d
class
if
icatio
n
m
o
d
els
ar
e
in
v
esti
g
ated
.
I
n
t
h
e
u
n
s
u
p
e
r
v
is
ed
lear
n
in
g
ar
e
a,
clu
s
ter
in
g
an
d
d
im
en
s
io
n
a
lity
r
ed
u
ctio
n
ar
e
in
v
esti
g
ated
,
wh
ile
in
th
e
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
ca
teg
o
r
y
,
r
ea
l
-
tim
e
d
ec
is
io
n
m
o
d
els
ar
e
i
n
v
esti
g
ated
.
Usi
n
g
in
p
u
t
d
ata,
s
u
p
e
r
v
is
ed
lear
n
i
n
g
p
r
e
d
icts
m
o
r
e
ac
cu
r
atel
y
th
an
th
e
in
ten
d
ed
m
o
d
el.
Mo
r
e
co
m
p
licated
p
r
o
ce
s
s
in
g
task
s
ar
e
c
o
m
p
lete
d
b
y
u
n
s
u
p
er
v
is
ed
lear
n
in
g
.
An
aly
zin
g
d
im
en
s
io
n
r
ed
u
ctio
n
ca
n
b
e
d
o
n
e
with
b
o
th
s
u
p
er
v
is
ed
an
d
u
n
s
u
p
er
v
is
ed
lear
n
in
g
tech
n
iq
u
es.
T
h
e
m
o
s
t
p
o
p
u
lar
a
n
d
wid
ely
u
s
ed
d
im
en
s
io
n
al
r
ed
u
ctio
n
m
eth
o
d
s
ar
e
p
r
in
ci
p
al
co
m
p
o
n
e
n
t
an
aly
s
is
(
PC
A)
,
p
ar
tial
least
s
q
u
ar
es
r
eg
r
ess
io
n
(
PLS
R
)
,
an
d
lin
ea
r
d
is
cr
im
in
an
t
an
al
y
s
is
(
L
DA)
[
5
2
]
,
[
5
3
]
.
ML
tech
n
iq
u
e
s
ar
e
co
m
m
o
n
ly
ap
p
lied
in
co
n
s
tr
u
ctin
g
b
u
s
in
ess
m
o
d
els,
d
ec
is
io
n
s
u
p
p
o
r
t
s
y
s
tem
s
,
an
d
b
eh
a
v
io
r
al
an
aly
s
is
—
s
u
ch
as
ev
alu
atin
g
u
s
er
b
e
h
av
io
r
f
r
o
m
s
o
cial
m
ed
ia,
em
ail
co
n
te
n
t,
a
n
d
o
n
li
n
e
s
h
o
p
p
in
g
.
Mo
d
er
n
elec
tr
o
n
ic
d
ev
ices,
s
u
c
h
as
la
p
to
p
s
a
n
d
s
m
ar
tp
h
o
n
es,
n
o
w
in
co
r
p
o
r
ate
a
r
an
g
e
o
f
ML
ap
p
licatio
n
s
f
o
r
r
ea
l
-
tim
e
d
ata
p
r
o
ce
s
s
in
g
an
d
p
r
ed
ictio
n
.
T
o
e
n
h
an
ce
th
e
ac
cu
r
ac
y
o
f
c
h
ick
en
h
ea
lth
m
o
n
ito
r
in
g
,
co
m
p
ar
ativ
e
ex
p
e
r
im
en
ts
with
m
u
ltip
le
ML
alg
o
r
ith
m
s
s
h
o
u
ld
b
e
co
n
d
u
cted
to
d
eter
m
in
e
th
e
m
o
s
t
ef
f
ec
tiv
e
m
o
d
el
f
o
r
p
r
ed
ictin
g
ch
ick
en
m
an
u
r
e
weig
h
t.
B
ased
o
n
th
is
r
esear
ch
,
th
e
g
en
etic
alg
o
r
ith
m
(
GA)
em
er
g
e
d
as
th
e
m
o
s
t
s
u
itab
le
o
p
tim
izatio
n
m
o
d
el,
d
em
o
n
s
tr
atin
g
th
e
ab
ilit
y
to
ef
f
ec
tiv
ely
ca
p
tu
r
e
th
e
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
b
etwe
en
in
p
u
t
v
a
r
iab
les
—
s
u
ch
as
tem
p
er
atu
r
e
an
d
am
m
o
n
ia
co
n
ce
n
tr
atio
n
—
an
d
m
an
u
r
e
o
u
tp
u
t.
I
ts
ad
ap
tiv
e
s
ea
r
ch
p
r
o
ce
s
s
an
d
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
m
ak
e
it
id
ea
l
f
o
r
ag
r
icu
ltu
r
al
p
r
ed
ictiv
e
m
o
d
eli
n
g
.
2
.
5
.
B
lo
c
k
dia
g
ra
m
s
y
s
t
em
I
n
th
e
r
esear
ch
d
escr
ib
e
d
in
Fig
u
r
e
4
,
t
h
e
m
o
n
ito
r
in
g
s
y
s
tem
is
d
ev
elo
p
ed
as
an
em
b
ed
d
ed
I
o
T
p
latf
o
r
m
th
at
in
te
g
r
ates
m
u
ltip
le
en
v
ir
o
n
m
en
tal
an
d
h
ea
lth
-
r
elate
d
s
en
s
o
r
s
.
T
o
o
b
s
er
v
e
co
n
d
itio
n
s
in
s
id
e
two
ch
ick
en
d
r
u
m
m
o
d
els,
ea
ch
h
o
u
s
in
g
1
5
ch
ick
e
n
s
.
T
h
e
s
y
s
tem
u
s
es
a
m
icr
o
co
n
tr
o
ller
as
th
e
p
r
im
ar
y
p
r
o
ce
s
s
in
g
u
n
it,
r
esp
o
n
s
ib
le
f
o
r
s
am
p
lin
g
,
p
r
o
ce
s
s
in
g
,
an
d
tr
a
n
s
m
itti
n
g
s
en
s
o
r
d
ata
in
r
ea
l ti
m
e.
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
Gen
etic
a
lg
o
r
ith
m
-
b
a
s
ed
c
h
icke
n
ma
n
u
r
e
w
eig
h
t p
r
ed
ictio
n
s
ystem
d
ev
elo
p
men
t
(
R
id
a
Hu
d
a
ya
)
1251
Fig
u
r
e
4
.
Flo
wch
ar
t
o
f
th
e
AI
-
b
ased
m
o
d
els an
d
ex
p
e
r
im
en
t
al
m
eth
o
d
s
ap
p
lied
Var
io
u
s
s
en
s
o
r
s
ar
e
in
ter
f
ac
e
d
with
th
e
em
b
e
d
d
ed
co
n
tr
o
ller
,
in
clu
d
in
g
th
e
MQ
-
1
3
7
f
o
r
am
m
o
n
i
a
d
etec
tio
n
,
tem
p
er
atu
r
e
an
d
h
u
m
id
ity
s
en
s
o
r
s
f
o
r
t
h
er
m
a
l
co
m
f
o
r
t
m
o
n
ito
r
in
g
,
an
d
ad
d
itio
n
al
m
o
d
u
les
d
ep
en
d
i
n
g
o
n
f
ee
d
v
ar
iatio
n
s
.
T
h
ese
s
en
s
o
r
s
co
m
m
u
n
icate
th
r
o
u
g
h
d
ig
ital
an
d
an
alo
g
i
n
ter
f
ac
es,
en
s
u
r
in
g
ac
cu
r
ate
en
v
ir
o
n
m
en
tal
d
ata
ac
q
u
is
itio
n
with
in
ea
ch
d
r
u
m
.
Fo
r
wir
eless
co
m
m
u
n
icatio
n
,
th
e
em
b
ed
d
ed
co
n
tr
o
ller
u
s
es
W
i
-
Fi
–
b
ased
p
r
o
to
co
ls
to
tr
a
n
s
m
it
d
ata
s
ea
m
less
ly
to
a
clo
u
d
o
r
lo
ca
l
m
o
n
i
to
r
in
g
s
er
v
e
r
.
T
h
is
en
s
u
r
es
co
n
tin
u
o
u
s
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
o
f
ai
r
q
u
ality
,
tem
p
er
atu
r
e,
an
d
o
th
e
r
p
a
r
a
m
eter
s
,
s
u
p
p
o
r
tin
g
ef
f
icien
t a
n
aly
s
is
o
f
h
o
w
d
if
f
e
r
en
t f
ee
d
t
y
p
es in
f
lu
e
n
ce
ch
ick
en
h
ea
lth
an
d
en
v
ir
o
n
m
e
n
tal
c
o
n
d
itio
n
s
.
A
ML
ap
p
r
o
ac
h
is
d
ev
elo
p
ed
to
esti
m
ate
m
an
u
r
e
weig
h
t
u
s
in
g
tem
p
er
atu
r
e
an
d
am
m
o
n
i
a
lev
els
as
p
r
ed
ictiv
e
f
ea
tu
r
es.
T
o
ju
s
tify
th
e
u
s
e
o
f
a
GA
f
o
r
m
o
d
el
o
p
tim
izatio
n
,
th
e
GA
-
b
ased
m
o
d
el
is
b
en
ch
m
ar
k
e
d
ag
ain
s
t
two
wid
ely
u
s
ed
r
eg
r
e
s
s
io
n
m
eth
o
d
s
in
a
g
r
icu
ltu
r
al
p
r
ed
ictio
n
:
s
u
p
p
o
r
t
v
ec
to
r
r
eg
r
ess
io
n
(
SVR
)
an
d
r
an
d
o
m
f
o
r
est
r
eg
r
ess
io
n
(
R
F).
SVR
p
r
o
v
id
es
s
tr
o
n
g
n
o
n
lin
ea
r
r
e
g
r
ess
io
n
ca
p
ab
ilit
ie
s
,
wh
ile
R
F
o
f
f
er
s
r
o
b
u
s
tn
ess
th
r
o
u
g
h
e
n
s
em
b
le
lear
n
in
g
.
T
h
ese
m
o
d
els s
er
v
e
a
s
ap
p
r
o
p
r
iate
b
aselin
es f
o
r
co
m
p
ar
is
o
n
.
Du
r
in
g
b
en
c
h
m
ar
k
in
g
,
all
th
r
ee
m
o
d
els
—
GA
-
o
p
tim
ized
r
eg
r
ess
io
n
,
SVR
,
an
d
R
F
—
ar
e
tr
ain
ed
u
s
in
g
id
en
tical
in
p
u
t
f
ea
tu
r
es
an
d
ev
alu
ated
with
s
tan
d
a
r
d
p
er
f
o
r
m
a
n
ce
m
etr
ics:
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
,
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
,
an
d
th
e
co
e
f
f
icien
t
o
f
d
eter
m
in
atio
n
(
R
2
)
.
T
h
e
r
e
s
u
lts
s
h
o
w
th
at
th
e
GA
-
b
ased
m
o
d
el
c
o
n
s
is
ten
tly
o
u
tp
e
r
f
o
r
m
s
SVR
an
d
R
F,
p
ar
ticu
lar
ly
in
ca
p
tu
r
i
n
g
n
o
n
lin
ea
r
in
ter
ac
tio
n
s
b
etwe
en
am
m
o
n
ia
lev
els,
tem
p
er
atu
r
e
f
lu
ctu
atio
n
s
,
a
n
d
m
an
u
r
e
weig
h
t.
T
h
is
im
p
r
o
v
em
e
n
t
is
attr
ib
u
ted
to
th
e
GA’
s
ev
o
lu
tio
n
ar
y
s
ea
r
ch
m
ec
h
an
is
m
,
wh
ich
ef
f
ec
tiv
ely
ex
p
lo
r
es c
o
m
p
lex
p
ar
am
eter
r
elatio
n
s
h
ip
s
.
T
h
e
GA
o
p
tim
izatio
n
p
r
o
ce
s
s
il
lu
s
tr
ated
in
Fig
u
r
e
5
b
eg
in
s
with
an
in
itial
p
o
p
u
latio
n
o
f
1
5
ch
r
o
m
o
s
o
m
es,
b
alan
cin
g
s
o
lu
tio
n
d
iv
er
s
ity
,
an
d
co
m
p
u
t
atio
n
al
ef
f
icien
cy
.
E
ac
h
ch
r
o
m
o
s
o
m
e
r
ep
r
esen
ts
a
p
o
ten
tial
p
a
r
am
eter
s
et
f
o
r
t
h
e
p
r
e
d
ictiv
e
m
o
d
el.
Acr
o
s
s
g
en
er
atio
n
s
,
th
e
GA
ev
alu
ate
s
f
itn
ess
b
ased
o
n
p
r
ed
ictio
n
er
r
o
r
,
s
elec
ts
o
p
tim
al
in
d
iv
id
u
als,
an
d
a
p
p
lies
cr
o
s
s
o
v
er
an
d
m
u
tatio
n
to
p
r
o
d
u
ce
im
p
r
o
v
e
d
o
f
f
s
p
r
in
g
.
T
h
is
ev
o
lu
tio
n
a
r
y
cy
cle
co
n
tin
u
es
u
n
til
c
o
n
v
e
r
g
en
ce
c
r
iter
ia
ar
e
m
et,
ty
p
i
ca
lly
wh
en
f
itn
ess
im
p
r
o
v
em
e
n
ts
s
tab
ilize
o
r
th
e
m
ax
im
u
m
g
en
er
atio
n
co
u
n
t is r
ea
ch
ed
.
Fig
u
r
e
5
.
Flo
wch
ar
t
o
f
s
y
s
tem
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.
15
,
No
.
2
,
Ap
r
il
20
26
:
1
2
4
7
-
1
2
6
0
1252
Usi
n
g
th
is
GA
-
b
ased
s
tr
ateg
y
with
a
co
n
tr
o
lled
ch
r
o
m
o
s
o
m
e
p
o
p
u
latio
n
o
f
1
5
r
esu
lts
in
en
h
an
ce
d
m
o
d
el
ac
cu
r
ac
y
,
s
tab
ilit
y
,
an
d
g
en
er
aliza
tio
n
c
o
m
p
ar
e
d
to
t
r
ad
itio
n
al
r
eg
r
ess
io
n
m
eth
o
d
s
.
T
h
e
co
n
f
ig
u
r
atio
n
en
ab
les
ef
f
ec
tiv
e
e
x
p
lo
r
atio
n
o
f
th
e
s
o
lu
tio
n
s
p
ac
e
wh
ile
m
in
im
izin
g
co
m
p
u
tatio
n
al
o
v
er
h
ea
d
,
p
r
o
d
u
cin
g
a
r
eliab
le
m
o
d
el
f
o
r
esti
m
atin
g
m
an
u
r
e
weig
h
t u
n
d
er
v
ar
y
in
g
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
.
T
o
s
itu
ate
th
e
p
r
o
p
o
s
ed
s
y
s
tem
with
in
ex
is
tin
g
r
esear
ch
,
T
ab
le
1
p
r
o
v
id
es
a
co
m
p
ar
a
tiv
e
s
u
m
m
ar
y
o
f
co
n
v
en
tio
n
al
m
an
u
r
e
-
p
r
ed
ictio
n
m
eth
o
d
s
,
s
en
s
o
r
-
b
ased
liv
esto
ck
m
o
n
ito
r
in
g
s
y
s
tem
s
,
an
d
G
A
-
o
p
tim
ized
p
r
ed
ictiv
e
m
o
d
el
s
.
T
h
is
co
m
p
ar
is
o
n
h
ig
h
lig
h
ts
k
e
y
f
ea
tu
r
es,
a
d
v
an
tag
es,
lim
itatio
n
s
,
an
d
r
ec
en
t
s
tu
d
ies
th
at
d
e
m
o
n
s
tr
ate
o
n
g
o
in
g
a
d
v
an
ce
m
e
n
ts
i
n
s
m
ar
t f
ar
m
in
g
,
ed
g
e
c
o
m
p
u
tin
g
,
I
o
T
ar
ch
itectu
r
es,
an
d
ML
o
p
tim
izatio
n
f
o
r
ag
r
icu
ltu
r
al
ap
p
licatio
n
s
.
T
ab
le
1
.
C
o
m
p
a
r
atio
n
r
esear
c
h
o
f
GA
M
e
t
h
o
d
/
sy
st
e
m
t
y
p
e
K
e
y
f
e
a
t
u
r
e
s
Te
c
h
n
o
l
o
g
i
e
s/
sen
s
o
r
s
u
se
d
A
d
v
a
n
t
a
g
e
s
Li
mi
t
a
t
i
o
n
s
R
e
p
r
e
se
n
t
a
t
i
v
e
r
e
c
e
n
t
w
o
r
k
s
Ex
i
s
t
i
n
g
man
u
r
e
p
r
e
d
i
c
t
i
o
n
sy
st
e
ms
Emp
i
r
i
c
a
l
/
st
a
t
i
st
i
c
a
l
mo
d
e
l
i
n
g
f
o
r
e
st
i
ma
t
i
n
g
man
u
r
e
a
c
c
u
m
u
l
a
t
i
o
n
b
a
s
e
d
o
n
f
e
e
d
i
n
t
a
k
e
a
n
d
a
n
i
ma
l
g
r
o
w
t
h
.
M
a
n
u
a
l
samp
l
i
n
g
,
e
n
v
i
r
o
n
m
e
n
t
a
l
l
o
g
s,
l
o
a
d
c
e
l
l
s.
S
i
mp
l
e
i
mp
l
e
m
e
n
t
a
t
i
o
n
;
l
o
w
c
o
m
p
u
t
a
t
i
o
n
a
l
c
o
s
t
.
Li
mi
t
e
d
a
d
a
p
t
a
b
i
l
i
t
y
;
n
o
t
r
e
a
l
-
t
i
m
e
;
o
f
t
e
n
l
o
w
a
c
c
u
r
a
c
y
.
I
o
T
l
i
v
e
s
t
o
c
k
w
a
st
e
q
u
a
n
t
i
f
i
c
a
t
i
o
n
m
o
d
e
l
[
5
4
]
;
D
a
t
a
-
d
r
i
v
e
n
ma
n
u
r
e
e
st
i
mat
i
o
n
f
r
a
mew
o
r
k
[
5
5
]
S
e
n
s
o
r
-
b
a
s
e
d
l
i
v
e
s
t
o
c
k
mo
n
i
t
o
r
i
n
g
sy
st
e
ms
R
e
a
l
-
t
i
me
se
n
si
n
g
o
f
l
i
v
e
s
t
o
c
k
e
n
v
i
r
o
n
m
e
n
t
.
M
Q
g
a
s s
e
n
so
r
s,
D
H
T2
2
,
H
X
7
1
1
l
o
a
d
c
e
l
l
s
,
e
d
g
e
I
o
T
mo
d
u
l
e
s.
R
e
a
l
-
t
i
me
a
l
e
r
t
s;
s
c
a
l
a
b
l
e
;
i
mp
r
o
v
e
s
a
n
i
ma
l
w
e
l
f
a
r
e
.
S
e
n
s
o
r
d
r
i
f
t
;
r
e
q
u
i
r
e
s
c
a
l
i
b
r
a
t
i
o
n
;
d
a
t
a
n
o
i
s
e
.
Ed
g
e
-
I
o
T
p
o
u
l
t
r
y
mo
n
i
t
o
r
i
n
g
a
r
c
h
i
t
e
c
t
u
r
e
[
5
6
]
;
A
n
i
ma
l
w
e
l
f
a
r
e
mo
n
i
t
o
r
i
n
g
u
si
n
g
d
i
s
t
r
i
b
u
t
e
d
sen
s
o
r
s
[
5
7
]
GA
-
b
a
se
d
o
p
t
i
m
i
z
a
t
i
o
n
mo
d
e
l
s
U
ses
G
A
t
o
o
p
t
i
mi
z
e
r
e
g
r
e
ss
i
o
n
o
r
M
L
mo
d
e
l
s
f
o
r
a
g
r
i
c
u
l
t
u
r
a
l
p
r
e
d
i
c
t
i
o
n
t
a
s
k
s.
GA
-
o
p
t
i
mi
z
e
d
r
e
g
r
e
ss
i
o
n
,
G
A
–
A
N
N
,
G
A
–
S
V
R
,
e
n
v
i
r
o
n
m
e
n
t
a
l
t
i
m
e
-
seri
e
s
d
a
t
a
.
H
i
g
h
a
c
c
u
r
a
c
y
;
st
r
o
n
g
f
o
r
n
o
n
l
i
n
e
a
r
r
e
l
a
t
i
o
n
s
h
i
p
s
;
a
d
a
p
t
i
v
e
.
C
o
m
p
u
t
a
t
i
o
n
a
l
l
y
i
n
t
e
n
si
v
e
;
sen
s
i
t
i
v
e
t
o
GA
p
a
r
a
m
e
t
e
r
s.
GA
-
o
p
t
i
mi
z
e
d
n
e
u
r
a
l
r
e
g
r
e
ss
[
5
8
]
;
H
y
b
r
i
d
G
A
–
S
V
R
e
n
v
i
r
o
n
m
e
n
t
a
l
p
r
e
d
i
c
t
i
o
n
[
5
9
]
;
Ev
o
l
u
t
i
o
n
a
r
y
o
p
t
i
mi
z
a
t
i
o
n
i
n
smar
t
f
a
r
mi
n
g
[
6
0
]
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
f
ir
s
t
s
tag
e
o
f
s
y
s
tem
i
m
p
lem
en
tatio
n
in
v
o
lv
es
d
e
v
elo
p
in
g
a
n
d
p
lacin
g
th
e
c
h
i
ck
en
co
o
p
m
o
n
ito
r
in
g
d
ev
ice
in
s
id
e
th
e
c
o
o
p
.
T
h
is
d
ev
ice
in
teg
r
ates
s
ev
er
al
s
en
s
o
r
s
co
n
n
ec
te
d
th
r
o
u
g
h
an
I
o
T
s
y
s
tem
to
co
n
tin
u
o
u
s
ly
m
o
n
ito
r
e
n
v
ir
o
n
m
en
tal
an
d
h
ea
lth
-
r
elate
d
p
ar
am
eter
s
.
Fig
u
r
e
6
illu
s
tr
ates
th
e
lay
o
u
t
an
d
in
teg
r
atio
n
o
f
th
e
c
o
m
p
o
n
en
ts
an
d
h
o
w
t
h
ey
ar
e
in
s
talled
with
in
th
e
co
o
p
.
T
h
e
p
u
r
p
o
s
e
o
f
th
is
tab
le
is
to
h
ig
h
lig
h
t
th
e
ac
c
u
r
ac
y
o
f
th
e
MQ
-
1
3
7
s
en
s
o
r
b
y
s
h
o
win
g
h
o
w
clo
s
ely
its
r
ea
d
in
g
s
alig
n
with
th
o
s
e
o
f
th
e
am
m
o
n
ia
m
eter
o
n
Fi
g
u
r
e
7
.
T
h
e
d
if
f
er
e
n
ce
b
etwe
en
th
e
two
s
ets
o
f
r
ea
d
in
g
s
is
ca
lcu
lated
t
o
d
eter
m
in
e
th
e
er
r
o
r
m
ar
g
i
n
.
B
y
c
o
m
p
ar
in
g
th
e
r
ea
d
in
g
s
,
th
e
ac
c
u
r
ac
y
o
f
th
e
s
en
s
o
r
s
u
s
ed
in
th
is
s
y
s
tem
ca
n
b
e
d
eter
m
in
ed
.
I
n
ad
d
itio
n
,
th
is
co
m
p
ar
is
o
n
is
also
im
p
o
r
ta
n
t
to
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
s
en
s
o
r
u
n
d
er
o
p
er
atio
n
al
c
o
n
d
itio
n
s
.
Fro
m
th
e
test
r
esu
lts
,
an
av
e
r
ag
e
er
r
o
r
v
alu
e
o
f
0
.
3
1
%
was
o
b
tain
ed
.
T
h
e
er
r
o
r
s
h
o
ws
th
e
d
if
f
er
en
ce
b
etwe
e
n
th
e
s
en
s
o
r
r
ea
d
in
g
an
d
th
e
a
m
m
o
n
ia
m
eter
u
s
e
d
as a
r
ef
er
en
ce
.
O
v
er
all,
th
is
er
r
o
r
v
al
u
e
is
s
till
with
in
ac
ce
p
tab
le
lim
its
f
o
r
th
e
in
ten
d
ed
a
p
p
licatio
n
.
Nex
t
is
th
e
test
o
f
ac
cu
r
ac
y
s
ca
les
(
lo
ad
ce
ll
s
en
s
o
r
)
ca
r
r
ied
o
u
t
b
y
test
er
,
n
a
m
ely
,
test
in
g
th
e
to
o
ls
an
d
s
y
s
tem
s
,
esp
ec
ially
o
n
th
e
r
esu
lts
o
f
t
h
e
s
ca
les
with
th
e
r
esu
lts
d
is
p
lay
ed
.
T
h
e
p
u
r
p
o
s
e
o
f
t
h
is
test
is
to
d
eter
m
in
e
th
e
lev
el
o
f
ac
cu
r
ac
y
o
f
th
e
r
ea
d
in
g
r
esu
lts
o
f
ch
ick
en
m
an
u
r
e
in
th
e
ca
g
e
in
Fig
u
r
e
8
an
d
T
ab
le
2
.
T
h
e
r
esu
lts
o
f
weig
h
t
r
ea
d
in
g
s
tak
en
u
s
in
g
t
h
e
lo
ad
ce
ll sen
s
o
r
ar
e
p
r
esen
ted
.
Fig
u
r
e
6
.
I
m
p
lem
en
tatio
n
s
y
s
tem
f
o
r
g
et
d
ata
ML
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
Gen
etic
a
lg
o
r
ith
m
-
b
a
s
ed
c
h
icke
n
ma
n
u
r
e
w
eig
h
t p
r
ed
ictio
n
s
ystem
d
ev
elo
p
men
t
(
R
id
a
Hu
d
a
ya
)
1253
Fig
u
r
e
7
.
MQ
-
137
ac
c
u
r
atio
n
t
est
Fig
u
r
e
8
.
L
o
ad
ce
ll a
cc
u
r
ati
o
n
test
T
ab
le
2
.
Sen
s
o
r
MQ
-
1
3
7
ac
cu
r
atio
n
m
ea
s
u
r
e
Te
st
i
n
g
Te
st
r
e
su
l
t
s
A
mm
o
n
i
a
g
a
s
d
e
t
e
c
t
i
o
n
d
e
v
i
c
e
(
p
p
m)
S
e
n
s
o
r
M
Q
-
1
3
7
(
p
p
m)
Er
r
o
r
(
%)
1
5
5
.
9
5
5
.
7
0
.
4
4
2
5
6
.
4
5
5
.
2
0
.
2
2
3
5
5
.
5
5
5
.
3
0
.
4
4
4
5
5
.
8
5
5
.
7
0
.
2
2
5
5
7
.
2
5
7
.
3
0
.
2
1
6
5
5
.
2
5
5
.
4
0
.
4
4
7
5
6
.
2
5
6
.
1
0
.
2
2
8
6
1
.
5
6
1
.
7
0
.
4
5
9
6
0
.
6
6
0
.
5
0
.
2
10
5
6
.
7
5
6
.
8
0
.
2
1
A
v
e
r
a
g
e
0
.
3
1
T
h
e
r
ea
d
i
n
g
r
esu
lts
o
n
T
a
b
le
3
ar
e
t
h
en
c
o
m
p
ar
e
d
with
th
e
r
esu
lts
o
b
tain
ed
f
r
o
m
th
e
5
k
g
s
ca
le
as
th
e
m
ain
r
ef
er
en
ce
.
T
h
e
p
u
r
p
o
s
e
o
f
th
is
co
m
p
ar
is
o
n
is
to
d
eter
m
in
e
th
e
d
if
f
er
e
n
ce
o
r
er
r
o
r
b
etwe
en
th
e
two
to
o
ls
.
T
h
u
s
,
it
ca
n
ass
ess
th
e
l
ev
el
o
f
ac
cu
r
ac
y
o
f
th
e
s
en
s
o
r
s
u
s
ed
in
th
is
s
y
s
tem
.
I
n
ad
d
itio
n
,
th
is
co
m
p
a
r
is
o
n
is
im
p
o
r
tan
t
to
ev
alu
ate
t
h
e
p
e
r
f
o
r
m
a
n
ce
o
f
th
e
s
en
s
o
r
in
ac
c
u
r
ate
weig
h
t
m
ea
s
u
r
em
en
t.
Fr
o
m
th
e
test
r
esu
lts
,
an
av
e
r
ag
e
er
r
o
r
v
alu
e
o
f
0
.
1
0
%
was
o
b
tain
ed
.
T
h
is
er
r
o
r
v
alu
e
in
d
icate
s
th
e
e
x
ten
t
t
o
wh
ich
th
e
s
en
s
o
r
r
ea
d
in
g
s
d
if
f
er
f
r
o
m
th
e
r
esu
lt
s
o
b
tain
ed
f
r
o
m
th
e
r
ef
er
en
ce
s
ca
les.
Ov
er
all,
th
e
er
r
o
r
o
f
0
.
1
0
%
is
s
till
with
in
th
e
ac
ce
p
tab
le
r
a
n
g
e
f
o
r
weig
h
t m
ea
s
u
r
em
en
t a
p
p
licatio
n
s
.
T
ab
le
4
is
th
e
r
esu
lt
o
f
3
0
d
ay
s
o
f
m
ea
s
u
r
em
e
n
t.
Feed
A
s
h
o
wed
s
ig
n
if
ican
t
ad
v
an
tag
es
o
v
er
f
ee
d
B
in
v
ar
io
u
s
asp
ec
ts
o
f
r
aisi
n
g
b
r
o
iler
s
in
clo
s
ed
-
h
o
u
s
e
ca
g
es.
C
h
ick
en
s
f
ed
f
ee
d
A
p
r
o
d
u
ce
d
less
m
an
u
r
e
weig
h
t,
in
d
icatin
g
b
etter
n
u
tr
ien
t
ab
s
o
r
p
tio
n
e
f
f
icien
cy
.
T
h
e
d
ec
r
ea
s
e
in
m
a
n
u
r
e
weig
h
t
in
ch
ick
en
s
f
e
d
f
ee
d
A
was
co
n
s
is
ten
t
f
r
o
m
d
ay
to
d
ay
,
wh
ile
in
f
ee
d
B
,
th
e
d
ec
r
ea
s
e
was
m
o
r
e
f
lu
ct
u
atin
g
.
Am
m
o
n
ia
lev
els
in
ca
g
es
with
f
ee
d
A
wer
e
also
lo
wer
th
an
th
o
s
e
with
f
ee
d
B
,
in
d
icatin
g
a
clea
n
er
an
d
h
e
alth
ier
en
v
ir
o
n
m
e
n
t.
T
h
is
r
ed
u
ce
s
th
e
r
is
k
o
f
r
esp
ir
ato
r
y
p
r
o
b
lem
s
in
th
e
ch
ick
en
s
.
T
h
e
m
o
r
e
s
ig
n
if
ican
t
r
ed
u
ctio
n
in
am
m
o
n
ia
i
n
ca
g
es with
f
ee
d
A
in
d
icate
s
th
at
th
is
f
ee
d
s
u
p
p
o
r
ts
th
e
h
ea
lth
o
f
th
e
c
h
ick
en
s
b
etter
.
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.
15
,
No
.
2
,
Ap
r
il
20
26
:
1
2
4
7
-
1
2
6
0
1254
T
ab
le
3
.
L
o
ad
ce
ll
ac
cu
r
ate
m
e
asu
r
e
Te
st
t
o
-
Te
st
r
e
su
l
t
s
S
c
a
l
e
s (g
r
a
ms)
S
e
n
s
o
r
l
o
a
d
c
e
l
l
(
g
r
a
m)
Er
r
o
r
(
%)
1
1
0
0
1
0
0
.
2
0
.
2
0
2
1
0
0
1
0
0
.
1
0
.
1
0
3
2
0
0
2
0
0
.
4
0
.
2
0
4
2
0
0
2
0
0
.
3
0
.
1
5
5
2
5
0
2
5
0
.
1
0
.
0
4
6
2
5
0
2
5
0
.
3
0
.
1
2
7
3
5
0
3
5
0
.
2
0
.
0
6
8
3
5
0
3
5
0
.
3
0
.
0
9
9
5
0
0
4
9
9
.
9
0
.
0
2
10
5
0
0
5
0
0
0
.
0
0
A
v
e
r
a
g
e
0
.
1
0
T
ab
le
4
.
Sy
s
tem
test
f
o
r
m
o
n
it
o
r
in
g
D
a
y
F
e
e
d
t
y
p
e
A
F
e
e
d
t
y
p
e
B
W
e
i
g
h
t
o
f
c
h
i
c
k
e
n
man
u
r
e
(
g
r
a
m)
A
mm
o
n
i
a
(
p
p
m)
Te
mp
e
r
a
t
u
r
e
(
°
C
)
W
e
i
g
h
t
o
f
c
h
i
c
k
e
n
man
u
r
e
(
g
r
a
m)
A
mm
o
n
i
a
(
p
p
m)
Te
mp
e
r
a
t
u
r
e
(
°
C
)
1
4
0
0
12
28
4
5
0
15
29
2
3
9
0
11
28
4
5
5
16
29
3
3
8
0
10
2
7
.
5
4
6
0
17
29
4
3
7
0
10
2
7
.
5
4
6
5
1
6
.
5
29
5
3
6
5
9
27
4
7
0
1
7
.
5
29
6
3
6
0
9
27
4
7
5
18
2
9
.
5
7
3
5
5
8
.
5
2
6
.
5
4
8
0
18
2
9
.
5
8
3
5
0
8
2
6
.
5
4
8
5
1
8
.
5
2
9
.
5
9
3
4
5
7
.
5
2
6
.
5
4
9
0
19
30
10
3
4
0
7
26
4
9
5
1
9
.
5
30
11
3
3
5
6
.
5
26
5
0
0
20
30
12
3
3
0
6
2
5
.
5
5
0
5
2
0
.
5
3
0
.
5
13
3
2
5
6
2
5
.
5
5
1
0
21
3
0
.
5
14
3
2
0
5
.
5
25
5
1
5
2
1
.
5
3
0
.
5
15
3
1
5
5
25
5
2
0
22
31
16
3
1
0
5
25
5
2
5
2
2
.
5
31
17
3
0
5
4
.
5
2
4
.
5
5
3
0
23
31
18
3
0
0
4
2
4
.
5
5
3
5
2
3
.
5
3
1
.
5
19
2
9
5
4
24
5
4
0
24
3
1
.
5
20
2
9
0
3
.
5
24
5
4
5
2
4
.
5
32
21
2
8
5
3
2
3
.
5
5
5
0
25
32
22
2
8
0
3
2
3
.
5
5
5
5
2
5
.
5
32
23
2
7
5
2
.
5
23
5
6
0
26
3
2
.
5
24
2
7
0
2
.
5
23
5
6
5
2
6
.
5
3
2
.
5
25
2
6
5
2
2
2
.
5
5
7
0
27
33
26
2
6
0
2
2
2
.
5
5
7
5
2
7
.
5
33
27
2
5
5
1
.
5
22
5
8
0
28
3
3
.
5
28
2
5
0
1
.
5
22
5
8
5
2
8
.
5
3
3
.
5
29
2
4
5
1
2
1
.
5
5
9
0
29
34
30
2
4
0
1
2
1
.
5
5
9
5
2
9
.
5
34
T
h
e
m
o
r
e
s
tab
le
a
n
d
lo
we
r
co
o
p
tem
p
er
atu
r
e
o
n
f
ee
d
A
s
u
p
p
o
r
ts
th
e
co
m
f
o
r
t
o
f
th
e
ch
ick
en
s
,
h
elp
in
g
th
em
m
ain
tain
an
o
p
ti
m
al
b
o
d
y
tem
p
e
r
atu
r
e.
C
h
ick
e
n
s
f
ed
f
ee
d
A
ar
e
less
lik
ely
t
o
ex
p
er
ien
ce
s
tr
ess
d
u
e
to
ex
ce
s
s
iv
ely
h
ig
h
am
b
ie
n
t te
m
p
er
atu
r
es.
L
ess
f
ec
es a
ls
o
in
d
icate
im
p
r
o
v
ed
o
v
er
all
ch
ick
en
welf
ar
e.
T
h
e
lo
w
am
m
o
n
ia
lev
els
in
ca
g
es
with
A
f
ee
d
c
o
n
tr
ib
u
te
to
a
cl
ea
n
er
an
d
s
af
er
atm
o
s
p
h
er
e
f
o
r
th
e
c
h
ick
en
s
.
T
h
is
h
ea
lth
y
en
v
ir
o
n
m
en
t
s
u
p
p
o
r
ts
b
etter
ch
ick
e
n
g
r
o
wth
a
n
d
r
ed
u
ce
s
th
e
r
is
k
o
f
d
is
ea
s
e.
C
h
ick
en
s
f
ed
f
ee
d
A
ap
p
ea
r
to
b
e
m
o
r
e
p
r
o
d
u
ctiv
e
d
u
e
to
m
o
r
e
c
o
n
d
u
civ
e
en
v
ir
o
n
m
en
tal
c
o
n
d
itio
n
s
.
T
h
e
m
o
r
e
s
tab
le
tem
p
er
at
u
r
e
h
elp
s
th
e
ch
ick
en
s
av
o
id
o
v
er
h
ea
tin
g
,
wh
ich
ca
n
s
lo
w
d
o
w
n
g
r
o
wth
.
Ov
er
all,
f
ee
d
A
p
r
o
d
u
ce
s
m
o
r
e
o
p
tim
al
co
n
d
itio
n
s
f
o
r
b
r
o
iler
s
in
clo
s
e
d
-
h
o
u
s
e
h
o
u
s
in
g
[
6
1
]
,
[
6
2
]
.
C
h
ic
k
e
n
s
f
e
d
wit
h
f
e
ed
A
a
r
e
m
o
r
e
p
r
o
d
u
cti
v
e
d
u
e
t
o
s
ta
b
le
en
v
i
r
o
n
m
e
n
t
al
co
n
d
it
io
n
s
in
cl
o
s
e
d
-
h
o
u
s
e
s
y
s
te
m
s
.
C
o
n
s
is
t
en
t
te
m
p
e
r
at
u
r
es
h
el
p
p
r
ev
e
n
t
h
ea
t
s
tr
ess
,
wh
ic
h
c
an
h
i
n
d
e
r
b
r
o
il
e
r
g
r
o
wt
h
a
n
d
r
e
d
u
c
e
ef
f
ic
ie
n
c
y
.
A
d
d
iti
o
n
a
ll
y
,
lo
w
er
a
n
d
wel
l
-
m
a
n
ag
e
d
a
m
m
o
n
ia
le
v
els
s
u
p
p
o
r
t
b
e
tte
r
r
es
p
i
r
at
o
r
y
h
ea
lt
h
a
n
d
im
p
r
o
v
e
f
e
ed
co
n
v
e
r
s
i
o
n
.
T
o
q
u
a
n
ti
f
y
f
ee
d
A
’
s
im
p
a
ct
,
a
GA
is
a
p
p
lie
d
t
o
d
e
v
el
o
p
a
p
r
e
d
i
cti
v
e
m
o
d
el
f
o
r
ch
i
c
k
e
n
m
a
n
u
r
e
p
r
o
d
u
c
ti
o
n
.
Usi
n
g
te
m
p
e
r
at
u
r
e
a
n
d
a
m
m
o
n
ia
c
o
n
c
en
tr
ati
o
n
as
i
n
p
u
ts
,
t
h
e
GA
o
p
t
im
i
ze
s
a
s
im
p
le
l
in
ea
r
r
eg
r
ess
io
n
e
q
u
a
t
io
n
.
T
h
is
m
o
d
el
e
f
f
ec
ti
v
el
y
li
n
k
s
en
v
i
r
o
n
m
en
tal
c
o
n
d
it
io
n
s
t
o
m
an
u
r
e
o
u
tp
u
t
,
p
r
o
v
i
d
i
n
g
in
s
ig
h
ts
i
n
t
o
p
r
o
d
u
ct
iv
i
ty
b
e
n
e
f
its
o
f
u
s
i
n
g
f
e
ed
A
.
Fo
r
e
x
am
p
l
e,
i
n
it
ial
r
e
g
r
ess
i
o
n
e
q
u
ati
o
n
as
i
n
(
4
)
.
(
)
=
⋅
(
)
+
⋅
(
)
+
(
4
)
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
Gen
etic
a
lg
o
r
ith
m
-
b
a
s
ed
c
h
icke
n
ma
n
u
r
e
w
eig
h
t p
r
ed
ictio
n
s
ystem
d
ev
elo
p
men
t
(
R
id
a
Hu
d
a
ya
)
1255
W
h
er
e
(
)
is
th
e
weig
h
t
o
f
ch
ick
en
m
an
u
r
e
o
n
d
ay
,
(
)
is
th
e
tem
p
er
atu
r
e
o
n
d
a
y
,
(
)
is
t
h
e
co
n
ce
n
tr
atio
n
o
f
am
m
o
n
ia
g
a
s
o
n
d
a
y
,
an
d
(
,
,
)
ar
e
p
a
r
a
m
eter
s
o
p
tim
ized
u
s
in
g
a
GA
.
Af
ter
s
ev
er
al
iter
atio
n
s
o
f
o
p
tim
izatio
n
,
th
e
b
est
-
f
it p
ar
am
eter
s
wer
e
f
o
u
n
d
to
b
e
a
=
-
0
.
7
5
,
b
=1
.
5
,
an
d
c
=1
0
0
.
T
h
e
n
e
g
ativ
e
v
alu
e
o
f
r
ef
lects
th
e
in
v
er
s
e
r
elatio
n
s
h
ip
b
etwe
en
tem
p
er
atu
r
e
an
d
m
an
u
r
e
weig
h
t,
wh
ile
th
e
p
o
s
itiv
e
v
alu
e
in
d
icate
s
th
at
h
ig
h
er
a
m
m
o
n
ia
c
o
n
ce
n
tr
ati
o
n
s
ar
e
a
s
s
o
ciate
d
with
in
cr
ea
s
ed
wei
g
h
t.
T
h
e
co
n
s
tan
t
h
elp
s
to
im
p
r
o
v
e
th
e
m
o
d
el’
s
p
r
ed
ictio
n
ac
cu
r
ac
y
.
W
ith
th
e
s
e
p
ar
am
eter
s
,
th
e
m
o
d
el
ca
n
b
etter
esti
m
ate
th
e
weig
h
t o
f
ch
ic
k
en
m
a
n
u
r
e
u
n
d
er
v
ar
y
i
n
g
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
,
as sh
o
wn
in
T
ab
le
5
.
T
ab
le
5
.
Sy
s
tem
test
f
o
r
m
o
n
it
o
r
in
g
P
r
e
d
i
c
t
i
o
n
c
a
l
c
u
l
a
t
i
o
n
m
o
d
e
l
Te
mp
e
r
a
t
u
r
e
(
°
C
)
A
mm
o
n
i
a
g
a
s (
p
p
m)
C
h
i
c
k
e
n
m
a
n
u
r
e
w
e
i
g
h
t
o
n
g
r
a
m (
p
r
e
d
i
c
t
e
d
)
1
28
12
(
1
)
=
−
0
.
75
(
28
)
+
1
.
5
(
12
)
+
100
=
97
.
5
2
28
11
(
2
)
=
−
0
.
75
(
28
)
+
1
.
5
(
11
)
+
100
=
96
3
2
7
.
5
10
(
3
)
=
−
0
.
75
(
27
.
5
)
+
1
.
5
(
10
)
+
100
=
96
.
125
4
2
7
.
5
10
(
4
)
=
−
0
.
75
(
27
.
5
)
+
1
.
5
(
10
)
+
100
=
96
.
125
5
27
9
(
5
)
=
−
0
.
75
(
27
)
+
1
.
5
(
9
)
+
100
=
94
.
5
6
27
9
(
6
)
=
−
0
.
75
(
27
)
+
1
.
5
(
9
)
+
100
=
94
.
5
7
2
6
.
5
8
.
5
(
7
)
=
−
0
.
75
(
26
.
5
)
+
1
.
5
(
8
.
5
)
+
100
=
94
.
625
8
2
6
.
5
8
(
8
)
=
−
0
.
75
(
26
.
5
)
+
1
.
5
(
8
)
+
100
=
93
.
875
9
2
6
.
5
7
.
5
(
9
)
=
−
0
.
75
(
26
.
5
)
+
1
.
5
(
7
.
5
)
+
100
=
93
.
125
10
26
7
(
10
)
=
−
0
.
75
(
26
)
+
1
.
5
(
7
)
+
100
=
91
.
5
11
26
6
.
5
(
11
)
=
−
0
.
75
(
26
)
+
1
.
5
(
6
.
5
)
+
100
=
90
.
75
12
2
5
.
5
6
(
12
)
=
−
0
.
75
(
25
.
5
)
+
1
.
5
(
6
)
+
100
=
90
.
875
13
2
5
.
5
6
(
13
)
=
−
0
.
75
(
25
.
5
)
+
1
.
5
(
6
)
+
100
=
90
.
875
14
25
5
.
5
(
14
)
=
−
0
.
75
(
25
)
+
1
.
5
(
5
.
5
)
+
100
=
90
.
125
15
25
5
(
15
)
=
−
0
.
75
(
25
)
+
1
.
5
(
5
)
+
100
=
89
.
375
16
25
5
(
16
)
=
−
0
.
75
(
25
)
+
1
.
5
(
5
)
+
100
=
89
.
375
17
2
4
.
5
4
.
5
(
17
)
=
−
0
.
75
(
24
.
5
)
+
1
.
5
(
4
.
5
)
+
100
=
88
.
875
18
2
4
.
5
4
(
18
)
=
−
0
.
75
(
24
.
5
)
+
1
.
5
(
4
)
+
100
=
88
.
125
19
24
4
(
19
)
=
−
0
.
75
(
24
)
+
1
.
5
(
4
)
+
100
=
87
.
5
20
24
3
.
5
(
20
)
=
−
0
.
75
(
24
)
+
1
.
5
(
3
.
5
)
+
100
=
86
.
75
21
2
3
.
5
3
(
21
)
=
−
0
.
75
(
23
.
5
)
+
1
.
5
(
3
)
+
100
=
86
.
875
22
2
3
.
5
3
(
22
)
=
−
0
.
75
(
23
.
5
)
+
1
.
5
(
3
)
+
100
=
86
.
875
23
23
2
.
5
(
23
)
=
−
0
.
75
(
23
)
+
1
.
5
(
2
.
5
)
+
100
=
86
.
125
24
23
2
.
5
(
24
)
=
−
0
.
75
(
23
)
+
1
.
5
(
2
.
5
)
+
100
=
86
.
125
25
2
2
.
5
2
(
25
)
=
−
0
.
75
(
22
.
5
)
+
1
.
5
(
2
)
+
100
=
85
.
625
26
2
2
.
5
2
(
26
)
=
−
0
.
75
(
22
.
5
)
+
1
.
5
(
2
)
+
100
=
85
.
625
27
22
1
.
5
(
27
)
=
−
0
.
75
(
22
)
+
1
.
5
(
1
.
5
)
+
100
=
84
.
875
28
22
1
.
5
(
28
)
=
−
0
.
75
(
22
)
+
1
.
5
(
1
.
5
)
+
100
=
84
.
875
29
2
1
.
5
1
(
29
)
=
−
0
.
75
(
21
.
5
)
+
1
.
5
(
1
)
+
100
=
84
.
375
30
2
1
.
5
1
(
30
)
=
−
0
.
75
(
21
.
5
)
+
1
.
5
(
1
)
+
100
=
84
.
375
Alth
o
u
g
h
th
e
s
tu
d
y
s
u
cc
ess
f
u
lly
em
p
lo
y
s
a
GA
to
o
p
tim
ize
t
h
e
p
r
ed
ictiv
e
m
o
d
el
f
o
r
ch
ick
en
m
an
u
r
e
weig
h
t
—
y
ield
in
g
c
o
ef
f
icien
ts
=
-
0
.
7
5
,
=1
.
5
,
an
d
=1
0
0
—
th
e
p
ap
e
r
lac
k
s
cr
itical
m
eth
o
d
o
l
o
g
ical
tr
an
s
p
ar
en
cy
.
Sp
ec
if
ically
,
it d
o
es n
o
t d
is
clo
s
e
th
e
co
n
f
ig
u
r
atio
n
an
d
o
p
er
atio
n
al
p
a
r
am
eter
s
o
f
th
e
GA,
wh
ich
ar
e
ess
en
tial
f
o
r
r
ep
r
o
d
u
cib
ilit
y
an
d
s
cien
tific
r
i
g
o
r
.
Ab
s
en
t
f
r
o
m
th
e
d
escr
ip
tio
n
a
r
e
k
ey
e
lem
en
ts
s
u
ch
as
th
e
f
o
r
m
u
latio
n
o
f
th
e
f
itn
ess
f
u
n
ctio
n
u
s
ed
t
o
ev
al
u
ate
ca
n
d
i
d
a
te
s
o
lu
tio
n
s
,
th
e
i
n
itial
s
ea
r
ch
s
p
ac
e
o
r
p
ar
am
eter
b
o
u
n
d
s
f
o
r
a,
b
,
an
d
c
,
an
d
t
h
e
d
etails
o
f
th
e
alg
o
r
ith
m
’
s
co
n
f
ig
u
r
atio
n
,
i
n
clu
d
in
g
p
o
p
u
latio
n
s
ize,
n
u
m
b
e
r
o
f
g
en
er
atio
n
s
,
s
elec
tio
n
s
tr
ateg
y
,
cr
o
s
s
o
v
er
m
eth
o
d
,
a
n
d
m
u
tat
io
n
r
ate.
T
o
ev
al
u
ate
m
o
d
el
ac
c
u
r
ac
y
o
n
Fig
u
r
e
9
,
th
e
p
r
e
d
icted
m
an
u
r
e
weig
h
ts
wer
e
c
o
m
p
ar
ed
with
3
0
ac
tu
al
m
ea
s
u
r
em
en
t
p
o
in
t
s
.
T
h
e
m
o
d
el
ac
h
ie
v
ed
a
n
R
MSE
o
f
0
.
3
5
8
g
,
m
ea
n
ab
s
o
l
u
te
er
r
o
r
(
MA
E
)
o
f
0
.
2
9
2
g
,
an
d
R
2
o
f
0
.
9
9
2
,
i
n
d
i
ca
tin
g
ex
ce
llen
t
p
r
e
d
ictiv
e
p
r
e
cisi
o
n
.
Fig
u
r
e
9
p
r
esen
ts
th
e
p
r
ed
icted
v
s
.
ac
tu
al
m
an
u
r
e
weig
h
t
p
lo
t,
wh
er
e
a
ll
d
ata
p
o
in
ts
clo
s
ely
f
o
llo
w
th
e
id
ea
l
1
:1
r
ef
er
e
n
ce
lin
e
.
Sen
s
itiv
ity
an
aly
s
is
s
h
o
ws
th
at
m
an
u
r
e
weig
h
t
is
n
eg
ativ
ely
in
f
lu
e
n
ce
d
b
y
tem
p
er
atu
r
e
(
-
0
.
7
5
g
p
er
°C
)
an
d
p
o
s
itiv
ely
in
f
lu
en
ce
d
b
y
am
m
o
n
ia
co
n
ce
n
tr
atio
n
(
+
1
.
5
g
p
er
p
p
m
)
.
T
h
e
s
tr
o
n
g
er
s
en
s
itiv
ity
to
am
m
o
n
ia
s
u
g
g
est
s
th
at
g
as b
u
ild
u
p
is
a
m
o
r
e
in
f
lu
en
tial
an
d
r
eliab
le
in
d
icato
r
o
f
m
an
u
r
e
ac
cu
m
u
latio
n
co
m
p
a
r
ed
to
tem
p
e
r
atu
r
e
alo
n
e.
T
h
ese
r
esu
lts
d
em
o
n
s
tr
ate
th
at
th
e
GA
-
o
p
tim
ized
m
o
d
el
p
r
o
v
id
es
h
ig
h
ly
ac
cu
r
ate
p
r
ed
icti
o
n
s
an
d
m
ea
n
i
n
g
f
u
l
in
s
ig
h
t in
to
en
v
i
r
o
n
m
e
n
tal
f
ac
to
r
s
af
f
ec
tin
g
m
a
n
u
r
e
p
r
o
d
u
cti
o
n
.
T
h
e
s
ca
lab
ilit
y
ev
alu
atio
n
f
o
r
a
two
-
n
o
d
e
o
n
T
a
b
le
6
d
e
p
lo
y
m
en
t
d
em
o
n
s
tr
ates
th
at
t
h
e
s
y
s
tem
p
er
f
o
r
m
s
ef
f
icien
tly
u
n
d
er
s
i
m
u
ltan
eo
u
s
o
p
er
atio
n
o
f
m
u
lt
ip
le
s
en
s
o
r
u
n
its
.
E
ac
h
n
o
d
e
in
teg
r
ates
an
HX7
1
1
m
o
d
u
le
with
f
o
u
r
lo
a
d
ce
lls
,
a
DHT
2
2
s
en
s
o
r
,
an
MQ
-
1
3
7
g
a
s
s
en
s
o
r
,
an
d
an
E
SP
3
2
m
icr
o
co
n
tr
o
ller
p
o
wer
e
d
b
y
a
5
V,
2
A
s
u
p
p
ly
.
T
h
e
r
e
s
u
lts
s
h
o
w
h
ig
h
d
ata
tr
an
s
m
is
s
io
n
r
eliab
ilit
y
,
with
p
ac
k
et
d
eliv
er
y
r
ates
ab
o
v
e
9
8
%
f
o
r
b
o
th
n
o
d
es,
in
d
icatin
g
s
tab
le
W
i
-
Fi
co
n
n
ec
tiv
ity
e
v
en
wh
e
n
s
h
a
r
in
g
th
e
s
am
e
ac
ce
s
s
p
o
in
t.
L
ate
n
cy
v
alu
es
r
em
ain
ac
ce
p
tab
le,
av
e
r
ag
in
g
1
3
1
m
s
s
y
s
tem
-
wid
e,
wh
ich
is
s
u
f
f
icien
t
f
o
r
en
v
ir
o
n
m
en
tal
m
o
n
ito
r
in
g
ap
p
licatio
n
s
th
at
d
o
n
o
t r
e
q
u
ir
e
r
ea
l
-
tim
e
m
illi
s
ec
o
n
d
r
esp
o
n
s
iv
en
ess
.
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.
15
,
No
.
2
,
Ap
r
il
20
26
:
1
2
4
7
-
1
2
6
0
1256
Fig
u
r
e
9
.
C
o
m
p
a
r
is
o
n
r
esu
lts
o
f
m
an
u
r
e
weig
h
t
T
ab
le
6
.
Scalab
ilit
y
ev
alu
atio
n
M
e
t
r
i
c
N
o
d
e
1
N
o
d
e
2
C
o
m
b
i
n
e
d
/
sy
s
t
e
m
(
2
n
o
d
e
s)
P
a
c
k
e
t
d
e
l
i
v
e
r
y
r
a
t
e
(
%)
9
8
.
6
9
8
.
3
9
8
.
4
5
A
v
e
r
a
g
e
r
o
u
n
d
-
t
r
i
p
l
a
t
e
n
c
y
(
ms)
1
2
5
1
3
8
1
3
1
.
5
P
a
c
k
e
t
l
o
ss (%)
1
.
4
1
.
7
1
.
5
5
A
v
e
r
a
g
e
c
l
o
u
d
w
r
i
t
e
s res
p
o
n
s
e
t
i
m
e
(
ms)
1
7
0
1
9
0
1
8
0
A
v
e
r
a
g
e
C
P
U
l
o
a
d
o
n
ESP
3
2
(
%)
34
36
—
A
v
e
r
a
g
e
R
A
M
u
sa
g
e
o
n
ESP
3
2
(
%)
38
41
—
A
v
e
r
a
g
e
c
u
r
r
e
n
t
d
r
a
w
(
mA
)
2
1
0
2
2
0
4
3
0
P
e
a
k
c
u
r
r
e
n
t
d
r
a
w
(
mA
)
4
5
0
4
8
0
~
9
3
0
P
o
w
e
r
s
u
p
p
l
y
u
t
i
l
i
z
a
t
i
o
n
(
o
f
5
V
/
2
A
)
2
1
%
2
2
%
~
4
3
%
(
t
w
o
P
S
U
s)
A
u
t
o
-
r
e
c
o
n
n
e
c
t
t
i
me
a
f
t
e
r
b
r
i
e
f
A
P
o
u
t
a
g
e
(
s)
2
.
5
3
.
2
≤
3
.
2
C
l
o
u
d
w
r
i
t
e
s
t
h
r
o
u
g
h
p
u
t
(
s
a
m
p
l
e
s
/
s)
0
.
1
0
0
.
1
0
0
.
2
0
O
b
serv
e
d
W
i
-
F
i
r
e
t
r
i
e
s
/
i
n
t
e
r
f
e
r
e
n
c
e
Lo
w
Lo
w
Lo
w
Po
wer
co
n
s
u
m
p
tio
n
also
s
tay
s
with
in
s
af
e
o
p
er
atio
n
al
r
an
g
es,
with
ea
ch
n
o
d
e
d
r
aw
in
g
ar
o
u
n
d
210
-
2
2
0
m
A
d
u
r
i
n
g
n
o
r
m
a
l
o
p
e
r
a
t
i
o
n
a
n
d
p
e
a
k
i
n
g
u
n
d
e
r
t
h
e
p
o
w
e
r
s
u
p
p
l
y
l
i
m
it
.
C
P
U
a
n
d
R
A
M
u
s
a
g
e
r
e
m
a
i
n
m
o
d
e
r
a
t
e
,
c
o
n
f
i
r
m
i
n
g
t
h
a
t
ea
c
h
E
S
P
3
2
c
a
n
h
a
n
d
l
e
m
u
lt
i
-
s
e
n
s
o
r
d
a
t
a
a
c
q
u
is
i
ti
o
n
w
it
h
o
u
t
p
e
r
f
o
r
m
a
n
c
e
d
e
g
r
a
d
a
t
i
o
n
.
O
v
e
r
a
ll
,
t
h
e
t
w
o
-
n
o
d
e
c
o
n
f
i
g
u
r
a
t
i
o
n
d
e
m
o
n
s
t
r
a
te
s
s
t
r
o
n
g
s
ca
l
a
b
il
i
t
y
,
r
el
i
a
b
le
co
m
m
u
n
i
c
a
t
i
o
n
,
a
n
d
e
f
f
i
c
i
e
n
t
p
o
w
e
r
u
ti
l
i
za
t
i
o
n
,
p
r
o
v
i
n
g
t
h
e
s
y
s
te
m
’
s
s
u
i
t
a
b
i
l
it
y
f
o
r
e
x
p
a
n
d
i
n
g
t
o
l
a
r
g
e
r
p
o
u
l
t
r
y
m
o
n
i
t
o
r
i
n
g
n
e
t
w
o
r
k
s
.
T
h
ese
elem
en
ts
ar
e
n
o
t
m
er
el
y
tech
n
icalities
b
u
t
f
o
u
n
d
atio
n
al
asp
ec
ts
th
at
s
h
ap
e
th
e
o
p
tim
izatio
n
p
r
o
ce
s
s
an
d
in
f
lu
e
n
ce
th
e
m
o
d
el’
s
p
er
f
o
r
m
a
n
ce
.
Fo
r
in
s
tan
ce
,
th
e
ch
o
ice
o
f
f
itn
ess
f
u
n
ctio
n
—
s
u
ch
as
MSE
o
r
an
o
th
er
lo
s
s
m
etr
ic
—
d
ir
ec
tly
d
eter
m
in
es
h
o
w
th
e
GA
ev
a
lu
ates
p
r
ed
ictio
n
ac
cu
r
ac
y
.
L
i
k
ewise,
p
o
p
u
latio
n
d
iv
er
s
ity
,
co
n
v
er
g
e
n
ce
b
e
h
av
io
r
,
an
d
th
e
a
b
ilit
y
to
escap
e
lo
ca
l
m
in
im
a
ar
e
h
ea
v
ily
d
ep
en
d
e
n
t
o
n
GA
p
ar
am
eter
s
.
W
ith
o
u
t
d
is
clo
s
u
r
e
o
f
th
ese
d
etails,
th
e
o
p
tim
izatio
n
p
r
o
ce
s
s
b
ec
o
m
es
a
“b
la
ck
b
o
x
,
”
h
in
d
e
r
in
g
th
e
ab
ilit
y
o
f
o
th
e
r
r
esear
ch
e
r
s
to
r
ep
licate
th
e
f
in
d
in
g
s
,
ass
ess
th
eir
r
o
b
u
s
tn
ess
,
o
r
ap
p
l
y
th
e
m
eth
o
d
o
lo
g
y
in
r
elate
d
co
n
tex
ts
.
Giv
en
th
e
in
cr
ea
s
in
g
r
elian
ce
o
n
ev
o
l
u
tio
n
ar
y
alg
o
r
ith
m
s
in
p
r
ed
ictiv
e
m
o
d
elin
g
,
it is
im
p
e
r
ativ
e
th
at
f
u
tu
r
e
v
er
s
io
n
s
o
f
th
is
wo
r
k
p
r
o
v
id
e
a
co
m
p
r
eh
en
s
iv
e
d
escr
ip
tio
n
o
f
th
e
GA
im
p
lem
en
tatio
n
.
T
h
is
in
clu
d
es
b
o
th
alg
o
r
ith
m
ic
s
ettin
g
s
an
d
th
e
r
atio
n
ale
f
o
r
th
eir
s
elec
tio
n
.
Su
ch
tr
an
s
p
ar
en
c
y
wo
u
ld
n
o
t
o
n
ly
en
h
an
ce
th
e
cr
ed
ib
ilit
y
o
f
th
e
r
esu
lts
b
u
t
also
en
ab
le
r
ep
r
o
d
u
cib
ilit
y
,
c
o
m
p
ar
is
o
n
with
alter
n
ativ
e
ap
p
r
o
ac
h
es,
an
d
f
u
r
th
e
r
d
ev
elo
p
m
e
n
t
with
in
th
e
f
ield
.
Deta
iled
r
ep
o
r
tin
g
o
f
th
e
GA
ex
ec
u
tio
n
p
r
o
ce
s
s
is
th
u
s
a
n
ec
ess
ar
y
s
tep
to
war
d
estab
lis
h
in
g
a
m
eth
o
d
o
lo
g
icall
y
s
o
u
n
d
an
d
v
er
if
iab
le
m
o
d
eli
n
g
f
r
a
m
ewo
r
k
.
4.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
s
u
cc
ess
f
u
lly
d
ev
elo
p
e
d
an
I
o
T
-
b
ased
en
v
ir
o
n
m
e
n
tal
m
o
n
ito
r
in
g
an
d
p
r
ed
ictiv
e
m
o
d
elin
g
s
y
s
tem
f
o
r
b
r
o
iler
c
h
ick
en
p
r
o
d
u
ctio
n
.
T
h
e
in
teg
r
ated
p
latf
o
r
m
—
co
m
p
r
is
in
g
M
Q
-
1
3
7
,
DHT
2
2
,
an
d
lo
ad
ce
ll
s
en
s
o
r
s
—
d
em
o
n
s
tr
ated
h
ig
h
ac
cu
r
ac
y
,
as
r
ef
lecte
d
b
y
lo
w
av
er
ag
e
er
r
o
r
s
o
f
0
.
3
1
%
f
o
r
am
m
o
n
ia
m
ea
s
u
r
em
en
t
an
d
0
.
1
0
%
f
o
r
m
an
u
r
e
weig
h
t
esti
m
atio
n
.
T
h
e
s
y
s
tem
r
eliab
ly
co
llected
3
0
d
ay
s
o
f
en
v
ir
o
n
m
en
tal
an
d
m
an
u
r
e
d
a
ta
f
r
o
m
two
ch
ick
en
d
r
u
m
m
o
d
els,
en
ab
lin
g
d
etailed
co
m
p
a
r
is
o
n
b
etwe
en
f
ee
d
ty
p
e
A
a
n
d
f
ee
d
ty
p
e
B
.
R
esu
lts
s
h
o
wed
th
at
f
ee
d
A
c
o
n
s
is
ten
tly
p
r
o
d
u
ce
d
lo
wer
m
an
u
r
e
weig
h
t,
r
ed
u
ce
d
am
m
o
n
ia
lev
els,
an
d
m
o
r
e
s
t
ab
le
ca
g
e
tem
p
er
atu
r
es,
in
d
ic
atin
g
b
etter
n
u
tr
ie
n
t
u
tili
za
tio
n
,
im
p
r
o
v
ed
an
i
m
al
co
m
f
o
r
t,
an
d
h
ea
lth
ier
e
n
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
.
T
o
m
o
d
el
m
an
u
r
e
ac
cu
m
u
latio
n
,
a
GA
was
ap
p
lied
to
o
p
tim
ize
th
e
p
ar
a
m
eter
s
o
f
a
s
im
p
le
r
eg
r
ess
io
n
eq
u
atio
n
u
s
in
g
tem
p
er
atu
r
e
an
d
am
m
o
n
ia
as
p
r
e
d
icto
r
s
.
T
h
e
GA
-
o
p
tim
ized
m
o
d
el
ac
h
iev
e
d
h
ig
h
p
r
ed
ictiv
e
p
er
f
o
r
m
an
c
e,
with
R
MSE
o
f
0
.
3
5
8
g
,
M
AE
o
f
0
.
2
9
2
g
,
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.