I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
,
p
p
.
4
4
1
~
4
4
9
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
6
.
i
1
.
pp
44
1
-
4
4
9
441
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Ca
tt
le
weig
ht
pre
diction mo
del
usi
ng
conv
o
lutiona
l neural
network a
nd
artif
icia
l neural ne
two
rk
Yulia
nin
g
s
ih
1
,
Sri N
urdia
t
i
2
,
H
er
u Suk
o
co
1
,
Cec
e
Su
m
a
n
t
ri
3
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
F
a
c
u
l
t
y
o
f
M
a
t
h
e
ma
t
i
c
s
a
n
d
N
a
t
u
r
a
l
S
c
i
e
n
c
e
,
I
P
B
U
n
i
v
e
r
s
i
t
y
,
B
o
g
o
r
,
I
n
d
o
n
e
s
i
a
2
D
e
p
a
r
t
me
n
t
o
f
M
a
t
h
e
m
a
t
i
c
s
,
F
a
c
u
l
t
y
o
f
M
a
t
h
e
mat
i
c
s
a
n
d
N
a
t
u
r
a
l
S
c
i
e
n
c
e
,
I
P
B
U
n
i
v
e
r
si
t
y
,
B
o
g
o
r
,
I
n
d
o
n
e
si
a
3
D
e
p
a
r
t
e
m
e
n
A
n
i
ma
l
P
r
o
d
u
c
t
i
o
n
a
n
d
Te
c
h
n
o
l
o
g
y
,
F
a
c
u
l
t
y
o
f
A
n
i
m
a
l
S
c
i
e
n
c
e
,
I
P
B
U
n
i
v
e
r
si
t
y
,
B
o
g
o
r
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
16
,
2
0
2
4
R
ev
is
ed
Ma
y
20
,
2
0
2
4
Acc
ep
ted
J
u
n
5
,
2
0
2
4
Th
e
we
ig
h
t
o
f
li
v
e
sto
c
k
is
a
c
ru
c
ial
m
e
tri
c
fo
r
e
v
a
lu
a
ti
n
g
m
a
n
a
g
e
m
e
n
t
e
ffica
c
y
,
in
fo
rm
i
n
g
p
o
li
c
y
d
e
c
isi
o
n
s,
a
n
d
d
e
term
in
i
n
g
th
e
m
a
rk
e
t
v
a
lu
e
o
f
a
n
ima
ls.
In
c
e
rtain
sc
e
n
a
rio
s,
c
o
n
v
e
n
ti
o
n
a
l
m
e
th
o
d
s
su
c
h
a
s
p
h
y
sic
a
l
we
ig
h
in
g
a
n
d
m
e
a
su
re
m
e
n
t
c
a
lcu
latio
n
s c
a
n
p
r
o
v
e
c
h
a
ll
e
n
g
i
n
g
,
i
n
c
l
u
d
i
n
g
t
h
e
a
b
se
n
c
e
o
f
li
v
e
sto
c
k
h
e
a
lt
h
re
c
o
rd
s
o
r
we
ig
h
i
n
g
e
q
u
ip
m
e
n
t
.
Th
i
s
re
se
a
r
c
h
a
ims
to
d
e
v
e
lo
p
a
p
re
d
ictiv
e
m
o
d
e
l
fo
r
e
stim
a
ti
n
g
t
h
e
li
v
e
we
ig
h
t
o
f
c
a
tt
le
th
ro
u
g
h
v
isu
a
l
a
ss
e
ss
m
e
n
ts
a
n
d
m
e
tad
a
ta,
in
c
lu
d
in
g
a
g
e
a
n
d
p
ix
e
l
c
o
u
n
t,
u
ti
li
z
i
n
g
a
c
o
m
b
i
n
a
ti
o
n
o
f
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
r
k
(CNN
)
a
n
d
a
rti
ficia
l
n
e
u
ra
l
n
e
two
r
k
(AN
N)
m
e
th
o
d
o
lo
g
ies
.
A
t
o
tal
o
f
2
2
3
d
a
ta
we
re
o
b
tai
n
e
d
fro
m
a
lo
c
a
l
fa
rm
b
e
fo
re
a
u
g
m
e
n
tatio
n
.
T
h
e
m
o
d
e
l'
s
p
re
d
ictiv
e
c
a
p
a
b
il
it
y
wa
s
su
c
c
e
ss
fu
ll
y
d
e
m
o
n
stra
ted
,
with
it
s
p
e
rfo
rm
a
n
c
e
q
u
a
n
ti
fi
e
d
b
y
a
n
a
v
e
ra
g
e
m
e
a
n
a
b
so
lu
te
p
e
rc
e
n
tag
e
e
rro
r
(M
APE
)
o
f
1
0
%
o
n
tes
t
d
a
ta.
Th
is
stu
d
y
d
e
m
o
n
stra
tes
th
a
t
t
h
ro
u
g
h
t
h
e
c
o
m
b
in
a
ti
o
n
o
f
CNN
a
n
d
AN
N,
a
s
we
ll
a
s
o
p
ti
m
a
l
p
a
ra
m
e
ter
tu
n
in
g
,
e
fficie
n
t
p
re
d
ictio
n
o
f
c
a
tt
le
we
ig
h
t
c
a
n
b
e
a
c
h
iev
e
d
.
K
ey
w
o
r
d
s
:
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
C
attle
weig
h
t
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
Me
an
ab
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
Pre
d
ictio
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
:
Yu
lian
in
g
s
ih
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
Facu
lty
o
f
Ma
th
em
atics a
n
d
Natu
r
al
Scien
ce
,
I
PB
Un
iv
er
s
ity
Stre
et
o
f
Ag
atis
,
C
am
p
u
s
I
PB
Dar
m
ag
a
B
o
g
o
r
1
6
6
8
0
,
I
n
d
o
n
esia
E
m
ail:
ip
b
_
y
u
lia
n
in
g
s
ih
@
ap
p
s
.
ip
b
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
liv
esto
ck
s
u
b
s
ec
to
r
’
s
ab
ilit
y
to
m
ee
t
th
e
d
em
an
d
f
o
r
an
im
al
-
s
o
u
r
c
ed
p
r
o
d
u
cts
is
h
ea
v
ily
in
f
lu
en
ce
d
b
y
m
a
n
ag
em
en
t
p
r
ac
tices.
I
n
I
n
d
o
n
esia,
v
ar
i
o
u
s
l
iv
esto
ck
co
m
m
o
d
ities
ar
e
p
r
o
d
u
ce
d
b
y
L
iv
esto
ck
B
u
s
in
ess
Ho
u
s
eh
o
ld
s
(
R
T
UP)
,
with
a
n
o
tab
le
in
c
r
ea
s
e
o
f
4
.
5
6
%
f
r
o
m
2
0
1
3
to
2
0
1
8
[
1
]
.
A
k
ey
in
d
icato
r
o
f
s
u
cc
ess
f
u
l
liv
esto
ck
r
ea
r
in
g
is
h
ea
lth
y
weig
h
t
g
ain
.
R
eg
u
lar
weig
h
t
m
ea
s
u
r
em
e
n
ts
ar
e
ess
en
tial
f
o
r
m
o
n
ito
r
in
g
liv
esto
ck
d
ev
elo
p
m
en
t
an
d
ass
ess
in
g
th
e
im
p
ac
t
o
f
tech
n
o
lo
g
ical
o
r
m
an
ag
e
m
en
t
in
ter
v
en
ti
o
n
s
.
Sev
er
al
m
eth
o
d
s
ar
e
cu
r
r
en
tl
y
u
s
ed
t
o
esti
m
ate
ca
ttle
weig
h
t.
T
h
ese
in
clu
d
e
f
o
r
m
u
las
b
ased
o
n
p
h
y
s
ical
d
im
en
s
io
n
s
lik
e
ch
est
cir
cu
m
f
er
en
ce
[
2
]
an
d
b
o
d
y
len
g
th
o
r
m
o
r
p
h
o
m
etr
ics
[
3
]
,
wh
ich
ar
e
b
eliev
ed
t
o
co
r
r
elate
with
weig
h
t.
Ho
wev
er
,
s
tu
d
ies
h
av
e
s
h
o
wn
th
at
th
ese
f
o
r
m
u
las
ca
n
d
ev
iate
f
r
o
m
ac
tu
al
weig
h
ts
[
4
]
.
E
f
f
o
r
ts
to
m
o
d
if
y
th
ese
f
o
r
m
u
las
to
s
u
it
d
if
f
er
en
t
ca
ttle
b
r
ee
d
s
h
av
e
n
o
t
y
ield
ed
a
u
n
iv
er
s
al
s
o
lu
tio
n
,
lar
g
ely
d
u
e
to
v
a
r
iatio
n
s
in
en
v
ir
o
n
m
en
tal
f
ac
to
r
s
,
f
ee
d
i
n
g
p
r
ac
tices,
an
d
th
e
s
ize
an
d
s
h
a
p
e
o
f
th
e
ca
ttle
[
5
]
,
[
6
]
in
clu
d
in
g
th
e
lack
o
f
s
u
f
f
icien
t
ly
co
m
p
r
e
h
en
s
iv
e
h
ea
lth
r
ec
o
r
d
s
.
An
o
th
er
m
et
h
o
d
,
d
ir
ec
t w
e
ig
h
in
g
with
s
ca
les,
ca
n
y
ield
m
o
r
e
ac
cu
r
ate
r
esu
lt
s
b
u
t
p
o
s
es
r
is
k
s
o
f
in
ju
r
y
o
r
s
tr
ess
to
th
e
an
im
als,
p
o
ten
tially
lead
in
g
to
weig
h
t
lo
s
s
,
a
n
d
r
eq
u
ir
es c
o
n
s
id
er
ab
le
lab
o
r
to
m
o
v
e
t
h
e
liv
esto
ck
to
th
e
weig
h
in
g
ar
ea
.
T
h
e
p
r
o
b
lem
in
th
is
s
tu
d
y
is
th
at
to
esti
m
ate
th
e
b
o
d
y
weig
h
t
o
f
ca
ttle,
s
p
ec
if
ically
B
ali
c
attle,
u
s
in
g
d
ata
s
o
u
r
ce
d
f
r
o
m
th
e
ch
ar
ac
t
er
is
tics
o
f
th
e
ca
ttle.
R
ec
en
t
s
t
u
d
ies
h
av
e
ex
p
lo
r
ed
th
e
u
s
e
o
f
m
ac
h
in
e
lear
n
in
g
f
o
r
m
ea
s
u
r
i
n
g
ca
ttle
weig
h
t.
Sev
er
al
m
eth
o
d
s
u
tili
zin
g
d
at
a
s
o
u
r
ce
d
f
r
o
m
m
ea
s
u
r
em
e
n
ts
o
r
m
o
r
p
h
o
m
etr
ics
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
44
1
-
4
4
9
442
h
av
e
b
ee
n
ex
ten
s
iv
ely
co
n
d
u
cted
.
T
h
e
a
p
p
licatio
n
o
f
a
n
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
u
s
in
g
th
r
ee
alg
o
r
ith
m
s
-
L
ev
e
n
b
er
g
-
Ma
r
q
u
ar
t,
B
ay
esian
r
eg
u
lar
izatio
n
,
a
n
d
s
ca
led
c
o
n
ju
g
ate
-
h
as
s
h
o
w
n
p
r
o
m
is
in
g
r
esu
lts
,
s
u
r
p
ass
in
g
b
o
th
m
u
ltip
le
lin
ea
r
r
eg
r
ess
io
n
[
7
]
a
n
d
r
an
d
o
m
f
o
r
est
(
R
F)
[
8
]
,
w
h
ich
s
till
r
ely
o
n
m
o
r
p
h
o
m
et
r
ic
d
ata.
On
th
e
o
th
er
h
an
d
,
r
esear
ch
in
v
o
lv
in
g
weig
h
t
m
ea
s
u
r
em
en
t
u
s
in
g
s
eg
m
en
ted
v
is
u
al
d
ata
with
m
u
lti
-
lay
er
p
e
r
ce
p
tr
o
n
(
ML
P)
an
d
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
(R
-
C
NN)
ap
p
r
o
ac
h
es
h
as b
ee
n
s
u
cc
ess
f
u
l
[
9
]
,
b
u
t
th
ese
s
tu
d
ies
d
id
n
o
t
in
clu
d
e
ad
d
itio
n
al
in
f
o
r
m
atio
n
lik
e
a
g
e
[
1
0
]
.
T
h
e
ca
p
a
b
ilit
ies
o
f
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NN)
[
1
1
]
an
d
co
m
p
u
ter
v
is
io
n
[
1
2
]
,
[
1
3
]
o
f
f
e
r
s
o
lu
tio
n
s
f
o
r
is
s
u
es
b
ased
o
n
v
is
u
al
o
b
s
er
v
atio
n
s
.
Dig
ital o
b
s
er
v
atio
n
with
s
p
ec
if
ic
alg
o
r
ith
m
s
allo
ws f
o
r
ea
s
ie
r
an
d
m
o
r
e
ac
cu
r
ate
o
b
ject
r
ec
o
g
n
itio
n
[
1
4
]
,
[
1
5
]
.
Ob
ject
d
etec
tio
n
,
class
if
icatio
n
,
an
d
p
r
ed
ictio
n
ar
e
co
m
m
o
n
ap
p
licatio
n
s
o
f
m
ac
h
in
e
le
ar
n
in
g
in
co
m
p
u
ter
v
is
io
n
d
ata
[
1
6
]
.
B
o
th
v
is
u
al
an
d
m
ea
s
u
r
em
e
n
t
m
eth
o
d
s
h
av
e
th
ei
r
r
esp
ec
tiv
e
ad
v
a
n
ta
g
es.
T
h
is
r
esear
ch
ad
d
r
ess
es th
e
ch
allen
g
e
o
f
d
eter
m
in
in
g
ca
ttle w
eig
h
ts
th
r
o
u
g
h
v
is
u
al
ass
e
s
s
m
en
ts
an
d
m
eta
d
a
ta,
in
clu
d
in
g
ag
e
an
d
p
ix
el
c
o
u
n
t,
u
tili
zin
g
a
co
m
b
in
atio
n
o
f
C
NN
an
d
ANN.
T
h
is
s
tu
d
y
also
ex
ten
s
iv
ely
i
n
v
o
lv
es
test
in
g
th
e
f
in
e
-
tu
n
in
g
o
f
s
ev
er
al
p
a
r
a
m
eter
s
,
in
clu
d
in
g
th
e
co
n
f
ig
u
r
atio
n
o
f
d
e
n
s
e
lay
er
s
,
s
elec
tio
n
o
f
ac
tiv
ati
o
n
f
u
n
ctio
n
s
,
a
n
d
d
eter
m
in
atio
n
o
f
th
e
b
est d
r
o
p
o
u
t r
ates w
h
ich
co
n
s
titu
tes p
ar
t o
f
th
e
i
n
n
o
v
atio
n
in
th
is
s
tu
d
y
.
2.
M
E
T
H
O
D
T
o
a
n
sw
e
r
th
e
r
esear
ch
o
b
jectiv
es,
a
f
r
a
m
ewo
r
k
o
f
th
o
u
g
h
t
was
p
r
ep
ar
ed
as
an
o
u
tlin
e
o
f
th
e
lo
g
ica
l
f
lo
w
o
f
th
e
r
esear
ch
as
s
h
o
w
n
in
Fig
u
r
e
1
.
Data
c
o
llectio
n
f
o
r
th
is
r
esear
c
h
in
v
o
lv
ed
g
a
th
er
in
g
b
o
th
im
a
g
e
an
d
m
o
r
p
h
o
m
et
r
ic
d
ata
f
r
o
m
t
h
e
Peo
p
le
’
s
An
im
al
Hu
s
b
an
d
r
y
S
ch
o
o
l (
SP
R
)
Mu
s
i
B
an
y
u
asin
an
d
lo
ca
l a
n
im
al
h
u
s
b
an
d
r
y
o
p
er
atio
n
s
in
Dep
o
k
,
W
est
J
av
a.
T
h
e
r
esear
ch
f
o
cu
s
ed
o
n
co
llectin
g
im
a
g
es
o
f
co
ws
f
r
o
m
tw
o
p
er
s
p
ec
tiv
es:
a
s
id
e
v
iew
o
r
l
ater
al
co
v
er
in
g
th
e
ar
ea
f
r
o
m
th
e
h
ea
d
to
th
e
b
ase
o
f
th
e
ta
il,
an
d
a
r
ea
r
v
iew
f
o
c
u
s
i
n
g
o
n
t
h
e
d
i
s
t
a
n
c
e
b
e
t
w
e
e
n
t
h
e
i
s
c
h
i
u
m
.
T
h
e
s
e
v
i
e
w
s
w
e
r
e
c
h
o
s
e
n
t
o
a
s
s
e
s
s
p
o
t
e
n
t
i
a
l
m
e
a
t
d
e
p
o
s
i
t
i
o
n
[
1
7
]
.
Ad
d
itio
n
ally
,
m
o
r
p
h
o
m
etr
ic
d
ata
s
u
ch
as
weig
h
t
an
d
ag
e
w
er
e
g
ath
er
ed
.
W
eig
h
t
was
u
s
ed
as
a
lab
el
in
th
e
s
tu
d
y
.
I
n
to
tal,
2
2
3
im
a
g
es o
f
ca
ttle in
s
id
e
v
iew
an
d
2
2
3
in
r
ea
r
v
iew
wer
e
co
llected
s
im
u
l
tan
eo
u
s
ly
to
en
s
u
r
e
ac
cu
r
ac
y
in
r
ep
r
esen
tin
g
t
h
e
a
ctu
al
co
n
d
itio
n
s
.
W
h
ile
C
NN
ar
ch
itectu
r
e
g
en
er
ally
r
eq
u
ir
es a
lar
g
e
d
ataset,
th
is
is
n
o
t
a
u
n
iv
e
r
s
al
r
u
le.
Fo
r
in
s
tan
ce
,
in
im
ag
e
class
if
icatio
n
,
u
s
in
g
1
0
0
h
u
m
an
b
r
ain
i
m
ag
es
y
ield
ed
a
n
ac
cu
r
ac
y
o
f
7
2
.
8
2
%,
wh
er
ea
s
th
e
s
am
e
n
u
m
b
er
o
f
s
h
o
u
ld
e
r
im
ag
es
r
esu
lted
in
an
ac
cu
r
ac
y
o
f
9
5
.
5
3
%
[
1
8
]
.
T
h
e
s
am
p
le
d
ataset
s
h
o
wn
in
T
ab
le
s
1
an
d
2
.
Fig
u
r
e
1
.
R
esear
ch
s
tag
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
C
a
ttle weig
h
t p
r
ed
ictio
n
mo
d
el
u
s
in
g
co
n
v
o
lu
tio
n
a
l
n
eu
r
a
l
n
etw
o
r
k
…
(
Yu
lia
n
in
g
s
ih
)
443
T
ab
le
1
.
Data
s
et
o
f
ca
ttle
ID
W
e
i
g
h
t
A
g
e
R
e
a
r
p
i
x
S
i
d
e
p
i
x
R
e
a
r
v
i
e
w
S
i
d
e
v
i
e
w
R
e
a
r
se
g
S
i
d
e
se
g
B
4
A
0
1
1
9
6
12
-
24
2
9
,
3
9
4
9
2
,
3
4
9
B
4
A
0
5
2
4
4
25
-
36
1
8
8
,
4
5
4
1
1
0
,
7
0
6
B
4
A
2
0
2
4
8
25
-
36
1
2
3
,
1
0
8
1
3
3
,
9
9
8
C
1
A
0
8
1
6
8
37
-
48
3
8
,
1
6
0
7
6
,
2
1
2
C
1
A
2
4
1
8
2
12
-
24
1
6
8
,
3
2
7
2
0
6
,
9
8
2
D
0
2
6
2
5
5
37
-
48
9
1
,
5
9
0
1
5
6
,
4
2
0
D
1
3
6
2
4
7
49
-
60
5
1
,
4
9
8
1
1
3
,
9
4
9
D
1
4
8
3
2
7
49
-
60
1
1
3
,
4
1
5
1
6
7
,
1
2
7
D
1
8
0
3
6
7
37
-
48
6
5
,
5
2
3
1
3
1
,
8
8
0
T
ab
le
2
.
Attr
ib
u
te
d
ataset
o
f
c
attle
No
A
t
t
r
i
b
u
t
e
D
e
scri
p
t
i
o
n
1
ID
I
d
n
u
m
b
e
r
,
A
-
D
i
n
d
i
c
a
t
i
o
n
o
f
d
a
t
a
l
o
c
a
t
i
o
n
s
i
t
e
2
W
EI
G
H
T
W
e
i
g
h
t
o
f
t
h
e
c
a
t
t
l
e
i
s
me
a
su
r
e
d
i
n
k
i
l
o
g
r
a
ms.
3
AGE
A
g
e
d
a
t
a
i
s
o
b
t
a
i
n
e
d
b
a
s
e
d
o
n
t
o
o
t
h
g
r
o
w
t
h
4
R
EA
R
_
P
I
X
P
i
x
e
l
c
o
u
n
t
f
r
o
m re
a
r
se
g
m
e
n
t
a
t
i
o
n
5
S
I
D
E_
P
I
X
P
i
x
e
l
c
o
u
n
t
f
r
o
m s
i
d
e
s
e
g
m
e
n
t
a
t
i
o
n
6
R
EA
R
_
V
I
EW
F
o
c
u
si
n
g
o
n
t
h
e
d
i
st
a
n
c
e
b
e
t
w
e
e
n
t
h
e
i
sc
h
i
u
m
7
S
I
D
E_
V
I
EW
C
o
v
e
r
i
n
g
t
h
e
a
r
e
a
f
r
o
m
t
h
e
h
e
a
d
t
o
t
h
e
b
a
se
o
f
t
h
e
t
a
i
l
8
R
EA
R
_
S
EG
S
e
g
m
e
n
t
a
t
i
o
n
r
e
s
u
l
t
s fr
o
m
r
e
a
r
9
S
I
D
E_
S
EG
S
e
g
m
e
n
t
a
t
i
o
n
r
e
s
u
l
t
s fr
o
m
si
d
e
T
h
e
d
ata
co
llectio
n
p
r
o
ce
s
s
is
d
etailed
in
Fig
u
r
e
2
.
T
h
e
m
o
r
p
h
o
m
etr
ic
m
ea
s
u
r
em
en
ts
wer
e
co
n
d
u
cte
d
u
s
in
g
a
d
i
g
ital
s
ca
le,
wh
ile
ag
e
d
eter
m
in
atio
n
w
as
b
ased
o
n
to
o
th
g
r
o
wth
.
C
at
tle
s
p
ec
im
en
s
wer
e
ca
p
tu
r
ed
f
r
o
m
a
d
is
tan
ce
o
f
2
2
0
cm
with
a
ca
m
er
a
h
eig
h
t
o
f
1
5
0
cm
.
T
h
e
im
ag
e
ca
p
tu
r
e
em
p
lo
y
ed
1
:1
asp
ec
t
r
atio
to
f
ac
ilit
ate
th
e
au
g
m
en
ta
tio
n
p
r
o
ce
s
s
.
Pre
p
r
o
ce
s
s
in
g
p
h
ase,
au
g
m
e
n
tatio
n
was
co
n
d
u
cted
b
y
r
o
tatin
g
ea
ch
im
ag
e
b
y
1
0
d
eg
r
ee
s
an
d
ap
p
ly
in
g
h
o
r
iz
o
n
tal
f
lip
p
in
g
to
en
h
an
ce
m
o
d
el
p
er
f
o
r
m
an
ce
an
d
p
r
ev
en
t
o
v
er
f
it
tin
g
[
1
9
]
.
Su
b
s
eq
u
en
tly
,
s
eg
m
en
tatio
n
was
p
er
f
o
r
m
ed
,
f
o
llo
wed
b
y
p
ix
el
c
o
u
n
tin
g
o
f
th
e
s
eg
m
en
ted
ar
ea
s
[
2
0
]
.
T
h
e
o
b
tain
e
d
r
esu
lts
s
er
v
ed
as n
ew
in
p
u
ts
f
o
r
th
e
A
NN
alg
o
r
ith
m
as in
d
e
p
en
d
e
n
t
v
ar
iab
les alo
n
g
s
id
e
ag
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
44
1
-
4
4
9
444
Fig
u
r
e
2
.
Data
co
llectio
n
s
tag
e
I
t
is
n
o
tewo
r
t
h
y
t
h
at
th
er
e
is
n
o
u
n
iv
er
s
ally
a
p
p
licab
le
s
eg
m
en
tatio
n
a
p
p
r
o
ac
h
,
as
ce
r
tai
n
m
eth
o
d
s
h
av
e
s
h
o
wn
g
r
ea
ter
e
f
f
icac
y
[
2
1
]
.
T
h
is
s
tu
d
y
u
tili
ze
d
R
-
Ma
s
k
C
NN
f
o
r
s
eg
m
en
tatio
n
[
2
2
]
,
wh
ich
h
as
p
r
o
v
e
n
to
b
e
ef
f
ec
tiv
e
in
d
etec
tio
n
a
n
d
lay
er
g
en
e
r
atio
n
[
2
3
]
,
[
2
4
]
,
co
m
p
a
r
ed
to
o
th
er
m
eth
o
d
s
s
u
ch
as
m
u
lti
-
task
n
etwo
r
k
ca
s
ca
d
es
(
MN
C
)
[
2
5
]
an
d
f
u
lly
co
n
v
o
lu
tio
n
al
in
s
t
an
ce
-
awa
r
e
s
em
an
tic
(
FC
I
S)
[
2
6
]
.
Alg
o
r
ith
m
1
is
th
e
p
s
eu
d
o
c
o
d
e
u
s
ed
to
p
er
f
o
r
m
p
i
x
el
co
u
n
tin
g
.
I
n
th
is
p
s
eu
d
o
co
d
e,
th
e
f
u
n
ctio
n
C
o
u
n
tPi
x
els
tak
es
tw
o
p
ar
am
eter
s
: m
ask
_
tem
p
late,
wh
ich
is
th
e
m
ask
tem
p
late,
an
d
tar
g
et_
co
lo
r
,
wh
ich
is
th
e
co
l
o
r
wh
o
s
e
p
ix
els we
wan
t
to
co
u
n
t.
T
h
is
f
u
n
ctio
n
it
er
ates
th
r
o
u
g
h
ea
c
h
p
ix
el
in
m
ask
_
tem
p
late
an
d
co
u
n
ts
th
e
p
ix
els
th
at
h
av
e
th
e
s
am
e
co
lo
r
as
tar
g
et
_
co
lo
r
.
T
h
e
r
esu
lt
is
th
en
r
etu
r
n
ed
as
p
i
x
el_
co
u
n
t.
I
n
t
h
e
c
o
d
e,
we
ca
l
l
th
is
f
u
n
ctio
n
with
m
ask
_
tem
p
late
as
th
e
f
ir
s
t
ar
g
u
m
en
t
an
d
[
1
2
2
,
1
2
0
,
2
4
]
as
th
e
s
ec
o
n
d
ar
g
u
m
en
t
to
co
u
n
t
p
ix
els
with
th
e
co
lo
r
[
1
2
2
,
1
2
0
,
2
4
]
.
T
h
e
r
esu
lt is
th
en
p
r
in
ted
.
Alg
o
r
ith
m
1
.
Ps
eu
d
o
co
d
e
u
s
ed
to
p
er
f
o
r
m
p
ix
el
co
u
n
tin
g
CountPixels(mask_template, target_color):
pixel_count = 0
for each pixel in mask_template:
if pixel is equal to target_color:
pixel_count = pixel_count + 1
return pixel_count
# Calling the function to count pixels with a specific color
n_pixel = CountPixels(mask_template, [122, 120, 24])
print(n_pixel)
Mo
d
elin
g
s
tag
e,
an
in
teg
r
atio
n
o
f
two
alg
o
r
ith
m
s
was
im
p
l
em
en
ted
.
T
h
e
C
NN
was
d
e
s
i
g
n
ated
f
o
r
th
e
cr
itic
al
task
o
f
f
ea
tu
r
e
ex
tr
ac
tio
n
f
r
o
m
im
ag
es,
wh
er
ea
s
th
e
ANN
was u
ti
lized
to
ass
im
i
late
s
u
p
p
lem
en
tar
y
in
f
o
r
m
atio
n
s
u
ch
as
th
e
ag
e
an
d
p
ix
el
co
u
n
t
f
o
r
ea
c
h
c
o
w
o
b
ject.
C
o
n
cu
r
r
en
tly
,
f
in
e
-
tu
n
in
g
o
f
s
ev
er
al
p
ar
am
eter
s
,
in
clu
d
i
n
g
th
e
c
o
n
f
ig
u
r
atio
n
o
f
d
en
s
e
lay
e
r
s
an
d
s
elec
tio
n
o
f
ac
tiv
ati
o
n
f
u
n
ctio
n
s
an
d
d
eter
m
in
atio
n
o
f
th
e
b
est
d
r
o
p
o
u
t
r
ates.
T
h
e
m
o
d
el
is
im
p
lem
en
ted
o
n
b
o
th
s
id
e
an
d
r
ea
r
v
iew
im
ag
e
d
ata
to
p
r
ed
ict
weig
h
t
s
ep
ar
ately
,
an
d
th
en
th
e
av
e
r
ag
e
v
alu
e
o
f
b
o
th
p
r
ed
ictio
n
s
is
d
eter
m
in
ed
.
T
h
is
ap
p
r
o
ac
h
f
o
r
co
n
s
tr
u
ctin
g
a
weig
h
t
p
r
ed
icti
o
n
r
eg
r
ess
io
n
m
o
d
el
was
ad
a
p
ted
an
d
m
o
d
if
ied
f
r
o
m
th
e
ex
p
er
im
en
tal
m
o
d
el
u
s
ed
in
th
e
I
n
ter
n
atio
n
al
Sk
in
I
m
ag
in
g
C
o
llab
o
r
atio
n
(
I
SIC)
2
0
1
9
s
k
in
lesi
o
n
class
if
icatio
n
ch
allen
g
e
[
2
7
]
.
T
esti
n
g
an
d
m
ea
s
u
r
in
g
t
h
e
ac
cu
r
ac
y
o
f
th
e
m
o
d
el
b
ased
o
n
th
e
b
est
m
ea
n
a
b
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
(
MA
PE
)
to
ex
am
in
e
th
e
ex
te
n
t
to
wh
ic
h
th
e
m
o
d
el
g
en
er
alize
s
th
e
p
r
ed
ictio
n
r
esu
lts
an
d
in
d
icate
h
o
w
m
u
ch
e
r
r
o
r
i
n
p
r
ed
ictin
g
wh
en
co
m
p
ar
ed
to
r
ea
l
o
r
ac
tu
al
v
alu
es.
T
h
e
o
p
tim
al
MA
PE
o
b
tain
ed
f
r
o
m
v
ar
io
u
s
p
ar
am
eter
co
m
b
in
atio
n
s
will b
e
r
ec
o
m
m
en
d
ed
f
o
r
th
e
p
r
ed
ictio
n
o
f
ca
ttle w
eig
h
t.
=
1
∑
|
−
|
100%
=
1
(
1
)
W
h
er
e
:
n
is
s
am
p
le
s
ize
,
Ai
is
th
e
ac
tu
al
d
ata
v
alu
e
,
an
d
Fi is
p
r
ed
icted
v
alu
e
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Pre
p
r
o
ce
s
s
in
g
p
h
ase
in
v
o
lv
ed
au
g
m
en
tatio
n
to
e
x
p
an
d
th
e
d
ataset
to
8
9
2
in
s
tan
ce
s
.
Fo
r
tr
ain
in
g
m
o
d
el
d
ata
d
i
v
id
ed
in
to
7
5
:2
5
.
Su
b
s
eq
u
en
tly
,
s
eg
m
e
n
tatio
n
was
co
n
d
u
cted
to
ca
lc
u
late
th
e
p
ix
el
co
u
n
t
o
f
s
eg
m
en
ted
o
b
jects.
T
h
e
n
u
m
b
er
o
f
p
i
x
els
in
ea
c
h
o
b
ject
r
ep
r
esen
ts
th
e
weig
h
t
o
f
th
e
ca
ttle.
T
ab
le
3
illu
s
tr
ates
th
e
p
ix
el
c
o
u
n
ti
n
g
r
esu
lts
f
o
r
e
ac
h
o
b
ject.
Fu
r
t
h
er
m
o
r
e,
th
e
r
esu
lts
o
f
p
ix
el
co
u
n
tin
g
f
o
r
ea
ch
o
b
ject
s
er
v
e
as
n
ew
in
p
u
ts
f
o
r
th
e
ANN
alg
o
r
i
th
m
to
ac
co
m
p
an
y
th
e
in
d
e
p
en
d
en
t v
ar
iab
le
o
f
a
g
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
C
a
ttle weig
h
t p
r
ed
ictio
n
mo
d
el
u
s
in
g
co
n
v
o
lu
tio
n
a
l
n
eu
r
a
l
n
etw
o
r
k
…
(
Yu
lia
n
in
g
s
ih
)
445
Mo
d
ellin
g
p
h
ase,
an
in
teg
r
ati
o
n
o
f
two
alg
o
r
ith
m
s
was
im
p
lem
en
ted
.
th
e
C
NN
was
d
es
i
g
n
ated
f
o
r
th
e
cr
itical
tas
k
o
f
f
ea
tu
r
e
ex
tr
ac
tio
n
f
r
o
m
im
a
g
es,
wh
er
ea
s
th
e
ANN
was
u
tili
ze
d
to
a
s
s
im
ilate
s
u
p
p
lem
en
tar
y
in
f
o
r
m
atio
n
s
u
ch
as
th
e
ag
e
a
n
d
p
ix
el
co
u
n
t
f
o
r
ea
c
h
ca
ttle
o
b
j
ec
t.
T
h
is
ap
p
r
o
a
ch
is
p
ar
ticu
lar
ly
in
n
o
v
ativ
e
in
its
u
s
e
o
f
th
e
n
u
m
b
er
o
f
p
i
x
e
ls
f
r
o
m
t
h
e
im
a
g
es
as
a
r
e
p
r
e
s
en
tatio
n
o
f
a
ce
r
tain
weig
h
t.
T
h
is
m
eth
o
d
o
lo
g
y
lev
er
ag
es
th
e
v
is
u
al
d
ata
f
o
r
a
m
o
r
e
ac
cu
r
ate
an
d
co
m
p
r
eh
en
s
iv
e
an
aly
s
is
,
wh
ile
th
e
tab
u
lar
d
ata
p
r
o
v
id
es
co
n
tex
tu
al
a
n
d
s
p
ec
if
ic
d
etails,
en
h
a
n
cin
g
t
h
e
o
v
er
all
p
r
e
d
ictiv
e
ca
p
ab
ilit
y
o
f
th
e
m
o
d
el.
A
n
illu
s
tr
atio
n
o
f
th
e
co
n
ce
p
tu
al
f
r
am
ewo
r
k
u
n
d
e
r
p
in
n
in
g
th
is
r
esear
ch
is
p
r
o
v
id
e
d
in
Fig
u
r
e
3
,
o
f
f
er
i
n
g
a
v
is
u
a
l
r
ep
r
esen
tatio
n
o
f
h
o
w
th
ese
d
if
f
er
en
t d
ata
ty
p
es a
r
e
co
m
b
in
e
d
an
d
u
tili
ze
d
wit
h
in
th
e
s
tu
d
y
.
T
ab
le
3
.
Pix
el
co
u
n
tin
g
r
esu
lts
ID
W
e
i
g
h
t
A
g
e
R
e
a
r
p
i
x
S
i
d
e
p
i
x
B
4
A
0
1
1
9
6
12
-
24
2
9
,
3
9
4
9
2
,
3
4
9
B
4
A
0
5
2
4
4
25
-
36
1
8
8
,
4
5
4
1
1
0
,
7
0
6
B
4
A
2
0
2
4
8
25
-
36
1
2
3
,
1
0
8
1
3
3
,
9
9
8
C
1
A
0
8
1
6
8
37
-
48
3
8
,
1
6
0
7
6
,
2
1
2
C
1
A
2
4
1
8
2
12
-
24
1
6
8
,
3
2
7
2
0
6
,
9
8
2
D
0
2
6
2
5
5
37
-
48
9
1
,
5
9
0
1
5
6
,
4
2
0
D
1
3
6
2
4
7
49
-
60
5
1
,
4
9
8
1
1
3
,
9
4
9
D
1
4
8
3
2
7
49
-
60
1
1
3
,
4
1
5
1
6
7
,
1
2
7
…
…
…
…
…
D
1
8
0
3
6
7
37
-
48
6
5
,
5
2
3
1
3
1
,
8
8
0
Fig
u
r
e
3
.
C
attle
weig
h
t p
r
e
d
ictio
n
m
o
d
el
T
h
er
e
ar
e
two
s
ep
a
r
ate
in
p
u
ts
to
th
is
m
o
d
el,
th
e
f
ir
s
t
in
p
u
t
l
ay
er
is
f
o
r
im
a
g
e
d
ata,
wh
ile
t
h
e
s
ec
o
n
d
in
p
u
t
lay
er
is
f
o
r
ad
d
itio
n
al
d
ata.
T
h
e
m
o
d
el
d
e
m
o
n
s
tr
ate
s
th
at
th
e
o
u
tp
u
ts
f
r
o
m
m
u
lt
ip
le
p
ath
way
s
ar
e
p
r
o
ce
s
s
ed
in
d
e
p
en
d
e
n
tly
b
ef
o
r
e
b
ei
n
g
co
m
b
i
n
ed
,
en
ab
lin
g
th
e
m
o
d
el
to
lear
n
f
r
o
m
b
o
th
im
ag
e
d
ata
an
d
ad
d
itio
n
al
d
ata
s
im
u
ltan
e
o
u
s
ly
.
T
h
e
o
u
tp
u
t
la
y
er
g
e
n
er
ate
s
th
e
m
o
d
el'
s
f
in
al
p
r
ed
ictio
n
u
tili
zin
g
a
s
in
g
le
n
eu
r
o
n
f
o
r
r
e
g
r
ess
io
n
task
s
.
Fo
r
th
e
o
u
tp
u
t
lay
er
th
at
p
e
r
f
o
r
m
s
r
eg
r
ess
io
n
,
a
lin
ea
r
o
p
e
r
atio
n
is
ap
p
lied
as
f
o
llo
ws:
=
+
(
1
)
wh
er
e:
Y
pred
is
th
e
p
r
ed
icted
weig
h
t
o
u
tco
m
es f
o
r
ea
ch
in
p
u
t.
Y^
is
T
h
e
av
er
ag
e
v
alu
e
o
f
th
e
two
p
r
ed
ictio
n
o
u
tco
m
es.
X
co
n
ca
t is th
e
o
u
t
p
u
t f
r
o
m
th
e
co
n
ca
ten
atio
n
lay
er
.
W
final
is
th
e
weig
h
t o
f
th
e
o
u
tp
u
t la
y
er
.
b
final
is
th
e
b
ias o
f
th
e
o
u
tp
u
t la
y
er
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
44
1
-
4
4
9
446
C
o
n
cu
r
r
en
tly
,
f
in
e
-
tu
n
in
g
o
f
s
ev
er
al
p
ar
am
eter
s
.
B
ef
o
r
e
th
e
in
teg
r
atio
n
,
C
NN
co
n
s
is
tin
g
o
f
f
ilter
s
6
4
,
8
,
1
6
with
a
2
:2
p
o
o
lin
g
l
ay
er
an
d
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U
)
ac
tiv
atio
n
,
wh
ile
in
A
NN,
th
ey
co
n
s
is
t
o
f
n
o
d
es
8
,
1
6
with
R
eL
U
ac
ti
v
atio
n
.
Su
b
s
eq
u
e
n
t
to
in
teg
r
atio
n
,
th
e
m
o
d
el
’
s
p
ar
am
eter
s
wer
e
ad
ju
s
ted
to
in
co
r
p
o
r
ate
4
u
n
its
in
to
tal,
co
m
p
r
is
in
g
a
s
in
g
le
o
u
tp
u
t
lay
er
u
n
it
with
lin
ea
r
ac
tiv
atio
n
.
Ad
d
itio
n
ally
,
a
d
r
o
p
o
u
t
f
u
n
ctio
n
with
a
r
ate
o
f
0
.
5
was
in
co
r
p
o
r
a
ted
,
an
d
th
e
Ad
am
o
p
tim
izer
was
em
p
lo
y
ed
.
W
e
co
n
d
u
cted
iter
atio
n
s
o
v
er
2
0
0
ep
o
ch
s
,
b
eg
in
n
in
g
with
a
co
m
b
in
atio
n
o
f
1
lay
er
in
t
h
e
C
NN
an
d
2
lay
er
s
in
th
e
ANN.
T
h
is
p
r
o
ce
s
s
co
n
tin
u
ed
u
n
til
r
ea
ch
i
n
g
a
co
m
b
i
n
atio
n
o
f
3
lay
er
s
in
b
o
th
wit
h
g
r
id
s
ea
r
ch
to
f
in
d
th
e
b
est
c
o
m
b
in
atio
n
.
T
o
i
d
en
tify
th
e
m
o
s
t
e
f
f
ec
tiv
e
m
o
d
el,
we
r
ec
o
r
d
e
d
th
e
MA
PE
v
alu
es.
T
h
e
e
x
h
au
s
tiv
e
g
r
id
s
ea
r
ch
p
r
o
ce
s
s
d
em
an
d
s
a
co
n
s
id
er
ab
le
am
o
u
n
t o
f
tim
e.
T
h
er
ef
o
r
e,
we
co
n
s
tr
ain
o
u
r
s
e
ar
ch
co
m
b
in
atio
n
s
to
a
m
ax
im
u
m
o
f
6
4
,
g
iv
e
n
th
e
lim
itatio
n
s
in
tim
e
an
d
r
eso
u
r
ce
s
.
B
ased
o
n
o
u
r
o
b
s
er
v
atio
n
s
,
we
h
av
e
n
o
te
d
th
at
as
th
e
co
m
p
lex
ity
o
f
M
APE
ca
lcu
latio
n
s
in
cr
ea
s
es,
th
er
e
is
n
o
co
r
r
esp
o
n
d
in
g
im
p
r
o
v
em
en
t
in
MA
PE
v
alu
es.
T
ab
les
4
an
d
5
p
r
esen
t
th
e
t
r
ain
in
g
r
esu
lts
f
o
r
b
o
t
h
s
id
e
-
v
iew
a
n
d
r
ea
r
-
v
iew
in
p
u
ts
.
B
ased
o
n
o
u
r
test
in
g
r
esu
lts
,
we
f
o
u
n
d
th
at
th
e
b
est
m
o
d
el
f
o
r
th
e
r
ea
r
-
v
i
ew
d
ata
ac
h
iev
ed
an
MA
PE
o
f
1
1
.
2
5
9
with
3
:2
co
m
b
in
atio
n
u
s
in
g
C
NN
f
ilte
r
s
o
f
6
4
,
8
,
1
6
,
an
d
ANN
n
o
d
es
8
,
1
6
.
Me
an
wh
ile,
th
e
b
est
m
o
d
el
f
o
r
th
e
s
id
e
-
v
iew
d
ata
attain
ed
an
M
APE
o
f
1
2
.
4
3
2
with
2
:
2
co
m
b
in
atio
n
u
s
in
g
C
NN
f
ilter
s
o
f
6
4
,
6
4
,
an
d
ANN
n
o
d
es o
f
6
4
,
6
4
.
T
ab
le
4
.
R
esu
lt tr
ain
in
g
m
o
d
el
r
ea
r
-
v
iew
im
ag
e
d
ata
Rear
-
v
i
e
w
i
m
a
g
e
d
a
t
a
C
o
m
b
i
n
a
t
i
o
n
C
N
N
ANN
M
A
P
E
1
:
2
(
8
-
64)
32
1
6
:
3
2
1
1
.
4
0
2
2:
1
(
8
-
64)
3
2
:
3
2
16
1
2
.
0
3
2
:
2
(
8
–
6
4
)
6
4
:
1
6
3
:
3
2
1
1
.
4
9
5
2:
3
(
8
-
64)
3
2
:
8
6
4
:
8
:
6
4
1
1
.
8
5
8
3
:
2
(
8
-
64)
6
4
:
8
:
1
6
8
:
1
6
1
1
.
2
5
9
3
:
3
(
8
-
64)
6
4
:
6
4
:
3
2
3
2
:
6
4
:
1
6
1
1
.
5
3
2
T
ab
le
5
.
R
esu
lt tr
ain
in
g
m
o
d
el
s
id
e
-
v
iew
im
ag
e
d
ata
S
i
d
e
-
v
i
e
w
d
a
t
a
C
o
m
b
i
n
a
t
i
o
n
C
N
N
ANN
M
A
P
E
1
:
2
(
8
-
64)
16
3
2
:
8
1
3
.
1
9
3
2:
1
(
8
-
64)
1
6
:
6
4
64
1
2
.
7
1
9
2
:
2
(
8
-
64)
6
4
:
6
4
6
4
:
6
4
1
2
.
4
3
2
2:
3
(
8
-
64)
8
:
8
6
4
:
8
:
6
4
1
2
.
6
5
6
3
:
2
(
8
-
64)
3
2
:
3
2
:
6
4
3
2
:
6
4
1
2
.
7
2
1
3
:
3
(
8
-
64)
8
:
3
2
:
8
6
4
:
3
2
:
1
6
1
2
.
4
8
8
Af
ter
id
en
tify
in
g
th
e
b
est
m
o
d
el
f
r
o
m
b
o
t
h
in
p
u
ts
,
th
e
av
er
ag
e
p
r
ed
ictio
n
v
al
u
es
u
s
in
g
th
e
test
d
ata
wer
e
d
eter
m
in
ed
,
as
s
h
o
wn
in
T
ab
le
6
.
T
o
m
ea
s
u
r
e
th
e
e
r
r
o
r
v
alu
e
b
etwe
en
th
e
p
r
ed
icted
an
d
ac
tu
al
v
alu
es,
th
e
MA
PE
m
ea
s
u
r
em
en
t m
eth
o
d
is
u
s
ed
.
T
h
e
s
am
e
p
r
o
ce
d
u
r
e
is
ap
p
lied
d
u
r
in
g
th
e
m
o
d
eli
n
g
p
r
o
ce
s
s
.
=
1
∑
|
−
|
100%
=
1
(2
)
W
h
er
e
:
n
is
s
am
p
le
s
ize
,
Ai
is
th
e
ac
tu
al
d
ata
v
alu
e
,
Fi is
p
r
e
d
icted
v
alu
e
.
T
h
e
av
er
ag
e
MA
PE
o
b
tain
e
d
was
1
0
.
I
n
t
h
e
an
aly
s
is
o
f
p
r
ed
ictio
n
o
u
tco
m
es
u
tili
zin
g
th
e
test
d
ataset,
as
d
elin
ea
ted
in
T
ab
le
6
,
wh
ich
en
co
m
p
ass
es
1
5
p
air
ed
b
o
v
i
n
e
im
ag
e
d
atasets
,
it
was
o
b
s
er
v
e
d
th
at
th
e
s
id
e
v
iew
asp
ec
t im
ag
es o
f
co
ws y
ield
ed
p
r
e
d
ictio
n
s
m
o
r
e
clo
s
ely
alig
n
ed
with
th
eir
ac
t
u
al
weig
h
t r
elativ
e
to
th
e
r
ea
r
-
v
iew
asp
ec
t
im
ag
e
s
.
No
n
eth
eless
,
b
o
th
s
ets
o
f
im
ag
e
d
ata
s
ig
n
if
ican
tly
c
o
n
tr
i
b
u
ted
to
th
e
o
v
er
all
p
r
ed
ictiv
e
ac
cu
r
ac
y
.
T
h
is
is
ev
id
en
ce
d
b
y
an
av
er
ag
e
M
APE
o
f
1
0
%,
u
n
d
er
s
co
r
in
g
t
h
e
ef
f
icac
y
o
f
th
e
em
p
lo
y
ed
p
r
ed
ictiv
e
m
o
d
el
i
n
esti
m
atin
g
b
o
v
in
e
weig
h
t w
ith
a
r
ea
s
o
n
ab
le
d
eg
r
ee
o
f
p
r
ec
is
io
n
.
T
h
e
r
esid
u
al
d
is
tr
ib
u
tio
n
o
f
o
u
r
m
o
d
el,
as
illu
s
tr
ated
in
Fi
g
u
r
e
4
,
is
r
elativ
ely
s
y
m
m
etr
i
ca
l
ar
o
u
n
d
th
e
ze
r
o
v
alu
e,
s
u
g
g
esti
n
g
th
at
th
e
m
o
d
el
d
o
es
n
o
t
p
o
s
s
es
s
a
s
ig
n
if
ican
t
s
y
s
tem
atic
b
ias
m
ea
n
in
g
it
n
eith
e
r
co
n
s
is
ten
tly
o
v
er
p
r
e
d
icts
n
o
r
u
n
d
er
p
r
ed
icts
.
T
h
is
s
y
m
m
etr
y
in
d
icate
s
th
at
th
e
m
o
d
el
g
en
e
r
ally
av
o
id
s
m
ak
in
g
lar
g
e
er
r
o
r
s
in
co
m
p
ar
is
o
n
to
t
h
e
tr
u
e
v
alu
es,
r
ef
lectin
g
a
c
o
m
m
en
d
a
b
le
lev
el
o
f
ac
c
u
r
ac
y
.
Var
iatio
n
s
in
th
e
r
esid
u
al
v
alu
es
s
u
g
g
est
th
at
w
h
ile
th
e
m
o
d
el
d
o
es
in
cu
r
p
r
e
d
ictio
n
er
r
o
r
s
,
th
ese
er
r
o
r
s
ar
e
co
n
tain
ed
with
in
a
ce
r
tain
r
an
g
e,
a
n
d
th
e
a
b
s
en
c
e
o
f
v
er
y
lar
g
e
er
r
o
r
s
p
o
in
ts
t
o
th
e
m
o
d
el'
s
co
n
s
is
ten
cy
.
M
o
r
eo
v
e
r
,
th
e
b
alan
ce
o
b
s
er
v
ed
b
etwe
en
p
o
s
itiv
e
an
d
n
eg
ativ
e
r
esid
u
als
f
u
r
th
er
i
m
p
lies
th
at
th
e
m
o
d
el
m
ain
tai
n
s
a
n
eu
t
r
al
ap
p
r
o
ac
h
in
its
p
r
e
d
ictiv
e
ac
c
u
r
ac
y
,
wi
th
o
u
t
a
ten
d
en
cy
to
s
k
ew
in
o
n
e
d
ir
ec
tio
n
.
T
h
e
r
esid
u
al
h
is
to
g
r
am
s
h
o
ws
a
m
ix
tu
r
e
o
f
p
o
s
itiv
e
an
d
n
eg
a
tiv
e
r
esid
u
als,
with
n
o
d
o
m
i
n
an
t
tr
en
d
t
o
eith
er
s
id
e.
T
h
i
s
in
d
icate
s
th
at
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
C
a
ttle weig
h
t p
r
ed
ictio
n
mo
d
el
u
s
in
g
co
n
v
o
lu
tio
n
a
l
n
eu
r
a
l
n
etw
o
r
k
…
(
Yu
lia
n
in
g
s
ih
)
447
p
r
o
p
o
s
ed
m
o
d
el
in
th
is
s
tu
d
y
d
o
es
n
o
t
s
y
s
tem
atica
lly
o
v
er
esti
m
ate
o
r
u
n
d
e
r
esti
m
ate
th
e
p
r
ed
icted
v
alu
es.
T
est
d
ata
was
co
llected
u
s
in
g
th
e
d
ig
ital
we
ig
h
t
ar
tific
ial
in
t
ellig
en
ce
(
DiW
AI
)
in
ter
f
ac
e
wh
ile
in
f
er
en
ce
was
d
o
n
e
o
n
a
s
er
v
er
p
r
ein
s
talled
with
a
p
r
ed
ictio
n
m
o
d
el,
as
illu
s
tr
ated
in
Fig
u
r
e
5
.
T
h
e
in
f
o
r
m
atio
n
th
at
ca
n
b
e
p
r
o
v
id
e
d
co
n
s
is
ts
o
f
p
r
ed
ictiv
e
o
u
tco
m
es,
ag
e
,
an
d
d
ata
co
ll
ec
tio
n
lo
ca
tio
n
s
.
T
ab
le
6
.
R
esu
lt o
f
im
p
lem
e
n
ta
tio
n
m
o
d
el
No
ID
A
c
t
u
a
l
w
e
i
g
h
t
(
k
g
)
A
ge
P
r
e
d
i
c
t
i
o
n
f
o
r
r
e
a
r
(
k
g
)
P
r
e
d
i
c
t
i
o
n
f
o
r
si
d
e
(
k
g
)
A
v
e
r
a
g
e
p
r
e
d
i
c
t
i
o
n
(
k
g
)
M
A
P
E
1
B
4
A
0
3
.
j
p
g
2
4
3
2
2
5
1
2
54
2
5
2
3
.
9
0
9
5
2
B
4
A
1
1
.
j
p
g
2
1
2
2
1
9
2
2
2
3
20
7
2
.
1
2
2
6
3
C
1
A
0
7
.
j
p
g
2
7
0
5
2
0
4
2
3
8
2
21
1
8
.
1
4
8
4
C
1
A
2
1
.
j
p
g
2
3
0
2
1
8
6
21
5
20
5
1
2
.
8
2
6
5
D
0
1
9
.
j
p
g
1
7
7
3
1
9
3
2
89
2
41
3
6
.
1
5
8
6
D
0
5
8
.
j
p
g
1
4
7
2
1
4
9
15
9
15
4
4
.
7
6
1
9
7
D
0
6
6
.
j
p
g
2
9
7
3
3
3
1
2
9
1
3
1
1
4
.
7
1
3
8
8
D
0
6
9
.
j
p
g
2
77
2
3
1
4
2
65
2
8
9
4
.
5
1
2
6
9
D0
75
.
j
p
g
2
91
3
2
3
9
2
54
2
46
1
5
.
2
9
2
10
D0
125
.
j
p
g
2
52
3
2
41
2
64
2
42
0
.
1
9
8
4
1
1
D
1
3
4
.
j
p
g
3
0
5
3
2
5
0
2
3
8
2
4
4
20
1
2
D
1
4
6
.
j
p
g
2
8
0
3
2
5
3
30
1
2
77
1
.
0
7
1
4
1
3
D
1
4
7
.
j
p
g
2
4
7
4
2
1
4
2
47
23
0
0
6
.
6
8
0
2
1
4
S
1
1
.
j
p
g
2
5
7
2
2
2
9
2
24
2
26
1
1
.
8
6
8
A
v
e
r
a
g
e
M
A
P
E
1
0
.
1
6
2
Fig
u
r
e
4
.
R
esid
u
al
h
is
to
g
r
am
f
r
o
m
test
in
g
Fig
u
r
e
5
.
DiW
AI
i
n
ter
f
ac
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
44
1
-
4
4
9
448
4.
CO
NCLU
SI
O
N
I
n
th
is
s
tu
d
y
,
to
o
b
tain
a
p
r
ed
i
ctiv
e
m
o
d
el
f
o
r
ca
ttle w
eig
h
t,
we
co
m
b
in
ed
C
NN
an
d
ANN
alg
o
r
ith
m
s
with
v
ar
io
u
s
p
ar
a
m
eter
c
o
m
b
in
atio
n
s
u
s
in
g
th
e
g
r
i
d
s
ea
r
ch
f
u
n
ctio
n
.
Ou
r
f
in
d
in
g
s
p
r
o
v
id
e
co
n
clu
s
iv
e
ev
id
en
ce
th
at
th
e
b
est
m
o
d
el
f
o
r
r
ea
r
-
v
iew
d
ata
ac
h
iev
ed
an
MA
PE
o
f
1
1
.
2
5
9
%
with
a
3
:2
c
o
m
b
in
atio
n
,
u
tili
zin
g
C
NN
f
ilter
s
o
f
6
4
,
8
,
1
6
,
an
d
ANN
n
o
d
es
o
f
8
,
1
6
.
Me
an
wh
ile,
th
e
o
p
tim
al
m
o
d
e
l
f
o
r
s
id
e
-
v
iew
d
ata
o
b
tain
ed
an
MA
PE
o
f
1
2
.
4
3
2
%
with
a
2
:2
co
m
b
in
atio
n
,
em
p
lo
y
in
g
C
NN
f
ilter
s
o
f
6
4
,
6
4
,
an
d
ANN
n
o
d
es
o
f
6
4
,
6
4
.
T
h
e
av
er
a
g
e
p
r
ed
ictio
n
o
f
b
o
th
m
o
d
els
y
ield
e
d
a
n
MA
PE
o
f
1
0
%.
T
h
e
r
ef
o
r
e,
th
e
s
e
p
r
ed
ictiv
e
m
o
d
els
o
n
th
ese
p
ar
am
eter
s
ca
n
b
e
r
ec
o
m
m
en
d
e
d
f
o
r
p
r
e
d
ictin
g
ca
ttle w
eig
h
t.
Fu
r
th
er
d
ev
elo
p
m
en
t
p
r
o
s
p
ec
ts
in
v
o
lv
e
ad
d
in
g
i
n
d
ep
e
n
d
en
t
v
ar
iab
les
s
u
ch
as b
r
ee
d
,
b
o
d
y
co
n
d
itio
n
s
co
r
e
(
B
C
S),
clim
ate
o
r
o
th
er
s
.
ACK
NO
WL
E
DG
E
M
E
NT
Gr
atitu
d
e
is
ex
p
r
ess
ed
to
th
e
Dep
ar
tm
en
t
o
f
C
o
m
p
u
ter
Scien
ce
I
PB
Un
iv
er
s
ity
,
Dep
ar
tm
en
t
o
f
Ma
th
em
atics
I
PB
Un
iv
er
s
ity
,
Dep
ar
tm
en
t
o
f
Pr
o
d
u
ctio
n
Sci
en
ce
an
d
T
ec
h
n
o
l
o
g
y
I
PB
Un
i
v
er
s
ity
,
I
n
d
r
ap
r
asta
PGR
I
Un
iv
er
s
ity
,
B
an
y
u
asin
Peo
p
le
’
s
L
iv
esto
ck
Sch
o
o
l
(
SP
R
)
,
Sap
ib
ag
u
s
f
ar
m
,
all
ac
ad
em
ic
s
taf
f
an
d
co
wo
r
k
er
s
th
at
h
av
e
p
o
s
itiv
ely
co
n
tr
ib
u
te
d
to
th
e
c
o
m
p
letio
n
o
f
th
is
r
esear
ch
.
RE
F
E
R
E
NC
E
S
[
1
]
D
i
t
j
e
n
P
K
H
,
“
Li
v
e
s
t
o
c
k
a
n
d
a
n
i
ma
l
h
e
a
l
t
h
st
a
t
i
st
i
c
s
2
0
2
3
(
i
n
I
n
d
o
n
e
i
s
a
n
:
s
t
a
t
i
s
t
i
k
p
e
t
e
r
n
a
k
a
n
d
a
n
k
e
se
h
a
t
a
n
h
e
w
a
n
2
0
2
3
)
,
”
v
o
l
.
2
.
D
i
r
e
k
t
o
r
a
t
J
e
n
d
e
r
a
l
P
e
t
e
r
n
a
k
a
n
d
a
n
K
e
se
h
a
t
a
n
H
e
w
a
n
K
e
me
n
t
e
r
i
a
n
P
e
r
t
a
n
i
a
n
R
I
,
I
n
d
o
n
e
s
i
a
,
p
.
2
7
8
,
2
0
2
3
.
[
2
]
J.
Ja
k
a
r
i
a
,
S
u
t
i
k
n
o
,
M
.
F
.
U
l
u
m,
a
n
d
R
.
P
r
i
y
a
n
t
o
,
“
Li
v
e
b
o
d
y
w
e
i
g
h
t
a
s
sessme
n
t
b
a
se
d
o
n
b
o
d
y
me
a
s
u
r
e
me
n
t
s
i
n
B
a
l
i
c
a
t
t
l
e
(
B
o
s
J
a
v
a
n
i
c
u
s)
a
t
e
x
t
e
n
s
i
v
e
r
e
a
r
i
n
g
s
y
st
e
m,”
P
a
k
i
st
a
n
J
o
u
rn
a
l
o
f
L
i
f
e
a
n
d
S
o
c
i
a
l
S
c
i
e
n
c
e
s
,
v
o
l
.
1
7
,
n
o
.
1
,
p
p
.
1
7
–
2
3
,
2
0
1
9
.
[
3
]
Y
.
A
d
i
n
a
t
a
,
R
.
R
.
N
o
o
r
,
R
.
P
r
i
y
a
n
t
o
,
L.
C
y
r
i
l
l
a
,
a
n
d
P
.
S
u
d
r
a
j
a
d
,
“
M
o
r
p
h
o
met
r
i
c
a
n
d
p
h
y
s
i
c
a
l
c
h
a
r
a
c
t
e
r
i
st
i
c
s
o
f
I
n
d
o
n
e
s
i
a
n
b
e
e
f
c
a
t
t
l
e
,
”
Arc
h
i
v
e
s
A
n
i
m
a
l
Bre
e
d
i
n
g
,
v
o
l
.
6
6
,
n
o
.
2
,
p
p
.
1
5
3
–
1
6
1
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
5
1
9
4
/
a
a
b
-
66
-
1
5
3
-
2
0
2
3
.
[
4
]
S
.
O
z
k
a
y
a
a
n
d
Y
.
B
o
z
k
u
r
t
,
“
T
h
e
a
c
c
u
r
a
c
y
o
f
p
r
e
d
i
c
t
i
o
n
o
f
b
o
d
y
w
e
i
g
h
t
f
r
o
m
b
o
d
y
me
a
s
u
r
e
me
n
t
s
i
n
b
e
e
f
c
a
t
t
l
e
,
”
Arc
h
i
v
e
s
A
n
i
m
a
l
Bre
e
d
i
n
g
,
v
o
l
.
5
2
,
n
o
.
4
,
p
p
.
3
7
1
–
3
7
7
,
O
c
t
.
2
0
0
9
,
d
o
i
:
1
0
.
5
1
9
4
/
a
a
b
-
52
-
3
7
1
-
2
0
0
9
.
[
5
]
J.
H
a
r
sa
,
D
.
H
e
r
i
y
a
d
i
,
a
n
d
D
.
R
a
m
d
a
n
i
,
“
W
e
i
g
h
t
e
s
t
i
m
a
t
i
o
n
a
c
c
u
r
a
c
y
o
f
c
e
r
t
i
f
i
c
a
t
e
d
g
a
r
u
t
e
w
e
s
b
y
u
si
n
g
n
o
v
e
l
f
o
r
m
u
l
a
,
s
c
h
o
o
r
l
f
o
r
mu
l
a
,
a
n
d
w
i
n
t
e
r
a
r
j
o
d
a
r
m
o
k
o
f
o
r
mu
l
a
,
”
J
u
rn
a
l
I
l
m
u
-
I
l
m
u
P
e
t
e
rn
a
k
a
n
,
v
o
l
.
3
0
,
n
o
.
2
,
p
p
.
1
0
9
–
1
1
4
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
2
1
7
7
6
/
u
b
.
j
i
i
p
.
2
0
2
0
.
0
3
0
.
0
2
.
0
2
.
[
6
]
G
.
S
r
i
n
i
v
a
s
a
n
a
n
d
T.
S
a
t
h
i
a
mo
o
r
t
h
y
,
“
M
o
r
p
h
o
m
e
t
r
i
c
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
o
f
p
u
l
i
k
u
l
a
m
c
a
t
t
l
e
b
r
e
e
d
i
n
a
n
u
c
l
e
u
s
h
e
r
d
,
”
J
o
u
r
n
a
l
o
f
En
t
o
m
o
l
o
g
y
a
n
d
Z
o
o
l
o
g
y
S
t
u
d
i
e
s
,
v
o
l
.
8
,
n
o
.
3
,
p
p
.
1
8
9
3
–
1
8
9
5
,
2
0
2
0
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
w
w
w
.
e
n
t
o
m
o
l
j
o
u
r
n
a
l
.
c
o
m.
[
7
]
S
.
A
k
k
o
l
,
A
.
A
k
i
l
l
i
,
a
n
d
İ
.
C
e
ma
l
,
“
C
o
m
p
a
r
i
so
n
o
f
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
m
u
l
t
i
p
l
e
l
i
n
e
a
r
r
e
g
r
e
ssi
o
n
f
o
r
p
r
e
d
i
c
t
i
o
n
o
f
l
i
v
e
w
e
i
g
h
t
i
n
h
a
i
r
g
o
a
t
s,
”
Y
u
zu
n
c
u
Y
i
l
U
n
i
v
e
rsi
t
y
J
o
u
r
n
a
l
o
f
A
g
ri
c
u
l
t
u
ra
l
S
c
i
e
n
c
e
s
,
v
o
l
.
2
7
,
n
o
.
1
,
p
p
.
2
1
–
2
9
,
2
0
1
7
,
d
o
i
:
1
0
.
2
9
1
3
3
/
y
y
u
t
b
d
.
2
6
3
9
6
8
.
[
8
]
Z.
E.
H
u
m
a
a
n
d
F
.
I
q
b
a
l
,
“
P
r
e
d
i
c
t
i
n
g
t
h
e
b
o
d
y
w
e
i
g
h
t
o
f
B
a
l
o
c
h
i
s
h
e
e
p
u
s
i
n
g
a
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
T
u
rk
i
sh
J
o
u
r
n
a
l
o
f
Ve
t
e
ri
n
a
r
y
a
n
d
An
i
m
a
l
S
c
i
e
n
c
e
s
,
v
o
l
.
4
3
,
n
o
.
4
,
p
p
.
5
0
0
–
5
0
6
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
3
9
0
6
/
v
e
t
-
1
8
1
2
-
2
3
.
[
9
]
O
.
R
u
d
e
n
k
o
,
Y
.
M
e
g
e
l
,
O
.
B
e
z
s
o
n
o
v
,
a
n
d
A
.
R
y
b
a
l
k
a
,
“
C
a
t
t
l
e
b
r
e
e
d
i
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
l
i
v
e
w
e
i
g
h
t
e
v
a
l
u
a
t
i
o
n
o
n
t
h
e
b
a
si
s
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
c
o
m
p
u
t
e
r
v
i
si
o
n
,
”
C
o
m
p
u
t
e
r
M
o
d
e
l
i
n
g
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
,
v
o
l
.
2
6
0
8
,
p
p
.
9
3
9
–
9
5
4
,
2
0
2
0
,
d
o
i
:
1
0
.
3
2
7
8
2
/
c
mi
s
/
2
6
0
8
-
7
0
.
[
1
0
]
T.
D
.
Te
f
e
r
a
,
Y
.
Y
.
M
u
mm
e
d
,
M
.
Y
.
K
u
r
t
u
,
M
.
U
.
Le
t
t
a
,
T.
G
.
O
’
Q
u
i
n
e
,
a
n
d
J.
L.
V
i
p
h
a
m,
“
Ef
f
e
c
t
o
f
a
g
e
a
n
d
b
r
e
e
d
s
o
f
c
a
t
t
l
e
o
n
c
a
r
c
a
s
s
a
n
d
m
e
a
t
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
o
f
A
r
si
,
B
o
r
a
n
,
a
n
d
H
a
r
a
r
C
a
t
t
l
e
i
n
E
t
h
i
o
p
i
a
,
”
O
p
e
n
J
o
u
rn
a
l
o
f
An
i
m
a
l
S
c
i
e
n
c
e
s
,
v
o
l
.
0
9
,
n
o
.
0
3
,
p
p
.
3
6
7
–
3
8
3
,
2
0
1
9
,
d
o
i
:
1
0
.
4
2
3
6
/
o
j
a
s.
2
0
1
9
.
9
3
0
3
0
.
[
1
1
]
S
.
K
a
t
i
y
a
r
a
n
d
S
.
K
.
B
o
r
g
o
h
a
i
n
,
“
C
o
mp
a
r
a
t
i
v
e
e
v
a
l
u
a
t
i
o
n
o
f
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
s
f
o
r
i
ma
g
e
c
a
p
t
i
o
n
g
e
n
e
r
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
1
,
n
o
.
1
2
,
p
p
.
7
9
3
–
8
0
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
0
.
0
1
1
1
2
9
1
.
[
1
2
]
A
.
C
o
mi
n
o
t
t
e
e
t
a
l
.
,
“
A
u
t
o
m
a
t
e
d
c
o
mp
u
t
e
r
v
i
si
o
n
sy
s
t
e
m
t
o
p
r
e
d
i
c
t
b
o
d
y
w
e
i
g
h
t
a
n
d
a
v
e
r
a
g
e
d
a
i
l
y
g
a
i
n
i
n
b
e
e
f
c
a
t
t
l
e
d
u
r
i
n
g
g
r
o
w
i
n
g
a
n
d
f
i
n
i
sh
i
n
g
p
h
a
s
e
s,”
L
i
v
e
s
t
o
c
k
S
c
i
e
n
c
e
,
v
o
l
.
2
3
2
,
p
.
1
0
3
9
0
4
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
l
i
v
sci
.
2
0
1
9
.
1
0
3
9
0
4
.
[
1
3
]
P
.
Ta
n
g
w
a
n
n
a
w
i
t
a
n
d
S
.
T
a
n
g
w
a
n
n
a
w
i
t
,
“
F
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
t
o
p
r
e
d
i
c
t
q
u
a
l
i
t
y
o
f
se
g
r
e
g
a
t
i
n
g
sw
e
e
t
t
a
m
a
r
i
n
d
u
si
n
g
i
ma
g
e
p
r
o
c
e
ss
i
n
g
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
EE
C
S
)
,
v
o
l
.
2
5
,
n
o
.
1
,
p
p
.
3
3
9
–
34
6
,
Jan
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
5
.
i
1
.
p
p
3
3
9
-
3
4
6
.
[
1
4
]
Z.
H
.
P
r
a
d
a
n
a
,
B
.
H
i
d
a
y
a
t
,
a
n
d
S
.
D
a
r
a
n
a
,
“
B
e
e
f
c
a
t
t
l
e
w
e
i
g
h
t
d
e
t
e
r
mi
n
e
b
y
u
si
n
g
d
i
g
i
t
a
l
i
ma
g
e
p
r
o
c
e
ss
i
n
g
,
”
i
n
2
0
1
6
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
n
t
r
o
l
,
El
e
c
t
r
o
n
i
c
s,
R
e
n
e
w
a
b
l
e
En
e
r
g
y
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
(
I
C
C
ER
EC
)
,
S
e
p
.
2
0
1
6
,
p
p
.
1
7
9
–
1
8
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
ER
E
C
.
2
0
1
6
.
7
8
1
4
9
5
5
.
[
1
5
]
C
.
B
h
a
t
t
,
A
.
H
a
ss
a
n
i
e
n
,
N
.
A
.
S
h
a
h
,
a
n
d
J.
T
h
i
k
,
“
B
a
r
q
i
b
r
e
e
d
sh
e
e
p
w
e
i
g
h
t
e
s
t
i
m
a
t
i
o
n
b
a
se
d
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
w
i
t
h
r
e
g
r
e
ss
i
o
n
,”
a
rXi
v
p
re
p
r
i
n
t
,
2
0
1
8
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s
/
1
8
0
7
.
1
0
5
6
8
.
[
1
6
]
A
.
I
.
K
h
a
n
a
n
d
S
.
A
l
-
H
a
b
s
i
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
c
o
m
p
u
t
e
r
v
i
si
o
n
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
6
7
,
p
p
.
1
4
4
4
–
1
4
5
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
0
.
0
3
.
3
5
5
.
[
1
7
]
B
.
W
.
P
u
t
r
a
,
A
.
M
.
F
u
a
h
,
H
.
N
u
r
a
i
n
i
,
a
n
d
R
.
P
r
i
y
a
n
t
o
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
d
i
g
i
t
a
l
i
m
a
g
e
t
e
c
h
n
i
q
u
e
f
o
r
m
o
r
p
h
o
me
t
r
i
c
s
m
e
a
s
u
r
e
m
e
n
t
o
n
B
a
l
i
a
n
d
O
n
g
o
l
e
C
a
t
t
l
e
,
”
J
u
r
n
a
l
I
l
m
u
P
e
rt
a
n
i
a
n
I
n
d
o
n
e
si
a
,
v
o
l
.
2
1
,
n
o
.
1
,
p
p
.
6
3
–
6
8
,
A
p
r
.
2
0
1
6
,
d
o
i
:
1
0
.
1
8
3
4
3
/
j
i
p
i
.
2
1
.
1
.
6
3
.
[
1
8
]
J.
C
h
o
,
K
.
L
e
e
,
E.
S
h
i
n
,
G
.
C
h
o
y
,
a
n
d
S
.
D
o
,
“
H
o
w
m
u
c
h
d
a
t
a
i
s
n
e
e
d
e
d
t
o
t
r
a
i
n
a
me
d
i
c
a
l
i
ma
g
e
d
e
e
p
l
e
a
r
n
i
n
g
s
y
st
e
m
t
o
a
c
h
i
e
v
e
n
e
c
e
ssar
y
h
i
g
h
a
c
c
u
r
a
c
y
?
,
”
a
r
Xi
v
p
re
p
ri
n
t
,
2
0
1
5
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s/
1
5
1
1
.
0
6
3
4
8
.
[
1
9
]
C
.
S
h
o
r
t
e
n
a
n
d
T.
M
.
K
h
o
s
h
g
o
f
t
a
a
r
,
“
A
su
r
v
e
y
o
n
i
ma
g
e
d
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
,
”
J
o
u
r
n
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
6
,
n
o
.
1
,
p
.
6
0
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
1
9
-
0
1
9
7
-
0.
[
2
0
]
Y
u
l
i
a
n
i
n
g
s
i
h
,
S
.
N
u
r
d
i
a
t
i
,
H
.
S
u
k
o
c
o
,
a
n
d
C
.
S
u
ma
n
t
r
i
,
“
E
x
p
l
o
r
i
n
g
p
i
x
e
l
se
g
me
n
t
a
t
i
o
n
w
i
t
h
m
a
s
k
R
-
C
N
N
:
i
m
p
l
i
c
a
t
i
o
n
s
f
o
r
p
r
e
d
i
c
t
i
n
g
c
a
t
t
l
e
w
e
i
g
h
t
,
”
i
n
2
0
2
3
3
r
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
m
a
r
t
C
i
t
i
e
s
,
Au
t
o
m
a
t
i
o
n
&
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
i
n
g
S
y
s
t
e
m
s
(
I
C
O
N
-
S
O
N
I
C
S
)
,
D
e
c
.
2
0
2
3
,
p
p
.
3
2
–
3
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
N
-
S
O
N
I
C
S
5
9
8
9
8
.
2
0
2
3
.
1
0
4
3
5
1
2
0
.
[
2
1
]
S
.
A
b
d
u
l
a
t
e
e
f
a
n
d
M
.
S
a
l
ma
n
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
f
i
m
a
g
e
s
e
g
m
e
n
t
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
,
”
I
r
a
q
i
J
o
u
r
n
a
l
f
o
r
E
l
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
7
,
n
o
.
2
,
p
p
.
1
6
6
–
1
7
5
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
3
7
9
1
7
/
i
j
e
e
e
.
1
7
.
2
.
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
C
a
ttle weig
h
t p
r
ed
ictio
n
mo
d
el
u
s
in
g
co
n
v
o
lu
tio
n
a
l
n
eu
r
a
l
n
etw
o
r
k
…
(
Yu
lia
n
in
g
s
ih
)
449
[
2
2
]
K
.
H
e
,
G
.
G
k
i
o
x
a
r
i
,
P
.
D
o
l
l
a
r
,
a
n
d
R
.
G
i
r
sh
i
c
k
,
“
M
a
sk
R
-
C
N
N
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
EEE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
(
I
C
C
V)
,
2
0
1
7
,
p
p
.
2
9
6
1
–
2
9
6
9
.
[
2
3
]
A
.
M
.
S
i
r
e
g
a
r
,
Y
.
A
.
P
u
r
w
a
n
t
o
,
S
.
H
.
W
i
j
a
y
a
,
a
n
d
N
.
N
a
h
r
o
w
i
,
“
Tw
o
-
st
a
g
e
s o
f
se
g
m
e
n
t
a
t
i
o
n
t
o
i
mp
r
o
v
e
a
c
c
u
r
a
c
y
o
f
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
b
a
s
e
d
o
n
d
a
i
r
y
c
o
w
m
o
r
p
h
o
l
o
g
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
(
I
J
EC
E)
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
2
0
9
3
–
21
0
0
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
2
.
p
p
2
0
9
3
-
2
1
0
0
.
[
2
4
]
C
.
Le
e
,
H
.
L
e
e
,
a
n
d
H
.
C
h
o
,
“
C
a
t
t
l
e
w
e
i
g
h
t
e
s
t
i
m
a
t
i
o
n
u
si
n
g
f
u
l
l
y
a
n
d
w
e
a
k
l
y
s
u
p
e
r
v
i
se
d
se
g
m
e
n
t
a
t
i
o
n
f
r
o
m
2
D
i
ma
g
e
s
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
5
,
p
.
2
8
9
6
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
0
5
2
8
9
6
.
[
2
5
]
J.
D
a
i
,
K
.
H
e
,
a
n
d
J.
S
u
n
,
“
I
n
st
a
n
c
e
-
a
w
a
r
e
s
e
ma
n
t
i
c
se
g
me
n
t
a
t
i
o
n
v
i
a
m
u
l
t
i
-
t
a
sk
n
e
t
w
o
r
k
c
a
sc
a
d
e
s,
”
i
n
2
0
1
6
I
E
E
E
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
(
C
VP
R)
,
J
u
n
.
2
0
1
6
,
p
p
.
3
1
5
0
–
3
1
5
8
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
6
.
3
4
3
.
[
2
6
]
Y
.
L
i
,
H
.
Q
i
,
J.
D
a
i
,
X
.
Ji
,
a
n
d
Y
.
W
e
i
,
“
F
u
l
l
y
c
o
n
v
o
l
u
t
i
o
n
a
l
i
n
st
a
n
c
e
-
a
w
a
r
e
sema
n
t
i
c
se
g
me
n
t
a
t
i
o
n
,
”
i
n
2
0
1
7
I
EE
E
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
(
C
VP
R)
,
J
u
l
.
2
0
1
7
,
p
p
.
4
4
3
8
–
4
4
4
6
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
7
.
4
7
2
.
[
2
7
]
N
.
G
e
sser
t
,
M
.
N
i
e
l
se
n
,
M
.
S
h
a
i
k
h
,
R
.
W
e
r
n
e
r
,
a
n
d
A
.
S
c
h
l
a
e
f
e
r
,
“
S
k
i
n
l
e
si
o
n
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
e
n
s
e
mb
l
e
s
o
f
m
u
l
t
i
-
r
e
s
o
l
u
t
i
o
n
Ef
f
i
c
i
e
n
t
N
e
t
s wi
t
h
me
t
a
d
a
t
a
,
”
Me
t
h
o
d
sX
,
v
o
l
.
7
,
p
.
1
0
0
8
6
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
e
x
.
2
0
2
0
.
1
0
0
8
6
4
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Yul
ia
n
i
n
g
sih
is
c
u
rre
n
tl
y
p
u
rsu
in
g
h
e
r
P
h
.
D.
in
Co
m
p
u
ter
S
c
ien
c
e
a
t
Bo
g
o
r
Ag
ricu
lt
u
ra
l
Un
iv
e
rsity
(IP
B)
.
S
h
e
h
o
ld
s
a
M
a
ste
r
o
f
S
c
ien
c
e
d
e
g
re
e
in
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
M
a
n
a
g
e
m
e
n
t
fro
m
S
e
k
o
lah
Ti
n
g
g
i
M
a
n
a
jem
e
n
In
fo
rm
a
ti
k
a
d
a
n
Ko
m
p
u
ter
(S
T
M
IK)
Nu
sa
M
a
n
d
iri
,
a
n
d
a
Ba
c
h
e
l
o
r
o
f
S
c
i
e
n
c
e
d
e
g
re
e
in
In
f
o
rm
a
ti
o
n
M
a
n
a
g
e
m
e
n
t
fro
m
G
u
n
a
d
a
rm
a
Un
iv
e
rsity
.
He
r
re
se
a
rc
h
in
tere
s
ts
in
c
lu
d
e
m
a
c
h
in
e
lea
rn
in
g
,
a
rt
ifi
c
ial
in
telli
g
e
n
c
e
,
sy
ste
m
d
e
v
e
lo
p
m
e
n
t,
a
n
d
wire
les
s
a
n
d
m
o
b
il
e
tec
h
n
o
lo
g
y
.
S
h
e
is
a
fa
c
u
lt
y
m
e
m
b
e
r
in
th
e
De
p
a
rtme
n
t
o
f
I
n
fo
rm
a
ti
c
s
E
n
g
i
n
e
e
rin
g
a
t
I
n
d
ra
p
ra
sta
Un
iv
e
rsit
y
.
F
o
r
a
c
a
d
e
m
ic
in
q
u
ir
ies
o
r
c
o
ll
a
b
o
ra
ti
o
n
s
,
sh
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
ip
b
_
y
u
li
a
n
i
n
g
si
h
@a
p
p
s.i
p
b
.
a
c
.
id
o
r
y
u
li
a
u
n
i
n
d
ra
@g
m
a
il
.
c
o
m
.
S
r
i
Nurdi
a
ti
is
a
P
ro
fe
ss
o
r
in
th
e
De
p
a
rtme
n
t
o
f
M
a
th
e
m
a
ti
c
s,
F
a
c
u
lt
y
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Na
tu
ra
l
S
c
ie
n
c
e
,
IP
B
Un
iv
e
rsity
.
S
h
e
h
o
ld
s
a
P
h
.
D.
in
A
p
p
li
e
d
M
a
t
h
e
m
a
ti
c
s
fro
m
th
e
Un
iv
e
rsit
y
o
f
Twe
n
te,
Ne
th
e
rlan
d
s,
a
M
a
ste
r
’
s
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
fro
m
t
h
e
Un
iv
e
rsity
o
f
Wes
tern
On
tari
o
,
Ca
n
a
d
a
,
a
n
d
a
Ba
c
h
e
lo
r'
s
d
e
g
re
e
in
S
tatisti
c
s
fro
m
IP
B
Un
iv
e
rsity
.
He
r
re
se
a
rc
h
fo
c
u
se
s
o
n
c
o
m
p
u
tati
o
n
a
l
m
a
th
e
m
a
ti
c
a
l
m
o
d
e
li
n
g
a
n
d
sta
ti
st
ics
in
v
a
rio
u
s
a
p
p
li
e
d
fiel
d
s.
A
sig
n
if
ica
n
t
p
a
rt
o
f
h
e
r
wo
r
k
in
v
o
l
v
e
s
a
n
a
ly
z
in
g
f
o
re
st
a
n
d
lan
d
fires
in
In
d
o
n
e
sia
u
si
n
g
m
a
th
e
m
a
ti
c
a
l
m
o
d
e
li
n
g
b
a
se
d
o
n
c
li
m
a
te
o
b
s
e
rv
a
ti
o
n
d
a
ta.
S
h
e
h
a
s
h
e
ld
stra
teg
ic
p
o
siti
o
n
s
i
n
e
d
u
c
a
ti
o
n
a
l
d
e
v
e
lo
p
m
e
n
t,
in
c
lu
d
i
n
g
De
a
n
o
f
t
h
e
F
a
c
u
lt
y
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Na
tu
ra
l
S
c
ien
c
e
s
(F
TM
IP
A)
a
t
IP
B
Un
i
v
e
rsity
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
n
u
r
d
iati@a
p
p
s.
ip
b
.
a
c
.
id
.
H
e
r
u
S
u
k
o
c
o
h
o
ld
s
a
B.
S
c
.
i
n
C
o
m
p
u
ter
S
c
ien
c
e
fr
o
m
IP
B,
a
n
M
.
E
n
g
.
i
n
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
fro
m
ITB,
a
n
d
a
Dr.
En
g
.
i
n
A
d
v
a
n
c
e
d
IT
a
n
d
In
f
o
rm
a
ti
c
s
fro
m
K
y
u
sh
u
Un
iv
e
rsity
.
He
c
u
rre
n
tl
y
wo
r
k
s
a
t
IP
B
Un
i
v
e
rsity
'
s
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ie
n
c
e
,
fo
c
u
si
n
g
h
is
re
se
a
rc
h
o
n
n
et
-
c
e
n
tri
c
c
o
m
p
u
ti
n
g
,
fu
t
u
re
in
tern
e
t
,
I
o
T,
wire
l
e
ss
a
n
d
m
o
b
il
e
tec
h
n
o
l
o
g
y
,
h
ig
h
p
e
rfo
rm
a
n
c
e
c
o
m
p
u
ti
n
g
,
a
n
d
a
g
ro
-
m
a
rit
ime
4
.
0
f
o
r
m
o
d
e
r
n
a
n
d
sm
a
rt
a
g
ricu
lt
u
re
.
He
is
a
m
e
m
b
e
r
o
f
APT
IKO
M
,
IE
EE
,
a
n
d
IEI
C
E,
re
c
e
iv
in
g
re
se
a
rc
h
g
ra
n
ts
fr
o
m
LP
D
P
,
Ke
m
e
n
d
ik
b
u
d
rist
e
k
,
a
n
d
BRIN.
Wi
t
h
a
str
o
n
g
b
a
c
k
g
r
o
u
n
d
i
n
a
c
a
d
e
m
ia
a
n
d
in
d
u
str
y
c
o
ll
a
b
o
ra
ti
o
n
,
h
e
h
a
s
p
u
b
li
sh
e
d
i
n
re
p
u
tab
le
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
t
io
n
a
l
p
u
b
li
c
a
ti
o
n
s.
He
h
a
s
a
lso
h
e
ld
v
a
rio
u
s
IT
m
a
n
a
g
e
m
e
n
t
p
o
siti
o
n
s
a
t
IP
B
a
n
d
is
a
c
ti
v
e
a
s
a
sc
h
o
lars
h
ip
a
n
d
jo
u
rn
a
l
re
v
iew
e
r.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
rsk
o
m
@a
p
p
s.
ip
b
.
a
c
.
id
.
Ce
c
e
S
u
m
a
n
tr
i
is
a
P
r
o
fe
ss
o
r
i
n
th
e
Div
isi
o
n
o
f
Li
v
e
sto
c
k
Bre
e
d
in
g
a
n
d
G
e
n
e
ti
c
s
a
t
th
e
De
p
a
rtme
n
t
o
f
An
ima
l
P
r
o
d
u
c
ti
o
n
a
n
d
Tec
h
n
o
l
o
g
y
,
F
a
c
u
lt
y
o
f
An
ima
l
Hu
s
b
a
n
d
ry
,
IP
B
Un
iv
e
rsity
.
He
h
o
ld
s
a
Do
c
t
o
ra
te
fro
m
Ya
m
a
g
u
c
h
i
U
n
iv
e
rsit
y
,
Ja
p
a
n
,
a
M
a
ste
r
’
s
d
e
g
re
e
fro
m
Na
g
o
y
a
U
n
iv
e
rsit
y
,
a
n
d
a
Ba
c
h
e
lo
r
’
s
d
e
g
re
e
i
n
An
ima
l
P
ro
d
u
c
ti
o
n
S
c
ien
c
e
fro
m
IP
B
Un
iv
e
rsity
.
His
re
se
a
rc
h
h
a
s
b
e
e
n
re
c
o
g
n
ize
d
with
a
wa
rd
s,
p
a
rti
c
u
larly
fo
r
h
is
wo
rk
i
n
d
e
v
e
lo
p
in
g
th
e
I
P
B
-
D1
su
p
e
ri
o
r
lo
c
a
l
c
h
ick
e
n
b
re
e
d
,
w
h
ich
c
o
m
b
in
e
s
fo
u
r
d
isti
n
c
t
c
h
ick
e
n
li
n
e
s.
He
is a m
e
m
b
e
r
o
f
th
e
p
ro
f
e
ss
o
rial
b
o
a
rd
a
t
IP
B
Un
i
v
e
rsity
a
n
d
se
rv
e
s a
s a
p
e
e
r
re
v
iew
e
r
fo
r
se
v
e
ra
l
jo
u
rn
a
ls.
He
h
a
s
e
sta
b
li
sh
e
d
c
o
l
lab
o
ra
ti
o
n
s
wit
h
v
a
rio
u
s
e
n
ti
t
ies
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
c
e
c
e
s@
a
p
p
s.ip
b
.
a
c
.
i
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.