I
nte
rna
t
io
na
l J
o
urna
l o
f
Rec
o
nfig
ura
ble a
nd
E
m
be
dd
e
d Sy
s
t
e
m
s
(
I
J
R
E
S)
Vo
l.
14
,
No
.
3
,
N
o
v
e
m
b
er
20
25
,
p
p
.
6
3
8
~
6
4
8
I
SS
N:
2089
-
4864
,
DOI
:
1
0
.
1
1
5
9
1
/i
j
r
es
.
v
14
.
i
3
.
pp
6
3
8
-
6
4
8
638
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
es.ia
esco
r
e.
co
m
Cla
ss
ificatio
n
m
et
rics for p
et
a
do
pti
o
n predict
io
n w
it
h
m
a
c
hine
lea
rning
I
s
la
m
iy
a
h
1
,
M
uh
a
mm
a
d Riv
a
ni I
bra
hi
m
1
,
S
uw
a
rdi G
u
na
w
a
n
2
,
Dy
na
M
a
risa
K
ha
irina
1
,
E
rnia
t
i
E
rnia
t
i
1
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
y
st
e
ms,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s
M
u
l
a
w
a
r
ma
n
,
S
a
mari
n
d
a
,
I
n
d
o
n
e
si
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
d
u
s
t
r
i
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s
M
u
l
a
w
a
r
ma
n
,
S
a
mari
n
d
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
8
,
2
0
2
4
R
ev
i
s
ed
A
u
g
2
1
,
2
0
2
5
A
cc
ep
ted
Sep
9
,
2
0
2
5
M
il
li
o
n
s
o
f
p
e
ts
a
re
te
m
p
o
ra
ril
y
p
lac
e
d
in
sh
e
lt
e
rs,
m
a
k
in
g
it
c
h
a
ll
e
n
g
in
g
f
o
r
sh
e
lt
e
rs t
o
e
n
su
re
p
e
ts f
in
d
p
e
rm
a
n
e
n
t
h
o
m
e
s.
Hi
g
h
a
d
o
p
ti
o
n
ra
tes
a
re
c
ru
c
ial
f
o
r
a
n
ima
l
w
e
l
f
a
r
e
a
n
d
th
e
su
sta
in
a
b
il
i
ty
o
f
sh
e
lt
e
r
o
p
e
ra
ti
o
n
s.
T
h
is
stu
d
y
a
ims
to
id
e
n
ti
fy
k
e
y
fa
c
to
rs i
n
f
lu
e
n
c
in
g
p
e
t
a
d
o
p
ti
o
n
a
n
d
c
re
a
te cla
s
sif
ica
ti
o
n
m
e
tri
c
s
u
sin
g
f
iv
e
m
a
c
h
in
e
lea
rn
in
g
(M
L
)
c
las
sif
ica
ti
o
n
m
o
d
e
l
a
p
p
ro
a
c
h
e
s
t
o
p
re
d
ict
th
e
li
k
e
li
h
o
o
d
o
f
p
e
t
a
d
o
p
t
io
n
,
t
o
f
in
d
th
e
b
e
st
m
o
d
e
l
p
e
rf
o
rm
a
n
c
e
f
o
r
e
a
c
h
a
n
a
l
y
sis.
T
h
e
d
a
tas
e
t
w
a
s
o
b
tai
n
e
d
f
ro
m
s
e
v
e
ra
l
f
e
a
tu
re
s
r
e
late
d
to
a
n
im
a
l
c
h
a
ra
c
teristics
a
n
d
a
d
o
p
ti
o
n
c
o
n
d
it
io
n
s.
T
h
e
re
su
lt
s
o
f
th
e
stu
d
y
p
re
se
n
t
c
las
sif
ic
a
ti
o
n
o
f
m
e
tri
c
m
o
d
e
ls
th
a
t
in
d
ica
te
d
e
c
isio
n
tree
a
n
d
ra
n
d
o
m
f
o
re
st
(RF
)
a
s
th
e
m
o
st
e
ff
e
c
ti
v
e
m
o
d
e
ls
w
it
h
su
p
e
rio
r
p
e
rf
o
r
m
a
n
c
e
in
term
s
o
f
a
c
c
u
ra
c
y
a
n
d
c
las
s
s
e
p
a
ra
ti
o
n
a
b
il
it
y
.
F
u
rth
e
r
re
se
a
rc
h
p
ro
v
i
d
e
s
in
it
ial
e
x
p
lo
ra
ti
o
n
o
f
M
L
m
o
d
e
ls
th
a
t
a
re
n
o
t
o
n
ly
li
m
it
e
d
to
c
las
sif
ica
ti
o
n
m
o
d
e
ls
b
u
t
a
lso
m
o
d
e
l
in
teg
ra
ti
o
n
in
t
o
i
n
tern
e
t
o
f
th
in
g
s
(
Io
T
)
sy
ste
m
s
f
o
r
th
e
im
p
lem
e
n
tatio
n
o
f
a
p
e
t
a
d
o
p
ti
o
n
p
re
d
icti
o
n
sy
ste
m
b
a
se
d
o
n
M
L
in
f
e
re
n
c
e
.
T
h
e
im
p
le
m
e
n
tatio
n
o
f
M
L
c
las
si
f
ica
ti
o
n
m
o
d
e
ls
h
e
lp
s
im
p
ro
v
e
th
e
e
f
f
ici
e
n
c
y
o
f
a
n
im
a
l
a
d
o
p
ti
o
n
p
r
o
g
ra
m
s
a
n
d
o
p
ti
m
ize
sh
e
lt
e
r
o
p
e
ra
ti
o
n
s,
u
lt
im
a
tel
y
in
c
re
a
sin
g
th
e
c
h
a
n
c
e
s
o
f
su
c
c
e
ss
f
u
l
p
e
t
a
d
o
p
t
io
n
.
T
h
e
re
su
lt
s
o
f
th
e
st
u
d
y
p
ro
v
id
e
in
sig
h
ts
i
n
to
f
a
c
to
rs
i
n
f
lu
e
n
c
in
g
p
e
t
a
d
o
p
t
io
n
,
m
in
im
izin
g
th
e
len
g
th
o
f
sta
y
(
L
OS)
in
sh
e
lt
e
rs,
a
n
d
c
o
n
tri
b
u
te
to
p
ra
c
ti
ti
o
n
e
rs/
re
se
a
rc
h
e
rs
a
s a
re
fe
re
n
c
e
f
o
r
e
x
p
lo
rin
g
n
e
w
re
late
d
f
a
c
to
rs a
n
d
e
x
p
lo
ri
n
g
th
e
p
e
rf
o
r
m
a
n
c
e
o
f
M
L
m
o
d
e
ls,
e
sp
e
c
iall
y
c
las
si
f
ica
ti
o
n
m
o
d
e
ls.
K
ey
w
o
r
d
s
:
C
las
s
i
f
icatio
n
m
etr
ics
Dec
is
io
n
tr
ee
Ma
ch
i
n
e
lear
n
i
n
g
P
et
ad
o
p
tio
n
P
r
ed
ictio
n
R
an
d
o
m
f
o
r
est
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
:
D
y
n
a
Ma
r
is
a
Kh
a
ir
in
a
Dep
ar
t
m
en
t o
f
I
n
f
o
r
m
atio
n
S
y
s
te
m
s
,
Fac
u
lt
y
o
f
E
n
g
i
n
ee
r
in
g
,
Un
i
v
er
s
itas
M
u
la
w
ar
m
a
n
Gu
n
u
n
g
Kelu
a
C
a
m
p
u
s
,
Sa
m
a
r
in
d
a
7
5
1
1
9
,
E
ast
-
Kali
m
an
ta
n
,
I
n
d
o
n
esia
E
m
ail: d
y
n
a.
m
ar
is
a
@
g
m
ai
l.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
An
i
m
al
ad
o
p
tio
n
is
a
p
r
o
ce
d
u
r
e
ca
r
r
ied
o
u
t
b
y
h
u
m
a
n
s
to
k
ee
p
an
i
m
als,
esp
ec
iall
y
th
e
m
o
s
t
co
m
m
o
n
o
n
es
s
u
c
h
a
s
ca
ts
an
d
d
o
g
s
,
b
u
t
cu
r
r
en
t
l
y
m
a
n
y
al
s
o
k
ee
p
o
t
h
er
p
ets.
On
e
o
f
t
h
e
w
a
y
s
to
co
n
tr
o
l
an
i
m
al
s
i
s
b
y
tak
i
n
g
lo
s
t
o
r
ab
an
d
o
n
ed
an
i
m
als
an
d
p
lacin
g
t
h
e
m
i
n
a
n
i
m
a
l
s
h
elter
s
[
1
]
.
Statis
tical
i
n
f
o
r
m
atio
n
o
n
p
ets
in
a
s
tu
d
y
co
n
d
u
cted
b
y
[
2
]
p
r
o
v
id
es
in
f
o
r
m
atio
n
th
at
ea
c
h
y
ea
r
,
ap
p
r
o
x
im
atel
y
6
.
5
m
illi
o
n
p
ets
en
d
u
p
in
a
n
i
m
al
s
h
elter
s
.
T
h
ese
a
n
i
m
als
ar
e
te
m
p
o
r
ar
il
y
h
o
u
s
ed
i
n
v
ar
io
u
s
l
o
ca
tio
n
s
,
s
u
c
h
as
an
i
m
al
s
h
el
ter
s
,
r
escu
e
g
r
o
u
p
s
h
elter
s
,
o
r
w
ild
li
f
e
s
a
n
ct
u
a
r
ies.
T
h
e
s
tu
d
y
also
r
ev
ea
led
th
at
o
f
th
e
6
.
5
m
illi
o
n
a
n
i
m
als
i
n
s
h
elter
s
,
o
n
l
y
ab
o
u
t
4
m
illi
o
n
ar
e
ad
o
p
ted
in
an
a
v
er
ag
e
y
ea
r
,
r
esu
l
tin
g
i
n
m
o
r
e
an
i
m
als
i
n
s
h
elter
s
.
L
i
u
an
d
Me
n
g
[
3
]
s
tated
t
h
at
th
e
in
cr
ea
s
i
n
g
n
u
m
b
er
o
f
ab
an
d
o
n
ed
an
i
m
al
s
n
o
t
o
n
l
y
af
f
ec
ts
a
n
i
m
al
s
i
n
n
at
u
r
e
b
u
t
also
h
u
m
a
n
l
if
e.
C
u
r
r
en
tl
y
,
an
i
m
a
l
r
escu
e
b
y
t
h
e
co
m
m
u
n
it
y
is
s
ti
ll
in
its
ea
r
l
y
s
tag
e
s
,
th
er
e
ar
e
a
s
er
ies
o
f
p
r
o
b
lem
s
s
u
c
h
as
li
m
ited
r
escu
e
lo
ca
tio
n
s
,
r
em
o
te
r
escu
e
lo
ca
tio
n
s
,
an
d
h
ig
h
in
v
e
s
t
m
en
t
d
em
a
n
d
.
A
d
o
p
tin
g
an
i
m
als
h
a
s
a
m
o
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
C
la
s
s
i
fica
tio
n
metrics
fo
r
p
et
a
d
o
p
tio
n
p
r
ed
ictio
n
w
ith
ma
c
h
in
e
lea
r
n
in
g
(
I
s
la
miya
h
)
639
r
ea
lis
tic
an
d
p
r
o
f
o
u
n
d
m
ea
n
i
n
g
w
h
e
n
y
o
u
h
a
v
e
ex
p
er
ien
ce
d
lif
e
w
it
h
p
ets.
A
d
o
p
tin
g
a
n
i
m
als
in
cr
ea
s
e
s
p
u
b
lic
a
w
ar
e
n
ess
o
f
ca
r
in
g
f
o
r
an
i
m
a
ls
.
A
d
o
p
tin
g
p
ets
ca
n
also
h
elp
ch
ild
r
en
d
ev
elo
p
aw
ar
en
e
s
s
to
p
r
o
tect
an
i
m
als,
h
av
e
a
s
e
n
s
e
o
f
co
m
p
as
s
io
n
,
an
d
h
elp
to
f
u
r
t
h
er
ap
p
r
ec
iate
th
e
ch
ar
m
o
f
n
at
u
r
e
an
d
p
r
o
t
ec
t
n
atu
r
e.
A
n
i
m
a
l
s
h
elter
s
f
a
ce
c
h
alle
n
g
e
s
in
e
n
s
u
r
in
g
t
h
at
p
ets f
in
d
p
er
m
a
n
en
t
an
d
lo
v
in
g
h
o
m
es.
Hig
h
ad
o
p
tio
n
r
ates
ar
e
c
r
itical
n
o
t
o
n
l
y
f
o
r
an
i
m
al
w
el
f
ar
e
b
u
t
also
f
o
r
th
e
s
u
s
tai
n
ab
ilit
y
o
f
s
h
elter
o
p
er
atio
n
s
.
Un
d
er
s
tan
d
i
n
g
th
e
f
ac
to
r
s
th
at
in
f
l
u
en
ce
ad
o
p
tio
n
lik
e
lih
o
o
d
ca
n
h
e
lp
s
h
el
t
er
s
o
p
ti
m
ize
s
h
elter
o
p
er
atio
n
s
,
tar
g
et
r
eso
u
r
ce
s
m
o
r
e
ef
f
ec
ti
v
el
y
,
an
d
u
lti
m
atel
y
i
m
p
r
o
v
e
ad
o
p
tio
n
o
u
tco
m
e
s
.
B
y
p
r
ed
ictin
g
p
et
ad
o
p
tio
n
lik
elih
o
o
d
an
d
id
en
tify
i
n
g
k
e
y
f
ac
to
r
s
,
s
h
elter
s
ca
n
b
etter
s
u
p
p
o
r
t
an
d
in
cr
ea
s
e
th
e
ch
a
n
ce
s
o
f
s
u
cc
e
s
s
f
u
l a
d
o
p
tio
n
.
Sev
er
al
s
t
u
d
ies
h
a
v
e
b
ee
n
co
n
d
u
cted
o
n
o
b
s
er
v
in
g
a
n
d
id
en
tify
i
n
g
c
h
ar
ac
ter
is
tic
s
t
h
at
i
n
f
l
u
en
ce
p
et
ad
o
p
tio
n
p
r
ed
ictio
n
.
Diesel
et
a
l.
[
4
]
r
ev
ea
led
th
at
th
e
ad
o
p
ti
o
n
r
ate
o
f
d
o
g
s
in
th
e
UK
ca
n
b
e
p
r
ed
icted
b
y
th
e
b
r
ee
d
an
d
s
ize
o
f
th
e
d
o
g
as
w
ell
as
s
ev
er
al
o
th
er
f
ac
to
r
s
a
n
d
p
r
o
v
id
es
f
ac
to
r
s
th
at
in
f
l
u
en
ce
th
e
s
u
cc
es
s
o
f
d
o
g
s
h
el
ter
s
i
n
t
h
e
U
K.
A
n
o
t
h
er
s
tu
d
y
b
y
[
5
]
s
h
o
w
ed
th
a
t
t
h
e
ca
t's
ac
ti
v
it
y
le
v
el
w
as
a
k
e
y
f
ac
to
r
i
n
ad
o
p
tio
n
r
ates.
A
s
u
b
s
eq
u
en
t
s
t
u
d
y
w
a
s
co
n
d
u
cted
b
y
[
6
]
w
h
o
lo
o
k
ed
at
t
w
o
an
i
m
al
s
h
e
lter
s
i
n
Ne
w
Yo
r
k
State
a
n
d
r
ev
ea
led
th
at
a
g
e,
b
r
ee
d
,
an
d
s
ize
h
ad
a
s
i
g
n
i
f
ica
n
t
e
f
f
ec
t
o
n
a
d
o
g
'
s
len
g
t
h
o
f
s
ta
y
(
L
O
S).
A
f
o
llo
w
-
u
p
s
t
u
d
y
w
a
s
co
n
d
u
cted
b
y
[
7
]
w
h
o
al
s
o
lo
o
k
ed
at
s
h
elter
s
i
n
t
h
e
C
ze
ch
R
ep
u
b
lic
a
n
d
r
ev
ea
led
t
h
at
lo
w
er
L
O
S
w
a
s
ass
o
ciate
d
w
it
h
s
m
all,
y
o
u
n
g
,
an
d
f
e
m
ale
d
o
g
s
.
A
n
Am
er
ica
n
s
t
u
d
y
[
8
]
s
h
o
w
ed
th
at
b
e
h
av
io
r
al
f
ac
to
r
s
,
s
u
c
h
as
f
r
ien
d
li
n
es
s
to
w
ar
d
ad
o
p
ter
s
an
d
a
h
ap
p
y
ca
t
ca
n
m
a
k
e
an
an
i
m
a
l
d
esira
b
le
to
ad
o
p
t.
T
h
e
n
ex
t
s
t
u
d
y
co
n
d
u
cted
b
y
[
9
]
s
h
o
w
ed
f
ac
to
r
s
th
at
h
elp
m
i
n
i
m
ize
th
e
le
n
g
t
h
o
f
ti
m
e
an
i
m
al
s
s
ta
y
i
n
s
h
elter
s
an
d
f
o
u
n
d
s
ev
er
al
p
et
c
h
ar
ac
ter
is
tic
s
s
u
c
h
as
ag
e,
co
lo
r
,
an
d
s
ize
t
h
at
a
f
f
ec
t
ad
o
p
tio
n
r
ates.
A
r
ec
en
t
s
tu
d
y
b
y
[
1
0
]
,
[
1
1
]
r
ev
ea
led
th
at
n
o
t
o
n
l
y
do
p
h
y
s
ical
ch
ar
ac
ter
is
tics
p
la
y
a
n
i
m
p
o
r
tan
t
r
o
le
b
u
t
th
e
lan
g
u
a
g
e
u
s
ed
in
p
et
ad
o
p
tio
n
ad
v
er
tis
e
m
en
t
s
i
s
also
a
f
ac
to
r
in
t
h
e
L
OS
a
n
d
ad
o
p
tio
n
.
E
v
en
a
r
ec
en
t
s
t
u
d
y
b
y
[
1
]
d
ev
el
o
p
ed
a
p
et
ad
o
p
tio
n
s
y
s
te
m
b
ased
o
n
ar
tif
icial
i
n
te
llig
e
n
ce
(
A
I
)
.
A
r
ec
en
t
s
t
u
d
y
b
y
[
1
2
]
d
ev
elo
p
ed
a
p
r
ed
ictiv
e
m
o
d
el
w
ith
te
x
t
u
al
g
r
ad
ien
t
en
h
an
ce
m
e
n
t
an
d
ap
p
lied
d
ata
m
i
n
in
g
tech
n
iq
u
es
to
p
r
ed
ict
a
d
o
p
tio
n
r
ates.
A
lt
h
o
u
g
h
p
r
ev
io
u
s
s
tu
d
ie
s
h
a
v
e
m
ad
e
m
aj
o
r
co
n
tr
ib
u
tio
n
s
,
ea
c
h
s
t
u
d
y
f
o
c
u
s
e
s
o
n
ce
r
tain
f
ac
to
r
s
,
s
o
f
u
r
th
er
ex
p
lo
r
atio
n
o
f
th
e
f
ac
to
r
s
th
a
t
in
f
l
u
en
ce
t
h
e
li
k
el
ih
o
o
d
o
f
p
et
ad
o
p
tio
n
is
n
ee
d
ed
to
ex
p
lo
r
e
m
o
r
e
w
id
el
y
th
e
m
o
d
el/
m
et
h
o
d
to
p
r
ed
ict
th
e
lik
eli
h
o
o
d
o
f
p
et
ad
o
p
tio
n
b
y
u
tili
zi
n
g
m
ac
h
i
n
e
lear
n
in
g
(
M
L
)
.
ML
i
ts
el
f
h
a
s
b
ee
n
p
r
o
v
e
n
u
s
ef
u
l
in
p
r
ev
io
u
s
s
t
u
d
ies b
y
[
1
3
]
f
o
r
p
r
ed
ictin
g
an
i
m
al
b
eh
a
v
io
r
.
I
n
th
i
s
r
eg
ar
d
,
to
f
ill
t
h
e
ex
i
s
ti
n
g
g
ap
,
th
i
s
s
t
u
d
y
ai
m
s
to
cr
e
ate
a
class
i
f
icatio
n
m
etr
ic
f
o
r
p
r
ed
ictin
g
th
e
li
k
eli
h
o
o
d
o
f
p
et
ad
o
p
tio
n
b
ased
o
n
t
h
e
id
en
ti
f
ica
tio
n
o
f
p
o
ten
tia
ll
y
in
f
l
u
e
n
tial
f
ac
to
r
s
b
y
u
tili
z
in
g
M
L
.
C
las
s
i
f
icatio
n
m
etr
ic
s
ar
e
ca
r
r
ied
o
u
t
as
a
n
ev
a
lu
at
io
n
o
f
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
clas
s
i
f
ic
atio
n
m
o
d
el
i
n
M
L
.
ML
co
n
s
is
t
s
o
f
ef
f
icie
n
t
m
o
d
e
l
d
esig
n
a
n
d
ac
cu
r
ate
p
r
ed
ictio
n
alg
o
r
ith
m
s
.
Mo
r
e
s
p
ec
if
ica
ll
y
,
ML
al
g
o
r
ith
m
s
ar
e
u
s
ed
to
d
etec
t
class
if
icati
o
n
an
d
p
r
ed
ictio
n
p
atter
n
s
f
r
o
m
b
i
g
d
ata
an
d
d
ev
elo
p
m
o
d
els
to
p
r
e
d
ict
f
u
tu
r
e
o
u
tco
m
es
[
1
4
]
.
T
h
e
u
s
e
o
f
ML
in
th
is
p
et
ad
o
p
tio
n
p
r
ed
ictio
n
s
t
u
d
y
is
d
u
e
to
th
e
in
v
o
lv
e
m
en
t
o
f
m
a
n
y
f
ac
to
r
s
th
at
i
n
f
lu
e
n
ce
p
et
ad
o
p
tio
n
w
h
ile
M
L
can
h
a
n
d
le
m
a
n
y
v
ar
iab
les
an
d
h
a
s
h
i
g
h
p
r
ed
ictiv
e
ca
p
ab
ilit
ies
w
h
ic
h
u
lti
m
atel
y
s
u
p
p
o
r
t
s
tr
ateg
ic
d
ec
is
io
n
m
ak
i
n
g
in
i
n
cr
ea
s
i
n
g
p
et
ad
o
p
tio
n
r
ates
.
Cl
ass
if
icatio
n
is
o
n
e
o
f
th
e
M
L
task
s
to
ca
teg
o
r
ize
in
p
u
t
d
ata
in
to
s
p
ec
if
ic
o
b
j
ec
t
class
es.
So
m
e
ML
a
n
d
d
ata
m
i
n
in
g
al
g
o
r
ith
m
s
f
o
r
class
i
f
icatio
n
an
d
p
r
ed
ictio
n
in
cl
u
d
e
lo
g
is
t
ic
r
eg
r
ess
io
n
(
L
R
)
,
d
ec
is
io
n
tr
ee
s
(
DT
)
,
r
an
d
o
m
f
o
r
est
(
R
F),
s
u
p
p
o
r
t v
ec
to
r
m
ac
h
in
e
(
SVM
)
/
s
u
p
p
o
r
t v
ec
to
r
class
i
f
ier
(
SV
C
)
,
an
d
n
aï
v
e
B
a
y
es (
NB
)
.
B
ased
o
n
th
e
ex
is
ti
n
g
ex
p
lan
a
tio
n
,
th
i
s
s
tu
d
y
e
v
al
u
ates
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
class
i
f
icat
io
n
m
o
d
el
in
M
L
b
y
cr
ea
ti
n
g
a
cla
s
s
i
f
ic
atio
n
m
etr
ic
to
p
r
ed
ict
th
e
li
k
elih
o
o
d
o
f
p
et
ad
o
p
tio
n
an
d
i
d
en
t
if
y
i
n
g
th
e
m
a
in
f
ac
to
r
s
t
h
at
i
n
f
lu
e
n
ce
p
et
ad
o
p
tio
n
.
T
h
is
s
t
u
d
y
co
n
tr
ib
u
te
s
t
o
p
r
o
v
id
in
g
i
n
s
ig
h
t
i
n
to
t
h
e
f
a
cto
r
s
th
at
i
n
f
l
u
en
ce
p
et
ad
o
p
tio
n
an
d
h
elp
s
m
i
n
i
m
ize
th
e
len
g
t
h
o
f
ti
m
e
an
i
m
al
s
s
ta
y
i
n
s
h
elter
s
an
d
co
n
tr
ib
u
tes
to
p
r
ac
titi
o
n
er
s
/r
esear
ch
er
s
a
s
a
r
ef
er
en
ce
to
ex
p
lo
r
e
n
e
w
f
ac
to
r
s
r
elate
d
to
p
et
a
d
o
p
tio
n
an
d
ex
p
lo
r
atio
n
o
f
M
L
m
o
d
el
s
f
o
r
k
n
o
w
led
g
e
o
f
ML
m
o
d
el
p
er
f
o
r
m
an
ce
,
esp
ec
iall
y
clas
s
if
icatio
n
m
o
d
els
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
s
t
e
p
s
i
n
t
h
i
s
s
t
u
d
y
c
a
n
b
e
s
e
e
n
i
n
F
i
g
u
r
e
1
,
w
h
i
c
h
b
e
g
i
n
s
w
i
t
h
d
a
t
a
s
e
t
c
o
l
l
e
c
t
i
o
n
a
n
d
p
r
e
-
p
r
o
c
e
s
s
i
n
g
,
e
x
p
l
o
r
a
t
o
r
y
d
a
t
a
a
n
a
l
y
s
i
s
(
E
D
A
)
,
f
e
a
t
u
r
e
e
n
g
i
n
e
e
r
i
n
g
,
M
L
m
o
d
e
l
s
,
e
v
a
l
u
a
t
i
o
n
,
a
n
d
v
i
s
u
a
l
i
z
a
t
i
o
n
.
C
l
a
s
s
i
f
i
c
a
t
i
o
n
m
e
t
r
i
c
a
n
a
l
y
s
i
s
u
s
e
s
5
(
f
i
v
e
)
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
o
d
e
l
s
,
n
a
m
e
ly
L
R
,
D
T
,
R
F
,
S
V
M
,
a
n
d
N
B
t
o
p
r
o
d
u
c
e
p
r
e
d
i
c
t
i
o
n
o
u
t
p
u
t
.
T
h
e
p
r
e
d
i
c
t
i
o
n
s
r
e
s
u
l
t
o
f
t
h
e
f
i
v
e
m
o
d
e
l
s
a
r
e
v
a
l
i
d
a
t
e
d
a
n
d
e
v
a
l
u
a
t
e
d
u
s
i
n
g
m
e
a
s
u
r
e
m
e
n
t
m
e
t
h
o
d
s
t
o
m
e
a
s
u
r
e
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
t
h
e
f
i
v
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
o
d
e
l
s
b
y
d
i
s
p
l
a
y
i
n
g
e
v
a
l
u
a
t
i
o
n
m
e
t
r
i
c
s
o
f
a
c
c
u
r
a
c
y
,
p
r
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
F
1
-
s
c
o
r
e
,
a
n
d
c
o
n
f
u
s
i
o
n
m
a
t
r
i
x
a
s
w
e
l
l
a
s
r
e
c
e
i
v
e
r
o
p
e
r
a
t
i
n
g
c
h
a
r
a
c
t
e
r
i
s
t
i
c
(
R
O
C
)
a
n
d
a
r
e
a
u
n
d
e
r
t
h
e
c
u
r
v
e
(
A
U
C
)
f
o
r
e
a
c
h
m
o
d
e
l
t
o
e
v
a
l
u
a
t
e
t
h
e
t
r
a
d
e
-
o
f
f
b
e
t
w
e
e
n
p
o
s
i
t
i
v
e
a
n
d
n
e
g
a
t
i
v
e
c
l
a
s
s
e
s
s
o
t
h
a
t
t
h
e
s
i
g
n
i
f
i
c
a
n
c
e
o
f
t
h
e
f
i
v
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
o
d
e
l
s
c
a
n
b
e
c
o
n
c
l
u
d
e
d
.
T
h
i
s
s
t
u
d
y
u
s
e
s
o
b
s
e
r
v
a
t
i
o
n
s
a
t
k
n
o
w
n
a
n
im
a
l
s
h
e
l
t
e
r
s
a
n
d
u
t
i
l
i
z
e
s
t
h
e
p
e
t
a
d
o
p
t
i
o
n
d
a
t
a
s
e
t
a
t
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
,
w
h
i
c
h
p
r
o
v
i
d
e
s
c
o
m
p
r
e
h
e
n
s
i
v
e
i
n
f
o
r
m
a
t
i
o
n
a
b
o
u
t
p
e
t
s
a
v
a
i
l
a
b
l
e
f
o
r
a
d
o
p
t
i
o
n
a
n
d
i
n
c
l
u
d
e
s
a
v
a
r
i
e
t
y
o
f
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
a
n
d
a
t
t
r
i
b
u
t
e
s
t
o
b
u
i
l
d
a
p
r
e
d
i
c
t
i
v
e
m
o
d
e
l
o
f
t
h
e
l
i
k
e
l
i
h
o
o
d
o
f
p
e
t
a
d
o
p
t
i
o
n
.
T
h
e
r
e
a
r
e
1
1
(
e
l
e
v
e
n
)
f
e
a
t
u
r
e
s
u
s
e
d
i
n
t
h
e
d
a
t
a
s
e
t
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
14
,
No
.
3
,
No
v
e
m
b
er
2
0
2
5
:
638
-
6
4
8
640
Fig
u
r
e
1
.
R
esear
ch
f
lo
w
ch
ar
t
2
.
1
.
Da
t
a
lo
a
din
g
a
nd
pre
-
pro
ce
s
s
ing
T
h
is
s
tag
e
in
v
o
lv
e
s
lo
ad
in
g
t
h
e
d
ataset
a
n
d
p
r
e
-
p
r
o
ce
s
s
in
g
th
e
d
ata
a
s
an
i
n
it
ial
s
tep
f
o
r
f
u
r
th
er
an
al
y
s
is
.
Data
s
et
lo
ad
in
g
is
d
o
n
e
b
y
i
m
p
o
r
ti
n
g
t
h
e
d
ata
in
to
t
h
e
p
r
o
g
r
a
m
,
w
h
ile
p
r
ep
r
o
ce
s
s
i
n
g
i
s
p
er
f
o
r
m
ed
as
a
d
ata
clea
n
in
g
s
tep
to
in
v
es
tig
ate
m
is
s
in
g
v
a
lu
e
s
in
t
h
e
d
ataset
an
d
h
an
d
le
t
h
e
m
.
P
r
ep
r
o
ce
s
s
in
g
i
s
also
p
er
f
o
r
m
ed
to
id
en
tify
ca
te
g
o
r
ical
d
ata
th
at
n
ee
d
s
to
b
e
c
o
n
v
er
ted
in
to
n
u
m
er
ic
f
o
r
m
s
o
it
ca
n
b
e
u
s
ed
an
d
p
r
o
ce
s
s
ed
in
a
ML
m
o
d
el
.
2
.
2
.
E
x
plo
ra
t
o
ry
da
t
a
a
na
l
y
s
is
T
h
is
s
tag
e
in
v
o
lv
e
s
d
ata
ex
p
l
o
r
atio
n
an
d
v
i
s
u
a
lizatio
n
to
u
n
d
er
s
tan
d
t
h
e
f
ea
tu
r
e
s
an
d
d
is
tr
ib
u
tio
n
o
f
f
ea
t
u
r
es
in
th
e
d
ataset.
E
DA
i
s
u
s
ed
as
an
ap
p
r
o
ac
h
to
an
aly
ze
th
e
d
ataset
s
o
th
at
it
is
ea
s
y
to
u
n
d
er
s
ta
n
d
th
e
s
tr
u
ct
u
r
e
an
d
p
atter
n
o
f
th
e
d
ata
b
ef
o
r
e
ap
p
ly
i
n
g
th
e
M
L
m
o
d
el.
De
s
cr
ip
tiv
e
s
tati
s
tics
o
f
th
e
f
ea
t
u
r
es
i
n
th
e
d
ataset
ar
e
p
r
esen
ted
in
T
ab
l
e
1
,
m
ea
n
w
h
i
le
Fi
g
u
r
e
2
p
r
esen
t
s
th
e
v
is
u
aliza
t
io
n
o
f
t
h
e
d
is
tr
ib
u
tio
n
o
f
t
h
e
f
ea
t
u
r
es.
B
ased
o
n
T
ab
le
1
d
escr
ip
tiv
e
s
tati
s
tics
ca
n
b
e
u
n
d
er
s
to
o
d
th
e
d
is
tr
ib
u
tio
n
an
d
ce
n
tr
al
te
n
d
en
c
y
o
f
v
ar
io
u
s
attr
ib
u
te
s
r
elate
d
to
p
ets
i
n
s
h
elter
s
,
f
o
r
e
x
a
m
p
le,
t
h
e
Ag
eM
o
n
t
h
s
f
ea
tu
r
e
p
r
o
d
u
c
es
an
av
er
a
g
e
v
al
u
e
o
f
9
2
.
6
3
m
o
n
th
s
(
±
7
.
7
y
ea
r
s
)
w
it
h
a
s
ta
n
d
ar
d
d
ev
iatio
n
o
f
5
1
.
5
3
m
o
n
t
h
s
(
±
4
.
3
y
ea
r
s
)
r
an
g
in
g
f
r
o
m
1
(
m
i
n
)
to
1
7
9
(
m
a
x
)
m
o
n
th
s
(
±
1
5
y
ea
r
s
)
.
T
h
e
d
ata
q
u
ar
tiles
s
h
o
w
t
h
e
f
ir
s
t
q
u
ar
tile/Q1
(
2
5
%)
4
9
m
o
n
th
s
w
h
ic
h
m
ea
n
s
2
5
%
o
f
p
ets
ar
e
less
th
a
n
o
r
eq
u
al
to
4
9
m
o
n
th
s
o
ld
,
th
e
m
ed
ian
o
r
s
ec
o
n
d
q
u
ar
tile/Q2
(
5
0
%)
9
3
m
o
n
th
s
w
h
ic
h
m
ea
n
s
5
0
%
o
f
p
ets
ar
e
less
th
an
o
r
eq
u
al
to
9
3
m
o
n
th
s
o
ld
,
an
d
th
e
th
ir
d
q
u
ar
tile/Q3
(
7
5
%)
1
3
8
m
o
n
t
h
s
w
h
ich
m
ea
n
s
7
5
%
o
f
p
ets
ar
e
less
th
an
o
r
e
q
u
al
to
1
3
8
m
o
n
th
s
o
ld
.
L
ik
e
w
is
e
f
o
r
th
e
v
alu
es
i
n
o
th
er
f
ea
t
u
r
es a
cc
o
r
d
in
g
to
T
ab
le
1
.
F
e
a
t
ur
e
s
E
n
g
i
ne
e
r
i
n
g
Da
t
a
s
e
t
P
r
e
-
P
r
o
c
e
s
s
i
n
g
E
x
p
l
o
r
a
to
r
y
Da
t
a
A
na
l
y
s
i
s
T
r
a
i
n
i
ng
D
a
t
a
T
e
s
t
i
n
g
D
a
t
a
M
ac
h
in
e
L
e
ar
n
in
g
M
o
d
e
l
s
E
v
a
l
ua
t
i
o
n
M
o
de
l
C
o
n
c
l
u
s
i
o
n
P
r
e
d
i
c
t
i
o
n
De
c
i
s
i
o
n
T
r
e
e
An
a
ly
s
i
s
M
o
de
l
L
o
gi
s
t
i
c
s
R
e
gr
e
s
s
i
o
n
An
a
ly
s
i
s
M
o
de
l
R
a
n
do
m
F
o
r
e
s
t
An
a
ly
s
i
s
M
o
de
l
Na
ï
v
e
B
a
y
e
s
An
a
ly
s
i
s
M
o
de
l
S
uppor
t
Ve
c
to
r
M
a
c
hi
ne
An
a
ly
s
i
s
M
o
de
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
C
la
s
s
i
fica
tio
n
metrics
fo
r
p
et
a
d
o
p
tio
n
p
r
ed
ictio
n
w
ith
ma
c
h
in
e
lea
r
n
in
g
(
I
s
la
miya
h
)
641
T
ab
le
1
.
Descr
ip
tiv
e
s
tatis
tic
s
o
f
f
ea
t
u
r
es i
n
th
e
d
atase
t
A
g
e
M
o
n
t
h
s
W
e
i
g
h
t
K
g
V
a
c
c
i
n
a
t
e
d
H
e
a
l
t
h
C
o
n
d
i
t
i
o
n
T
i
meI
n
S
h
e
l
t
e
r
D
a
y
s
A
d
o
p
t
i
o
n
F
e
e
P
r
e
v
i
o
u
sO
w
n
e
r
C
o
u
n
t
2
0
0
7
2
0
0
7
2
0
0
7
2
0
0
7
2
0
0
7
2
0
0
7
2
0
0
7
M
e
a
n
9
2
.
6
3
1
5
.
7
0
.
7
1
0
.
2
4
4
.
8
2
2
5
1
.
6
9
0
.
3
1
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
5
1
.
5
3
8
.
4
4
0
.
4
5
0
.
4
2
5
.
6
8
1
4
4
.
5
5
0
.
4
6
M
i
n
1
1
.
0
4
0
0
1
0
0
2
5
%
49
8
.
6
6
0
0
22
1
2
9
.
5
0
5
0
%
93
1
5
.
7
5
1
0
45
2
5
0
0
7
5
%
1
3
8
2
3
.
1
4
1
0
67
3
7
4
1
M
a
x
1
7
9
2
9
.
9
9
1
1
89
4
9
9
1
Fig
u
r
e
2
.
Dis
tr
ib
u
tio
n
o
f
f
ea
tu
r
es in
th
e
d
ata
s
et
2
.
3
.
F
e
a
t
ure
eng
ineering
T
h
is
s
tag
e
i
n
v
o
lv
e
s
s
elec
ti
n
g
an
d
cr
ea
tin
g
r
elev
a
n
t
f
ea
tu
r
es
f
r
o
m
t
h
e
ex
i
s
ti
n
g
d
ata
to
i
m
p
r
o
v
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
M
L
m
o
d
e
l.
T
h
is
s
tag
e
is
d
o
n
e
b
y
s
ep
ar
atin
g
th
e
d
ata
in
to
f
ea
t
u
r
es
(
x
)
an
d
tar
g
ets
(
y
)
an
d
d
iv
id
in
g
t
h
e
d
ata
in
to
a
tr
ain
i
n
g
s
et
a
n
d
a
test
s
et
f
o
r
m
o
d
el
e
v
alu
a
tio
n
.
K
u
r
n
ia
s
ar
i
et
a
l.
[
1
5
]
r
ev
ea
led
th
at
t
h
e
g
en
er
al
d
ata
-
s
h
ar
i
n
g
r
ate
i
s
8
0
%
f
o
r
tr
ai
n
in
g
a
n
d
2
0
%
f
o
r
test
i
n
g
an
d
t
h
er
e
i
s
n
o
d
ef
i
n
it
e
r
u
le
r
e
g
ar
d
in
g
t
h
e
o
p
tim
a
l
r
atio
n
al
r
atio
f
o
r
ea
c
h
d
ataset
i
n
d
ata
s
h
ar
i
n
g
.
I
n
s
o
m
e
s
tu
d
ie
s
,
s
o
m
e
s
u
g
g
e
s
t
a
te
s
t
s
et
s
ize
b
et
w
ee
n
2
5
%
an
d
5
0
%
[
1
6
]
,
an
d
s
o
m
e
r
ec
o
m
m
e
n
d
a
test
s
e
t
s
ize
o
f
5
0
%
[
1
7
]
.
Ho
w
e
v
er
,
ex
te
n
s
iv
e
n
u
m
er
ical
s
tu
d
ie
s
s
h
o
w
t
h
at
th
e
o
p
ti
m
a
l
test
d
at
a
r
atio
is
ab
o
u
t
3
0
%
[1
8
]
–
[
20
]
.
T
h
e
d
ata
d
is
tr
ib
u
tio
n
in
t
h
e
s
tu
d
y
w
a
s
d
o
n
e
b
y
d
iv
id
in
g
it
in
to
7
0
%
f
o
r
tr
a
in
i
n
g
a
n
d
3
0
%
f
o
r
test
in
g
.
T
r
ain
in
g
d
ata
is
u
s
ed
to
id
e
n
ti
f
y
p
atter
n
s
an
d
r
elatio
n
s
h
ip
s
b
et
w
ee
n
f
ea
t
u
r
es
an
d
lab
els
w
h
ile
test
d
ata
i
s
u
s
ed
to
test
t
h
e
p
er
f
o
r
m
a
n
c
e
o
f
th
e
M
L
m
o
d
el
af
ter
th
e
tr
ai
n
i
n
g
p
r
o
ce
s
s
.
2
.
4
.
M
a
chine
lea
rning
m
o
de
ls
T
h
is
s
tag
e
i
n
v
o
lv
e
s
s
elec
ti
n
g
,
tr
ain
in
g
,
an
d
i
m
p
le
m
en
t
in
g
a
ML
m
o
d
el
to
p
r
ed
ict
th
e
lik
elih
o
o
d
o
f
p
et
ad
o
p
tio
n
b
ased
o
n
id
en
tifie
d
f
ea
tu
r
es.
T
h
i
s
s
tag
e
is
ca
r
r
ied
o
u
t
b
y
in
itializ
in
g
th
e
m
o
d
el
w
h
er
e
in
th
i
s
s
tu
d
y
5
(
f
i
v
e)
class
i
f
icatio
n
m
o
d
el
s
ar
e
u
s
ed
,
tr
ain
in
g
th
e
m
o
d
el
w
ith
tr
ai
n
i
n
g
d
ata
an
d
m
a
k
i
n
g
p
r
ed
ictio
n
s
u
s
i
n
g
th
e
tr
ai
n
ed
m
o
d
el
to
m
a
k
e
p
r
ed
ictio
n
s
o
n
t
h
e
test
d
ata.
T
h
e
f
iv
e
clas
s
if
icatio
n
m
o
d
els
u
s
ed
ar
e
L
R
,
DT
,
R
F,
SVM,
a
n
d
NB
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
14
,
No
.
3
,
No
v
e
m
b
er
2
0
2
5
:
638
-
6
4
8
642
2
.
5
.
M
o
del
ev
a
lua
t
i
o
n
T
h
is
s
ta
g
e
i
n
v
o
l
v
es
ev
al
u
ati
n
g
m
o
d
el
p
er
f
o
r
m
a
n
ce
u
s
i
n
g
e
v
a
lu
atio
n
m
etr
ics to
d
eter
m
i
n
e
t
h
e
m
o
d
el
's
p
er
f
o
r
m
a
n
ce
i
n
p
r
ed
ictin
g
t
h
e
lik
eli
h
o
o
d
o
f
p
et
ad
o
p
tio
n
.
C
l
ass
i
f
icatio
n
m
o
d
el
e
v
alu
a
tio
n
is
a
cr
u
cial
s
ta
g
e
i
n
th
e
ML
m
o
d
el
d
ev
elo
p
m
e
n
t
a
n
d
ev
alu
at
io
n
p
r
o
ce
s
s
.
Mo
d
el
p
er
f
o
r
m
a
n
ce
is
m
ea
s
u
r
ed
th
r
o
u
g
h
v
alid
atio
n
an
d
ev
alu
a
tio
n
p
r
o
ce
s
s
es.
Valid
ati
o
n
an
d
ev
al
u
atio
n
ar
e
u
s
ed
as
m
ea
s
u
r
in
g
to
o
ls
to
d
eter
m
i
n
e
h
o
w
w
ell
th
e
m
o
d
el
p
er
f
o
r
m
s
in
m
a
k
i
n
g
p
r
ed
ict
io
n
s
,
th
u
s
r
ev
ea
li
n
g
s
ig
n
i
f
ica
n
t
d
if
f
er
e
n
ce
s
.
Mo
d
el
p
er
f
o
r
m
an
ce
is
an
al
y
ze
d
an
d
ev
alu
a
ted
th
r
o
u
g
h
v
ar
io
u
s
m
e
asu
r
es
g
e
n
er
ated
f
r
o
m
th
e
co
n
f
u
s
io
n
m
atr
i
x
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
r
e
s
u
l
ts
ar
e
o
b
tain
ed
af
ter
th
e
class
i
f
icatio
n
p
r
o
ce
s
s
is
tr
ain
ed
o
n
th
e
v
alid
atio
n
s
et
to
id
en
tify
w
h
ich
cl
ass
es
ar
e
co
n
f
u
s
i
n
g
th
e
clas
s
i
f
icatio
n
a
n
d
th
e
n
a
m
o
r
e
s
p
ec
if
ic
clas
s
i
f
icati
o
n
s
tr
u
ct
u
r
e
ca
n
b
e
cr
ea
ted
[2
1
]
–
[2
3
]
.
A
s
a
r
ep
r
esen
tatio
n
o
f
t
h
e
r
esu
lt
s
o
f
th
e
clas
s
if
icatio
n
p
r
o
ce
s
s
,
th
er
e
ar
e
f
o
u
r
v
alu
e
s
:
tr
u
e
p
o
s
itiv
e
(
T
P),
tr
u
e
n
eg
at
iv
e
(
T
N)
,
f
alse
p
o
s
iti
v
e
(
FP
)
,
an
d
f
alse
n
eg
a
tiv
e
(
FN)
[2
4
]
.
T
P
is
th
e
n
u
m
b
er
o
f
p
o
s
i
tiv
e
d
ata
co
r
r
ec
tl
y
o
b
tain
ed
,
w
h
ile
th
e
T
N
v
a
lu
e
is
t
h
e
n
u
m
b
er
o
f
n
e
g
ati
v
e
d
ata
co
r
r
ec
tly
co
llected
.
T
h
e
m
o
d
el
co
n
f
u
s
io
n
m
atr
i
x
ca
n
b
e
s
ee
n
i
n
T
ab
le
2
[2
5
]
.
T
ab
le
2
.
C
o
n
f
u
s
io
n
m
atr
i
x
m
o
d
el
C
l
a
ss
P
r
e
d
i
c
t
e
d
a
s
p
o
si
t
i
v
e
(
+
)
P
r
e
d
i
c
t
e
d
a
s
n
e
g
a
t
i
v
e
(
-
)
P
o
si
t
i
v
e
(
+
)
TP
FN
N
e
g
a
t
i
v
e
(
-
)
FP
TN
Oth
er
ev
al
u
atio
n
m
etr
ic
s
u
s
e
d
f
o
r
v
alid
atio
n
ar
e
ac
cu
r
ac
y
,
w
h
ic
h
d
escr
ib
es
h
o
w
ac
c
u
r
atel
y
t
h
e
m
o
d
el
m
ak
e
s
co
r
r
ec
t
p
r
ed
ictio
n
s
;
p
r
ec
is
io
n
,
w
h
ic
h
d
escr
ib
es
h
o
w
ac
cu
r
atel
y
t
h
e
m
o
d
el
id
en
ti
f
ies
t
h
e
p
o
s
itiv
e
class
;
r
ec
all,
w
h
ic
h
d
escr
ib
es
h
o
w
ac
c
u
r
atel
y
t
h
e
m
o
d
el
id
en
ti
f
ies
all
T
P
class
es;
F1
-
s
co
r
e,
w
h
ic
h
ex
a
m
i
n
es
th
e
b
alan
ce
b
et
w
ee
n
p
r
ec
is
io
n
an
d
r
ec
all;
an
d
R
OC
an
d
A
UC
to
m
ea
s
u
r
e
th
e
m
o
d
el's
p
er
f
o
r
m
a
n
ce
in
class
i
f
y
in
g
p
o
s
iti
v
e
an
d
n
e
g
at
iv
e
class
e
s
.
A
t
th
i
s
s
ta
g
e,
th
e
m
o
s
t
i
n
f
l
u
e
n
tial
f
ea
tu
r
e
s
in
t
h
e
ML
class
i
f
ica
tio
n
m
o
d
el
ar
e
also
id
en
t
if
ied
.
T
h
e
f
o
r
m
u
la
f
o
r
ea
ch
e
v
al
u
atio
n
m
etr
ic
u
s
ed
is
r
ep
r
esen
ted
i
n
(
1
)
-
(
4
)
.
=
+
+
+
+
(
1
)
=
(
+
)
(
2
)
=
(
+
)
(
3
)
1
−
=
2
(
)
+
(
4
)
2
.
6
.
M
o
del
v
is
ua
liza
t
io
n
T
h
is
s
tag
e
in
v
o
lv
e
s
v
is
u
aliz
in
g
th
e
m
o
d
el
r
esu
lt
s
to
u
n
d
er
s
t
an
d
an
d
p
r
esen
t
th
e
m
o
d
el
p
e
r
f
o
r
m
an
c
e
in
t
u
iti
v
el
y
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Ana
ly
s
is
a
nd
re
s
ults
Fiv
e
clas
s
i
f
icatio
n
m
o
d
els
w
e
r
e
u
s
ed
as
an
ap
p
r
o
ac
h
to
d
et
er
m
in
e
t
h
e
m
o
d
el
t
h
at
p
er
f
o
r
m
ed
b
est
in
class
i
f
y
in
g
t
h
e
li
k
eli
h
o
o
d
o
f
p
et
ad
o
p
tio
n
p
r
ed
ictio
n
s
.
T
h
e
f
iv
e
clas
s
i
f
icatio
n
m
o
d
els
u
s
ed
f
o
r
co
m
p
ar
is
o
n
i
n
th
is
s
tu
d
y
w
er
e
L
R
,
DT
,
R
F,
SVM,
an
d
NB
to
p
r
o
d
u
ce
p
r
e
d
ictio
n
o
u
tp
u
t.
T
h
e
f
iv
e
m
o
d
e
ls
w
er
e
tr
ain
ed
an
d
test
ed
b
ased
o
n
th
e
d
ata
d
iv
i
s
io
n
o
f
7
0
%
f
o
r
tr
ain
i
n
g
an
d
3
0
%
f
o
r
test
i
n
g
.
Af
ter
tr
ai
n
i
n
g
a
n
d
tes
tin
g
d
ata
p
r
ed
ictio
n
,
th
e
d
ec
is
io
n
tr
ee
m
o
d
el
w
a
s
co
n
s
id
er
ed
m
o
r
e
ef
f
ec
tiv
e
in
d
eter
m
in
in
g
clas
s
i
f
ic
atio
n
w
it
h
a
h
ig
h
er
ac
cu
r
ac
y
v
al
u
e
th
a
n
th
e
o
th
e
r
4
(
f
o
u
r
)
class
if
icat
io
n
m
o
d
els.
T
a
b
le
3
p
r
esen
ts
d
etails
o
f
th
e
p
er
f
o
r
m
an
ce
r
esu
lt
s
o
f
t
h
e
f
i
v
e
M
L
clas
s
if
ic
atio
n
m
o
d
els
.
I
n
g
en
er
al,
th
e
f
iv
e
M
L
class
i
f
icatio
n
m
o
d
els
h
a
v
e
ac
h
ie
v
ed
g
o
o
d
ac
cu
r
ac
y
r
esu
lts
w
it
h
s
c
o
r
es
ab
o
v
e
8
0
%.
T
h
e
d
ec
is
io
n
tr
ee
an
d
R
F
c
lass
if
ica
tio
n
m
o
d
els
h
av
e
al
m
o
s
t
t
h
e
s
a
m
e
p
er
f
o
r
m
an
ce
i
n
ac
h
iev
i
n
g
ac
cu
r
ac
y
as
t
h
e
p
er
f
o
r
m
an
ce
o
f
alg
o
r
ith
m
s
t
h
at
u
s
e
a
tr
ee
-
b
ased
p
ar
ad
ig
m
i
n
b
u
ild
i
n
g
cl
ass
i
f
icatio
n
m
o
d
els.
Fig
u
r
e
3
d
is
p
la
y
s
a
v
i
s
u
aliza
t
io
n
o
f
f
ea
t
u
r
e
i
m
p
o
r
tan
ce
s
t
h
at
in
f
o
r
m
th
e
f
ac
to
r
s
t
h
at
m
o
s
t
i
n
f
lu
e
n
ce
a
n
i
m
al
ad
o
p
tio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
C
la
s
s
i
fica
tio
n
metrics
fo
r
p
et
a
d
o
p
tio
n
p
r
ed
ictio
n
w
ith
ma
c
h
in
e
lea
r
n
in
g
(
I
s
la
miya
h
)
643
T
ab
le
3
.
C
lass
if
icatio
n
m
o
d
el
p
er
f
o
r
m
a
n
ce
r
es
u
lts
C
l
a
ssi
f
i
c
a
t
i
o
n
mo
d
e
l
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
si
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
s
c
o
r
e
(
%)
LR
9
0
.
5
9
4
.
5
7
6
.
5
8
4
.
6
DT
9
5
.
4
94
9
2
.
1
6
9
3
.
1
RF
95
9
5
.
8
8
9
.
2
9
2
.
4
S
V
M
9
0
.
5
9
5
.
1
76
8
4
.
5
NB
8
7
.
9
8
4
.
3
7
8
.
9
8
1
.
5
Fig
u
r
e
3
.
Featu
r
e
i
m
p
o
r
tan
ce
o
f
ea
ch
clas
s
i
f
icatio
n
m
o
d
el
Fro
m
Fi
g
u
r
e
3
,
it
ca
n
b
e
u
n
d
er
s
to
o
d
w
h
ich
attr
ib
u
te
s
ar
e
m
o
s
t
i
n
f
lu
e
n
tial
i
n
m
ak
i
n
g
p
r
ed
ictio
n
s
.
T
h
e
DT
an
d
R
F
m
o
d
els
ar
e
m
o
d
els
th
at
d
ir
ec
tl
y
s
u
p
p
o
r
t
f
ea
tu
r
e
im
p
o
r
ta
n
ce
s
,
w
h
i
le
th
e
L
R
,
SVM,
an
d
NB
m
o
d
el
s
ar
e
m
o
d
els
th
a
t
d
o
n
o
t
d
ir
ec
tl
y
s
u
p
p
o
r
t
f
ea
tu
r
e
i
m
p
o
r
ta
n
ce
s
b
u
t
u
s
e
m
o
d
el
co
ef
f
ic
ien
t
s
as
a
p
r
o
x
y
f
o
r
f
ea
tu
r
e
i
m
p
o
r
tan
ce
s
.
I
n
t
h
e
d
iag
r
a
m
in
Fi
g
u
r
e
3
,
th
e
y
-
ax
i
s
s
h
o
w
s
th
e
f
ea
t
u
r
es
,
a
n
d
th
e
x
-
a
x
is
s
h
o
w
s
t
h
e
r
elati
v
e
i
m
p
o
r
tan
ce
o
f
t
h
e
f
ea
t
u
r
es.
T
h
e
f
ea
t
u
r
e
w
ith
th
e
h
i
g
h
est
v
al
u
e
in
t
h
e
d
iag
r
a
m
s
h
o
w
s
t
h
at
t
h
e
f
ea
t
u
r
e
m
a
k
es t
h
e
g
r
ea
test
co
n
tr
ib
u
tio
n
a
n
d
is
c
o
n
s
id
er
ed
m
o
r
e
i
m
p
o
r
tan
t
in
in
f
lu
e
n
ci
n
g
p
r
ed
ictio
n
s
.
B
ased
o
n
Fig
u
r
e
3
,
th
e
Ag
eM
o
n
t
h
s
,
W
eig
h
tK
g
,
an
d
T
im
eI
n
Sh
el
ter
Da
y
s
f
ac
to
r
s
ar
e
th
e
m
o
s
t
i
m
p
o
r
tan
t
a
n
d
in
f
lu
en
tial
f
ea
t
u
r
es
i
n
p
r
ed
ictin
g
p
et
ad
o
p
tio
n
in
t
h
e
DT
an
d
R
F
m
o
d
els
as
t
h
e
m
o
d
els
id
en
ti
f
ied
w
it
h
th
e
b
es
t
m
o
d
el
p
er
f
o
r
m
an
ce
.
Fro
m
th
ese
r
es
u
lt
s
,
ar
ea
s
o
f
im
p
r
o
v
e
m
e
n
t
ca
n
b
e
id
en
ti
f
ie
d
to
in
cr
ea
s
e
ad
o
p
tio
n
r
ates,
s
u
c
h
as
th
e
n
ee
d
to
f
o
cu
s
o
n
an
i
m
al
h
ea
lt
h
co
n
d
iti
o
n
s
,
co
m
p
lete
n
ess
o
f
an
i
m
al
v
ac
cin
atio
n
s
,
an
d
d
u
r
atio
n
i
n
s
h
elter
s
.
T
h
e
co
n
f
u
s
io
n
m
atr
i
x
f
o
r
ea
ch
p
et
a
d
o
p
tio
n
class
is
s
h
o
w
n
in
Fig
u
r
e
4
,
w
h
ich
is
g
e
n
er
ated
f
r
o
m
ea
c
h
m
ac
h
in
e
-
lear
n
in
g
cla
s
s
i
f
icati
o
n
m
o
d
el.
Fi
g
u
r
e
4
v
is
u
ali
ze
s
th
e
r
es
u
lt
s
o
f
t
h
e
co
n
f
u
s
io
n
m
a
tr
ix
a
s
a
n
ev
alu
a
tio
n
to
o
l
to
d
eter
m
in
e
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
class
i
f
icatio
n
m
o
d
el.
T
h
e
c
o
n
f
u
s
io
n
m
atr
i
x
p
r
o
v
id
es
in
f
o
r
m
atio
n
o
n
th
e
n
u
m
b
er
o
f
co
r
r
ec
t
an
d
in
co
r
r
ec
t
p
r
ed
ic
tio
n
s
.
W
h
e
n
v
ie
w
ed
i
n
Fi
g
u
r
e
3
,
it
p
r
o
v
id
es
an
an
al
y
s
is
t
h
at
t
h
e
DT
an
d
R
F
m
o
d
el
s
p
r
o
v
id
e
t
h
e
b
est
p
er
f
o
r
m
an
ce
in
ter
m
s
o
f
ac
cu
r
ac
y
a
n
d
m
in
i
m
al
n
u
m
b
er
o
f
er
r
o
r
s
,
th
u
s
s
h
o
w
i
n
g
a
s
tr
o
n
g
ab
ilit
y
to
p
r
ed
ict
class
es
co
r
r
ec
tl
y
.
L
R
an
d
SVM
also
h
av
e
g
o
o
d
p
er
f
o
r
m
a
n
c
e
b
u
t
s
li
g
h
tl
y
m
o
r
e
er
r
o
r
s
th
a
n
t
h
e
tr
ee
-
b
ased
m
o
d
el.
W
h
ile
N
B
h
as
t
h
e
lo
w
est
p
er
f
o
r
m
an
ce
a
m
o
n
g
all
m
o
d
el
s
w
it
h
a
h
ig
h
er
n
u
m
b
er
o
f
er
r
o
r
s
.
T
h
e
f
in
a
l
e
v
alu
a
tio
n
m
etr
ic
u
s
ed
to
v
alid
ate
t
h
e
m
o
d
el
p
er
f
o
r
m
an
ce
w
as
test
ed
u
s
i
n
g
R
OC
an
d
A
U
C
in
clas
s
i
f
y
in
g
p
o
s
iti
v
e
a
n
d
n
e
g
ativ
e
cla
s
s
es.
R
O
C
A
U
C
m
ea
s
u
r
es
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
o
d
el
in
clas
s
if
y
i
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
14
,
No
.
3
,
No
v
e
m
b
er
2
0
2
5
:
638
-
6
4
8
644
p
o
s
itiv
e
a
n
d
n
e
g
ati
v
e
clas
s
es.
R
OC
A
U
C
h
a
s
a
r
an
g
e
o
f
v
alu
es
b
et
w
ee
n
0
a
n
d
1
,
w
it
h
1
in
d
icatin
g
p
er
f
ec
t
p
er
f
o
r
m
a
n
ce
.
R
O
C
A
U
C
p
r
o
v
id
es
an
o
v
er
all
p
er
f
o
r
m
an
ce
o
f
t
h
e
cla
s
s
i
f
icat
io
n
m
o
d
el
at
v
ar
io
u
s
cla
s
s
i
f
icatio
n
th
r
es
h
o
ld
s
an
d
h
as
s
tab
ilit
y
t
h
at
is
n
o
t
to
o
in
f
l
u
en
ce
d
b
y
th
e
d
is
tr
ib
u
tio
n
o
f
clas
s
es
i
n
th
e
d
ata,
m
ak
in
g
it
a
m
o
r
e
s
tab
le
m
ea
s
u
r
e
t
h
an
o
th
er
m
etr
ics
s
u
ch
as
ac
c
u
r
ac
y
a
n
d
f
ac
i
litati
n
g
co
m
p
ar
is
o
n
o
f
th
e
p
er
f
o
r
m
a
n
ce
o
f
v
ar
io
u
s
cla
s
s
i
f
icat
io
n
m
o
d
el
s
.
T
h
e
v
is
u
a
lizatio
n
o
f
t
h
e
R
O
C
A
U
C
c
u
r
v
e
o
f
t
h
e
f
i
v
e
clas
s
i
f
i
ca
tio
n
m
o
d
els
ca
n
b
e
s
ee
n
in
F
ig
u
r
e
5
.
Fig
u
r
e
4
.
C
o
n
f
u
s
io
n
m
atr
ix
o
f
ea
ch
class
if
icatio
n
m
o
d
el
Fig
u
r
e
5
.
R
OC
A
U
C
cu
r
v
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
C
la
s
s
i
fica
tio
n
metrics
fo
r
p
et
a
d
o
p
tio
n
p
r
ed
ictio
n
w
ith
ma
c
h
in
e
lea
r
n
in
g
(
I
s
la
miya
h
)
645
T
h
e
R
OC
c
u
r
v
e
in
Fi
g
u
r
e
5
p
r
o
v
id
es
in
f
o
r
m
at
io
n
t
h
at
R
F
h
as
an
AUC
v
al
u
e
o
f
0
.
9
9
w
h
i
ch
is
clo
s
e
to
1
,
th
u
s
i
n
d
icati
n
g
a
v
er
y
e
x
tr
ao
r
d
in
ar
y
p
er
f
o
r
m
a
n
ce
an
d
t
h
e
b
est
m
o
d
el
i
n
s
ep
ar
ati
n
g
cl
ass
es
b
ased
o
n
t
h
e
R
OC
cu
r
v
e
s
h
o
w
n
is
al
m
o
s
t
c
lo
s
e
to
a
p
er
f
ec
t
m
o
d
el.
L
R
a
n
d
SVM
h
a
v
e
AUC
v
al
u
es
o
f
0
.
9
5
w
h
ic
h
i
n
d
icate
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
an
d
ar
e
e
q
u
iv
ale
n
t
to
h
i
g
h
A
U
C
an
d
g
o
o
d
an
d
ef
f
ec
ti
v
e
p
r
ed
ictiv
e
a
b
ilit
y
i
n
s
ep
ar
atin
g
class
es.
DT
also
s
h
o
w
s
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
w
i
th
an
A
U
C
v
alu
e
o
f
0
.
9
4
w
h
ich
is
s
li
g
h
tl
y
lo
w
er
th
a
n
L
R
an
d
SVM,
b
u
t
th
is
d
if
f
er
e
n
ce
is
q
u
ite
s
m
all
,
an
d
th
e
DT
m
o
d
el
s
till
h
as
g
o
o
d
p
r
ed
ictiv
e
ab
il
it
y
,
w
h
ile
NB
h
a
s
s
lig
h
tl
y
lo
w
er
p
er
f
o
r
m
an
ce
t
h
an
o
th
er
m
o
d
els
w
it
h
a
lo
w
er
A
U
C
v
al
u
e
o
f
0
.
9
0
.
Ho
w
e
v
e
r
,
th
e
NB
m
o
d
el
is
s
till
q
u
i
te
g
o
o
d
at
s
ep
ar
atin
g
c
lass
es b
u
t i
s
n
o
t a
s
ac
cu
r
ate
as
o
th
er
m
o
d
els.
T
h
e
co
n
clu
s
io
n
t
h
at
ca
n
b
e
g
iv
e
n
i
n
th
e
r
esear
c
h
r
esu
l
ts
is
g
iv
e
n
i
n
th
e
v
is
u
aliza
t
io
n
o
f
th
e
co
m
p
ar
is
o
n
r
es
u
lts
o
f
t
h
e
f
iv
e
class
i
f
icatio
n
m
o
d
els
th
at
h
av
e
b
ee
n
test
ed
a
n
d
ev
al
u
at
ed
an
d
s
h
o
w
s
th
e
p
r
o
p
o
r
tio
n
o
f
p
r
ed
ictio
n
s
w
h
i
ch
ca
n
b
e
s
ee
n
in
Fi
g
u
r
e
6
.
F
ig
u
r
e
6
p
r
o
v
id
es
a
v
is
u
aliza
ti
o
n
o
f
th
e
ac
cu
r
ac
y
r
esu
lt
s
th
at
h
a
v
e
b
ee
n
p
r
esen
t
ed
in
T
ab
le
3
.
T
h
is
v
is
u
aliza
ti
o
n
also
s
er
v
e
s
as
an
e
x
p
lan
a
ti
o
n
o
f
th
e
p
r
ed
ictio
n
an
d
ev
al
u
atio
n
r
es
u
lt
s
t
h
at
h
a
v
e
b
ee
n
ca
r
r
ied
o
u
t
o
n
th
e
f
iv
e
ML
clas
s
if
icatio
n
m
o
d
els
wh
er
e
i
n
g
e
n
er
al
t
h
e
f
i
v
e
ML
clas
s
i
f
icatio
n
m
o
d
el
s
h
av
e
ac
h
ie
v
ed
g
o
o
d
ac
cu
r
ac
y
r
esu
lts
w
it
h
s
co
r
es
ab
o
v
e
8
0
%,
b
u
t
th
e
DT
an
d
R
F
m
o
d
els
h
av
e
p
er
f
o
r
m
a
n
c
e
th
at
ten
d
s
to
b
e
th
e
s
a
m
e
an
d
is
th
e
b
est
in
ac
h
iev
i
n
g
ac
cu
r
ac
y
w
ith
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
al
g
o
r
ith
m
th
at
u
s
es
th
e
tr
ee
-
b
ased
m
o
d
el
in
b
u
ild
in
g
th
e
clas
s
i
f
icatio
n
m
o
d
el
co
m
p
ar
ed
to
th
e
o
th
er
t
h
r
ee
m
o
d
els
.
Fig
u
r
e
6
.
Mo
d
el
c
o
m
p
ar
is
o
n
3
.
2
.
Dis
cus
s
io
n
a
nd
f
uture
r
esea
rc
h
T
h
e
p
r
ev
io
u
s
s
ta
g
e
h
as
p
r
o
v
id
ed
th
e
r
esu
lts
o
f
th
e
an
a
l
y
s
is
o
f
th
e
f
i
v
e
clas
s
i
f
icatio
n
m
o
d
el
s
th
at
h
a
v
e
b
ee
n
test
ed
an
d
ev
alu
a
ted
to
p
r
o
v
id
e
a
p
r
o
p
o
r
tio
n
o
f
p
et
ad
o
p
tio
n
p
r
ed
ictio
n
s
.
Of
th
e
f
iv
e
clas
s
i
f
icatio
n
m
o
d
el
s
,
th
e
y
p
r
o
v
id
e
g
o
o
d
ac
cu
r
ac
y
r
es
u
lts
w
i
t
h
a
s
co
r
e
o
f
m
o
r
e
th
an
8
0
%,
alt
h
o
u
g
h
o
f
co
u
r
s
e
th
er
e
is
t
h
e
b
est
m
o
d
el
w
it
h
th
e
h
ig
h
es
t
ac
cu
r
ac
y
p
er
f
o
r
m
a
n
ce
.
I
n
o
r
d
e
r
to
im
p
r
o
v
e
th
e
u
s
ef
u
l
n
es
s
o
f
th
e
p
et
ad
o
p
tio
n
p
r
ed
ictio
n
m
o
d
el,
th
i
s
s
y
s
te
m
ca
n
b
e
in
teg
r
ated
in
to
th
e
in
t
er
n
et
o
f
th
i
n
g
s
(
I
o
T
)
ar
ch
itect
u
r
e.
T
h
e
I
o
T
-
b
ased
m
o
n
ito
r
i
n
g
s
y
s
te
m
al
lo
w
s
t
h
e
co
llectio
n
o
f
a
n
i
m
al
b
e
h
av
io
r
d
ata
in
r
ea
l
ti
m
e
t
h
r
o
u
g
h
v
ar
io
u
s
s
en
s
o
r
s
,
s
u
ch
as
ca
m
er
as,
m
o
tio
n
s
en
s
o
r
s
,
ac
ce
ler
o
m
e
ter
s
,
an
d
te
m
p
er
atu
r
e
o
r
h
ea
r
t
r
ate
s
en
s
o
r
s
.
T
h
e
d
at
a
is
th
en
s
en
t
v
ia
a
w
ir
ele
s
s
co
n
n
ec
t
io
n
to
a
s
er
v
er
o
r
ed
g
e
d
ev
ice
to
b
e
a
n
al
y
ze
d
u
s
in
g
a
M
L
cla
s
s
i
f
i
ca
tio
n
m
o
d
el.
T
h
i
s
in
te
g
r
atio
n
allo
w
s
au
to
m
atic
d
etec
tio
n
o
f
b
eh
a
v
io
r
al
ch
a
n
g
es,
a
n
al
y
s
is
o
f
ad
o
p
tio
n
tr
en
d
s
o
v
er
ti
m
e,
a
n
d
p
r
o
v
id
es
d
ata
-
b
ased
in
s
i
g
h
ts
t
o
p
et
s
h
elter
m
a
n
ag
er
s
.
I
n
i
m
p
le
m
en
t
in
g
a
p
et
ad
o
p
tio
n
p
r
ed
ictio
n
s
y
s
te
m
,
t
wo
m
ai
n
ap
p
r
o
ac
h
es
ca
n
b
e
u
s
ed
t
o
r
u
n
M
L
m
o
d
el
i
n
f
er
en
ce
,
n
a
m
el
y
clo
u
d
-
b
ased
an
d
ed
g
e
-
b
ased
,
alth
o
u
g
h
b
o
th
ap
p
r
o
ac
h
es
h
av
e
th
eir
o
w
n
a
d
v
an
ta
g
es
a
n
d
li
m
itat
io
n
s
.
H
o
w
e
v
er
,
in
th
e
co
n
te
x
t
o
f
an
i
m
al
s
h
elter
s
,
ed
g
e
-
b
ased
in
f
er
e
n
ce
i
s
m
o
r
e
s
u
i
ta
b
le
f
o
r
lo
ca
tio
n
s
w
it
h
li
m
ited
in
ter
n
et
co
n
n
ec
ti
v
it
y
a
n
d
i
m
p
r
o
v
es
d
ata
s
ec
u
r
it
y
an
d
s
y
s
te
m
r
esp
o
n
s
i
v
en
e
s
s
.
F
ig
u
r
e
7
illu
s
tr
ates
t
h
e
f
lo
w
d
iag
r
a
m
/ar
ch
itect
u
r
e
o
f
I
o
T
in
teg
r
atio
n
w
it
h
M
L
in
f
er
en
ce
f
o
r
m
o
n
ito
r
i
n
g
a
n
d
p
r
ed
ictin
g
p
et
ad
o
p
tio
n
w
ith
ed
g
e
an
d
clo
u
d
ap
p
r
o
ac
h
es
.
B
ased
o
n
Fig
u
r
e
7
,
it
ca
n
b
e
illu
s
tr
ated
th
at
I
o
T
in
teg
r
ati
o
n
w
ith
M
L
i
n
f
er
en
ce
b
e
g
in
s
w
it
h
d
ata
co
llectio
n
t
h
r
o
u
g
h
v
ar
io
u
s
s
e
n
s
o
r
s
w
h
ic
h
ar
e
t
h
e
n
p
r
e
-
p
r
o
ce
s
s
ed
,
an
d
i
n
it
ial
M
L
i
n
f
er
en
ce
is
ca
r
r
ied
o
u
t
o
n
ed
g
e
d
ev
ices
u
s
i
n
g
f
ie
ld
p
r
o
g
r
a
m
m
ab
le
g
ate
ar
r
a
y
(
FP
G
A
)
.
T
h
e
r
esu
lts
o
f
t
h
e
p
r
o
ce
s
s
ar
e
s
en
t
v
ia
t
h
e
n
et
w
o
r
k
an
d
s
to
r
ed
in
clo
u
d
s
to
r
ag
e
f
o
r
th
e
ad
v
an
ce
d
M
L
m
o
d
el
t
r
ain
in
g
p
r
o
ce
s
s
.
T
h
e
r
es
u
lts
o
f
th
e
a
n
al
y
s
is
a
n
d
p
r
ed
ictio
n
ar
e
s
en
t b
ac
k
to
th
e
ed
g
e
d
ev
ices to
u
p
d
ate
th
e
M
L
m
o
d
el
a
n
d
i
m
p
r
o
v
e
ac
cu
r
ac
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
14
,
No
.
3
,
No
v
e
m
b
er
2
0
2
5
:
638
-
6
4
8
646
Fig
u
r
e
7
.
A
r
ch
itectu
r
e
d
ia
g
r
am
o
f
p
et
ad
o
p
tio
n
p
r
ed
ictio
n
w
it
h
Io
T
in
teg
r
atio
n
a
n
d
ML
i
n
f
er
e
n
ce
4.
CO
NCLU
SI
O
N
B
ased
o
n
a
co
m
p
r
eh
e
n
s
i
v
e
ev
alu
atio
n
o
f
s
e
v
er
al
class
i
f
icat
i
o
n
m
o
d
els
f
o
r
p
et
ad
o
p
tio
n
p
r
ed
ictio
n
,
it
ca
n
b
e
co
n
clu
d
ed
th
at
th
e
DT
an
d
R
F
m
o
d
els
ar
e
th
e
m
o
s
t
ef
f
ec
t
iv
e
m
o
d
el
s
to
u
s
e
in
th
i
s
co
n
tex
t.
B
o
t
h
m
o
d
el
s
n
o
t
o
n
l
y
s
h
o
w
v
er
y
h
i
g
h
ac
c
u
r
ac
y
b
u
t
al
s
o
a
g
o
o
d
b
alan
ce
b
et
w
ee
n
p
r
ec
is
io
n
a
n
d
r
ec
all
an
d
a
n
ea
r
-
p
er
f
ec
t
A
U
C
v
al
u
e.
T
h
is
s
h
o
w
s
t
h
at
b
o
th
m
o
d
els
ar
e
m
o
r
e
r
eliab
le
in
b
alan
cin
g
t
h
e
a
b
ilit
y
to
r
ec
o
g
n
ize
an
i
m
als
th
at
ar
e
tr
u
l
y
p
o
te
n
ti
all
y
ad
o
p
tab
le
w
h
ile
m
i
n
i
m
iz
in
g
p
r
ed
ictio
n
er
r
o
r
s
.
T
h
e
L
R
an
d
SV
M
m
o
d
el
s
also
p
r
o
v
id
e
ad
eq
u
ate
p
er
f
o
r
m
an
ce
a
n
d
ca
n
b
e
co
n
s
id
er
e
d
r
eliab
le
alter
n
ativ
es.
Ho
w
e
v
er
,
th
e
NB
m
o
d
el,
alth
o
u
g
h
s
i
m
p
ler
an
d
f
a
s
ter
,
s
h
o
w
s
les
s
o
p
ti
m
al
p
er
f
o
r
m
an
c
e
co
m
p
ar
ed
to
o
th
er
m
o
d
els
i
n
ter
m
s
o
f
ac
c
u
r
ac
y
,
r
ec
all,
an
d
A
UC
.
C
o
n
s
id
er
in
g
th
e
r
esu
lts
o
f
th
is
an
al
y
s
is
,
th
e
s
elec
tio
n
o
f
th
e
o
p
ti
m
a
l
m
o
d
el
is
h
i
g
h
l
y
d
ep
en
d
en
t o
n
th
e
s
p
ec
if
ic
o
b
j
e
ctiv
es
an
d
d
es
ir
ed
p
er
f
o
r
m
an
c
e
cr
iter
ia.
T
h
e
r
esu
lti
n
g
cla
s
s
i
f
icatio
n
m
etr
ics
ca
n
p
r
o
v
id
e
a
co
m
p
r
eh
en
s
iv
e
e
v
alu
a
tio
n
o
f
m
o
d
el
p
er
f
o
r
m
an
ce
in
p
r
ed
ictin
g
p
et
ad
o
p
tio
n
an
d
id
en
ti
f
y
p
o
ten
tial/
m
ain
f
ac
to
r
s
t
h
at
i
n
f
l
u
en
ce
p
r
ed
ictin
g
p
et
ad
o
p
tio
n
w
it
h
t
h
e
u
s
e
o
f
ML
.
T
h
e
p
r
ac
tical
i
m
p
licat
io
n
is
th
at
th
e
DT
an
d
R
F
m
o
d
els
ca
n
b
e
u
s
ed
b
y
s
h
el
ter
s
o
r
ad
o
p
ti
o
n
o
r
g
an
izatio
n
s
to
p
r
io
r
itize
an
i
m
als
w
it
h
a
lo
w
lik
eli
h
o
o
d
o
f
i
m
m
ed
iate
ad
o
p
tio
n
,
allo
w
in
g
t
h
e
m
to
r
ec
ei
v
e
s
p
ec
ialized
in
ter
v
en
tio
n
s
s
u
ch
as
m
o
r
e
i
n
te
n
s
i
v
e
p
r
o
m
o
tio
n
o
r
b
eh
av
io
r
al
tr
ain
in
g
p
r
o
g
r
a
m
s
.
T
h
u
s
,
i
m
p
le
m
en
tin
g
th
e
s
e
m
o
d
els
ca
n
h
e
lp
in
cr
ea
s
e
ad
o
p
tio
n
s
u
cc
e
s
s
r
ates
w
h
i
le
o
p
ti
m
izi
n
g
s
h
elter
r
eso
u
r
ce
s
.
F
u
r
th
er
r
esear
ch
ca
n
b
e
d
o
n
e
b
y
co
n
d
u
cti
n
g
a
b
r
o
ad
e
r
ex
p
lo
r
atio
n
o
f
o
t
h
er
M
L
m
o
d
els
t
h
at
ar
e
n
o
t
li
m
ited
to
cla
s
s
i
f
icatio
n
m
o
d
els
as
w
e
ll
as
th
e
i
n
te
g
r
a
tio
n
o
f
p
r
ed
ictio
n
m
o
d
els
in
to
I
o
T
s
y
s
te
m
s
f
o
r
p
et
a
d
o
p
tio
n
m
o
n
i
to
r
in
g
a
n
d
th
e
i
m
p
le
m
e
n
tat
io
n
o
f
a
p
et
ad
o
p
tio
n
p
r
ed
ictio
n
s
y
s
te
m
b
ased
o
n
M
L
i
n
f
er
e
n
ce
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
w
o
u
ld
li
k
e
to
ex
p
r
ess
h
i
s
g
r
atit
u
d
e
to
th
e
Facu
lt
y
o
f
E
n
g
i
n
ee
r
in
g
,
Mu
la
w
ar
m
a
n
Un
i
v
er
s
it
y
,
Sa
m
ar
i
n
d
a
f
o
r
th
e
f
u
n
d
in
g
an
d
s
u
p
p
o
r
t
p
r
o
v
id
e
d
.
T
h
e
au
th
o
r
also
ex
p
r
ess
es
h
is
g
r
atitu
d
e
f
o
r
th
e
s
u
p
p
o
r
t o
f
th
e
an
i
m
a
l sh
e
lter
t
h
at
is
w
i
lli
n
g
to
b
e
a
p
lace
f
o
r
r
esear
ch
o
b
s
er
v
atio
n
.
RE
F
E
R
E
NC
E
S
[
1
]
S
.
K
a
j
b
a
j
e
,
R
.
S
a
w
a
n
t
,
R
.
L
o
k
e
,
a
n
d
V
.
P
a
t
i
l
,
“
A
I
-
B
a
se
d
P
e
t
A
d
o
p
t
i
o
n
S
y
st
e
m,”
I
n
t
e
rn
a
t
i
o
n
a
l
R
e
se
a
rc
h
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
9
,
n
o
.
4
,
p
p
.
2
5
6
7
–
2
5
7
1
,
2
0
2
2
.
[
2
]
Z
.
M
.
B
e
c
e
r
r
a
,
S
.
P
a
r
m
a
r
,
K
.
M
a
y
,
a
n
d
R
.
E.
S
t
u
c
k
,
“
Ex
p
l
o
r
i
n
g
U
se
r
I
n
f
o
r
mat
i
o
n
N
e
e
d
s
i
n
O
n
l
i
n
e
P
e
t
A
d
o
p
t
i
o
n
P
r
o
f
i
l
e
s,”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
H
u
m
a
n
Fa
c
t
o
rs
a
n
d
Er
g
o
n
o
m
i
c
s
S
o
c
i
e
t
y
A
n
n
u
a
l
M
e
e
t
i
n
g
,
v
o
l
.
6
4
,
n
o
.
1
,
p
p
.
1
3
0
8
–
1
3
1
2
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
7
7
/
1
0
7
1
1
8
1
3
2
0
6
4
1
3
1
1
.
[
3
]
H
.
L
i
u
a
n
d
X
.
M
e
n
g
,
“
JS
P
-
B
a
se
d
P
e
t
A
d
o
p
t
i
o
n
S
y
st
e
m,”
i
n
2
0
1
9
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
V
i
rt
u
a
l
Re
a
l
i
t
y
a
n
d
I
n
t
e
l
l
i
g
e
n
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
C
la
s
s
i
fica
tio
n
metrics
fo
r
p
et
a
d
o
p
tio
n
p
r
ed
ictio
n
w
ith
ma
c
h
in
e
lea
r
n
in
g
(
I
s
la
miya
h
)
647
S
y
s
t
e
m
s (I
C
VRIS
)
,
S
e
p
.
2
0
1
9
,
p
p
.
2
3
1
–
2
3
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
V
R
I
S
.
2
0
1
9
.
0
0
0
6
4
.
[
4
]
G
.
D
i
e
s
e
l
,
D
.
U
.
P
f
e
i
f
f
e
r
,
a
n
d
D
.
B
r
o
d
b
e
l
t
,
“
F
a
c
t
o
r
s
a
f
f
e
c
t
i
n
g
t
h
e
su
c
c
e
ss
o
f
r
e
h
o
mi
n
g
d
o
g
s
i
n
t
h
e
U
K
d
u
r
i
n
g
2
0
0
5
,
”
Pre
v
e
n
t
i
v
e
Ve
t
e
ri
n
a
r
y
Me
d
i
c
i
n
e
,
v
o
l
.
8
4
,
n
o
.
3
–
4
,
p
p
.
2
2
8
–
2
4
1
,
M
a
y
2
0
0
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
e
v
e
t
me
d
.
2
0
0
7
.
1
2
.
0
0
4
.
[
5
]
J.
M
.
F
a
n
t
u
z
z
i
,
K
.
A
.
M
i
l
l
e
r
,
a
n
d
E.
W
e
i
ss,
“
F
a
c
t
o
r
s
R
e
l
e
v
a
n
t
t
o
A
d
o
p
t
i
o
n
o
f
C
a
t
s
i
n
a
n
A
n
i
mal
S
h
e
l
t
e
r
,
”
J
o
u
r
n
a
l
o
f
A
p
p
l
i
e
d
An
i
m
a
l
W
e
l
f
a
r
e
S
c
i
e
n
c
e
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
1
7
4
–
1
7
9
,
M
a
r
.
2
0
1
0
,
d
o
i
:
1
0
.
1
0
8
0
/
1
0
8
8
8
7
0
0
9
0
3
5
8
3
4
6
7
.
[
6
]
W
.
P
.
B
r
o
w
n
,
J.
P
.
D
a
v
i
d
so
n
,
a
n
d
M
.
E.
Z
u
e
f
l
e
,
“
Ef
f
e
c
t
s
o
f
P
h
e
n
o
t
y
p
i
c
C
h
a
r
a
c
t
e
r
i
s
t
i
c
s
o
n
t
h
e
L
e
n
g
t
h
o
f
S
t
a
y
o
f
D
o
g
s
a
t
Tw
o
N
o
K
i
l
l
A
n
i
mal
S
h
e
l
t
e
r
s,”
J
o
u
r
n
a
l
o
f
Ap
p
l
i
e
d
A
n
i
m
a
l
We
l
f
a
re
S
c
i
e
n
c
e
,
v
o
l
.
1
6
,
n
o
.
1
,
p
p
.
2
–
1
8
,
J
a
n
.
2
0
1
3
,
d
o
i
:
1
0
.
1
0
8
0
/
1
0
8
8
8
7
0
5
.
2
0
1
3
.
7
4
0
9
6
7
.
[
7
]
J.
Ž
á
k
,
E
.
V
o
sl
á
ř
o
v
á
,
V
.
V
e
č
e
r
e
k
,
a
n
d
I
.
B
e
d
á
ň
o
v
á
,
“
S
e
x
,
a
g
e
a
n
d
si
z
e
a
s
f
a
c
t
o
r
s
a
f
f
e
c
t
i
n
g
t
h
e
l
e
n
g
t
h
o
f
st
a
y
o
f
d
o
g
s
i
n
C
z
e
c
h
sh
e
l
t
e
r
s,”
Ac
t
a
Ve
t
e
r
i
n
a
r
i
a
Br
n
o
,
v
o
l
.
8
4
,
n
o
.
4
,
p
p
.
4
0
7
–
4
1
3
,
2
0
1
5
,
d
o
i
:
1
0
.
2
7
5
4
/
a
v
b
2
0
1
5
8
4
0
4
0
4
0
7
.
[
8
]
L
.
S
i
n
n
,
“
F
a
c
t
o
r
s
a
f
f
e
c
t
i
n
g
t
h
e
se
l
e
c
t
i
o
n
o
f
c
a
t
s
b
y
a
d
o
p
t
e
r
s,”
J
o
u
r
n
a
l
o
f
Ve
t
e
ri
n
a
r
y
Be
h
a
v
i
o
r
,
v
o
l
.
1
4
,
p
p
.
5
–
9
,
Ju
l
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
v
e
b
.
2
0
1
6
.
0
6
.
0
0
1
.
[
9
]
K
.
Z
h
a
n
g
a
n
d
S
.
Z
h
a
n
g
,
“
P
e
t
F
i
n
d
e
r
C
h
a
l
l
e
n
g
e
:
P
r
e
d
i
c
t
i
n
g
P
e
t
A
d
o
p
t
i
o
n
S
p
e
e
d
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
A
C
M
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
M
u
l
t
i
-
m
e
d
i
a
,
N
i
c
e
,
Fr
a
n
c
e
,
2
0
1
9
,
p
p
.
1
–
6.
[
1
0
]
D
.
M
.
M
a
r
k
o
w
i
t
z
,
“
P
u
t
t
i
n
g
y
o
u
r
b
e
st
p
e
t
f
o
r
w
a
r
d
:
L
a
n
g
u
a
g
e
p
a
t
t
e
r
n
s
o
f
p
e
r
su
a
s
i
o
n
i
n
o
n
l
i
n
e
p
e
t
a
d
v
e
r
t
i
se
me
n
t
s
,
”
J
o
u
r
n
a
l
o
f
Ap
p
l
i
e
d
S
o
c
i
a
l
Psy
c
h
o
l
o
g
y
,
v
o
l
.
5
0
,
n
o
.
3
,
p
p
.
1
6
0
–
1
7
3
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
1
1
/
j
a
s
p
.
1
2
6
4
7
.
[
1
1
]
J.
B
r
a
d
l
e
y
a
n
d
S
.
R
a
j
e
n
d
r
a
n
,
“
I
n
c
r
e
a
si
n
g
a
d
o
p
t
i
o
n
r
a
t
e
s
a
t
a
n
i
m
a
l
sh
e
l
t
e
r
s:
a
t
w
o
-
p
h
a
se
a
p
p
r
o
a
c
h
t
o
p
r
e
d
i
c
t
l
e
n
g
t
h
o
f
s
t
a
y
a
n
d
o
p
t
i
m
a
l
sh
e
l
t
e
r
a
l
l
o
c
a
t
i
o
n
,
”
BM
C
V
e
t
e
ri
n
a
ry
Re
s
e
a
rc
h
,
v
o
l
.
1
7
,
n
o
.
1
,
p
.
7
0
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
9
1
7
-
0
2
0
-
0
2
7
2
8
-
2.
[
1
2
]
A
.
Z
a
d
e
h
,
K
.
C
o
m
b
s,
B
.
B
u
r
k
e
y
,
J.
D
o
p
,
K
.
D
u
f
f
y
,
a
n
d
N
.
N
o
so
u
d
i
,
“
P
e
t
a
n
a
l
y
t
i
c
s:
P
r
e
d
i
c
t
i
n
g
a
d
o
p
t
i
o
n
s
p
e
e
d
o
f
p
e
t
s
f
r
o
m
t
h
e
i
r
o
n
l
i
n
e
p
r
o
f
i
l
e
s,”
E
x
p
e
rt
S
y
st
e
m
s w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
0
4
,
p
.
1
1
7
5
9
6
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
2
.
1
1
7
5
9
6
.
[
1
3
]
D
.
C
l
a
r
k
,
D
.
S
h
a
w
,
A
.
V
e
l
a
,
S
.
W
e
i
n
st
o
c
k
,
a
n
d
J
.
S
a
n
t
e
r
r
e
,
“
U
si
n
g
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
M
e
t
h
o
d
s
t
o
P
r
e
d
i
c
t
t
h
e
M
o
v
e
me
n
t
T
r
a
j
e
c
t
o
r
i
e
s o
f
t
h
e
L
o
u
i
si
a
n
a
B
l
a
c
k
B
e
a
r
,
”
S
MU D
a
t
a
S
c
i
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
5
,
n
o
.
1
,
p
.
1
1
,
2
0
2
1
.
[
1
4
]
M
.
A
.
W
a
l
l
e
r
a
n
d
S
.
E
.
F
a
w
c
e
t
t
,
“
D
a
t
a
S
c
i
e
n
c
e
,
P
r
e
d
i
c
t
i
v
e
A
n
a
l
y
t
i
c
s,
a
n
d
B
i
g
D
a
t
a
:
A
R
e
v
o
l
u
t
i
o
n
T
h
a
t
W
i
l
l
T
r
a
n
sf
o
r
m
S
u
p
p
l
y
C
h
a
i
n
D
e
si
g
n
a
n
d
M
a
n
a
g
e
me
n
t
,
”
J
o
u
rn
a
l
o
f
B
u
si
n
e
ss
L
o
g
i
s
t
i
c
s
,
v
o
l
.
3
4
,
n
o
.
2
,
p
p
.
7
7
–
8
4
,
Ju
n
.
2
0
1
3
,
d
o
i
:
1
0
.
1
1
1
1
/
j
b
l
.
1
2
0
1
0
.
[
1
5
]
D
.
K
u
r
n
i
a
s
a
r
i
,
W
.
W
a
r
so
n
o
,
M
.
U
s
man
,
F
.
R
.
L
u
mb
a
n
r
a
j
a
,
a
n
d
W
.
W
a
mi
l
i
a
n
a
,
“
L
S
T
M
-
C
N
N
H
y
b
r
i
d
M
o
d
e
l
P
e
r
f
o
r
man
c
e
I
mp
r
o
v
e
me
n
t
w
i
t
h
B
i
o
W
o
r
d
V
e
c
f
o
r
B
i
o
me
d
i
c
a
l
R
e
p
o
r
t
B
i
g
D
a
t
a
C
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
I
n
d
o
n
e
si
a
,
v
o
l
.
9
,
n
o
.
2
,
p
p
.
2
7
3
–
2
8
3
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
2
6
5
5
4
/
s
t
i
.
2
0
2
4
.
9
.
2
.
2
7
3
-
2
8
3
.
[
1
6
]
R
.
R
.
P
i
c
a
r
d
a
n
d
K
.
N
.
B
e
r
k
,
“
D
a
t
a
S
p
l
i
t
t
i
n
g
,
”
T
h
e
Am
e
r
i
c
a
n
S
t
a
t
i
st
i
c
i
a
n
,
v
o
l
.
1
4
,
n
o
.
2
,
p
p
.
1
4
0
–
1
4
7
,
1
9
9
0
.
[
1
7
]
G
.
A
f
e
n
d
r
a
s
a
n
d
M
.
M
a
r
k
a
t
o
u
,
“
O
p
t
i
mal
i
t
y
o
f
t
r
a
i
n
i
n
g
/
t
e
st
si
z
e
a
n
d
r
e
samp
l
i
n
g
e
f
f
e
c
t
i
v
e
n
e
ss
i
n
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
S
t
a
t
i
st
i
c
a
l
Pl
a
n
n
i
n
g
a
n
d
I
n
f
e
r
e
n
c
e
,
v
o
l
.
1
9
9
,
p
p
.
2
8
6
–
3
0
1
,
M
a
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
s
p
i
.
2
0
1
8
.
0
7
.
0
0
5
.
[
1
8
]
K
.
K
.
D
o
b
b
i
n
a
n
d
R
.
M
.
S
i
mo
n
,
“
O
p
t
i
m
a
l
l
y
sp
l
i
t
t
i
n
g
c
a
se
s
f
o
r
t
r
a
i
n
i
n
g
a
n
d
t
e
st
i
n
g
h
i
g
h
d
i
me
n
si
o
n
a
l
c
l
a
ssi
f
i
e
r
s,”
BM
C
M
e
d
i
c
a
l
G
e
n
o
m
i
c
s
,
v
o
l
.
4
,
n
o
.
1
,
p
.
3
1
,
D
e
c
.
2
0
1
1
,
d
o
i
:
1
0
.
1
1
8
6
/
1
7
5
5
-
8
7
9
4
-
4
-
3
1
.
[
1
9
]
Q
.
H
.
N
g
u
y
e
n
e
t
a
l
.
,
“
I
n
f
l
u
e
n
c
e
o
f
D
a
t
a
S
p
l
i
t
t
i
n
g
o
n
P
e
r
f
o
r
man
c
e
o
f
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
M
o
d
e
l
s
i
n
P
r
e
d
i
c
t
i
o
n
o
f
S
h
e
a
r
S
t
r
e
n
g
t
h
o
f
S
o
i
l
,
”
M
a
t
h
e
m
a
t
i
c
a
l
Pr
o
b
l
e
m
s
i
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
2
1
,
p
p
.
1
–
1
5
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
4
8
3
2
8
6
4
.
[
2
0
]
B
.
T
.
P
h
a
m,
I
.
P
r
a
k
a
s
h
,
A
.
Jaa
f
a
r
i
,
a
n
d
D
.
T
.
B
u
i
,
“
S
p
a
t
i
a
l
P
r
e
d
i
c
t
i
o
n
o
f
R
a
i
n
f
a
l
l
-
I
n
d
u
c
e
d
L
a
n
d
sl
i
d
e
s
U
si
n
g
A
g
g
r
e
g
a
t
i
n
g
O
n
e
-
D
e
p
e
n
d
e
n
c
e
Est
i
ma
t
o
r
s
C
l
a
ss
i
f
i
e
r
,
”
J
o
u
r
n
a
l
o
f
t
h
e
I
n
d
i
a
n
S
o
c
i
e
t
y
o
f
Re
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
4
6
,
n
o
.
9
,
p
p
.
1
4
5
7
–
1
4
7
0
,
S
e
p
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
5
2
4
-
018
-
0
7
9
1
-
1.
[
2
1
]
M.
H
a
sn
a
i
n
,
M
.
F
.
P
a
s
h
a
,
I
.
G
h
a
n
i
,
M
.
I
mr
a
n
,
M
.
Y
.
A
l
z
a
h
r
a
n
i
,
a
n
d
R
.
B
u
d
i
a
r
t
o
,
“
Ev
a
l
u
a
t
i
n
g
T
r
u
st
P
r
e
d
i
c
t
i
o
n
a
n
d
C
o
n
f
u
si
o
n
M
a
t
r
i
x
M
e
a
s
u
r
e
s
f
o
r
W
e
b
S
e
r
v
i
c
e
s
R
a
n
k
i
n
g
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
9
0
8
4
7
–
9
0
8
6
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
9
4
2
2
2
.
[
2
2
]
P
.
C
a
v
a
l
i
n
a
n
d
L
.
O
l
i
v
e
i
r
a
,
“
C
o
n
f
u
si
o
n
M
a
t
r
i
x
-
B
a
se
d
B
u
i
l
d
i
n
g
o
f
H
i
e
r
a
r
c
h
i
c
a
l
C
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
i
n
L
e
c
t
u
r
e
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
s
u
b
s
e
ri
e
s L
e
c
t
u
r
e
N
o
t
e
s
i
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
re
N
o
t
e
s
i
n
Bi
o
i
n
f
o
rm
a
t
i
c
s
,
2
0
1
9
,
p
p
.
2
7
1
–
2
7
8
.
[
2
3
]
T
.
M
a
u
r
i
t
si
u
s,
S
.
A
l
a
t
a
s,
F
.
B
i
n
sar,
R
.
Jay
a
d
i
,
a
n
d
N
.
L
e
g
o
w
o
,
“
P
r
o
mo
A
b
u
se
M
o
d
e
l
i
n
g
i
n
E
-
C
o
mm
e
r
c
e
U
si
n
g
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
A
p
p
r
o
a
c
h
,
”
i
n
2
0
2
0
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
O
ra
n
g
e
T
e
c
h
n
o
l
o
g
y
(
I
C
O
T
)
,
D
e
c
.
2
0
2
0
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
T
5
1
8
7
7
.
2
0
2
0
.
9
4
6
8
7
4
4
.
[
2
4
]
N
.
U
mar
a
n
d
B
.
E.
W
.
A
sr
u
l
,
“
I
mp
l
e
me
n
t
a
t
i
o
n
o
f
T
O
P
S
I
S
M
e
t
h
o
d
s
i
n
D
e
t
e
r
mi
n
i
n
g
M
a
k
a
ss
a
r
S
p
e
c
i
a
l
C
u
l
i
n
a
r
y
B
u
si
n
e
ss
L
o
c
a
t
i
o
n
,
”
i
n
2
0
1
8
2
n
d
Ea
s
t
I
n
d
o
n
e
s
i
a
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
EI
C
o
n
C
I
T
)
,
N
o
v
.
2
0
1
8
,
p
p
.
8
2
–
8
5
,
d
o
i
:
1
0
.
1
1
0
9
/
E
I
C
o
n
C
I
T
.
2
0
1
8
.
8
8
7
8
5
9
7
.
[
2
5
]
L
.
A
v
e
r
san
o
e
t
a
l
.
,
“
T
h
y
r
o
i
d
D
i
se
a
se
T
r
e
a
t
me
n
t
p
r
e
d
i
c
t
i
o
n
w
i
t
h
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,
”
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
9
2
,
p
p
.
1
0
3
1
–
1
0
4
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s
.
2
0
2
1
.
0
8
.
1
0
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Is
la
m
iy
a
h
e
a
rn
e
d
h
e
r
Ba
c
h
e
lo
r
o
f
In
f
o
rm
a
ti
c
s
En
g
in
e
e
rin
g
f
ro
m
S
T
M
IK
Dip
a
n
e
g
a
ra
,
M
a
k
a
s
sa
r,
In
d
o
n
e
sia
in
2
0
0
8
a
n
d
e
a
rn
e
d
h
e
r
M
a
ste
r
o
f
In
f
o
r
m
a
ti
c
s
En
g
in
e
e
rin
g
f
ro
m
S
T
M
IK
Am
ik
o
m
,
Yo
g
y
a
k
a
r
ta,
In
d
o
n
e
sia
in
2
0
1
3
.
He
r
re
se
a
rc
h
f
ield
s in
c
lu
d
e
in
f
o
rm
a
ti
o
n
s
y
ste
m
s,
d
e
c
isio
n
s
u
p
p
o
r
t
sy
st
e
m
s,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
d
a
ta
m
in
in
g
.
S
h
e
is
a
m
e
m
b
e
r
o
f
A
s
so
c
iatio
n
o
f
In
d
o
n
e
sia
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
I
n
f
o
rm
a
ti
c
s
I
n
stit
u
t
io
n
s
(A
P
T
IKO
M
)
a
n
d
In
d
o
n
e
sia
n
In
f
o
rm
a
ti
o
n
S
y
ste
m
A
s
so
c
iatio
n
(A
IS
IND
O).
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
isla
m
i
y
a
h
u
n
m
u
l@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.