I
n
t
e
r
n
at
ion
al
Jou
r
n
a
l
of
I
n
f
o
r
m
at
ics
an
d
Com
m
u
n
icat
ion
T
e
c
h
n
ol
ogy
(
I
J
-
I
CT
)
Vo
l
.
1
5
,
N
o
.
1
,
M
a
r
c
h
20
2
6
,
pp.
1
3
8
~
1
5
1
I
S
S
N:
2252
-
8776
,
DO
I
:
10
.
11591/i
ji
c
t
.
v
1
5
i
1
.
pp
1
3
8
-
1
5
1
138
Jou
r
n
al
h
o
m
e
page
:
ht
tp:
//
ij
ict
.
iaes
c
or
e
.
c
om
A
d
e
c
is
io
n
su
p
p
or
t
sy
st
e
m
f
or
m
u
s
h
r
oo
m
c
la
ssi
f
ic
at
io
n
u
s
in
g
N
aï
v
e
B
a
ye
si
an
a
lg
or
ith
m
Vil
c
h
o
r
G
.
P
e
r
d
id
o
1
,
T
h
e
l
m
a
D
.
P
al
aoag
2
1
D
e
pa
r
tm
e
nt
of
C
o
mpu
te
r
S
c
ie
n
c
e
,
C
o
ll
e
ge
of
I
n
f
or
ma
ti
o
n
T
e
c
hno
l
o
g
y
E
duc
a
ti
o
n
,
N
ue
v
a
V
iz
c
a
y
a
S
ta
te
U
ni
ve
r
s
it
y
, N
u
e
v
a
V
iz
c
a
y
a
, P
hi
li
ppi
n
e
s
2
C
o
ll
e
g
e
of
I
n
f
o
r
ma
ti
o
n
T
e
c
hn
o
l
o
g
y
a
nd C
o
mput
e
r
S
c
i
e
n
c
e
, U
n
iv
e
r
s
it
y
of
t
h
e
C
o
r
di
l
le
r
a
s
, B
a
gui
o
C
it
y
,
P
hi
li
ppi
n
e
s
Ar
t
ic
l
e
I
n
f
o
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
i
ve
d
No
v
28,
2024
R
e
vi
s
e
d
J
u
l
29,
2025
A
c
c
e
pt
e
d
Oc
t
7
,
2025
Mu
s
h
ro
o
m
s
ar
e
r
i
c
h
i
n
v
i
t
a
m
i
n
s
an
d
p
ro
t
ei
n
s
,
a
w
el
l
-
k
n
o
w
n
s
u
p
e
rfo
o
d
,
h
o
w
ev
e
r,
c
as
e
s
o
f
h
ar
m
fu
l
mu
s
h
ro
o
m
co
n
s
u
m
p
t
i
o
n
w
o
rl
d
w
i
d
e
r
e
s
u
l
t
i
n
h
al
l
u
c
i
n
at
i
o
n
s
,
i
l
l
n
e
s
s
,
o
r
d
e
at
h
.
A
s
i
g
n
i
f
i
c
an
t
ch
al
l
en
g
e
i
s
t
h
at
s
o
me
p
o
i
s
o
n
o
u
s
m
u
s
h
r
o
o
m
s
c
l
o
s
el
y
r
e
s
em
b
l
e
e
d
i
b
l
e
v
ar
i
e
t
i
es
,
m
ak
i
n
g
i
t
d
i
ff
i
cu
l
t
fo
r
mu
s
h
ro
o
m
fo
ra
g
e
rs
t
o
d
i
s
t
i
n
g
u
i
s
h
b
e
t
w
een
t
h
em
.
T
h
i
s
s
t
u
d
y
i
n
t
ro
d
u
ce
d
K
ab
u
T
e
a
c
h
,
a
d
eci
s
i
o
n
s
u
p
p
o
rt
s
y
s
t
em
(D
SS)
d
e
s
i
g
n
e
d
t
o
cl
as
s
i
f
y
mu
s
h
ro
o
m
s
b
as
e
d
o
n
t
h
ei
r
m
o
rp
h
o
l
o
g
i
c
al
c
h
ar
a
c
t
e
ri
s
t
i
c
s
u
s
i
n
g
t
h
e
N
aï
v
e
Bay
e
s
(N
B)
al
g
o
r
i
t
h
m
.
T
h
e
cl
as
s
i
fi
c
at
i
o
n
mo
d
el
w
as
ap
p
l
i
ed
t
o
a
r
e
al
-
w
o
r
l
d
d
at
as
e
t
o
f
8
,
1
2
4
i
n
s
t
an
c
e
s
fro
m
K
a
g
g
l
e
,
c
o
n
t
ai
n
i
n
g
2
3
a
t
t
ri
b
u
t
e
s
.
E
v
al
u
at
i
o
n
me
t
ri
c
s
,
i
n
c
l
u
d
i
n
g
a
ccu
racy
,
r
ec
a
l
l
,
p
reci
s
i
o
n
,
s
p
eci
fi
ci
t
y
,
an
d
F1
-
s
c
o
r
e
,
w
e
r
e
u
s
e
d
t
o
as
s
e
s
s
t
h
e
c
l
as
s
i
fi
e
r
’
s
p
e
rfo
r
m
an
ce.
R
e
s
u
l
t
s
i
n
d
i
c
at
ed
t
h
at
t
h
e
NB
c
l
as
s
i
fi
c
at
i
o
n
al
g
o
r
i
t
h
m
i
n
t
e
g
rat
e
d
i
n
t
o
K
ab
u
T
e
a
ch
a
ch
i
e
v
ed
a
h
i
g
h
accu
ra
cy
l
ev
e
l
o
f
8
9
.
1
3
%
,
u
s
i
n
g
a
7
0
:
3
0
d
at
a
s
p
l
i
t
an
d
5
-
fo
l
d
c
r
o
s
s
-
v
al
i
d
at
i
o
n
ap
p
ro
ac
h
e
s
.
T
h
e
0
.
9
8
A
U
C
(
ar
e
a
u
n
d
e
r
t
h
e
cu
rv
e
)
v
a
l
u
e
fu
rt
h
e
r
c
o
n
c
l
u
d
ed
t
h
at
t
h
e
mo
d
el
w
as
e
x
cel
l
en
t
i
n
cl
as
s
i
f
y
i
n
g
b
e
t
w
een
ed
i
b
l
e
a
n
d
p
o
i
s
o
n
o
u
s
mu
s
h
ro
o
m
s
.
T
h
e
s
e
fi
n
d
i
n
g
s
s
h
o
w
ed
t
h
at
K
ab
u
T
e
a
c
h
i
s
a
r
e
l
i
ab
l
e
c
l
as
s
i
fi
c
at
i
o
n
t
o
o
l
t
h
at
a
i
d
s
mu
s
h
ro
o
m
f
o
rag
e
rs
i
n
d
i
ff
e
r
e
n
t
i
at
i
n
g
m
u
s
h
r
o
o
m
s
an
d
p
ro
mo
t
i
n
g
s
af
e
r
co
n
s
u
m
p
t
i
o
n
p
rac
t
i
ce
s
.
T
h
i
s
i
n
n
o
v
at
i
o
n
i
n
a
g
ri
cu
l
t
u
ra
l
t
e
ch
n
o
l
o
g
y
co
u
l
d
p
o
t
en
t
i
al
l
y
r
e
d
u
ce
h
e
al
t
h
ri
s
k
s
b
y
mi
n
i
m
i
zi
n
g
a
cc
i
d
e
n
t
al
i
n
g
e
s
t
i
o
n
o
f
t
o
x
i
c
m
u
s
h
r
o
o
m
s
,
u
l
t
i
m
at
el
y
co
n
t
ri
b
u
t
i
n
g
t
o
p
u
b
l
i
c
h
e
al
t
h
s
afe
t
y
.
K
e
y
w
o
r
d
s
:
A
r
e
a
u
n
de
r
t
h
e
c
ur
v
e
C
l
a
s
s
if
i
c
a
t
i
o
n
m
o
de
l
C
r
o
s
s
-
v
a
li
da
t
i
o
n
De
c
i
s
i
o
n
s
uppo
r
t
s
y
s
t
e
m
K
a
b
uT
e
a
c
h
Na
ï
v
e
B
a
y
e
s
a
l
go
r
i
t
hm
Th
i
s
i
s
a
n
o
p
en
a
c
ces
s
a
r
t
i
c
l
e
u
n
d
e
r
t
h
e
CC
B
Y
-
SA
l
i
cen
s
e.
C
or
r
e
s
pon
din
g
A
u
th
or
:
V
i
l
c
h
o
r
G
.
P
e
r
di
do
De
pa
r
t
m
e
n
t
o
f
C
o
m
put
e
r
S
c
i
e
n
c
e
,
C
o
l
l
e
ge
o
f
I
nf
o
r
m
a
t
i
o
n
T
e
c
hn
o
l
o
g
y
E
duc
a
t
i
o
n
Nue
v
a
V
i
z
c
a
y
a
S
t
a
t
e
Uni
v
e
r
s
i
t
y
B
a
y
o
m
b
o
n
g,
Nue
v
a
V
i
z
c
a
y
a
,
P
hil
i
pp
i
ne
s
E
m
a
i
l
:
v
gpe
r
d
i
do
@nv
s
u.
e
du.
ph
1.
I
NT
RODU
C
T
I
ON
M
us
h
r
o
o
m
s
a
r
e
i
n
c
r
e
a
s
i
n
g
ly
r
e
c
o
gni
z
e
d
a
s
o
n
e
o
f
t
h
e
h
e
a
l
t
hi
e
s
t
f
o
o
ds
due
to
t
h
e
i
r
r
i
c
h
n
ut
r
i
t
i
o
n
a
l
c
o
n
t
e
n
t
,
i
nc
l
ud
i
n
g
c
a
l
c
i
u
m
,
p
h
o
s
ph
o
r
us
,
vi
t
a
mi
ns
,
a
n
d
pr
o
t
e
i
n
s
.
T
h
e
y
o
f
f
e
r
n
u
m
e
r
o
us
he
a
l
t
h
be
n
e
f
i
t
s
,
s
uc
h
a
s
b
o
o
s
t
i
n
g
im
m
u
ni
t
y
,
a
i
d
i
ng
i
n
w
e
i
g
h
t
l
o
s
s
,
a
n
d
c
o
m
ba
t
i
n
g
c
a
n
c
e
r
[
1]
.
De
s
p
i
t
e
t
h
e
i
r
b
e
n
e
f
i
t
s
,
d
i
s
t
i
ngu
i
s
hi
ng
b
e
t
we
e
n
e
d
i
bl
e
a
n
d
po
i
s
o
n
o
us
m
us
h
r
o
o
m
s
r
e
m
a
in
s
a
s
i
g
nif
i
c
a
n
t
c
h
a
ll
e
n
ge
,
a
s
m
a
ny
s
p
e
c
i
e
s
r
e
s
e
m
b
l
e
o
n
e
a
n
o
t
h
e
r
,
a
n
d
i
n
c
o
r
r
e
c
t
i
de
n
t
i
f
i
c
a
t
i
o
n
c
a
n
l
e
a
d
to
s
e
v
e
r
e
h
e
a
l
t
h
c
o
n
s
e
que
n
c
e
s
[
2]
.
T
h
e
n
a
t
i
o
n
a
l
po
i
s
o
n
da
t
a
s
y
s
t
e
m
i
n
t
h
e
U
ni
t
e
d
S
t
a
tes
r
e
c
o
r
de
d
133
,
700
c
a
s
e
s
o
f
m
u
s
h
r
oo
m
e
x
po
s
ur
e
b
e
t
we
e
n
1999
a
n
d
2016,
w
i
t
h
a
n
a
dd
i
t
i
o
n
a
l
6,
136
c
a
s
e
s
r
e
po
r
t
e
d
i
n
2017
[
3]
.
I
n
Ge
r
m
a
ny
,
h
o
s
p
i
t
a
l
d
a
t
a
f
r
o
m
2000
to
2018
d
o
c
um
e
n
t
e
d
4
,
412
h
o
s
p
i
t
a
l
i
z
a
t
i
o
n
s
a
n
d
22
f
a
t
a
l
i
t
i
e
s
c
a
us
e
d
by
t
h
e
to
xi
c
e
f
f
e
c
t
s
o
f
m
us
h
r
o
o
m
c
o
n
s
u
m
pt
i
o
n
[
4]
.
Di
s
t
i
n
gu
i
s
hi
ng
b
e
t
we
e
n
e
d
i
bl
e
a
n
d
p
o
i
s
o
n
o
us
m
u
s
h
r
oo
m
s
i
s
c
h
a
ll
e
n
g
i
ng
a
n
d
r
e
qu
i
r
e
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
A
de
c
is
ion
s
uppor
t
s
y
s
tem
f
or
mus
hr
oom
c
las
s
if
ication
us
ing
N
aïve
B
ay
e
s
ian
…
(
V
il
c
hor
Gar
c
ia
P
e
r
d
ido
)
139
s
pe
c
i
a
li
z
e
d
kn
o
w
l
e
dg
e
.
S
i
n
c
e
m
o
s
t
m
us
h
r
o
o
m
s
a
r
e
i
n
e
d
i
b
l
e
,
c
o
n
s
u
mi
ng
f
o
r
a
ge
d
m
u
s
h
r
o
o
m
s
w
i
t
h
o
ut
pr
o
pe
r
i
de
n
t
i
f
i
c
a
t
i
o
n
i
s
a
s
e
r
i
o
us
mi
s
t
a
ke
.
T
h
e
c
o
n
s
e
qu
e
n
c
e
s
o
f
e
a
t
i
n
g
po
i
s
o
n
o
us
m
us
h
r
o
o
m
s
c
o
u
l
d
r
a
nge
f
r
o
m
mi
l
d
s
ym
pt
o
m
s
t
o
de
a
t
h
.
A
s
m
u
s
h
r
oo
m
s
be
c
o
m
e
i
n
c
r
e
a
s
i
ng
l
y
po
pu
l
a
r
a
s
a
f
o
o
d
s
o
ur
c
e
,
t
h
e
d
i
f
f
i
c
u
l
t
y
i
n
vi
s
u
a
l
ly
d
i
s
t
i
n
gu
i
s
hi
ng
po
i
s
o
n
o
us
v
a
r
i
e
t
i
e
s
f
r
o
m
e
d
i
bl
e
o
n
e
s
mi
g
h
t
e
x
p
l
a
i
n
t
h
e
r
i
s
i
ng
n
u
m
be
r
o
f
p
o
i
s
o
ni
ng
i
nc
i
de
n
t
s
[
5]
.
T
h
e
c
l
a
s
s
if
i
c
a
t
i
o
n
o
f
o
bj
e
c
t
s
i
s
a
n
i
m
po
r
t
a
n
t
a
r
e
a
w
i
t
hi
n
t
h
e
f
i
e
l
d
o
f
da
t
a
m
i
n
i
ng,
a
n
d
i
t
s
a
pp
l
i
c
a
t
i
o
n
e
x
t
e
n
d
s
to
a
v
a
r
i
e
t
y
o
f
a
r
e
a
s
.
W
i
t
h
a
d
v
a
nc
e
m
e
nt
s
i
n
e
m
e
r
g
i
n
g
t
e
c
hn
o
l
o
g
i
e
s
,
m
a
c
hi
ne
l
e
a
r
ni
ng
(
M
L
)
ha
s
b
e
c
o
m
e
a
po
we
r
f
u
l
t
oo
l
f
o
r
l
e
a
r
ni
ng
f
r
o
m
l
a
r
ge
,
pr
o
bl
e
m
-
s
pe
c
if
i
c
t
r
a
i
ni
ng
da
t
a
s
e
t
s
,
e
n
a
bli
ng
t
h
e
a
ut
o
m
a
t
i
o
n
o
f
i
n
t
e
l
l
i
g
e
n
t
m
o
de
l
b
u
il
d
i
ng
a
n
d
s
o
l
vi
ng
a
s
s
o
c
i
a
t
e
d
t
a
s
ks
[
6]
.
M
L
h
a
s
b
e
c
o
m
e
a
pi
v
o
t
a
l
too
l
i
n
c
l
a
s
s
if
i
c
a
t
i
o
n
t
a
s
ks
,
e
n
a
bli
ng
c
o
m
put
e
r
s
to
l
e
a
r
n
f
r
o
m
d
a
t
a
a
n
d
m
a
ke
pr
e
d
i
c
t
i
o
n
s
w
i
t
h
o
ut
e
x
p
l
i
c
i
t
pr
o
gr
a
m
mi
ng.
C
l
a
s
s
if
i
c
a
t
i
o
n
i
nv
o
l
v
e
s
pr
e
d
i
c
t
i
n
g
c
a
t
e
g
o
r
i
c
a
l
o
utco
m
e
s
b
a
s
e
d
o
n
i
n
put
f
e
a
t
ur
e
s
[
7]
a
n
d
i
s
w
i
de
ly
us
e
d
i
n
im
a
ge
c
l
a
s
s
if
i
c
a
t
i
o
n
,
pr
e
d
i
c
t
i
v
e
m
o
de
li
ng,
a
n
d
d
a
t
a
m
i
n
i
ng
do
m
a
i
ns
.
F
o
r
i
n
s
t
a
n
c
e
,
w
h
e
n
M
L
mo
de
l
s
a
r
e
a
pp
l
i
e
d
t
o
m
us
h
r
o
o
m
c
l
a
s
s
if
i
c
a
t
i
o
n
,
t
h
e
y
c
o
u
l
d
h
e
l
p
i
de
n
t
i
f
y
e
d
i
bl
e
a
n
d
po
i
s
o
n
o
us
s
pe
c
i
e
s
ba
s
e
d
o
n
m
o
r
p
h
o
l
o
g
i
c
a
l
f
e
a
t
ur
e
s
[
8]
.
W
i
t
h
t
h
e
s
e
m
a
s
s
i
v
e
c
o
l
l
e
c
t
i
o
n
s
o
f
m
u
s
h
r
oo
m
da
t
a
a
v
a
il
a
bl
e
,
c
l
a
s
s
i
f
yi
n
g
po
i
s
o
n
o
us
o
r
to
xi
c
a
n
d
e
d
i
bl
e
m
u
s
h
r
o
o
m
s
i
s
im
p
o
r
t
a
n
t
to
a
ddr
e
s
s
t
h
e
g
l
o
b
a
l
i
s
s
ue
o
f
m
us
h
r
o
o
m
p
o
i
s
o
n
i
ng
[
9]
,
e
s
pe
c
i
a
l
ly
t
o
t
h
e
l
o
c
a
l
c
o
m
m
u
ni
t
i
e
s
.
S
e
v
e
r
a
l
c
l
a
s
s
if
i
c
a
t
i
o
n
a
l
go
r
i
t
hm
s
a
r
e
c
o
m
m
o
nly
us
e
d
i
n
ML
,
e
a
c
h
w
i
t
h
i
t
s
s
t
r
e
n
gt
h
s
a
n
d
we
a
k
n
e
s
s
e
s
.
T
h
e
s
e
i
nc
l
ude
B
a
y
e
s
i
a
n
n
e
t
wo
r
ks
,
de
c
i
s
i
o
n
t
r
e
e
(
DT
)
i
n
duc
t
i
o
n
,
K
-
n
e
a
r
e
s
t
n
e
i
g
hb
o
r
(
K
NN
)
c
l
a
s
s
i
f
i
e
r
s
,
a
n
d
s
uppo
r
t
v
e
c
to
r
m
a
c
hi
ne
s
(
S
VM
)
[
10
]
,
[
11
]
.
M
o
r
e
a
dv
a
n
c
e
d
t
e
c
hni
que
s
l
i
ke
r
a
n
do
m
f
o
r
e
s
t
s
(
R
F
)
,
e
x
t
r
e
m
e
gr
a
d
i
e
n
t
b
o
o
s
t
i
n
g
(
XG
B
o
o
s
t
)
,
a
n
d
Na
ï
v
e
B
a
y
e
s
(
NB
)
a
r
e
f
r
e
que
n
t
l
y
e
m
p
l
o
y
e
d
f
o
r
t
h
e
i
r
c
o
m
put
a
t
i
o
n
a
l
e
f
f
i
c
i
e
n
c
y
a
n
d
a
c
c
ur
a
c
y
i
n
s
pe
c
i
f
i
c
t
a
s
ks
[
12]
,
[
13]
.
A
dd
i
t
i
o
n
a
ll
y
,
w
i
t
h
t
h
e
h
e
l
p
o
f
de
c
i
s
i
o
n
s
uppo
r
t
s
y
s
t
e
m
s
(
DSS
)
a
n
d
t
h
e
i
n
t
e
gr
a
t
i
o
n
o
f
t
h
e
s
e
v
a
r
i
o
us
M
L
a
l
go
r
i
t
hm
s
,
i
t
pr
o
vi
de
s
a
n
i
nt
e
r
a
c
t
i
v
e
p
l
a
t
f
o
r
m
to
a
s
s
i
s
t
us
e
r
s
i
n
m
a
k
i
ng
i
nf
o
r
m
e
d
de
c
i
s
io
n
s
.
A
DSS
a
r
c
hi
t
e
c
t
u
r
e
m
o
s
t
l
y
c
o
n
s
i
s
t
s
o
f
t
h
e
da
tab
a
s
e
(
o
r
kn
o
w
l
e
dge
b
a
s
e
)
,
t
h
e
m
o
de
l
o
r
a
l
go
r
i
t
hm
,
a
n
d
t
h
e
us
e
r
i
n
t
e
r
f
a
c
e
[
14]
.
T
hi
s
s
t
ud
y
de
v
e
l
o
pe
d
a
DSS
a
pp
l
i
c
a
t
i
o
n
t
o
c
l
a
s
s
if
y
m
u
s
h
r
oo
m
s
de
pe
n
d
i
ng
o
n
t
h
e
i
r
m
o
r
ph
o
l
o
gi
c
a
l
f
e
a
t
ur
e
s
o
r
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
.
T
h
e
a
n
a
ly
s
i
s
wa
s
b
a
s
e
d
o
n
t
h
e
e
n
d
-
us
e
r
’
s
i
n
t
e
r
a
c
t
i
o
n
w
i
t
h
t
h
e
s
y
s
t
e
m
.
T
h
e
n
t
h
e
m
us
h
r
o
o
m
wa
s
c
l
a
s
s
i
f
i
e
d
u
s
i
ng
t
h
e
NB
c
l
a
s
s
if
i
c
a
t
i
o
n
a
l
go
r
i
t
hm
,
a
n
d
t
h
e
r
e
s
u
l
t
s
w
e
r
e
pr
e
s
e
n
t
e
d
a
s
a
f
i
na
l
de
c
i
s
i
o
n
o
n
wh
e
t
h
e
r
i
t
wa
s
a
n
e
di
bl
e
o
r
p
o
i
s
o
n
o
us
m
u
s
h
r
o
o
m
.
T
h
e
s
t
udy
a
l
s
o
w
o
ul
d
l
i
ke
to
de
t
e
r
mi
ne
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
t
h
e
s
y
s
t
e
m
w
i
t
h
t
h
e
s
e
l
e
c
t
e
d
c
l
a
s
s
if
i
e
r
m
o
de
l
a
pp
li
e
d
t
o
a
r
e
a
l
-
wo
r
l
d
da
t
a
s
e
t
.
C
o
m
m
o
n
e
v
a
l
ua
t
i
o
n
m
e
a
s
ur
e
s
s
o
m
e
t
i
m
e
s
r
e
f
e
r
r
e
d
to
a
s
pe
r
f
o
r
m
a
nc
e
m
e
t
r
i
c
s
,
we
r
e
e
m
p
l
o
y
e
d
to
m
e
a
s
ur
e
t
h
e
e
f
f
i
c
a
c
y
o
r
e
f
f
e
c
t
i
v
e
n
e
s
s
o
f
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
o
de
l
.
2.
RE
S
E
AR
CH
M
E
T
HO
D
T
hi
s
s
e
c
t
i
o
n
de
l
ve
s
i
n
t
o
t
h
e
m
us
h
r
o
o
m
da
t
a
s
e
t
a
nd
t
h
e
m
e
t
h
o
ds
us
e
d
f
o
r
c
l
a
s
s
if
i
c
a
t
i
o
n
.
T
h
e
go
a
l
o
f
t
hi
s
s
t
ud
y
wa
s
t
h
e
c
l
a
s
s
if
i
c
a
t
i
o
n
i
f
m
us
h
r
o
o
m
s
w
e
r
e
e
d
i
bl
e
o
r
p
o
i
s
o
n
o
us
by
i
n
t
e
gr
a
t
i
n
g
a
m
a
c
hi
ne
-
l
e
a
r
ni
n
g
t
e
c
h
ni
que
.
T
hi
s
c
o
u
l
d
b
e
a
c
hi
e
ve
d
by
de
v
e
l
o
p
i
ng
K
a
b
uT
e
a
c
h
,
a
DSS
t
h
a
t
a
n
a
l
y
z
e
d
t
h
e
i
nput
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
a
n
d
c
o
nc
l
ud
e
d
pr
e
c
i
s
e
de
c
i
s
i
o
n
s
t
h
a
t
l
e
d
t
o
m
us
h
r
o
o
m
c
l
a
s
s
if
i
c
a
t
i
o
n
.
T
h
e
c
l
a
s
s
if
i
c
a
t
i
o
n
m
e
t
h
o
ds
we
r
e
d
i
vi
de
d
i
n
t
o
f
o
ur
s
t
a
ge
s
:
i
)
da
t
a
s
o
u
r
c
e
;
i
i
)
s
a
m
p
li
ng;
ii
i
)
m
u
s
h
r
oo
m
c
l
a
s
s
i
f
i
c
a
t
i
o
n;
a
n
d
i
v
)
m
o
de
l
pe
r
f
o
r
m
a
n
c
e
e
v
a
l
ua
t
i
o
n
.
T
h
e
ge
n
e
r
a
l
f
l
o
w
o
f
t
h
e
pr
o
c
e
s
s
i
s
i
ll
us
t
r
a
t
e
d
i
n
t
h
e
c
o
n
c
e
pt
ua
l
f
r
a
m
e
wo
r
k
s
h
o
wn
i
n
F
i
gur
e
1.
F
i
gur
e
1
.
T
h
e
c
o
n
c
e
pt
ua
l
f
r
a
m
e
wo
r
k
o
f
t
h
e
s
t
udy
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
1
5
,
N
o.
1
,
M
a
r
c
h
20
2
6
:
13
8
-
15
1
140
T
h
e
pr
o
c
e
s
s
b
e
ga
n
w
i
t
h
t
h
e
da
t
a
p
r
e
pa
r
a
t
i
o
n
.
T
h
e
da
t
a
s
o
u
r
c
e
o
f
t
h
e
s
y
s
t
e
m
us
e
d
a
m
u
s
h
r
oo
m
da
t
a
s
e
t
d
o
wnl
o
a
de
d
f
r
o
m
a
n
o
pe
n
-
s
o
ur
c
e
m
us
h
r
oo
m
r
e
po
s
i
t
or
y
o
n
t
h
e
i
n
t
e
r
n
e
t
.
Da
t
a
pr
o
f
i
li
ng
a
n
d
da
t
a
c
l
e
a
ni
ng
a
c
t
i
vi
t
i
e
s
a
r
e
do
n
e
i
n
t
h
e
f
i
r
s
t
s
t
a
ge
.
T
h
e
f
i
r
s
t
a
c
t
i
vi
t
y
i
s
do
ne
to
a
n
a
ly
z
e
t
h
e
s
t
a
t
i
s
t
i
c
a
l
f
e
a
t
ur
e
s
i
nc
l
ud
i
ng
t
h
e
da
t
a
s
i
z
e
a
n
d
t
y
p
e
o
f
t
h
e
da
t
a
.
T
h
e
l
a
tt
e
r
i
s
c
o
n
duc
t
e
d
to
a
v
o
i
d
da
t
a
a
n
o
m
a
li
e
s
a
n
d
i
r
r
e
gu
l
a
r
i
t
i
e
s
i
n
de
c
i
s
i
o
n
-
m
a
k
i
n
g
a
n
d
e
ns
ur
e
t
h
e
r
e
l
i
a
bil
i
t
y
o
f
da
t
a
f
o
r
m
o
r
e
a
c
c
ur
a
t
e
p
r
e
d
i
c
t
i
v
e
m
o
de
l
s
.
Ne
x
t
,
t
h
e
e
n
r
i
c
h
e
d
da
t
a
i
s
up
l
o
a
de
d
i
n
t
o
t
h
e
s
y
s
t
e
m
a
n
d
s
p
li
t
i
n
t
o
tr
a
i
ni
ng
a
n
d
t
e
s
t
i
n
g
da
t
a
s
e
t
s
.
T
h
e
s
e
s
a
m
p
l
e
da
t
a
s
e
t
s
a
r
e
s
tor
e
d
i
n
a
s
e
p
a
r
a
t
e
t
a
bl
e
i
n
t
h
e
da
t
a
ba
s
e
.
I
n
t
h
e
m
us
h
r
o
o
m
c
l
a
s
s
i
f
i
c
a
t
i
o
n
,
t
h
e
tr
a
i
ni
ng
da
t
a
s
e
t
i
s
us
e
d
to
b
u
i
l
d
a
n
d
t
r
a
i
n
t
h
e
M
L
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
l
go
r
i
t
hm
t
o
c
o
m
e
up
w
i
t
h
a
tr
a
i
ne
d
m
o
de
l
.
I
n
a
dd
i
t
i
o
n
,
a
hy
pe
r
pa
r
a
m
e
t
e
r
t
uni
n
g
m
e
c
h
a
ni
s
m
i
s
a
dde
d
to
r
e
v
e
a
l
w
h
e
t
h
e
r
t
h
e
m
o
de
l
i
s
o
v
e
r
f
i
t
t
i
n
g
or
un
de
r
f
i
t
t
i
n
g.
T
hi
s
v
a
li
da
t
i
o
n
m
o
de
l
s
e
l
e
c
t
s
t
h
e
b
e
s
t
m
o
de
l
c
o
nf
i
gur
a
t
i
o
n
t
o
i
m
pr
o
v
e
t
h
e
r
e
l
i
a
bil
i
t
y
o
f
t
h
e
m
o
de
l
e
v
a
l
ua
t
i
o
n
(
c
l
a
s
s
if
i
e
r
m
o
de
l
)
.
On
c
e
t
h
e
f
i
na
l
m
o
de
l
i
s
t
un
e
d
up,
t
h
e
n
,
t
h
e
K
a
b
uT
e
a
c
h
wi
t
h
t
h
e
h
e
l
p
o
f
t
h
e
c
l
a
s
s
if
i
e
r
m
o
de
l
l
e
a
r
ns
s
o
m
e
ki
n
d
o
f
pa
tt
e
r
n
s
f
r
o
m
t
h
e
tr
a
i
ni
n
g
da
t
a
s
e
t
a
n
d
a
pp
l
i
e
s
t
h
e
m
t
o
t
h
e
t
e
s
t
da
t
a
s
e
t
to
b
u
i
l
d
a
de
c
i
s
i
o
n
i
n
pr
e
d
ict
i
n
g
o
r
c
l
a
s
s
if
yi
ng
wh
e
t
h
e
r
a
n
i
ns
t
a
n
c
e
o
f
t
h
e
t
e
s
t
da
t
a
i
s
e
d
i
bl
e
o
r
a
p
o
i
s
o
n
o
us
m
us
h
r
o
o
m
.
P
e
r
f
o
r
m
a
n
c
e
m
e
t
r
i
c
s
s
uc
h
a
s
t
h
e
c
o
nf
us
i
o
n
m
a
t
r
i
x
,
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
s
pe
c
if
i
c
i
t
y
,
a
n
d
F
1
-
s
c
o
r
e
,
i
n
c
l
ud
i
ng
t
h
e
a
r
e
a
un
d
e
r
c
ur
v
e
(
A
UC
)
r
e
c
e
i
ve
r
o
pe
r
a
t
i
n
g
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
(
R
O
C
)
s
c
o
r
e
a
r
e
pr
e
s
e
n
t
e
d
t
h
r
o
ugh
a
vi
s
ua
li
z
a
t
i
o
n
pa
ge
o
f
t
h
e
de
v
e
l
o
pe
d
s
y
s
t
e
m
.
2.
1.
Dat
a
s
ou
r
c
e
T
h
e
da
t
a
s
e
t
us
e
d
i
n
t
hi
s
s
t
udy
w
a
s
c
o
l
l
e
c
t
e
d
f
r
o
m
t
h
e
UC
i
r
vi
ne
m
a
c
hi
ne
l
e
a
r
ni
ng
(
UC
I
M
L
)
r
e
po
s
i
t
o
r
y
t
h
r
o
ugh
t
h
e
K
a
gg
l
e
we
b
po
r
t
a
l
,
a
p
o
p
u
l
a
r
o
n
l
i
ne
p
l
a
t
f
o
r
m
f
o
r
da
t
a
s
c
i
e
n
t
i
s
t
s
a
n
d
ML
e
x
pe
r
t
s
o
r
pr
o
f
e
s
s
i
o
n
a
l
s
[
15]
.
T
hi
s
da
t
a
s
e
t
wa
s
d
o
n
a
t
e
d
to
U
C
I
M
L
by
J
e
f
f
r
e
y
S
c
hli
mm
e
r
o
n
A
pr
i
l
27,
1987,
i
n
c
l
ud
i
ng
de
s
c
r
i
pt
i
o
ns
o
f
hy
po
t
h
e
t
i
c
a
l
s
a
m
p
l
e
s
c
o
r
r
e
s
po
n
di
ng
to
23
s
pe
c
i
e
s
o
f
g
i
ll
e
d
m
us
h
r
o
o
m
s
i
n
t
h
e
A
gar
icu
s
a
nd
L
e
piot
a
F
a
m
il
y
o
f
m
us
h
r
o
o
m
s
[
16]
,
[
17]
.
Da
t
a
p
r
e
pr
o
c
e
s
s
i
n
g
:
m
o
r
ph
o
l
o
gi
c
a
l
f
e
a
t
ur
e
s
a
r
e
e
x
t
r
a
c
t
e
d
a
n
d
us
e
d
i
n
t
h
e
tr
a
i
ni
ng.
T
h
e
s
e
m
o
r
p
h
o
l
o
g
i
c
a
l
f
e
a
t
ur
e
s
(
a
tt
r
i
b
ut
e
s
)
a
s
s
um
m
a
r
i
z
e
d
i
n
T
a
bl
e
1
we
r
e
us
e
d
i
n
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
o
f
m
us
h
r
o
o
m
s
.
Da
t
a
pr
e
-
p
r
o
c
e
s
s
i
n
g
i
nv
o
l
ve
s
pr
e
pa
r
i
n
g
t
h
e
da
t
a
f
o
r
t
h
e
M
L
m
o
de
l
.
T
hi
s
da
t
a
m
i
n
i
ng
t
e
c
hni
que
i
s
us
e
d
to
c
o
n
v
e
r
t
r
a
w
da
t
a
i
n
t
o
a
m
o
r
e
i
n
t
e
r
pr
e
t
a
bl
e
a
n
d
s
t
r
uc
t
ur
e
d
f
o
r
m
a
t
i
n
t
e
n
de
d
f
o
r
us
e
a
s
t
r
a
i
ni
ng
da
t
a
b
e
f
o
r
e
t
h
e
mi
n
i
ng
pr
o
c
e
s
s
[
18
]
,
[
19
]
.
T
hi
s
s
t
ud
y
e
m
p
l
o
y
e
d
two
da
t
a
p
r
e
-
pr
o
c
e
s
s
i
n
g
s
t
a
ge
s
.
Da
t
a
pr
o
f
i
li
ng
wa
s
t
h
e
f
i
r
s
t
s
t
a
ge
whi
c
h
wa
s
do
n
e
by
e
x
a
mi
n
i
ng
a
n
d
a
n
a
ly
z
in
g
i
ns
t
a
n
c
e
s
o
f
t
h
e
c
o
l
l
e
c
t
e
d
m
u
s
h
r
oo
m
da
t
a
s
e
t
to
c
o
l
l
e
c
t
s
t
a
t
i
s
t
i
c
s
a
b
o
ut
i
t
s
da
t
a
c
o
n
t
e
n
t.
T
h
e
r
e
we
r
e
22
a
tt
r
i
but
e
s
t
h
a
t
r
e
pr
e
s
e
n
t
e
d
t
h
e
m
o
r
ph
o
l
o
g
i
c
a
l
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
o
f
t
h
e
m
u
s
h
r
o
o
m
us
e
d
a
s
t
h
e
b
a
s
i
s
f
o
r
de
s
i
g
ni
ng
t
h
e
c
l
a
s
s
if
i
e
r
m
o
du
l
e
o
f
t
h
e
DSS
.
T
a
bl
e
1.
A
tt
r
i
b
ut
e
s
o
f
m
us
h
r
o
o
m
de
s
c
r
i
pt
i
o
n
i
n
t
h
e
da
t
a
s
e
t
No
A
tt
r
ib
ut
e
D
e
s
c
r
ip
ti
o
n a
nd
v
a
lu
e
s
1
c
a
p s
ha
pe
b=
be
ll
, c
=
c
o
ni
c
a
l,
x
=
c
o
n
v
e
x
,
f
=
f
la
t
, k=
kno
bb
e
d
,
s
=
s
unke
n
2
c
a
p s
ur
f
a
c
e
f
=
f
ib
r
o
us
,
g=
gr
oove
s
,
y
=
s
c
a
l
y
, s
=
s
moo
th
3
c
a
p c
o
l
or
n=
br
o
w
n
, b=
bu
f
f
,
c
=
c
in
na
m
o
n, g=
gr
a
y
, r
=
gr
e
e
n
, p=
pi
nk
, u=
pur
pl
e
,
e
=
r
e
d, w
=
w
hi
t
e
,
y
=
y
e
l
l
o
w
4
br
ui
s
e
s
t=
br
ui
s
e
s
, f
=
n
o
5
o
d
o
r
a
=
a
lm
o
nd
, l
=
a
ni
s
e
, c
=
c
r
e
o
s
o
t
e
,
y
=
f
is
h
y
,
f
=
f
o
u
l
, m=
mus
t
y
, n=
n
o
n
e
, p=
punge
nt
, s
=
s
pi
c
y
6
gi
ll
a
tt
a
c
hm
e
nt
a
=
a
tt
a
c
he
d
, d=
de
s
c
e
ndi
ng,
f
=
f
r
e
e
, n=
n
o
t
c
he
d
7
gi
ll
s
pa
c
in
g
c
=
c
l
o
s
e
, w
=
c
r
o
w
d
e
d, d=
di
s
ta
nt
8
gi
ll
s
iz
e
b=
br
o
a
d
, n=
na
r
r
o
w
9
gi
ll
c
o
l
or
k=
bl
a
c
k
, n=
br
o
w
n, b=
bu
f
f
, h=
c
h
oc
o
la
t
e
, g=
gr
a
y
, r
=
gr
e
e
n
,
o
=
o
r
a
nge
, p=
pi
nk,
u=
pur
pl
e
,
e
=
r
e
d
, w
=
w
hi
t
e
,
y
=
y
e
ll
o
w
10
s
ta
lk
s
ha
pe
e
=
e
nl
a
r
gi
ng
, t
=
ta
p
e
r
in
g
11
s
ta
lk
r
oo
t
b=
bul
bo
us
, c
=
c
lu
b, u=
c
up, e
=
e
qua
l
, z
=
r
hi
z
o
m
or
phs
, r
=
r
oo
t
e
d
,
?
=
mi
s
s
in
g
12
s
ta
lk
s
ur
f
a
c
e
a
b
ove
r
in
g
f
=
f
ib
r
o
us
,
y
=
s
c
a
l
y
, k=
s
il
k
y
, s
=
s
moo
th
13
s
ta
lk
s
ur
f
a
c
e
b
e
l
o
w
r
in
g
f
=
f
ib
r
o
us
,
y
=
s
c
a
l
y
, k=
s
il
k
y
, s
=
s
moo
th
14
s
ta
lk
c
o
l
or
a
bove
r
in
g
n=
br
o
w
n
, b=
bu
f
f
,
c
=
c
in
na
m
o
n, g=
gr
a
y
,
o
=
or
a
nge
, p=
pi
nk
, e
=
r
e
d, w
=
w
hi
te
,
y
=
y
e
ll
o
w
15
s
ta
lk
c
o
l
or
be
l
o
w
r
in
g
n=
br
o
w
n
, b=
bu
f
f
,
c
=
c
in
na
m
o
n, g=
gr
a
y
,
o
=
or
a
nge
, p=
pi
nk
, e
=
r
e
d, w
=
w
hi
te
,
y
=
y
e
ll
o
w
16
ve
il
t
y
p
e
p=
pa
r
ti
a
l
, u=
uni
v
e
r
s
a
l
17
ve
il
c
o
l
o
r
n=
br
o
w
n
,
o
=
or
a
nge
, w
=
w
hi
te
,
y
=
y
e
ll
o
w
18
r
in
g numbe
r
n=
no
ne
,
o
=
o
n
e
, t
=
two
19
r
in
g t
y
pe
c
=
c
o
bw
e
bb
y
, e
=
e
v
a
ne
s
c
e
nt
,
f
=
f
la
r
in
g, l
=
la
r
g
e
, n=
no
n
e
, p=
pe
n
da
nt
, s
=
s
he
a
th
in
g, z
=
z
o
n
e
20
s
po
r
e
pr
in
t
c
o
l
o
r
k=
bl
a
c
k
,
n=
br
o
w
n, b=
bu
f
f
, h=
c
h
oc
o
la
t
e
, g=
gr
e
e
n
,
o
=
o
r
a
ng
e
, u
=
pur
pl
e
, w
=
w
hi
te
,
y
=
y
e
l
l
o
w
21
po
pul
a
ti
o
n
a
=
a
bunda
nt
, c
=
c
lu
s
te
r
e
d, n=
nume
r
o
us
, s
=
s
c
a
tt
e
r
e
d
,
v
=
s
e
ve
r
a
l,
y
=
s
o
li
ta
r
y
22
ha
bi
ta
t
g=
gr
a
s
s
e
s
, l
=
le
a
v
e
s
, m=
me
a
d
o
w
s
, p=
pa
th
s
, u=
ur
ba
n
, w
=
w
a
s
te
, d=
w
o
o
ds
23
c
la
s
s
T
h
is
i
s
t
he
t
a
r
g
e
t
v
a
r
ia
bl
e
t
ha
t
mus
t
pr
e
di
c
t
or
f
o
r
e
c
a
s
t;
a
v
a
lu
e
of
‘
e
’
de
n
ot
e
s
a
mus
hr
oo
m i
s
e
di
bl
e
w
he
r
e
a
s
a
v
a
lu
e
of
‘
p
’
in
di
c
a
t
e
s
a
po
is
o
n
o
us
mus
hr
oo
m.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
A
de
c
is
ion
s
uppor
t
s
y
s
tem
f
or
mus
hr
oom
c
las
s
if
ication
us
ing
N
aïve
B
ay
e
s
ian
…
(
V
il
c
hor
Gar
c
ia
P
e
r
d
ido
)
141
T
h
e
a
tt
r
i
b
ut
e
c
l
a
s
s
wa
s
us
e
d
by
t
h
e
NB
a
l
go
r
i
t
hm
t
o
c
o
m
put
e
t
h
e
pr
o
b
a
bil
i
t
y
a
n
d
pr
e
d
i
c
t
a
n
i
n
s
t
a
nc
e
(
m
us
h
r
o
o
m
)
wh
e
t
h
e
r
i
t
wa
s
a
n
e
d
i
b
l
e
o
r
p
o
i
s
o
n
o
us
c
l
a
s
s
.
E
a
c
h
a
tt
r
i
b
ut
e
or
c
h
a
r
a
c
t
e
r
h
a
d
v
a
l
u
e
s
t
o
s
e
l
e
c
t
,
a
n
d
v
a
l
ue
s
we
r
e
c
o
de
d
o
r
r
e
pr
e
s
e
n
t
e
d
by
t
e
x
t
s
.
T
h
e
gi
ll
c
o
l
o
r
a
tt
r
i
b
ut
e
h
a
d
t
h
e
hi
g
h
e
s
t
n
u
m
b
e
r
o
f
v
a
l
ue
s
wi
t
h
12
v
a
l
ue
s
w
hil
e
b
r
u
i
s
e
s
,
g
il
l
s
i
z
e
,
s
t
a
l
k
s
ha
pe
,
v
e
il
t
y
pe
,
a
n
d
r
i
n
g
n
u
m
be
r
a
t
t
r
i
b
ut
e
s
c
o
ns
i
s
t
o
f
t
w
o
v
a
l
u
e
s
.
Da
t
a
c
l
e
a
ns
i
ng
wa
s
t
h
e
s
e
c
o
n
d
s
t
a
ge
a
n
d
wa
s
c
o
n
duc
ted
us
i
n
g
P
y
t
h
o
n
l
i
br
a
r
i
e
s
.
T
hi
s
wa
s
do
n
e
to
pr
e
v
e
n
t
da
t
a
a
n
o
m
a
li
e
s
by
e
li
mi
na
t
i
n
g
or
r
e
m
o
vi
ng
m
i
s
s
i
ng
(
n
u
ll
)
v
a
l
ue
s
a
n
d
dup
l
i
c
a
t
e
d
f
e
a
t
ur
e
s
i
n
t
h
e
m
u
s
h
r
o
o
m
da
t
a
s
e
t
[
20]
,
[
21]
.
Da
t
a
tr
a
n
s
f
o
r
m
a
t
i
o
n
(
c
a
t
e
gor
i
c
a
l
t
o
n
um
e
r
i
c
a
l
o
r
vi
c
e
v
e
r
s
a
)
wa
s
n
o
l
o
n
ge
r
pe
r
f
o
r
m
e
d
i
n
t
hi
s
s
t
a
ge
s
i
nc
e
v
a
l
ue
s
o
f
t
h
e
i
ns
t
a
n
c
e
s
i
n
t
h
e
da
t
a
s
e
t
we
r
e
i
n
c
a
t
e
g
o
r
i
c
a
l
f
o
r
m
.
T
he
NB
a
l
go
r
i
t
hm
i
s
a
c
l
a
s
s
if
i
e
r
t
h
a
t
wa
s
m
o
s
t
l
y
a
pp
li
e
d
i
n
t
e
x
t
c
l
a
s
s
if
i
c
a
t
i
o
n
,
s
o
pe
r
f
o
r
m
e
d
we
ll
w
i
t
h
c
a
t
e
go
r
i
c
a
l
i
nput
v
a
r
i
a
bl
e
s
c
o
m
pa
r
e
d
to
n
u
m
e
r
i
c
a
l
va
l
u
e
s
[
22]
.
2.
2.
S
am
p
l
in
g
T
h
e
e
f
f
e
c
t
i
v
e
n
e
s
s
o
f
M
L
m
o
de
l
s
c
o
ul
d
b
e
t
e
s
t
e
d
u
s
i
n
g
c
r
o
ss
-
v
a
li
da
t
i
o
n
(
C
V)
t
e
c
h
ni
que
s
.
T
hi
s
c
o
ul
d
b
e
pe
r
f
o
r
m
e
d
by
s
p
li
t
t
i
n
g
t
h
e
wh
o
l
e
da
t
a
i
n
t
o
tr
a
i
ni
ng
a
n
d
t
e
s
t
i
n
g
da
t
a
s
e
t
s
[
23]
.
T
o
ge
t
r
e
l
i
a
bl
e
f
i
nd
i
n
gs
f
r
o
m
a
l
l
o
f
t
h
e
da
t
a
,
t
h
e
a
c
c
ur
a
c
y
o
f
e
a
c
h
K
-
m
o
de
l
’
s
r
e
s
u
l
t
s
i
s
t
h
e
n
a
ve
r
a
ge
d.
T
h
e
pur
po
s
e
o
f
K
-
f
o
l
d
CV
wa
s
t
o
r
e
m
o
v
e
bi
a
s
f
r
o
m
t
h
e
da
t
a
.
I
n
t
hi
s
pa
pe
r
,
a
5
-
f
o
l
d
CV
m
e
t
h
o
d
w
i
t
h
a
70:30
b
a
l
a
n
c
e
r
a
t
i
o
f
o
r
t
r
a
i
ni
ng
a
n
d
t
e
s
t
i
n
g
wa
s
a
pp
l
i
e
d
w
h
e
r
e
t
h
e
wh
o
l
e
da
t
a
wa
s
d
i
vi
de
d
i
n
to
f
i
ve
(
5)
f
o
l
ds
a
n
d
r
e
pe
a
t
e
d
f
i
ve
(
5)
t
i
m
e
s
.
2.
3.
M
u
s
h
r
oom
c
l
as
s
if
icat
ion
u
s
in
g
t
h
e
Naïve
B
aye
s
ian
a
l
go
r
it
h
m
T
h
e
r
e
wa
s
n
o
“
b
e
s
t
”
ML
a
l
go
r
i
t
hm
a
n
d
us
ua
ll
y
c
r
i
t
i
c
a
l
a
n
d
d
i
f
f
i
c
u
l
t
t
o
c
h
oo
s
e
,
h
o
we
v
e
r
,
t
h
e
c
o
r
r
e
c
t
s
e
l
e
c
t
i
o
n
wa
s
ne
c
e
s
s
a
r
y
[
24]
.
F
i
n
d
i
ng
a
s
u
i
t
a
bl
e
a
lgo
r
i
t
hm
de
p
e
n
ds
o
n
t
h
e
t
y
pe
o
f
pr
o
bl
e
m
t
o
s
o
l
v
e
[
25]
a
n
d
o
n
m
a
ny
f
a
c
t
o
r
s
s
uc
h
a
s
t
h
e
s
i
z
e
,
qua
l
i
t
y
,
a
n
d
t
y
p
e
o
r
n
a
t
ur
e
o
f
da
t
a
s
e
t
s
[
26]
.
T
h
e
NB
a
l
go
r
i
t
hm
wa
s
c
h
o
s
e
n
a
s
t
h
e
c
l
a
s
s
if
i
c
a
t
i
o
n
m
o
de
l
f
o
r
s
e
v
e
r
a
l
r
e
a
s
o
n
s
.
F
i
r
s
t
,
s
i
nc
e
t
h
e
m
a
i
n
o
bj
e
c
t
i
v
e
o
f
t
hi
s
s
t
udy
wa
s
to
d
e
v
e
l
o
p
a
DSS
i
n
t
r
a
i
ni
ng
a
m
o
de
l
f
o
r
pr
e
d
i
c
t
i
o
n
,
t
h
e
r
e
f
o
r
e
a
s
upe
r
vi
s
e
d
l
e
a
r
ni
ng
t
y
pe
o
f
ML
a
l
go
r
i
t
hm
wa
s
n
e
e
de
d.
S
e
c
o
n
d,
t
h
e
pu
bl
i
c
ly
a
v
a
il
a
bl
e
m
us
h
r
o
o
m
da
t
a
s
e
t
c
o
n
t
a
i
n
e
d
22
a
t
t
r
i
b
ut
e
s
(
i
n
de
pe
n
de
n
t
v
a
r
i
a
bl
e
)
w
hi
c
h
we
r
e
us
e
d
to
c
l
a
s
s
i
f
y
a
t
a
r
ge
t
v
a
r
i
a
bl
e
(
c
l
a
s
s
)
wh
e
t
h
e
r
e
d
i
bl
e
(
‘
e
’
)
or
p
o
i
s
o
n
o
us
(
‘
p
’
)
c
a
t
e
g
o
r
y
,
t
h
us
a
c
l
a
s
s
i
f
i
c
a
t
i
o
n
t
e
c
h
ni
que
w
a
s
n
e
c
e
s
s
a
r
y
.
I
n
a
dd
i
t
i
o
n
,
da
t
a
s
e
t
s
t
h
a
t
h
a
d
m
a
ny
a
t
t
r
i
b
ut
e
s
c
o
ul
d
b
e
h
a
n
d
l
e
d
by
t
h
e
NB
a
lgo
r
i
t
h
m
[
16]
.
T
hi
r
d,
i
n
s
t
a
n
c
e
s
(
r
o
ws
)
i
n
t
h
e
da
t
a
s
e
t
we
r
e
o
r
ga
ni
z
e
d
by
s
p
e
c
i
f
i
c
m
o
r
p
h
o
l
o
gi
c
a
l
f
e
a
t
ur
e
s
o
r
a
tt
r
i
b
ut
e
s
a
s
s
h
o
w
n
i
n
T
a
bl
e
1,
e
a
c
h
w
i
t
h
c
a
t
e
go
r
i
c
a
l
v
a
l
ue
s
(
t
e
x
t
)
r
e
pr
e
s
e
n
t
i
n
g
t
h
e
p
hy
s
i
c
a
l
c
ha
r
a
c
t
e
r
i
s
t
i
c
s
o
f
m
u
s
h
r
o
o
m
s
.
T
h
e
NB
a
l
go
r
i
t
hm
wa
s
c
o
m
m
o
nly
a
pp
l
i
e
d
i
n
v
a
r
i
o
us
a
pp
li
c
a
t
i
o
ns
w
hi
c
h
wa
s
o
f
t
e
n
hi
g
hly
a
pp
l
i
e
d
i
n
t
e
x
t
c
l
a
s
s
if
i
c
a
t
i
o
n
,
s
pa
m
f
il
t
e
r
i
ng,
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
,
m
e
d
i
c
a
l
d
i
a
g
n
o
s
i
s
,
a
n
d
r
e
c
o
m
m
e
n
de
r
s
y
s
t
e
m
s
.
L
a
s
t
l
y
,
w
i
t
h
o
v
e
r
8
,
000
r
o
ws
o
f
da
t
a
f
o
un
d
i
n
t
h
e
da
t
a
s
e
t
,
t
hi
s
a
l
go
r
i
t
hm
wa
s
k
n
o
wn
f
o
r
i
t
s
s
i
m
p
li
c
i
t
y
,
e
f
f
i
c
i
e
n
c
y
,
a
n
d
e
f
f
e
c
t
i
v
e
n
e
s
s
w
i
t
h
hi
g
h
a
c
c
ur
a
c
y
a
n
d
s
pe
e
d
i
n
h
a
nd
l
i
ng
l
a
r
ge
da
t
a
s
e
t
s
[
17]
,
[
20]
.
M
o
de
l
t
r
a
i
ni
ng
a
n
d
de
c
i
s
i
o
n
b
u
il
d
i
ng
:
t
he
NB
m
o
d
e
l
wa
s
n
ot
o
nl
y
s
i
m
p
l
e
b
ut
a
l
s
o
e
a
s
y
t
o
b
u
i
l
d.
T
hi
s
c
l
a
s
s
if
i
c
a
t
i
o
n
a
l
go
r
i
t
hm
o
pe
r
a
t
e
d
o
n
t
h
e
pr
i
n
c
i
p
l
e
o
f
c
o
n
d
i
t
i
o
n
a
l
i
nde
pe
n
de
n
c
e
,
m
e
a
ni
ng
i
t
a
s
s
u
m
e
d
t
h
a
t
t
h
e
v
a
l
ue
o
f
e
a
c
h
a
t
tr
i
b
ut
e
w
i
t
hi
n
a
s
pe
c
if
i
c
c
l
a
s
s
d
i
d
n
o
t
de
pe
n
d
o
n
t
h
e
v
a
l
u
e
s
o
f
ot
h
e
r
a
tt
r
i
b
ut
e
s
[
27]
.
I
m
p
l
e
m
e
n
t
i
n
g
t
h
e
NB
a
l
go
r
i
t
hm
t
o
t
h
e
DSS
s
y
s
t
e
m
i
nv
o
l
ve
d
s
e
v
e
r
a
l
k
e
y
s
t
e
ps
t
h
a
t
e
n
s
ur
e
d
a
c
c
ur
a
te
m
o
de
l
t
r
a
i
ni
ng
a
n
d
e
f
f
e
c
t
i
ve
c
l
a
s
s
if
i
c
a
t
i
o
n
:
1)
L
o
a
d
t
h
e
m
us
h
r
o
o
m
da
t
a
s
e
t
f
o
r
da
t
a
pr
o
f
i
li
ng
a
n
d
c
l
e
a
ni
ng.
2)
D
i
vi
de
o
r
s
pl
i
t
t
h
e
da
t
a
s
e
t
i
n
t
o
t
w
o:
tr
a
i
ni
n
g
a
n
d
t
e
s
t
i
n
g
s
u
bs
e
t
s
.
3)
A
pp
ly
t
h
e
c
l
a
s
s
if
i
c
a
t
i
o
n
a
l
go
r
i
t
hm
t
o
tr
a
i
n
t
h
e
t
r
a
i
ni
ng
s
u
b
s
e
t
s
.
4)
T
un
e
up
t
h
e
t
r
a
i
n
e
d
m
o
de
l
u
s
i
n
g
a
v
a
li
da
t
i
o
n
t
e
c
h
ni
que
to
c
o
m
e
up
w
i
t
h
a
f
i
na
l
m
o
d
e
l
.
5)
T
h
e
f
i
na
l
(
c
l
a
s
s
i
e
r
)
m
o
de
l
c
l
a
s
s
i
f
i
e
s
m
u
s
h
r
oo
m
s
us
i
ng
t
h
e
f
o
l
l
o
w
i
n
g
pr
o
c
e
dur
e
s
:
a.
C
a
l
c
u
l
a
t
e
t
h
e
pr
i
o
r
pr
o
b
a
bil
i
t
y
f
o
r
e
a
c
h
c
l
a
s
s
(
‘
e
’
o
r
‘
p
’
)
by
f
i
nd
i
ng
t
h
e
pr
o
p
o
r
t
i
o
n
o
f
e
a
c
h
t
a
r
ge
t
c
l
a
s
s
i
n
t
h
e
t
r
a
i
ni
n
g
da
t
a
.
b.
F
o
r
e
a
c
h
f
e
a
t
ur
e
i
n
t
h
e
da
t
a
s
e
t
,
de
t
e
r
m
i
ne
t
h
e
pr
o
b
a
bil
i
t
y
(
li
ke
li
h
o
o
d)
o
f
e
a
c
h
po
s
s
i
bl
e
va
l
ue
o
c
c
ur
r
i
ng
w
i
t
hi
n
e
a
c
h
c
l
a
s
s
.
c.
F
o
r
a
n
e
w
i
ns
t
a
n
c
e
,
c
a
l
c
u
l
a
t
e
t
h
e
po
s
t
e
r
i
o
r
pr
o
b
a
bil
i
t
y
u
s
i
ng
t
h
e
f
o
r
m
u
l
a
i
n
(
1)
de
r
i
ve
d
f
r
o
m
B
a
y
e
s
’
T
h
e
o
r
e
m
.
(
|
)
=
(
|
)
.
(
)
(
)
(
1
)
T
h
e
f
o
r
m
u
l
a
o
f
NB
c
l
a
s
s
if
i
c
a
t
i
o
n
w
i
t
h
m
u
l
t
i
p
l
e
f
e
a
t
ur
e
s
1
,
2
,
3
,
…
c
o
ul
d
b
e
e
x
t
e
n
de
d
i
n
(
2)
.
(
|
1
,
2
,
3
,
…
)
=
(
1
|
)
.
(
2
|
)
.
(
3
|
)
…
(
|
)
.
(
)
(
1
,
2
,
3
,
…
)
(
2)
L
ike
li
hood
C
las
s
P
r
ior
P
r
obabil
it
y
P
r
obabil
it
y
P
os
te
r
ior
P
r
obabil
it
y
P
r
e
dicto
r
P
r
ior
P
r
obabil
it
y
P
r
obabil
it
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
1
5
,
N
o.
1
,
M
a
r
c
h
20
2
6
:
13
8
-
15
1
142
wh
e
r
e
,
(
|
1
,
2
,
3
,
…
)
wa
s
t
h
e
po
s
t
e
r
i
o
r
p
r
o
b
a
bi
li
t
y
o
f
a
m
us
hr
oo
m
b
e
i
ng
i
n
a
s
pe
c
i
f
ic
c
l
a
s
s
(
e
i
t
h
e
r
‘
e
’
f
o
r
‘
e
d
i
bl
e
’
o
r
‘
p
’
f
o
r
po
i
s
o
n
o
us
)
g
i
v
e
n
t
h
e
f
e
a
t
ur
e
s
1
,
2
,
3
,
…
,
(
1
|
)
,
(
2
|
)
,
(
3
|
)
…
(
|
)
we
r
e
t
h
e
c
o
n
d
i
t
i
o
n
a
l
pr
o
b
a
bil
i
t
i
e
s
(
l
i
k
e
l
i
h
o
o
d)
o
f
h
o
w
l
i
ke
ly
i
t
wa
s
to
o
b
s
e
r
v
e
e
a
c
h
f
e
a
t
ur
e
(
m
u
s
h
r
oo
m
a
tt
r
i
b
ut
e
s
)
i
f
t
h
e
m
us
h
r
o
o
m
b
e
l
o
n
g
s
to
t
h
a
t
c
l
a
s
s
,
(
)
wa
s
t
h
e
pr
i
o
r
pr
o
b
a
bi
li
t
y
o
f
t
h
e
c
l
a
s
s
,
r
e
pr
e
s
e
n
t
i
n
g
t
h
e
l
i
k
e
l
i
h
o
o
d
o
f
a
m
us
h
r
o
o
m
be
i
n
g
i
n
t
h
a
t
c
l
a
s
s
(
‘
e
’
o
r
‘
p
’
)
w
i
t
h
o
ut
c
o
n
s
i
de
r
i
ng
a
ny
f
e
a
t
ur
e
s
,
a
n
d
(
1
|
)
,
(
2
|
)
,
(
3
|
)
…
(
|
)
wa
s
t
h
e
tot
a
l
pr
o
b
a
bil
i
t
y
o
f
o
b
s
e
r
vi
ng
t
h
e
f
e
a
t
ur
e
s
X
1
,
2
,
3
,
…
a
c
r
o
s
s
a
l
l
c
l
a
s
s
e
s
.
6)
T
e
s
t
t
h
e
t
e
s
t
i
n
g
s
u
bs
e
t
s
i
n
t
o
t
h
e
c
l
a
s
s
i
e
r
m
o
de
l
.
T
he
c
l
a
s
s
i
f
i
c
a
t
i
o
n
o
ut
c
o
m
e
(
‘
e
d
i
b
l
e
’
o
r
‘
po
i
s
o
n
o
us
’
)
wa
s
de
t
e
r
m
i
ne
d
by
t
h
e
c
l
a
s
s
w
i
t
h
t
h
e
hi
g
h
e
s
t
p
o
s
t
e
r
i
o
r
pr
o
b
a
bil
i
t
y
.
2.
4.
P
e
r
f
o
r
m
an
c
e
m
e
as
u
r
e
s
an
d
e
val
u
at
ion
T
h
e
f
i
na
l
a
c
c
ur
a
c
y
o
f
t
h
e
m
o
de
l
wa
s
a
s
s
e
s
s
e
d
t
h
r
o
ugh
a
c
o
n
f
u
s
i
o
n
m
a
t
r
i
x
(
e
r
r
or
m
a
t
r
i
x
)
.
T
y
p
i
c
a
ll
y
,
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
l
go
r
i
t
hm
s
wa
s
e
v
a
l
ua
t
e
d
b
a
s
e
d
o
n
t
h
e
i
r
o
v
e
r
a
ll
r
e
s
u
l
t
s
o
n
t
h
e
t
e
s
t
da
t
a
s
e
t
[
17]
,
[
28]
.
I
n
t
hi
s
c
a
s
e
,
t
h
e
n
u
m
be
r
o
f
e
d
i
b
l
e
a
n
d
po
i
s
o
n
o
u
s
m
u
s
h
r
o
o
m
s
t
h
a
t
we
r
e
c
or
r
e
c
t
l
y
a
n
d
i
nc
o
r
r
e
c
t
l
y
c
l
a
s
s
if
i
e
d
by
t
h
e
c
l
a
s
s
if
i
e
r
c
o
u
l
d
be
s
u
mm
a
r
i
z
e
d
a
nd
ge
n
e
r
a
t
e
d
t
h
r
o
ugh
a
c
o
nf
us
i
o
n
m
a
t
r
i
x
.
T
a
bl
e
2
s
ho
ws
t
h
e
c
o
nf
us
i
o
n
m
a
t
r
i
x
,
a
t
a
b
u
l
a
r
r
e
pr
e
s
e
n
t
a
t
i
o
n
t
h
a
t
i
ll
us
t
r
a
t
e
s
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
a
n
a
l
go
r
i
t
hm
o
r
m
o
de
l
in
c
l
a
s
s
if
i
c
a
t
i
o
n
t
a
s
ks
.
T
a
bl
e
2.
Vi
s
ua
li
z
a
t
i
o
n
o
f
t
h
e
c
o
nf
us
i
o
n
m
a
t
r
i
x
C
la
s
s
if
ic
a
ti
o
n
V
a
lu
e
p
r
e
di
c
ti
o
ns
E
di
bl
e
P
o
is
o
n
o
us
A
c
tu
a
l
v
a
lu
e
E
di
bl
e
T
r
u
e
p
o
s
it
iv
e
(
T
P
)
F
a
ls
e
n
e
ga
ti
ve
(
F
N
)
P
o
is
o
n
o
us
F
a
ls
e
p
o
s
it
i
ve
(
F
P
)
T
r
u
e
n
e
ga
ti
ve
(
T
N
)
B
a
s
e
d
o
n
t
h
e
da
t
a
s
h
o
wn
i
n
t
h
e
c
o
nf
us
i
o
n
m
a
t
r
i
x
,
t
h
e
r
e
we
r
e
c
o
m
m
o
n
e
va
l
ua
t
i
o
n
m
e
t
r
i
c
s
t
h
a
t
c
o
ul
d
b
e
us
e
d
to
m
e
a
s
ur
e
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
t
h
e
NB
a
l
g
o
r
i
t
hm
s
pe
c
if
i
c
a
ll
y
t
o
i
t
s
a
c
c
ur
a
c
y
,
i
nd
i
c
a
t
i
n
g
t
h
e
p
r
e
c
i
s
i
o
n
o
r
c
o
r
r
e
c
t
n
e
s
s
i
n
c
l
a
s
s
i
f
yi
ng
e
d
i
b
l
e
o
r
p
o
i
s
o
n
o
us
m
us
h
r
o
o
m
s
f
r
o
m
t
h
e
g
i
v
e
n
da
t
a
s
e
t
.
A
c
c
ur
a
c
y
wa
s
c
o
m
put
e
d
us
i
n
g
t
h
e
f
o
r
m
u
l
a
i
n
(
3)
.
=
(
+
)
(
+
+
+
)
100%
(
3)
Ot
h
e
r
m
e
t
r
i
c
s
we
r
e
a
l
s
o
a
ppl
i
e
d
i
n
t
hi
s
s
t
ud
y
.
P
r
e
c
i
s
i
o
n
c
o
u
l
d
b
e
c
o
m
put
e
d
i
n
(
4)
,
r
e
c
a
l
l
wa
s
c
a
l
c
u
l
a
t
e
d
i
n
(
5)
,
a
n
d
S
pe
c
i
f
i
c
i
t
y
c
o
u
l
d
be
s
o
l
ve
d
us
i
n
g
t
h
e
f
o
r
m
u
l
a
i
n
(
6)
.
=
(
)
(
+
)
100%
(
4)
=
(
)
(
+
)
100%
(
5)
=
(
)
(
+
)
100%
(
6)
On
t
h
e
ot
h
e
r
h
a
n
d,
t
h
e
F
1
-
s
c
o
r
e
wa
s
t
h
e
h
a
r
m
o
ni
c
m
e
a
n
o
f
pr
e
c
i
s
i
o
n
a
n
d
r
e
c
a
l
l
w
hi
c
h
c
a
n
be
c
o
m
put
e
d
us
i
n
g
t
h
e
f
o
r
m
u
l
a
i
n
(
7)
.
1
−
=
2
(
)
(
+
)
100%
(
7)
T
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
t
h
e
m
o
de
l
wa
s
f
ur
t
h
e
r
e
v
a
l
u
a
t
e
d
us
i
n
g
t
h
e
R
OC
c
ur
v
e
a
n
d
t
h
e
A
UC
m
e
t
r
i
c
s
,
whi
c
h
we
r
e
m
o
s
t
us
e
d
i
n
ML
to
e
v
a
l
ua
t
e
t
h
e
e
f
f
e
c
t
i
v
e
n
e
s
s
o
f
a
t
w
o
-
c
l
a
s
s
c
l
a
s
s
if
i
c
a
t
i
o
n
m
o
de
l
[
29]
.
T
h
e
R
O
C
c
ur
v
e
wa
s
c
r
e
a
t
e
d
by
p
l
o
tt
i
n
g
t
h
e
t
r
ue
p
o
s
i
t
i
v
e
r
a
te
(
T
P
R
)
,
a
l
s
o
kn
o
wn
a
s
r
e
c
a
ll
/s
e
ns
i
t
i
vi
t
y
,
a
ga
i
ns
t
t
h
e
f
a
l
s
e
po
s
i
t
i
v
e
r
a
t
e
(
F
P
R
)
a
t
di
f
f
e
r
e
n
t
t
h
r
e
s
h
o
l
d
l
e
v
e
l
s
,
w
hil
e
t
h
e
A
UC
s
c
o
r
e
wa
s
a
s
i
n
g
l
e
s
c
a
l
a
r
v
a
l
ue
t
h
a
t
ga
v
e
a
n
o
v
e
r
a
l
l
i
nd
i
c
a
t
i
o
n
o
f
h
o
w
a
c
c
ur
a
t
e
t
h
e
c
l
a
s
s
if
i
e
r
c
a
n
d
i
f
f
e
r
e
n
t
i
a
t
e
b
e
t
we
e
n
c
l
a
s
s
e
s
[
30]
.
T
h
e
A
UC
s
c
o
r
e
c
o
ul
d
b
e
c
o
m
put
e
d
us
i
n
g
t
h
e
t
r
a
p
e
z
o
i
da
l
r
u
l
e
[
31]
a
f
t
e
r
ge
n
e
r
a
t
i
n
g
t
h
e
R
OC
c
ur
v
e
b
e
c
a
us
e
t
h
e
A
UC
r
e
pr
e
s
e
n
t
e
d
t
h
e
a
r
e
a
be
n
e
a
t
h
t
he
c
ur
v
e
[
32]
.
T
h
e
a
r
e
a
o
f
t
h
e
t
r
a
pe
z
o
i
d
wa
s
c
a
l
c
u
l
a
t
e
d
f
o
r
e
a
c
h
a
d
j
a
c
e
n
t
pa
i
r
o
f
po
i
n
t
s
(
,
)
a
n
d
(
+
1
,
+
1
)
us
i
n
g
t
h
e
f
o
r
m
u
la
s
h
o
wn
i
n
(
8)
.
T
o
ge
t
t
h
e
tot
a
l
AU
C
s
c
o
r
e
,
s
um
t
h
e
a
r
e
a
o
f
e
a
c
h
t
r
a
pe
z
o
i
d
a
c
r
o
s
s
a
l
l
a
d
j
a
c
e
n
t
po
i
n
t
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
A
de
c
is
ion
s
uppor
t
s
y
s
tem
f
or
mus
hr
oom
c
las
s
if
ication
us
ing
N
aïve
B
ay
e
s
ian
…
(
V
il
c
hor
Gar
c
ia
P
e
r
d
ido
)
143
A
r
e
a
=
(
+
1
−
)
×
(
+
1
+
)
2
(
8)
W
h
e
r
e
,
(
+
1
−
)
r
e
p
r
e
s
e
n
t
e
d
t
h
e
di
f
f
e
r
e
n
c
e
i
n
F
P
R
b
e
t
we
e
n
t
w
o
c
o
n
s
e
c
ut
i
v
e
po
i
n
t
s
,
(
+
1
+
)
r
e
pr
e
s
e
n
t
e
d
t
h
e
di
f
f
e
r
e
n
c
e
i
n
F
P
R
b
e
t
we
e
n
t
w
o
c
on
s
e
c
ut
i
v
e
po
i
n
t
s
,
1
2
⁄
a
v
e
r
a
ge
s
t
h
e
c
o
m
bi
ne
d
h
e
i
g
h
t
o
f
t
h
e
t
r
a
pe
z
o
i
d
to
a
c
c
o
un
t
f
o
r
t
h
e
f
o
r
m
u
l
a
f
o
r
t
h
e
a
r
e
a
o
f
a
t
r
a
pe
z
o
i
d,
A
r
e
a
de
n
ot
e
d
t
h
e
c
a
l
c
u
l
a
t
e
d
A
UC
f
o
r
t
h
e
i
n
t
e
r
v
a
l
b
e
t
we
e
n
t
h
e
-
t
h
a
n
d
(
+
1
)
-
t
h
p
o
i
n
t
s
.
I
n
ML
,
t
h
e
A
UC
s
c
o
r
e
f
o
r
a
R
OC
c
ur
v
e
wa
s
t
y
p
ica
l
ly
e
v
a
l
ua
t
e
d
o
n
a
s
c
a
l
e
f
r
o
m
0
to
1
[
31]
,
[
33]
,
w
i
t
h
d
i
f
f
e
r
e
n
t
r
a
n
ge
s
o
f
t
e
n
i
n
t
e
r
pr
e
t
e
d
us
i
n
g
a
L
i
k
e
r
t
-
s
t
y
l
e
r
a
t
i
n
g
a
s
s
h
o
wn
i
n
T
a
bl
e
3.
A
s
c
o
r
e
j
u
s
t
a
b
o
v
e
0.
5
s
h
o
we
d
t
h
e
m
o
de
l
h
a
s
m
i
n
im
a
l
pr
e
d
i
c
t
i
v
e
po
we
r
,
whi
c
h
wa
s
u
s
ua
ll
y
i
ns
u
f
f
i
c
i
e
n
t
f
o
r
pr
a
c
t
i
c
a
l
a
pp
li
c
a
t
i
o
ns
.
Ge
n
e
r
a
ll
y
,
a
n
R
OC
A
UC
s
c
o
r
e
o
v
e
r
0.
8
wa
s
r
e
ga
r
de
d
a
s
goo
d
,
a
n
d
a
b
o
v
e
0.
9
wa
s
c
o
n
s
i
de
r
e
d
e
x
c
e
l
l
e
n
t
.
T
hi
s
r
a
t
i
n
g
s
y
s
t
e
m
wa
s
us
e
d
to
i
n
t
e
r
pr
e
t
A
UC
va
l
ue
s
to
e
v
a
l
u
a
t
e
c
l
a
s
s
if
i
e
r
e
f
f
e
c
t
i
ve
n
e
s
s
a
c
r
o
s
s
d
i
f
f
e
r
e
n
t
pr
o
b
a
bil
i
t
y
t
h
r
e
s
h
o
l
ds
.
T
a
bl
e
3.
A
UC
-
R
OC
pe
r
f
o
r
m
a
n
c
e
m
e
a
s
ur
e
m
e
n
t
A
U
C
r
a
nge
R
a
ti
ng
D
e
s
c
r
ip
ti
o
n
0.90
-
1.00
E
xc
e
ll
e
nt
O
ut
s
ta
ndi
ng dis
c
r
im
in
a
ti
o
n be
tw
e
e
n
c
la
s
s
e
s
.
0.80
-
0.90
G
oo
d
S
tr
o
ng c
la
s
s
if
i
e
r
, r
e
li
a
bl
e
f
or
m
o
s
t
a
ppl
ic
a
ti
o
ns
.
0.70
-
0.79
F
a
ir
M
o
de
r
a
te
di
s
c
r
im
in
a
ti
o
n, us
e
f
ul
i
n ma
n
y
s
c
e
na
r
i
o
s
.
0.60
-
0.69
P
oor
W
e
a
k c
la
s
s
if
ie
r
;
s
o
m
e
i
mp
r
ov
e
me
nt
mi
ght
b
e
ne
c
e
s
s
a
r
y
.
0.50
-
0.59
V
e
r
y
p
oo
r
B
a
r
e
l
y
be
t
te
r
th
a
n r
a
nd
o
m;
g
e
ne
r
a
ll
y
una
c
c
e
pt
a
bl
e
.
<
0.50
N
o
di
s
c
r
im
in
a
ti
o
n
T
h
e
m
o
d
e
l
p
e
r
f
or
ms
n
o
be
t
te
r
t
ha
n r
a
nd
o
m c
ha
n
c
e
.
3.
RE
S
UL
T
S
AN
D
DI
S
CU
S
S
I
ON
T
hi
s
s
t
ud
y
pr
i
m
a
r
i
ly
f
o
c
us
e
d
o
n
t
h
e
de
v
e
l
o
p
men
t
o
f
a
DSS
hi
g
hli
g
h
t
i
n
g
t
h
e
pot
e
n
t
i
a
l
o
f
a
n
e
m
b
e
dde
d
a
l
go
r
i
t
hm
f
o
r
t
h
e
pr
e
c
i
s
e
c
l
a
s
s
if
i
c
a
t
i
o
n
tas
k.
T
h
e
DSS
i
s
a
we
b
a
pp
l
i
c
a
t
i
o
n
de
s
i
g
n
e
d
f
o
r
m
us
h
r
o
o
m
p
i
c
ke
r
s
o
r
f
o
r
a
ge
r
s
,
a
l
l
o
w
i
ng
t
h
e
m
to
i
n
t
e
r
a
c
t
w
i
t
h
t
h
e
s
y
s
t
e
m
by
s
e
l
e
c
t
i
n
g
pr
e
de
f
i
ne
d
m
o
r
pho
l
o
g
i
c
a
l
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
.
T
h
e
s
y
s
t
e
m
t
h
e
n
a
ut
o
m
a
t
i
c
a
ll
y
c
l
a
s
s
i
f
i
e
s
t
h
e
m
u
s
h
r
oo
m
a
s
e
i
t
h
e
r
e
d
i
b
l
e
o
r
p
o
i
s
o
n
o
us
.
S
e
v
e
r
a
l
s
t
udi
e
s
h
a
ve
ut
i
li
z
e
d
DSS
f
o
r
m
u
s
h
r
oo
m
c
l
a
s
s
i
f
i
c
a
t
i
o
n;
h
o
we
v
e
r
,
m
o
s
t
o
f
t
h
e
s
e
we
r
e
de
s
i
g
n
e
d
a
n
d
de
p
l
o
y
e
d
a
s
m
o
bi
l
e
a
pp
li
c
a
t
i
o
n
s
us
i
ng
i
m
a
ge
pr
o
c
e
s
s
i
n
g
[
34
]
–
[
37]
,
whi
l
e
o
t
h
e
r
s
we
r
e
pur
e
l
y
c
o
m
pa
r
is
o
n
s
o
f
a
l
go
r
i
t
hm
s
w
i
t
h
n
o
a
c
t
ua
l
a
pp
l
i
c
a
t
i
o
n
de
ve
l
o
p
m
e
nt
[
38]
–
[
41]
.
T
h
e
s
t
udy
f
o
l
l
o
we
d
t
h
e
c
o
m
m
o
n
c
o
m
po
n
e
n
t
s
i
nv
o
l
ve
d
i
n
b
u
il
d
i
ng
a
DSS
,
whi
c
h
i
n
c
l
ude
da
t
a
s
e
l
e
c
t
i
o
n
,
t
h
e
de
s
i
g
ni
ng
o
f
us
e
r
i
n
t
e
r
f
a
c
e
s
,
a
n
d
t
h
e
t
r
a
i
n
i
ng
o
f
t
h
e
m
o
de
l
a
n
d
t
e
s
t
i
n
g
o
f
i
t
s
pe
r
f
o
r
m
a
n
c
e
.
T
h
e
pr
e
s
e
n
t
s
t
udy
e
x
p
l
a
i
ns
t
h
e
r
e
s
u
l
t
s
o
f
t
h
e
s
e
c
o
m
po
n
e
n
t
s
,
a
s
i
t
i
s
de
t
a
i
l
e
d
i
n
t
h
e
f
o
l
l
o
w
i
ng
t
h
r
e
e
s
u
b
-
s
e
c
t
i
o
n
s
.
3.
1.
Dat
a
p
r
e
p
ar
at
ion
an
d
p
r
e
p
r
oc
e
s
s
in
g
A
r
a
w
da
t
a
o
f
m
u
s
h
r
oo
m
s
o
b
t
a
i
ne
d
f
r
o
m
K
a
gg
l
e
[
17]
,
a
n
o
n
l
i
ne
da
t
a
s
o
ur
c
e
,
wa
s
us
e
d
a
s
t
h
e
da
t
a
s
e
t
o
f
t
hi
s
s
t
ud
y
.
T
hi
s
r
a
w
da
t
a
i
s
o
r
i
g
i
na
ll
y
s
t
o
r
e
d
i
n
a
c
o
m
m
a
-
s
e
p
a
r
a
t
e
d
v
a
l
u
e
s
(
C
S
V)
f
il
e
a
n
d
374
KB
o
f
f
il
e
s
i
z
e
.
T
hi
s
s
t
ud
y
ut
i
li
z
e
d
P
y
t
h
o
n
t
o
c
r
e
a
t
e
a
da
t
a
s
e
t
f
r
o
m
t
h
e
r
a
w
da
t
a
c
o
m
m
a
n
de
d
i
n
t
h
e
J
up
y
t
e
r
Note
b
o
o
k.
I
t
h
a
d
a
tot
a
l
n
u
m
be
r
o
f
8,
124
da
t
a
s
a
m
p
l
e
s
[
42]
,
[
4
3
]
wi
t
h
23
c
o
l
u
m
ns
a
s
s
h
o
wn
i
n
F
i
gur
e
2.
T
h
e
s
e
c
o
l
u
m
n
s
we
r
e
t
h
e
22
m
o
r
ph
o
l
o
g
i
c
a
l
c
h
a
r
a
c
t
e
r
s
(
a
tt
r
i
b
ut
e
s
)
o
f
m
us
h
r
o
o
m
s
[
8]
,
[
16]
,
[
18]
whi
c
h
we
r
e
i
m
p
o
r
t
a
n
t
to
c
l
a
s
s
if
y
o
n
e
(
1)
t
a
r
ge
t
f
e
a
t
ur
e
(
c
l
a
s
s
)
,
e
i
t
h
e
r
a
n
e
d
i
bl
e
(
‘
e
’
)
o
r
a
p
o
i
s
o
n
o
us
(
‘
p
’
)
t
y
p
e
o
f
m
u
s
h
r
oom
.
I
t
wa
s
f
o
u
n
d
t
h
a
t
t
h
e
r
e
we
r
e
4
,
208
(
51
%
)
i
ns
t
a
n
c
e
s
b
e
l
o
n
g
i
ng
to
t
h
e
e
d
i
bl
e
c
a
t
e
gor
y
w
hil
e
a
tot
a
l
n
u
m
be
r
o
f
3,
916
(
49%
)
i
ns
t
a
n
c
e
s
we
r
e
i
n
c
l
ude
d
i
n
t
h
e
po
i
s
o
n
o
us
c
a
t
e
g
o
r
y
a
s
s
h
o
wn
i
n
F
i
gur
e
3.
F
i
gur
e
2.
S
tr
uc
t
ur
e
a
n
d
f
e
a
t
ur
e
s
o
f
t
h
e
da
t
a
s
o
ur
c
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
1
5
,
N
o.
1
,
M
a
r
c
h
20
2
6
:
13
8
-
15
1
144
F
i
gur
e
3.
C
o
un
t
o
f
t
h
e
e
d
i
bl
e
a
n
d
po
i
s
o
n
o
us
c
l
a
s
s
e
s
A
dd
i
t
i
o
n
a
ll
y
,
s
e
e
F
i
gur
e
4
,
t
h
e
da
t
a
t
y
pe
o
f
t
h
e
s
e
c
o
l
u
m
ns
wa
s
f
o
un
d
o
bj
e
c
t
s
a
s
s
h
o
wn
in
F
i
gur
e
4(
a
)
,
wh
e
r
e
v
a
l
ue
s
c
o
n
t
a
i
n
e
d
t
e
x
t
s
,
t
h
us
th
e
e
x
pe
c
t
e
d
t
y
pe
o
f
da
t
a
f
o
r
e
a
c
h
i
n
s
t
a
n
c
e
(
r
o
w
)
o
f
t
h
e
da
t
a
s
e
t
wa
s
i
n
c
a
t
e
go
r
i
c
a
l
f
o
r
m
.
A
s
m
e
n
t
i
o
n
e
d,
t
h
e
NB
a
l
go
r
i
t
hm
wa
s
hi
g
hl
y
a
pp
l
i
e
d
i
n
t
e
x
t
c
l
a
s
s
i
f
i
c
a
t
i
o
n
.
I
n
da
t
a
c
l
e
a
ni
ng,
i
de
n
t
i
f
yi
ng
m
i
s
s
i
ng
wa
s
n
e
c
e
s
s
a
r
y
i
n
t
hi
s
s
t
ud
y
pr
i
o
r
to
t
h
e
t
r
a
i
ni
ng
a
n
d
t
e
s
t
i
ng
o
f
t
h
e
c
l
a
s
s
if
i
c
a
t
i
o
n
a
l
go
r
i
t
hm
.
B
y
us
i
ng
b
u
il
t
-
i
n
f
u
n
c
t
i
o
n
s
i
n
P
y
t
h
o
n
,
i
t
f
o
un
d
o
ut
t
h
a
t
t
h
e
r
e
we
r
e
n
o
n
u
l
l
va
l
ue
s
s
h
o
w
n
i
n
F
i
gur
e
4(
b
)
,
t
h
us
t
h
e
da
t
a
s
e
t
h
a
d
g
oo
d
da
t
a
qua
l
i
t
y
.
(
a
)
(
b
)
F
i
gur
e
4.
T
h
e
e
x
t
r
a
c
t
e
d
m
us
h
r
o
o
m
va
r
i
a
bl
e
s
f
r
o
m
th
e
da
t
a
s
e
t
to
b
e
us
e
d
i
n
c
l
a
s
s
i
f
i
c
a
t
i
o
n
c
o
ns
i
s
t
o
f
(
a
)
o
bj
e
c
t
da
t
a
t
y
p
e
s
a
n
d
(
b
)
n
o
n
-
n
u
l
l
v
a
l
ue
s
3.
2.
T
h
e
DSS
f
or
m
u
s
h
r
oo
m
c
l
as
s
i
f
icat
ion
u
s
in
g
Naïve
B
aye
s
a
l
gor
it
h
m
T
h
e
de
v
e
l
o
pe
d
DSS
wa
s
kn
o
wn
a
s
Ka
b
uT
e
a
c
h
,
de
s
i
g
n
e
d
to
di
f
f
e
r
e
n
t
i
a
t
e
o
r
c
l
a
s
s
if
y
a
m
u
s
h
r
oo
m
,
e
i
t
h
e
r
e
d
i
b
l
e
(
e
a
t
a
bl
e
)
o
r
p
o
i
s
o
n
o
us
(
to
xi
c
)
b
a
s
e
d
o
n
i
t
s
m
o
r
ph
o
l
o
g
i
c
a
l
f
e
a
t
ur
e
s
a
s
t
h
e
i
n
pu
t
s
.
T
h
e
f
u
n
c
t
i
o
n
a
li
t
i
e
s
we
r
e
m
a
i
n
ly
de
ve
l
o
pe
d
us
i
n
g
L
a
r
a
v
e
l
11,
a
n
o
pe
n
-
s
o
ur
c
e
P
HP
f
r
a
m
e
wo
r
k,
w
hil
e
us
e
r
i
n
t
e
r
f
a
c
e
s
we
r
e
ge
n
e
r
a
l
ly
de
s
i
g
ne
d
i
n
B
o
ot
s
t
r
a
p
5.
T
h
e
M
a
r
i
a
DB
da
t
a
b
a
s
e
wa
s
us
e
d
to
s
to
r
e
t
h
e
da
t
a
s
e
t
s
us
e
d
dur
i
n
g
t
h
e
tr
a
i
ni
ng
a
n
d
t
e
s
t
i
n
g
o
f
t
h
e
NB
c
l
a
s
s
if
i
c
a
t
i
o
n
a
l
go
r
i
t
hm
.
T
h
e
c
l
a
s
s
if
i
e
r
m
o
du
l
e
o
f
t
h
e
s
y
s
t
e
m
wa
s
us
e
d
by
t
he
f
o
r
a
ge
s
(
m
us
h
r
o
o
m
p
i
c
ke
r
s
)
to
t
e
s
t
t
h
e
c
l
a
s
s
if
i
c
a
t
i
o
n
o
f
a
c
o
l
l
e
c
t
e
d
a
n
d
c
h
a
r
a
c
t
e
r
i
z
e
d
m
us
h
r
o
o
m
.
Al
l
m
o
r
p
h
o
l
o
g
i
c
a
l
c
h
a
r
a
c
t
e
r
s
we
r
e
e
n
c
o
de
d
by
c
a
r
e
f
u
ll
y
s
e
l
e
c
t
i
n
g
v
a
l
ue
s
i
n
t
h
e
c
o
m
b
o
b
o
x
e
s
.
Af
t
e
r
s
e
l
e
c
t
i
n
g
a
l
l
t
h
e
n
e
c
e
s
s
a
r
y
c
h
a
r
a
c
t
e
r
s
,
t
h
e
s
y
s
t
e
m
m
a
t
c
h
e
d
t
h
e
s
e
c
h
a
r
a
c
t
e
r
s
w
i
t
h
a
ll
t
h
e
i
ns
t
a
n
c
e
s
(
r
e
c
o
r
ds
)
f
r
o
m
t
h
e
hi
s
t
o
r
i
c
a
l
da
t
a
s
e
t
i
n
t
h
e
da
t
a
ba
s
e
.
I
f
n
o
n
e
o
f
t
h
e
e
x
a
m
p
l
e
s
m
a
t
c
h
e
s
,
t
h
e
n
t
h
e
NB
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
l
go
r
i
t
hm
c
l
a
s
s
i
f
i
e
s
t
h
e
m
i
n
F
i
gur
e
5,
a
s
e
d
i
b
l
e
(
s
e
e
F
i
gur
e
5(
a
)
)
or
p
o
i
s
o
n
o
us
(
s
e
e
F
i
gur
e
5(
b
)
)
,
d
e
pe
n
d
i
ng
o
n
whi
c
h
c
a
t
e
go
r
y
h
a
s
t
h
e
hi
g
h
e
s
t
po
s
t
e
r
i
o
r
pr
o
b
a
bil
i
t
y
,
a
n
d
s
to
r
e
s
t
h
e
m
i
n
t
h
e
t
e
s
t
da
t
a
s
e
t
i
n
t
h
e
da
t
a
b
a
s
e
.
3700
3800
3900
4000
4100
4200
4300
E
di
bl
e
Pois
o
n
o
u
s
Fre
q
u
e
n
c
y
H
i
s
t
o
g
ram
o
f
E
d
i
b
l
e
an
d
Po
i
s
o
n
o
u
s
Mu
s
h
ro
o
m
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
A
de
c
is
ion
s
uppor
t
s
y
s
tem
f
or
mus
hr
oom
c
las
s
if
ication
us
ing
N
aïve
B
ay
e
s
ian
…
(
V
il
c
hor
Gar
c
ia
P
e
r
d
ido
)
145
(
a
)
(
b
)
F
i
gur
e
5.
T
h
e
c
l
a
s
s
if
i
c
a
t
i
o
n
o
f
m
us
h
r
o
o
m
s
us
i
ng
t
h
e
B
a
y
e
s
’
T
h
e
o
r
e
m
i
n
t
e
gr
a
t
e
d
i
n
t
o
t
h
e
c
l
a
s
s
if
i
e
r
m
o
du
l
e
o
f
K
a
b
uT
e
a
c
h
pr
e
d
i
c
t
s
t
w
o
c
l
a
s
s
e
s
(
a
)
e
d
i
bl
e
a
n
d
(
b
)
po
i
s
o
n
o
us
3.
3.
P
e
r
f
o
r
m
an
c
e
r
e
s
u
l
t
s
T
o
m
e
a
s
ur
e
t
h
e
e
f
f
i
c
a
c
y
o
f
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
t
h
e
NB
c
l
a
s
s
if
i
c
a
t
i
o
n
a
l
go
r
i
t
hm
(
m
o
de
l
)
,
K
a
b
uT
e
a
c
h
pr
o
vi
de
d
a
m
o
du
l
e
w
h
e
r
e
i
t
c
o
ul
d
t
r
a
i
n
a
n
d
t
e
s
t
t
h
e
m
o
de
l
.
T
h
e
s
p
l
i
t
t
i
n
g
o
f
da
t
a
i
n
t
o
t
w
o
da
t
a
s
e
t
s
a
n
d
K
-
f
o
l
d
c
r
o
s
s
-
v
a
l
i
d
a
t
i
o
n
a
ppr
o
a
c
h
e
s
we
r
e
a
pp
l
i
e
d
i
n
t
hi
s
s
t
udy
.
T
hi
s
s
t
ud
y
a
pp
li
e
d
t
h
e
70:30
r
a
t
i
o
[
43]
r
a
n
do
m
s
p
l
i
t
t
i
n
g
m
e
c
h
a
n
i
s
m
,
w
h
e
r
e
70%
(
5,
686)
o
f
t
h
e
d
a
t
a
we
r
e
us
e
d
i
n
t
r
a
i
ni
ng
t
h
e
NB
c
l
a
s
s
i
f
i
c
a
t
i
o
n
mo
de
l
.
T
h
e
r
e
m
a
i
n
i
ng
30%
(
2
,
438)
we
r
e
e
m
p
l
o
y
e
d
to
t
e
s
t
o
r
e
v
a
l
u
a
t
e
i
t
s
pe
r
f
o
r
m
a
n
c
e
o
n
t
h
e
t
r
a
i
n
e
d
m
o
de
l
.
T
h
e
e
v
a
l
ua
t
i
o
n
m
e
t
r
i
c
s
we
r
e
de
r
i
v
e
d
f
r
o
m
t
h
e
r
e
s
u
l
t
i
n
g
c
o
nf
us
i
o
n
m
a
t
r
i
x
o
f
t
h
e
t
e
s
t
i
n
g
da
t
a
f
e
d
t
o
t
h
e
a
l
go
r
i
t
hm
s
h
o
w
n
i
n
F
i
gur
e
6
ge
n
e
r
a
t
e
d
by
t
h
e
K
a
b
uT
e
a
c
h
s
ys
t
e
m
.
F
i
gur
e
6.
T
h
e
c
o
nf
u
s
i
o
n
m
a
t
r
i
x
F
r
o
m
t
hi
s
c
o
nf
us
i
o
n
m
a
t
r
i
x
,
t
h
e
a
c
t
ua
l
n
u
m
be
r
o
f
e
di
bl
e
m
u
s
h
r
oo
m
s
i
s
1,
274,
whi
l
e
t
h
e
n
u
m
be
r
o
f
po
i
s
o
n
o
us
m
u
s
h
r
oo
m
s
wa
s
1,
164,
b
ot
h
s
tor
e
d
i
n
t
h
e
t
e
s
t
i
n
g
da
t
a
s
e
t
.
I
n
t
hi
s
f
i
gur
e
,
t
h
e
NB
c
l
a
s
s
if
i
c
a
t
i
o
n
m
o
de
l
c
o
r
r
e
c
t
l
y
c
l
a
s
s
i
f
i
e
d
97.
72%
(
TP
)
o
f
t
h
e
e
d
i
bl
e
m
u
s
h
r
o
o
m
s
,
w
i
t
h
2.
28%
(
FN
)
c
l
a
s
s
i
f
i
e
d
i
nc
o
r
r
e
c
t
l
y
.
O
n
t
h
e
ot
h
e
r
h
a
n
d,
77.
66%
(
TN
)
o
f
t
h
e
po
i
s
o
n
o
us
m
u
s
h
r
oo
m
s
we
r
e
c
o
r
r
e
c
t
l
y
i
de
n
t
i
f
i
e
d.
Ho
we
v
e
r
,
i
t
mi
s
c
l
a
s
s
if
i
e
d
22.
34%
(
FP
)
a
s
e
di
bl
e
,
w
hi
c
h
i
s
a
s
i
g
ni
f
i
c
a
n
t
n
u
m
b
e
r
g
i
ve
n
t
h
e
r
i
s
k
o
f
c
o
n
s
u
mi
ng
p
o
i
s
o
n
o
us
m
us
h
r
o
o
m
s
.
W
i
t
h
t
h
e
s
e
f
i
gur
e
s
i
nd
i
c
a
t
e
d
f
r
o
m
t
he
c
o
nf
us
i
o
n
m
a
t
r
i
x
,
t
h
e
NB
c
l
a
s
s
i
f
i
e
r
pe
r
f
o
r
m
e
d
we
l
l
w
i
t
h
e
d
i
bl
e
m
us
h
r
o
o
m
s
b
ut
s
t
r
uggl
e
d
w
i
t
h
po
i
s
o
n
o
us
on
e
s
,
whi
c
h
c
o
u
l
d
l
e
a
d
t
o
p
ot
e
n
t
i
a
l
h
e
a
l
t
h
r
i
s
ks
.
W
hil
e
t
h
e
T
P
r
a
t
e
f
o
r
e
d
i
bl
e
m
us
h
r
o
o
m
s
i
s
pr
o
m
i
s
i
ng,
t
h
e
F
P
r
a
t
e
f
o
r
p
o
i
s
o
n
o
us
m
us
h
r
o
o
m
s
hi
g
hli
g
h
t
s
a
r
i
s
k
a
r
e
a
t
h
a
t
n
e
e
d
s
i
m
pr
o
v
e
m
e
n
t
.
T
hi
s
s
t
ud
y
s
ugge
s
t
s
t
h
a
t
t
h
e
m
o
de
l
c
o
u
l
d
i
m
pr
o
v
e
t
h
e
m
o
de
l
’
s
a
c
c
ur
a
c
y
,
e
s
p
e
c
i
a
ll
y
f
o
r
i
de
n
t
i
f
y
i
ng
po
i
s
o
n
o
us
m
us
h
r
o
o
m
s
,
whi
c
h
c
o
u
l
d
i
nv
o
l
v
e
r
e
f
i
n
i
ng
f
e
a
t
ur
e
s
,
ga
t
h
e
r
i
n
g
m
o
r
e
da
t
a
,
o
r
e
x
p
l
o
r
i
n
g
ot
h
e
r
c
l
a
s
s
if
i
c
a
t
i
o
n
m
o
de
l
s
.
M
o
r
e
o
v
e
r
,
t
h
e
o
v
e
r
a
l
l
m
o
de
l
’
s
A
c
c
ur
a
c
y
r
a
t
e
de
r
i
ve
d
f
r
o
m
t
h
e
c
o
nf
us
i
o
n
m
a
t
r
i
x
a
n
d
c
o
m
put
e
d
us
i
n
g
t
h
e
f
o
r
m
u
l
a
i
n
(
9)
.
=
(
1245
+
904
)
(
1245
+
904
+
260
+
29
)
100
=
2149
2438
100
=
88
.
15
=
0
.
8
8
1
4
6
0
2
1
3
2
8
9
5
8
1
6
100
=
88
.
15%
(
r
o
un
de
d
to
t
w
o
de
c
i
m
a
l
p
l
a
c
e
s
)
(
9)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
1
5
,
N
o.
1
,
M
a
r
c
h
20
2
6
:
13
8
-
15
1
146
B
a
s
e
d
o
n
t
hi
s
c
o
m
put
a
t
i
o
n
,
t
h
e
m
o
de
l
yi
e
l
de
d
a
high
a
c
c
ur
a
c
y
r
a
t
e
o
f
88.
15%
c
or
r
e
c
t
c
l
a
s
s
if
i
c
a
t
i
o
n
.
T
hi
s
i
n
d
i
c
a
t
e
d
t
h
a
t
t
h
e
c
l
a
s
s
if
i
e
r
pe
r
f
o
r
m
e
d
e
f
f
e
c
t
i
v
e
ly
a
n
d
r
e
l
i
a
bly
i
n
d
i
s
t
i
ngu
i
s
hi
ng
b
e
t
we
e
n
e
d
i
bl
e
a
n
d
po
i
s
o
n
o
us
m
us
h
r
o
o
m
s
.
T
hi
s
l
e
v
e
l
o
f
a
c
c
ur
a
c
y
i
mp
l
i
e
d
t
h
a
t
t
h
e
m
o
de
l
s
e
r
v
e
d
i
t
s
i
n
t
e
n
de
d
pur
po
s
e
a
n
d
wa
s
goo
d
e
n
o
ugh
to
b
e
us
e
d
i
n
r
e
a
l
-
wo
r
l
d
a
pp
l
i
c
a
t
i
o
ns
,
f
o
l
l
o
w
i
ng
t
h
e
e
va
l
u
a
t
i
o
n
s
t
a
n
da
r
ds
i
n
T
a
bl
e
3
a
pp
l
i
e
d
i
n
t
h
e
s
t
udy
o
f
C
r
uz
[
27]
.
On
t
h
e
ot
h
e
r
h
a
n
d,
t
h
e
a
c
c
ur
a
c
y
o
f
t
h
e
NB
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
o
de
l
i
n
c
l
a
s
s
if
yi
ng
m
u
s
h
r
oo
m
s
wa
s
e
nh
a
nc
e
d
w
i
t
h
t
h
e
i
n
t
e
gr
a
t
i
o
n
o
f
t
h
e
5
-
f
o
l
d
CV
t
e
c
hni
que
.
T
h
e
r
e
s
u
l
t
o
b
t
a
i
ne
d
a
n
89.
13%
hi
g
h
a
c
c
ur
a
c
y
r
a
t
e
.
S
e
v
e
r
a
l
s
t
ud
i
e
s
ha
v
e
u
s
e
d
t
h
e
NB
c
l
a
s
s
if
i
c
a
t
i
o
n
m
o
de
l
i
n
m
u
s
h
r
oo
m
c
l
a
s
s
if
i
c
a
t
i
o
n
[
16]
,
[
18
]
,
[
44
]
,
whi
c
h
c
l
o
s
e
ly
r
e
s
e
m
bl
e
s
t
h
e
a
c
c
ur
a
c
y
r
a
t
e
a
c
hi
e
v
e
d
i
n
t
his
s
t
udy
,
goo
d
e
n
o
ugh
to
b
e
a
pp
l
i
e
d
i
n
c
l
a
s
s
i
f
yi
ng
t
h
e
t
y
pe
s
o
f
po
i
s
o
n
o
us
a
n
d
e
d
i
bl
e
m
us
h
r
o
o
m
s
.
T
h
e
r
e
s
u
l
t
s
ob
t
a
i
n
e
d
f
r
o
m
t
h
e
c
r
o
s
s
-
v
a
li
da
t
i
o
n
a
c
c
ur
a
c
y
a
n
d
t
h
e
t
e
s
t
i
n
g
a
c
c
ur
a
c
y
im
p
li
e
d
t
h
a
t
t
h
e
m
o
de
l
pe
r
f
o
r
m
e
d
c
o
ns
i
s
t
e
n
t
l
y
a
c
r
o
s
s
d
i
f
f
e
r
e
n
t
s
ub
s
e
t
s
o
f
t
h
e
da
t
a
a
n
d
wa
s
we
l
l
-
s
u
i
t
e
d
f
o
r
pr
a
c
t
i
c
a
l
a
pp
li
c
a
t
i
o
ns
.
Ot
h
e
r
m
e
t
r
i
c
s
,
s
u
c
h
a
s
pr
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
s
pe
c
if
i
c
i
t
y
,
F
1
-
s
c
o
r
e
,
[
44]
,
[
45]
a
n
d
K
-
f
o
l
d
c
r
o
s
s
-
v
a
l
i
da
t
i
o
n
,
we
r
e
a
uto
m
a
t
i
c
a
ll
y
c
o
m
pu
t
e
d
by
K
a
b
uT
e
a
c
h
,
a
s
s
h
o
wn
i
n
F
i
gur
e
7.
F
i
gur
e
7.
T
h
e
pe
r
f
o
r
m
a
n
c
e
m
e
t
r
i
c
s
o
f
t
h
e
NB
c
l
a
s
s
if
i
c
a
t
i
o
n
m
o
de
l
I
n
t
e
r
m
s
o
f
pr
e
c
i
s
i
o
n
,
t
h
e
m
o
de
l
c
o
r
r
e
c
t
l
y
i
d
e
n
t
i
f
i
e
d
82.
72%
e
d
i
bl
e
m
us
h
r
o
o
m
s
a
s
s
h
o
wn
i
n
(
10
)
wh
e
n
i
t
pr
e
di
c
t
e
d
a
m
us
h
r
o
o
m
to
b
e
e
d
i
bl
e
.
A
l
o
we
r
pr
e
c
i
s
i
o
n
i
n
d
i
c
a
t
e
d
s
o
m
e
FP
(
p
o
i
s
o
n
o
us
m
us
h
r
o
o
m
s
c
l
a
s
s
if
i
e
d
a
s
e
d
i
bl
e
)
,
whi
c
h
c
o
u
l
d
b
e
r
i
s
k
y
.
=
(
1245
)
(
1245
+
260
)
100
=
(
1245
)
(
1505
)
100
=
(
0
.
8
2
7
2
4
2
5
2
4
9
1
6
9
4
3
5
100
)
=
82
.
72
%
(
r
o
un
de
d
to
t
w
o
de
c
i
m
a
l
p
l
a
c
e
s
)
(
10
)
On
t
h
e
ot
h
e
r
h
a
n
d,
a
hi
g
h
pr
e
c
i
s
i
o
n
o
f
96.
89%
c
o
m
put
e
d
i
n
(
1
1
)
f
o
r
p
o
i
s
o
n
o
us
m
us
h
r
o
o
m
s
m
e
a
n
t
t
h
a
t
t
h
e
m
o
de
l
wa
s
ge
n
e
r
a
ll
y
a
c
c
ur
a
t
e
wh
e
n
i
t
pr
e
d
i
c
t
e
d
a
m
us
h
r
o
o
m
a
s
po
i
s
o
n
o
us
.
T
hi
s
hi
g
h
pr
e
c
i
s
i
o
n
r
e
duc
e
d
t
h
e
l
i
ke
l
i
h
o
o
d
o
f
e
d
i
bl
e
m
us
h
r
o
o
m
s
be
in
g
f
a
l
s
e
l
y
c
l
a
s
s
i
f
i
e
d
a
s
po
i
s
o
n
o
us
,
whi
c
h
wa
s
ge
n
e
r
a
ll
y
pr
e
f
e
r
a
bl
e
.
T
hi
s
r
e
s
u
l
t
i
m
p
li
e
s
t
h
a
t
t
h
e
hi
g
h
e
r
pr
e
c
is
i
o
n
f
o
r
po
i
s
o
n
o
us
m
us
h
r
o
o
m
s
s
ugge
s
t
e
d
t
h
a
t
t
h
e
c
l
a
s
s
if
i
e
r
wa
s
c
o
n
s
e
r
v
a
t
i
v
e
,
pr
i
o
r
i
t
i
z
i
ng
s
a
f
e
t
y
by
l
e
a
ni
ng
to
wa
r
ds
c
l
a
s
s
if
yi
ng
m
u
s
h
r
oo
m
s
a
s
po
i
s
o
n
o
us
unl
e
s
s
i
t
wa
s
hi
g
hly
c
o
nf
i
de
n
t
.
T
hi
s
wa
s
a
be
n
e
f
i
c
i
a
l
t
r
a
i
t
f
o
r
h
e
a
l
t
h
-
s
e
ns
i
t
i
ve
a
pp
l
i
c
a
t
i
o
n
s
,
a
s
i
t
m
i
n
im
i
z
e
d
t
h
e
c
h
a
n
c
e
o
f
po
i
s
o
n
o
us
m
u
s
h
r
oo
m
s
b
e
i
ng
mi
s
c
l
a
s
s
if
i
e
d
a
s
e
d
i
ble.
=
(
904
)
(
904
+
29
)
10
=
(
904
)
(
933
)
100
0
.
9
6
8
9
1
7
4
7
0
5
2
5
1
8
7
6
100
=
96
.
89
%
(
r
o
un
de
d
to
t
w
o
de
c
i
m
a
l
p
l
a
c
e
s
)
(1
1
)
T
h
e
r
e
c
a
ll
r
e
s
u
l
t
c
o
m
put
e
d
i
n
(
1
2
)
wa
s
v
e
r
y
hi
g
h
w
i
t
h
97.
72%
,
i
n
d
i
c
a
t
i
n
g
t
ha
t
n
e
a
r
l
y
a
ll
e
d
i
b
l
e
m
us
h
r
o
o
m
s
w
e
r
e
c
o
r
r
e
c
t
l
y
i
de
n
t
i
f
i
e
d
by
t
h
e
m
o
de
l
.
T
hi
s
r
e
duc
e
d
t
h
e
c
h
a
n
c
e
o
f
e
d
i
b
l
e
m
us
h
r
o
om
s
be
i
n
g
mi
s
c
l
a
s
s
if
i
e
d
a
s
po
i
s
o
n
o
us
,
whi
c
h
h
e
l
pe
d
f
o
r
a
ge
r
s
a
v
o
i
d
m
i
s
t
a
ke
nly
d
i
s
c
a
r
d
i
ng
s
a
f
e
m
u
s
h
r
oo
m
s
.
=
(
1245
)
(
1245
+
29
)
10
0
=
(
1245
)
(
1274
)
100
=
(
0
.
9
7
7
2
3
7
0
4
8
6
6
5
6
2
0
1
)
100
=
97
.
72%
(
r
o
un
de
d
to
t
w
o
de
c
i
m
a
l
p
l
a
c
e
s
)
(1
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
A
de
c
is
ion
s
uppor
t
s
y
s
tem
f
or
mus
hr
oom
c
las
s
if
ication
us
ing
N
aïve
B
ay
e
s
ian
…
(
V
il
c
hor
Gar
c
ia
P
e
r
d
ido
)
147
S
pe
c
i
f
i
c
i
t
y
,
o
r
t
h
e
t
r
ue
n
e
ga
t
i
ve
r
a
t
e
(
T
NR
)
c
o
m
p
ut
e
d
i
n
(
1
3
)
,
i
n
d
i
c
a
t
e
s
t
h
a
t
t
h
e
c
l
a
s
s
i
f
i
e
r
c
o
r
r
e
c
t
ly
i
de
n
t
i
f
i
e
s
po
i
s
o
n
o
us
m
us
h
r
o
o
m
s
77.
66%
o
f
t
h
e
t
i
m
e
.
T
hi
s
i
s
a
s
i
g
ni
f
i
c
a
n
t
m
e
t
r
i
c
b
e
c
a
us
e
i
t
r
e
f
lec
t
s
t
h
e
m
o
de
l
’
s
e
f
f
e
c
t
i
v
e
n
e
s
s
i
n
r
e
j
e
c
t
i
n
g
da
n
g
e
r
o
us
m
u
s
h
r
o
o
m
s
.
W
hil
e
t
h
e
r
e
s
u
l
t
i
s
m
o
de
r
a
t
e
l
y
hi
g
h
,
e
nh
a
n
c
i
ng
s
pe
c
i
f
i
c
i
t
y
c
o
u
l
d
f
ur
t
h
e
r
e
n
s
ur
e
us
e
r
s
a
f
e
t
y
by
mi
n
im
i
z
i
ng
t
h
e
n
u
m
be
r
o
f
po
i
s
o
n
o
us
m
u
s
h
r
o
o
m
s
c
l
a
s
s
i
f
i
e
d
a
s
e
d
i
bl
e
.
=
(
904
)
(
904
+
260
)
100
=
(
904
)
(
1164
)
100
=
(
0
.
7
7
6
6
3
2
3
0
2
4
0
5
4
9
8
3
100
)
=
77
.
66%
(
r
o
un
de
d
to
t
w
o
de
c
i
m
a
l
p
l
a
c
e
s
)
(1
3
)
T
h
e
F1
-
s
c
o
r
e
c
a
l
c
u
l
a
t
e
d
us
i
n
g
t
h
e
f
o
r
m
u
l
a
i
n
(
1
4
)
,
whi
c
h
wa
s
t
h
e
h
a
r
m
o
n
i
c
m
e
a
n
o
f
r
e
c
a
l
l
a
n
d
pr
e
c
i
s
i
o
n
yi
e
l
de
d
89.
60%
,
h
i
g
hli
g
h
t
e
d
t
h
a
t
b
ot
h
m
e
t
r
i
c
s
pe
r
f
o
r
m
e
d
we
l
l
a
n
d
we
r
e
b
a
l
a
nc
e
d
i
n
t
h
e
m
o
de
l
’
s
c
l
a
s
s
if
i
c
a
t
i
o
n
s
.
T
hi
s
f
ur
t
h
e
r
e
x
p
l
a
i
ne
d
t
h
a
t
hi
g
h
r
e
c
a
l
l
wa
s
pa
r
t
i
c
u
l
a
r
ly
c
r
i
t
i
c
a
l
b
e
c
a
us
e
m
i
s
c
l
a
s
s
i
f
yi
ng
a
po
i
s
o
n
o
us
m
u
s
h
r
oo
m
a
s
e
d
i
b
l
e
c
o
ul
d
r
e
s
u
l
t
i
n
s
e
r
io
us
h
e
a
l
t
h
r
i
s
k
s
.
T
h
e
hi
g
h
r
e
c
a
l
l
(
97.
7%
)
i
n
d
i
c
a
t
e
s
t
h
a
t
t
h
e
m
o
de
l
c
o
u
l
d
m
i
n
im
i
z
e
s
uc
h
r
i
s
k
s
.
On
t
h
e
ot
h
e
r
h
a
n
d,
pr
e
c
i
s
i
o
n
(
82.
7%
)
wa
s
g
oo
d
b
ut
c
o
ul
d
b
e
im
p
r
o
v
e
d
to
e
ns
ur
e
f
e
we
r
e
d
i
bl
e
m
us
h
r
o
o
m
s
we
r
e
i
nc
o
r
r
e
c
t
l
y
c
l
a
s
s
if
i
e
d
a
s
po
i
s
o
n
o
us
.
1
−
=
(
2
(
82
.
72
97
.
72
)
(
82
.
72
+
97
.
72
)
)
100
1
−
=
(
2
(
8
0
8
3
.
3
9
8
4
)
(
180
.
44
)
)
100
1
−
=
(
2
44
.
7
9
8
2
6
2
0
2
6
1
5
8
2
8
)
100
1
−
=
(
89
.
5
9
6
5
2
4
0
5
2
3
1
6
5
6
)
100
=
89
.
60%
(
r
o
un
de
d
to
t
w
o
de
c
i
m
a
l
p
l
a
c
e
s
)
(1
4
)
T
o
f
ur
t
h
e
r
de
t
e
r
m
i
ne
t
h
e
de
gr
e
e
o
f
pe
r
f
o
r
m
a
nc
e
o
r
e
f
f
e
c
t
i
v
e
n
e
s
s
o
f
t
h
e
NB
a
l
go
r
i
t
hm
,
K
a
b
uT
e
a
c
h
p
l
o
tt
e
d
a
c
h
a
r
t
o
f
t
h
e
R
OC
c
ur
v
e
a
pp
li
e
d
t
o
t
h
e
t
e
s
t
da
t
a
s
h
o
w
i
n
g
t
h
e
T
P
R
i
n
t
h
e
y
-
a
xi
s
a
ga
i
ns
t
t
h
e
F
P
R
i
n
t
h
e
x
-
a
xi
s
f
o
r
t
h
e
di
f
f
e
r
e
n
t
t
h
r
e
s
h
o
l
ds
a
s
s
h
o
wn
i
n
F
i
gur
e
8.
T
hi
s
h
e
l
pe
d
t
h
e
a
bil
i
t
y
o
f
t
h
e
a
l
go
r
i
t
hm
t
o
d
i
f
f
e
r
e
n
t
i
a
t
e
b
e
t
we
e
n
e
d
i
b
l
e
a
n
d
po
i
s
o
n
o
us
c
l
a
s
s
e
s
i
n
t
h
e
da
t
a
s
e
t
.
F
r
o
m
t
hi
s
R
OC
c
ur
v
e
pr
e
s
e
n
t
e
d,
t
h
e
A
UC
[
4
6]
–
[
48
]
wa
s
s
u
m
m
a
r
i
z
e
d,
c
o
m
put
e
d
us
i
n
g
t
h
e
T
r
a
pe
z
o
i
da
l
ru
l
e
,
a
n
d
o
b
t
a
i
n
e
d
a
s
c
o
r
e
o
f
0.
98.
T
h
e
e
f
f
e
c
t
i
v
e
n
e
s
s
o
f
a
m
o
de
l
u
s
i
ng
t
hi
s
m
e
t
r
i
c
wa
s
m
e
a
s
ur
e
d
f
r
o
m
0
to
1.
A
hi
g
h
e
r
AU
C
s
c
o
r
e
(
c
l
o
s
e
to
1)
i
n
d
i
c
a
t
e
d
b
e
t
t
e
r
m
o
de
l
pe
r
f
o
r
m
a
nc
e
,
l
i
k
e
t
h
e
s
t
ud
y
o
f
[
49]
whi
c
h
a
ll
t
h
e
f
o
ur
m
o
de
l
s
u
s
e
d
e
xhi
b
i
t
e
d
a
hi
g
h
AU
C
s
c
o
r
e
o
f
a
b
o
v
e
0.
90.
I
n
t
hi
s
s
t
ud
y
,
w
i
t
h
t
h
e
AU
C
v
a
l
u
e
c
o
m
put
e
d,
i
t
c
l
e
a
r
l
y
s
h
o
we
d
t
h
a
t
t
h
e
NB
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
o
de
l
wa
s
“
e
x
c
e
l
l
e
n
t
”
i
n
c
l
a
s
s
i
f
yi
ng
be
t
we
e
n
e
d
i
ble
a
n
d
po
i
s
o
n
o
us
m
u
s
h
r
oo
m
s
a
s
i
n
d
i
c
a
t
e
d
i
n
T
a
bl
e
3.
F
ur
t
h
e
r
m
o
r
e
,
t
h
e
a
c
hi
e
v
e
d
A
UC
s
c
o
r
e
m
e
a
n
s
t
h
a
t
t
h
e
r
e
i
s
a
v
e
r
y
hi
g
h
pr
o
b
a
bil
i
t
y
(
98%
)
t
h
a
t
t
h
e
NB
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
o
de
l
c
o
r
r
e
c
t
l
y
d
i
s
t
i
n
gu
i
s
h
e
s
a
r
a
n
do
m
ly
c
h
o
s
e
n
e
d
i
bl
e
m
us
h
r
o
o
m
a
n
d
a
r
a
n
do
m
ly
c
h
o
s
e
n
po
i
s
o
no
us
o
n
e
.
G
i
v
e
n
t
hi
s
hi
g
h
A
UC
s
c
o
r
e
,
t
hi
s
s
t
ud
y
s
t
r
o
n
g
ly
a
gr
e
e
s
w
i
t
h
t
h
e
m
o
de
l
’
s
a
bi
li
t
y
t
o
c
or
r
e
c
t
l
y
c
l
a
s
s
if
y
m
u
s
h
r
oo
m
s
.
Ho
we
v
e
r
,
t
h
e
pr
e
s
e
n
t
s
t
udy
s
t
i
ll
s
ugge
s
t
s
f
ur
t
h
e
r
v
a
li
da
t
i
o
n
a
n
d
pot
e
n
t
i
a
l
im
pr
o
v
e
m
e
n
t
s
f
o
r
e
v
e
n
gr
e
a
t
e
r
r
e
l
i
a
bil
i
t
y
,
e
s
pe
c
i
a
ll
y
i
n
r
e
a
l
-
wo
r
l
d
a
pp
l
i
c
a
t
i
o
ns
.
F
i
gur
e
8.
T
h
e
t
e
s
t
i
n
g
da
t
a
pl
o
tt
e
d
i
n
t
h
e
R
OC
c
ur
ve
Evaluation Warning : The document was created with Spire.PDF for Python.