I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
rm
a
t
ics a
nd
Co
m
m
un
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
15
,
No
.
4
,
Dec
em
b
er
20
26
,
p
p
.
1
5
6
1
~1
5
7
6
I
SS
N:
2252
-
8
7
7
6
,
DOI
:
1
0
.
1
1
5
9
1
/iji
ct
.
v15
i
4
.
pp
1
5
6
1
-
1
5
7
6
1561
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ict.
ia
esco
r
e.
co
m
Dev
elo
pment of
K
a
buTea
ch:
a
ch
a
ra
cter
-
ba
sed d
ec
isio
n suppo
rt
sy
stem f
o
r mush
r
o
o
m cla
ss
ificatio
n
Vilcho
r
G
.
P
er
did
o
1
,
M
elin
d
a
A.
B
enins
ig
2
,
Da
niel
M
a
rv
in B
.
Ra
m
el
3
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
C
o
l
l
e
g
e
o
f
I
n
f
o
r
ma
t
i
o
n
T
e
c
h
n
o
l
o
g
y
E
d
u
c
a
t
i
o
n
,
N
u
e
v
a
V
i
z
c
a
y
a
S
t
a
t
e
U
n
i
v
e
r
s
i
t
y
,
B
a
y
o
m
b
o
n
g
,
P
h
i
l
i
p
p
i
n
e
s
2
C
o
l
l
e
g
e
o
f
I
n
f
o
r
ma
t
i
o
n
Te
c
h
n
o
l
o
g
y
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
y
o
f
t
h
e
C
o
r
d
i
l
l
e
r
a
s,
B
a
g
u
i
o
C
i
t
y
,
P
h
i
l
i
p
p
i
n
e
s
3
D
e
p
a
r
t
me
n
t
o
f
N
a
t
u
r
a
l
S
c
i
e
n
c
e
s,
C
o
l
l
e
g
e
o
f
A
r
t
s
a
n
d
S
c
i
e
n
c
e
s,
N
u
e
v
a
V
i
z
c
a
y
a
S
t
a
t
e
U
n
i
v
e
r
si
t
y
,
B
a
y
o
m
b
o
n
g
,
P
h
i
l
i
p
p
i
n
e
s
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
1
2
,
2
0
2
5
R
ev
is
ed
J
u
l 7
,
2
0
2
6
Acc
ep
ted
J
u
l 1
9
,
2
0
2
6
M
u
sh
r
o
o
m
m
isi
d
e
n
ti
fica
ti
o
n
re
m
a
in
s
a
p
e
rsiste
n
t
p
u
b
li
c
h
e
a
lt
h
ris
k
i
n
r
u
ra
l
c
o
m
m
u
n
it
ies
,
c
a
u
sin
g
p
o
is
o
n
i
n
g
a
n
d
fa
talit
ies
wo
rl
d
wid
e
.
T
h
is
stu
d
y
p
re
se
n
ts
Ka
b
u
Tea
c
h
,
a
we
b
-
b
a
se
d
d
e
c
isio
n
su
p
p
o
r
t
sy
ste
m
(DSS
)
fo
r
c
las
sify
in
g
m
u
sh
ro
o
m
s
a
s
e
d
ib
le
o
r
p
o
iso
n
o
u
s.
T
h
e
sy
ste
m
is
trai
n
e
d
o
n
t
h
e
UCI
m
u
sh
ro
o
m
d
a
tas
e
t
(8
,
1
2
4
in
sta
n
c
e
s,
2
2
c
a
teg
o
r
ica
l
m
o
rp
h
o
lo
g
ica
l
a
tt
rib
u
tes
)
u
sin
g
t
h
e
c
a
te
g
o
r
ica
l
Na
ïv
e
Ba
y
e
s
a
lg
o
rit
h
m
wit
h
Lap
lac
e
sm
o
o
th
i
n
g
(α
=
1
.
0
)
t
h
ro
u
g
h
t
h
e
R
u
b
i
x
M
L
fra
m
e
wo
rk
.
Th
e
sy
ste
m
e
m
p
lo
y
e
d
a
h
y
b
ri
d
in
tera
c
ti
v
e
stru
c
t
u
re
a
n
d
e
v
e
n
t
-
d
ri
v
e
n
a
rc
h
it
e
c
tu
re
with
t
h
e
m
o
d
e
l
–
v
iew
–
c
o
n
tro
ll
e
r
p
a
t
tern
,
e
n
a
b
li
n
g
re
a
l
-
ti
m
e
c
las
sifica
ti
o
n
,
h
u
m
a
n
-
in
-
th
e
-
l
o
o
p
e
x
p
e
rt
v
a
li
d
a
ti
o
n
,
a
n
d
S
M
S
-
b
a
se
d
re
su
lt
d
e
li
v
e
ry
fo
r
lo
w
-
c
o
n
n
e
c
t
iv
it
y
ru
ra
l
e
n
v
iro
n
m
e
n
ts.
M
o
d
e
l
e
v
a
lu
a
ti
o
n
u
sin
g
a
7
0
:
3
0
h
o
ld
o
u
t
m
e
th
o
d
a
c
h
iev
e
d
9
9
.
6
3
%
a
c
c
u
ra
c
y
,
wh
il
e
5
-
f
o
ld
c
ro
ss
-
v
a
li
d
a
ti
o
n
y
ield
e
d
a
m
e
a
n
a
c
c
u
ra
c
y
o
f
9
9
.
6
6
%
(±0
.
1
1
1
8
%
).
P
e
rfo
rm
a
n
c
e
m
e
tri
c
s,
in
c
lu
d
i
n
g
a
c
o
n
f
u
si
o
n
m
a
tri
x
,
p
e
r
-
fo
ld
re
su
lt
s
with
sta
n
d
a
rd
d
e
v
iatio
n
s,
p
re
c
isio
n
,
re
c
a
ll
,
F
1
-
s
c
o
re
,
a
n
d
sp
e
c
ifi
c
it
y
,
c
o
n
f
irm
m
o
d
e
l
ro
b
u
stn
e
ss
,
a
tt
ri
b
u
ted
to
t
h
e
c
lea
n
a
n
d
d
isc
rimin
a
ti
v
e
c
a
teg
o
rica
l
fe
a
tu
r
e
s
o
f
th
e
d
a
tas
e
t
a
n
d
th
e
u
se
o
f
Lap
lac
e
sm
o
o
th
i
n
g
.
Us
a
b
il
it
y
tes
ti
n
g
with
1
0
2
re
sp
o
n
d
e
n
ts
u
sin
g
th
e
USE
q
u
e
sti
o
n
n
a
ire
a
c
h
iev
e
d
a
g
ra
n
d
m
e
a
n
o
f
5
.
9
3
(a
g
re
e
).
Re
li
a
n
c
e
o
n
th
e
N
o
rth
Am
e
rica
n
UCI
d
a
tas
e
t
li
m
it
s
d
irec
t
P
h
il
i
p
p
i
n
e
a
p
p
li
c
a
b
il
it
y
;
f
u
tu
re
wo
rk
will
fo
c
u
s
o
n
lo
c
a
ll
y
so
u
rc
e
d
,
e
x
p
e
rt
-
lab
e
led
d
a
tas
e
ts.
Ka
b
u
Tea
c
h
is
a
re
li
a
b
le,
in
terp
re
tab
le,
a
n
d
u
se
r
-
c
e
n
tere
d
DSS
th
a
t
b
ri
d
g
e
s
trad
i
ti
o
n
a
l
k
n
o
wle
d
g
e
a
n
d
m
o
d
e
rn
ICT
fo
r
sa
fe
r
ru
ra
l
m
u
sh
r
o
o
m
fo
ra
g
in
g
.
K
ey
w
o
r
d
s
:
Dec
is
io
n
s
u
p
p
o
r
t sy
s
tem
Kab
u
T
ea
ch
L
ap
lace
s
m
o
o
th
in
g
Ma
ch
in
e
lear
n
in
g
Mu
s
h
r
o
o
m
class
if
icatio
n
MV
C
ar
ch
itectu
r
al
p
atter
n
Naïv
e
B
ay
es a
lg
o
r
ith
m
UC
I
m
u
s
h
r
o
o
m
d
ataset
USE
q
u
esti
o
n
n
air
e
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
:
Vilch
o
r
G.
Per
d
id
o
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
C
o
lleg
e
o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
E
d
u
ca
tio
n
Nu
ev
a
Vizc
ay
a
State
Un
iv
e
r
s
ity
B
ay
o
m
b
o
n
g
,
Nu
ev
a
Vizc
ay
a,
Ph
ilip
p
in
es
E
m
ail:
v
g
p
er
d
id
o
@
n
v
s
u
.
ed
u
.
p
h
1.
I
NT
RO
D
UCT
I
O
N
Mu
s
h
r
o
o
m
s
ar
e
g
lo
b
ally
r
e
co
g
n
ized
f
o
r
th
eir
n
u
tr
itio
n
al
an
d
m
ed
icin
al
p
r
o
p
e
r
ties
,
p
r
o
v
i
d
in
g
ca
lciu
m
,
p
h
o
s
p
h
o
r
u
s
,
v
itam
in
s
,
p
r
o
tein
s
,
an
d
an
tio
x
i
d
an
t
s
,
a
n
d
co
n
tr
i
b
u
tin
g
t
o
tr
ea
tm
en
ts
f
o
r
illn
ess
es
s
u
ch
as
ca
n
ce
r
an
d
o
b
esit
y
[
1
]
.
Ho
w
ev
er
,
m
u
s
h
r
o
o
m
c
o
n
s
u
m
p
tio
n
p
o
s
es
s
ig
n
if
ican
t
p
u
b
lic
h
e
alth
r
is
k
s
,
as
s
o
m
e
s
p
ec
ies
ar
e
p
o
is
o
n
o
u
s
a
n
d
ca
n
ca
u
s
e
s
ev
er
e
illn
ess
o
r
d
ea
th
wh
en
m
is
id
en
tifie
d
[
2
]
.
B
etwe
en
1
9
9
9
an
d
2
0
1
6
,
th
e
Un
ited
States
r
ec
o
r
d
ed
o
v
er
1
3
3
,
7
0
0
m
u
s
h
r
o
o
m
p
o
i
s
o
n
in
g
ca
s
es,
wh
ile
Ger
m
an
y
d
o
cu
m
e
n
ted
2
2
f
atalities
f
r
o
m
2
0
0
0
to
2
0
1
8
[
3
]
.
I
n
th
e
Ph
ilip
p
in
es,
p
o
is
o
n
i
n
g
in
cid
e
n
ts
r
em
ain
p
r
e
v
alen
t,
with
r
ec
en
t
ca
s
es
in
Kalin
g
a,
B
en
g
u
et,
an
d
M
o
u
n
t
ain
Pro
v
in
ce
a
f
f
ec
tin
g
d
o
ze
n
s
o
f
in
d
iv
id
u
als,
in
clu
d
in
g
c
h
ild
r
en
[
4
]
.
I
n
No
r
t
h
er
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
15
,
No
.
4
,
Dec
em
b
er
20
26
:
1
5
6
1
-
1
5
7
6
1562
L
u
zo
n
,
p
a
r
ticu
lar
ly
Nu
ev
a
Vi
zc
ay
a,
m
u
s
h
r
o
o
m
f
o
r
a
g
in
g
r
e
m
ain
s
an
im
p
o
r
tan
t
liv
elih
o
o
d
an
d
f
o
o
d
s
o
u
r
ce
f
o
r
f
ar
m
er
s
,
in
d
i
g
en
o
u
s
g
r
o
u
p
s
,
a
n
d
lo
w
-
in
c
o
m
e
h
o
u
s
eh
o
ld
s
.
Mu
s
h
r
o
o
m
id
e
n
tific
atio
n
in
m
an
y
r
u
r
al
co
m
m
u
n
ities
ac
r
o
s
s
th
e
Ph
ilip
p
in
es
lar
g
ely
d
ep
en
d
s
o
n
in
d
ig
en
o
u
s
k
n
o
wled
g
e
an
d
m
o
r
p
h
o
lo
g
ical
o
b
s
er
v
atio
n
.
Pra
ctice
s
d
o
cu
m
en
te
d
in
B
ico
l
N
atu
r
al
Par
k
an
d
Aeta
s
ettlem
en
ts
in
C
en
tr
al
L
u
zo
n
s
h
o
w
r
elian
ce
o
n
l
o
ca
l
te
r
m
in
o
lo
g
y
,
p
r
ep
a
r
atio
n
r
itu
al
s
,
an
d
g
en
er
atio
n
al
k
n
o
wled
g
e
[
5
]
,
[
6
]
.
At
th
e
s
am
e
tim
e,
f
o
l
k
lo
r
e,
s
u
ch
as
th
e
ass
o
ciatio
n
o
f
m
u
s
h
r
o
o
m
g
r
o
wth
with
lig
h
tn
in
g
,
is
ev
id
en
t in
Gad
d
an
g
tr
ad
itio
n
s
[
7]
.
Alth
o
u
g
h
cu
ltu
r
ally
s
ig
n
if
ican
t,
th
ese
p
r
ac
tices r
ely
h
ea
v
ily
o
n
v
is
ib
le
tr
aits
s
u
ch
as
co
lo
r
,
s
ize,
a
n
d
s
h
ap
e,
m
ak
in
g
th
e
m
v
u
ln
er
a
b
le
to
m
is
id
en
tific
atio
n
.
T
o
x
ic
s
p
ec
ies
o
f
ten
r
esem
b
le
ed
ib
le
v
ar
ieties
[
8
]
,
an
d
im
m
a
tu
r
e
o
r
d
am
a
g
ed
s
p
ec
im
en
s
f
u
r
th
er
r
ed
u
ce
th
e
r
eliab
ilit
y
o
f
m
o
r
p
h
o
lo
g
ical
cu
es
[
9
]
.
W
h
ile
m
o
lecu
lar
tec
h
n
iq
u
es
s
u
ch
as
DNA
b
ar
c
o
d
in
g
o
f
f
er
h
ig
h
er
ac
c
u
r
ac
y
[
8
]
,
[
1
0
]
,
t
h
ese
m
eth
o
d
s
r
em
ain
im
p
r
ac
tical
in
r
u
r
al
s
ettin
g
s
.
T
h
e
ch
allen
g
e
ex
ten
d
s
g
lo
b
ally
:
T
h
ailan
d
r
ec
o
r
d
s
an
n
u
al
p
o
is
o
n
i
n
g
f
atalities
[
1
1
]
,
th
e
d
ea
th
ca
p
m
u
s
h
r
o
o
m
ac
c
o
u
n
ts
f
o
r
a
s
ig
n
if
ican
t
p
r
o
p
o
r
tio
n
o
f
Ger
m
a
n
m
u
s
h
r
o
o
m
d
ea
th
s
[
1
2
]
,
an
d
t
h
e
C
h
in
a
ce
n
ter
s
f
o
r
d
is
ea
s
e
co
n
tr
o
l
an
d
p
r
ev
en
ti
o
n
(
C
DC
)
r
ep
o
r
te
d
5
0
5
p
o
is
o
n
in
g
ca
s
es
in
2
0
2
3
in
v
o
lv
in
g
9
7
to
x
ic
s
p
ec
ies
[
1
3
]
.
So
m
e
co
u
n
tr
ies
m
itig
ate
th
ese
r
is
k
s
th
r
o
u
g
h
ex
p
e
r
t
co
n
s
u
ltatio
n
s
er
v
ices,
s
u
ch
as
f
r
ee
m
y
co
l
o
g
ical
ev
al
u
atio
n
s
in
I
taly
[
1
4
]
.
T
h
ese
g
l
o
b
al
an
d
l
o
ca
l
s
ce
n
ar
io
s
em
p
h
asize
th
e
u
r
g
en
cy
o
f
ac
cu
r
ate,
ac
ce
s
s
ib
le,
an
d
f
ield
-
u
s
ab
le
class
if
icatio
n
to
o
ls
.
Ad
v
an
ce
s
in
d
ig
ital
tech
n
o
l
o
g
y
a
n
d
m
ac
h
in
e
lear
n
in
g
(
ML
)
p
r
o
v
id
e
p
r
o
m
is
in
g
s
o
lu
tio
n
s
.
ML
alg
o
r
ith
m
s
ca
n
an
aly
ze
s
tr
u
ctu
r
ed
d
atas
ets,
d
etec
t
p
atter
n
s
,
a
n
d
g
en
er
ate
ac
cu
r
ate
p
r
ed
ictio
n
s
with
o
u
t
ex
p
licit
p
r
o
g
r
a
m
m
in
g
[
1
5
]
.
T
h
eir
ap
p
licab
ilit
y
h
as
b
ee
n
d
em
o
n
s
tr
a
ted
ac
r
o
s
s
h
ea
lth
ca
r
e,
ag
r
icu
lt
u
r
e,
cy
b
e
r
s
ec
u
r
ity
,
an
d
s
m
ar
t
s
y
s
tem
s
[
1
6
]
–
[
2
0
]
.
I
n
m
y
c
o
lo
g
y
,
ch
ar
ac
ter
-
b
ased
class
if
icatio
n
u
s
in
g
m
o
r
p
h
o
lo
g
ical
tr
aits
s
u
ch
as
ca
p
s
h
ap
e,
g
ill
attac
h
m
en
t,
a
n
d
s
p
o
r
e
co
lo
r
h
as
p
r
o
v
en
ef
f
ec
tiv
e
in
d
is
tin
g
u
is
h
in
g
ed
ib
le
f
r
o
m
p
o
is
o
n
o
u
s
m
u
s
h
r
o
o
m
s
[
2
1
]
,
[
2
2
]
.
Stu
d
ie
s
ap
p
ly
in
g
Naïv
e
B
ay
es,
K
-
n
ea
r
est
n
eig
h
b
o
r
s
,
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
to
th
e
UC
I
m
u
s
h
r
o
o
m
d
ataset
h
av
e
ac
h
iev
ed
h
ig
h
ac
cu
r
ac
y
[
2
3
]
,
[
2
4
]
,
with
Naïv
e
B
ay
es
s
h
o
win
g
r
o
b
u
s
tn
ess
,
in
ter
p
r
etab
ilit
y
,
an
d
ef
f
icien
c
y
f
o
r
ca
teg
o
r
ical
d
ata
[
2
5
]
,
[
2
6
]
.
Ad
d
itio
n
al
en
h
a
n
ce
m
en
ts
,
s
u
ch
as
f
ea
tu
r
e
au
g
m
en
tatio
n
,
d
im
en
s
io
n
ality
r
ed
u
ctio
n
,
a
n
d
ex
p
lain
ab
le
f
r
a
m
ewo
r
k
s
,
h
av
e
f
u
r
th
e
r
im
p
r
o
v
ed
its
p
er
f
o
r
m
a
n
ce
[
2
7
]
,
[
2
8
]
.
B
ey
o
n
d
class
if
icatio
n
m
o
d
els,
s
ev
er
al
m
u
s
h
r
o
o
m
-
r
elate
d
d
e
cisi
o
n
s
u
p
p
o
r
t
s
y
s
tem
s
(
DSS)
h
av
e
b
ee
n
d
ev
elo
p
e
d
:
a
m
u
s
h
r
o
o
m
d
ia
g
n
o
s
is
ass
i
s
tan
ce
s
y
s
t
em
(
M
DAS)
[
2
9
]
,
a
m
o
b
ile
DSS
ac
h
iev
in
g
9
4
.
1
9
%
ac
cu
r
ac
y
in
T
h
ailan
d
[
3
0
]
,
an
d
in
ter
n
et
o
f
th
in
g
s
(
I
oT
)
-
e
n
a
b
led
s
y
s
tem
s
f
o
r
s
m
ar
t
m
u
s
h
r
o
o
m
f
ar
m
i
n
g
[
3
1
]
.
Ho
wev
er
,
th
ese
s
y
s
tem
s
p
r
im
ar
ily
f
o
c
u
s
o
n
al
g
o
r
ith
m
ic
p
e
r
f
o
r
m
a
n
ce
o
r
c
o
n
tr
o
lled
en
v
ir
o
n
m
en
ts
an
d
lac
k
in
teg
r
atio
n
with
r
ea
l
-
wo
r
ld
co
n
s
tr
ain
ts
s
u
ch
as
lim
ited
co
n
n
ec
tiv
ity
,
u
s
er
ac
ce
s
s
ib
ilit
y
,
an
d
ex
p
er
t
v
alid
atio
n
.
I
n
th
e
Ph
ilip
p
in
e
co
n
tex
t,
r
esear
ch
o
n
DSS
in
teg
r
atio
n
r
em
ain
s
lim
ited
,
f
o
c
u
s
in
g
lar
g
ely
o
n
s
p
ec
ies
d
o
cu
m
e
n
tatio
n
[
5
]
,
[
8
]
,
[
9
]
,
with
o
n
ly
a
f
ew
ex
p
lo
r
in
g
ML
-
b
as
ed
class
if
icatio
n
[
3
2
]
,
[
3
3]
,
an
d
ex
is
tin
g
s
y
s
tem
s
lack
in
g
in
teg
r
ated
d
ec
is
io
n
s
u
p
p
o
r
t
[
3
4
]
.
Un
lik
e
p
r
io
r
s
tu
d
ies
th
at
p
r
i
m
ar
ily
em
p
h
asize
alg
o
r
ith
m
i
c
p
er
f
o
r
m
an
ce
,
th
is
s
tu
d
y
f
o
cu
s
es
o
n
s
y
s
tem
-
lev
el
in
n
o
v
atio
n
b
y
d
ev
elo
p
in
g
a
d
ep
lo
y
a
b
le
an
d
u
s
er
-
ce
n
ter
ed
DSS.
Sp
ec
if
ically
,
Kab
u
T
ea
ch
in
tr
o
d
u
ce
s
th
r
ee
k
e
y
co
n
tr
ib
u
tio
n
s
b
ey
o
n
d
th
e
class
if
icatio
n
en
g
in
e:
(
1
)
a
h
y
b
r
i
d
ar
ch
it
ec
tu
r
al
f
r
am
ewo
r
k
co
m
b
in
in
g
in
ter
ac
tiv
e
s
tr
u
ctu
r
e
an
d
ev
en
t
-
d
r
iv
e
n
ar
ch
itectu
r
e
with
th
e
m
o
d
el
-
v
iew
-
c
o
n
tr
o
l
ler
(
MV
C
)
p
atter
n
,
en
ab
lin
g
m
o
d
u
lar
an
d
m
ain
tain
ab
le
s
y
s
tem
d
esig
n
;
(
2
)
an
SMS
-
b
ased
d
ec
is
io
n
s
u
p
p
o
r
t
m
ec
h
an
is
m
im
p
lem
en
ted
v
ia
th
e
Sem
ap
h
o
r
e
ap
p
licatio
n
p
r
o
g
r
am
m
i
n
g
in
ter
f
ac
e
(
API
)
,
en
s
u
r
in
g
class
if
icatio
n
r
esu
lt
d
eliv
er
y
ev
e
n
in
lo
w
-
co
n
n
ec
tiv
ity
r
u
r
al
e
n
v
ir
o
n
m
en
ts
—
a
ca
p
ab
ilit
y
ab
s
en
t
in
c
o
m
p
ar
a
b
le
s
y
s
tem
s
s
u
ch
as
MD
AS
[
2
9
]
o
r
th
e
T
h
ailan
d
m
o
b
ile
DSS
[
3
0
]
;
an
d
(
3
)
a
h
u
m
an
-
in
-
th
e
-
lo
o
p
ex
p
e
r
t
v
al
id
atio
n
lay
er
th
r
o
u
g
h
th
e
m
u
s
h
r
o
o
m
r
eso
u
r
ce
s
r
esea
r
ch
an
d
d
ev
elo
p
m
en
t
ce
n
ter
(
MRR
D
C
)
,
wh
er
e
m
y
co
lo
g
is
ts
r
ev
iew
an
d
f
in
alize
ML
-
g
en
er
ated
class
if
icatio
n
s
b
ef
o
r
e
r
esu
lts
ar
e
co
m
m
u
n
ic
ated
to
m
u
s
h
r
o
o
m
p
ick
er
s
,
s
er
v
in
g
as
a
cr
itical
s
af
ety
ch
ec
k
ag
ain
s
t
f
alse
n
eg
ativ
es.
T
h
ese
co
n
tr
ib
u
tio
n
s
ex
ten
d
b
ey
o
n
d
class
if
icatio
n
ac
cu
r
ac
y
,
em
p
h
asizin
g
r
ea
l
-
wo
r
ld
ap
p
licab
ilit
y
,
ac
ce
s
s
ib
ilit
y
,
an
d
s
af
ety
in
r
u
r
al
Ph
i
lip
p
in
e
co
m
m
u
n
ities
.
T
h
is
s
tu
d
y
ad
d
r
ess
es
th
e
id
en
tifie
d
g
ap
b
y
d
ev
el
o
p
in
g
Kab
u
T
ea
ch
,
a
c
h
ar
ac
ter
-
b
ased
DSS
f
o
r
m
u
s
h
r
o
o
m
class
if
icatio
n
.
T
h
e
s
y
s
tem
in
teg
r
ates
a
Naïv
e
B
ay
es
class
if
ier
tr
ain
ed
o
n
th
e
Un
iv
er
s
ity
o
f
C
alif
o
r
n
ia
(
UC
I
)
m
u
s
h
r
o
o
m
d
ataset
with
in
a
h
y
b
r
id
ar
ch
ite
ctu
r
al
f
r
am
ewo
r
k
alig
n
ed
with
MV
C
an
d
clien
t
–
s
er
v
er
p
atter
n
s
.
User
s
ca
n
in
p
u
t
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
es
s
u
ch
as
ca
p
s
h
a
p
e,
g
ill
ty
p
e,
a
n
d
h
ab
itat
to
o
b
tain
im
m
ed
iate
class
if
icatio
n
r
esu
l
ts
,
wh
ich
ar
e
f
u
r
th
er
v
alid
ate
d
b
y
ex
p
e
r
ts
.
B
y
b
r
id
g
in
g
tr
a
d
itio
n
al
k
n
o
wled
g
e
an
d
m
o
d
er
n
I
C
T
,
Kab
u
T
ea
ch
aim
s
to
p
r
o
m
o
te
s
af
er
m
u
s
h
r
o
o
m
f
o
r
ag
in
g
,
r
e
d
u
ce
p
o
is
o
n
in
g
in
ci
d
en
t
s
,
an
d
s
u
p
p
o
r
t su
s
tain
ab
le
f
o
o
d
p
r
ac
t
ices in
r
u
r
al
co
m
m
u
n
ities
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
is
s
tu
d
y
ad
o
p
ted
a
s
tr
u
ctu
r
ed
m
eth
o
d
o
l
o
g
y
f
o
r
th
e
d
esig
n
,
d
ev
elo
p
m
en
t,
an
d
ev
alu
at
io
n
o
f
th
e
Kab
u
T
ea
ch
DSS.
T
h
e
o
v
er
all
p
r
o
ce
s
s
was
g
u
id
e
d
b
y
th
e
r
ap
id
ap
p
licatio
n
d
e
v
elo
p
m
e
n
t
(
R
AD)
m
o
d
el,
wh
ich
allo
wed
iter
ativ
e
p
r
o
to
ty
p
in
g
an
d
co
n
tin
u
o
u
s
u
s
er
f
ee
d
b
ac
k
,
an
d
was
f
u
r
th
er
co
m
p
lem
e
n
ted
b
y
th
e
d
esig
n
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
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
Dev
elo
p
men
t o
f Ka
b
u
Tea
c
h
:
a
ch
a
r
a
cter
-
b
a
s
ed
d
ec
is
io
n
s
u
p
p
o
r
t sys
tem
fo
r
… (
V
ilch
o
r
G.
P
erd
id
o
)
1563
th
in
k
in
g
p
r
o
ce
s
s
to
en
s
u
r
e
a
u
s
er
-
ce
n
ter
ed
s
o
lu
tio
n
.
T
h
e
m
eth
o
d
o
lo
g
y
in
clu
d
e
d
d
ata
c
o
llectio
n
,
p
r
ep
r
o
ce
s
s
in
g
,
m
o
d
el
tr
ain
in
g
,
s
y
s
tem
ar
ch
itectu
r
e
d
esig
n
,
iter
ativ
e
p
r
o
to
ty
p
i
n
g
,
test
in
g
,
d
e
p
lo
y
m
e
n
t,
an
d
u
s
ab
ilit
y
ev
alu
atio
n
.
2
.
1
.
Resea
rc
h
des
i
gn
T
h
is
s
tu
d
y
co
m
b
i
n
ed
q
u
a
n
titativ
e
an
d
d
e
v
elo
p
m
e
n
tal
r
esea
r
ch
d
esig
n
s
.
T
h
e
q
u
an
titativ
e
ap
p
r
o
ac
h
m
ea
s
u
r
ed
s
y
s
tem
u
s
ab
ilit
y
th
r
o
u
g
h
s
tr
u
ctu
r
ed
s
u
r
v
ey
s
u
s
in
g
th
e
u
s
ef
u
ln
ess
,
s
atis
f
ac
tio
n
,
an
d
ea
s
e
o
f
u
s
e
(
USE
)
q
u
esti
o
n
n
air
e
t
ool
[
3
5
]
,
wh
ile
th
e
d
ev
elo
p
m
en
tal
a
p
p
r
o
ac
h
f
o
c
u
s
ed
o
n
co
n
s
tr
u
ctin
g
a
f
u
n
ctio
n
al
DSS
p
o
wer
ed
b
y
th
e
Naïv
e
B
ay
es
alg
o
r
ith
m
,
s
elec
ted
f
o
r
its
ef
f
icien
cy
in
h
an
d
li
n
g
ca
teg
o
r
ic
al
d
ata
an
d
p
r
o
v
e
n
ac
cu
r
ac
y
in
m
u
s
h
r
o
o
m
class
if
icatio
n
[
2
3
]
.
2
.
2
.
So
f
t
wa
re
dev
elo
p
m
ent
m
o
del
T
h
e
s
tu
d
y
ad
o
p
ted
th
e
R
AD
m
o
d
el
s
h
o
wn
in
Fig
u
r
e
1
as
th
e
p
r
im
a
r
y
s
o
f
twar
e
d
ev
elo
p
m
en
t
m
eth
o
d
o
l
o
g
y
,
em
p
h
asizin
g
it
er
ativ
e
p
r
o
to
ty
p
in
g
,
ac
tiv
e
u
s
er
in
v
o
lv
em
en
t,
an
d
f
aster
d
e
li
v
er
y
o
f
f
u
n
ctio
n
al
s
y
s
tem
s
[
3
6
]
–
[
4
0
]
.
T
h
e
p
r
o
ce
s
s
b
eg
an
with
q
u
ick
d
esig
n
a
n
d
r
e
q
u
ir
em
e
n
t
g
at
h
er
in
g
,
f
o
llo
wed
b
y
cy
cles
o
f
p
r
o
to
ty
p
in
g
,
u
s
er
test
in
g
,
an
d
r
ef
in
em
en
t.
E
ac
h
cy
cle
in
v
o
lv
ed
m
u
s
h
r
o
o
m
ex
p
er
ts
an
d
tr
ai
n
ed
p
ick
e
r
s
,
wh
o
s
e
f
ee
d
b
ac
k
g
u
id
e
d
im
p
r
o
v
em
e
n
ts
in
f
u
n
ctio
n
ality
a
n
d
u
s
ab
ilit
y
.
Alo
n
g
with
R
AD,
th
is
s
tu
d
y
a
p
p
lied
th
e
f
iv
e
s
tag
es
o
f
t
h
e
d
esig
n
th
in
k
in
g
f
r
am
ew
o
r
k
,
as
illu
s
tr
ated
in
Fig
u
r
e
2
,
to
e
n
s
u
r
e
a
u
s
er
-
ce
n
ter
ed
an
d
iter
ativ
e
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
[
4
1
]
,
[
4
2
]
.
User
in
s
ig
h
ts
f
r
o
m
th
e
em
p
ath
ize
an
d
d
e
f
in
e
p
h
ases
wer
e
tr
an
s
lated
in
to
s
y
s
tem
r
e
q
u
ir
em
en
ts
th
r
o
u
g
h
in
te
r
v
iew
s
an
d
s
u
r
v
ey
s
[
4
3
]
.
T
h
e
I
d
ea
te
a
n
d
Pro
t
o
ty
p
e
p
h
a
s
es
p
r
o
d
u
ce
d
a
n
d
r
ef
in
ed
s
o
lu
tio
n
co
n
ce
p
ts
u
s
in
g
u
s
e
ca
s
e
s
,
wir
ef
r
am
es,
an
d
f
u
n
ctio
n
al
m
o
d
u
les
[
4
4
]
,
[
4
5
]
b
u
ilt
with
L
ar
a
v
el,
B
o
o
ts
tr
ap
,
an
d
R
u
b
ix
ML
.
Sy
s
tem
p
er
f
o
r
m
an
ce
an
d
u
s
ab
ilit
y
wer
e
v
alid
ated
in
t
h
e
test
s
tag
e.
Fig
u
r
e
1
.
T
h
e
R
AD
s
o
f
twar
e
d
ev
elo
p
m
en
t lif
e
cy
cle
m
o
d
el
Fig
u
r
e
2
.
T
h
e
f
iv
e
s
t
ag
es o
f
th
e
d
esig
n
th
in
k
i
n
g
p
r
o
ce
s
s
f
r
am
ewo
r
k
2
.
3
.
Da
t
a
s
o
urce
a
nd
prepro
ce
s
s
ing
T
h
e
s
tu
d
y
r
elied
o
n
th
e
UC
I
m
u
s
h
r
o
o
m
d
ataset
[
4
6
]
,
ac
ce
s
s
ed
f
r
o
m
Kag
g
le
[
4
7
]
,
co
n
s
is
tin
g
o
f
8
,
1
2
4
in
s
tan
ce
s
with
2
2
ca
teg
o
r
ical
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
es,
in
cl
u
d
in
g
ca
p
s
h
ap
e
,
g
ill
s
ize,
an
d
s
p
o
r
e
p
r
in
t
co
l
o
r
.
T
h
is
d
ataset
was
p
r
e
-
p
r
o
ce
s
s
ed
u
s
in
g
Py
th
o
n
in
J
u
p
y
ter
No
t
eb
o
o
k
,
co
n
f
ir
m
e
d
to
h
av
e
n
o
m
is
s
in
g
v
alu
es,
an
d
ex
h
ib
ited
a
b
alan
ce
d
d
is
tr
ib
u
tio
n
o
f
ed
ib
le
(
5
2
%)
an
d
p
o
is
o
n
o
u
s
(
4
8
%)
class
es.
Sin
ce
th
e
Ph
ilip
p
in
es d
o
es n
o
t
y
et
p
r
o
v
id
e
a
d
ig
ital
an
d
ML
-
r
ea
d
y
m
u
s
h
r
o
o
m
d
ataset,
th
e
m
o
r
p
h
o
lo
g
ical
attr
ib
u
tes
wer
e
v
alid
ated
with
t
h
e
MRR
D
C
o
f
Nu
ev
a
Vizc
ay
a
Stat
e
Un
iv
er
s
ity
(
NVSU
)
to
co
n
f
ir
m
th
eir
r
elev
an
ce
f
o
r
t
h
e
class
if
icatio
n
o
f
lo
ca
lly
f
o
r
a
g
ed
s
p
ec
ies.
Emp
h
a
t
h
i
z
e
D
e
f
i
n
e
I
d
e
a
t
e
P
r
o
t
o
t
y
p
e
Te
st
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
15
,
No
.
4
,
Dec
em
b
er
20
26
:
1
5
6
1
-
1
5
7
6
1564
I
t
is
ac
k
n
o
wled
g
ed
th
at
th
e
U
C
I
m
u
s
h
r
o
o
m
d
ataset
r
ep
r
esen
ts
No
r
th
Am
er
ican
Ag
ar
ic
u
s
a
n
d
L
e
p
io
ta
f
am
ilies
an
d
m
ay
n
o
t
f
u
lly
ca
p
tu
r
e
th
e
b
io
d
iv
e
r
s
ity
o
f
Ph
ili
p
p
in
e
m
u
s
h
r
o
o
m
s
.
Field
d
ata
in
th
e
Ph
ilip
p
in
es
m
ay
in
clu
d
e
n
o
is
e,
i
n
co
m
p
let
e
o
b
s
er
v
atio
n
s
,
an
d
s
p
ec
ies
v
ar
iab
ilit
y
n
o
t
p
r
esen
t
in
t
h
e
b
e
n
ch
m
ar
k
d
ataset.
T
o
ad
d
r
ess
th
is
lim
itatio
n
,
f
u
tu
r
e
wo
r
k
will
f
o
cu
s
o
n
:
(
1
)
f
ield
d
ata
co
llectio
n
in
c
o
llab
o
r
atio
n
with
MR
R
DC
to
b
u
ild
a
Ph
ilip
p
in
e
-
s
p
ec
if
ic
an
n
o
tated
m
u
s
h
r
o
o
m
d
ataset; (
2
)
ex
p
er
t
-
lab
eled
s
am
p
lin
g
o
f
en
d
em
ic
s
p
ec
ies f
r
o
m
Nu
ev
a
Vizc
ay
a,
B
en
g
u
et,
an
d
Kalin
g
a;
an
d
(
3
)
m
o
d
el
r
etr
a
in
in
g
o
r
tr
an
s
f
er
lear
n
in
g
u
s
in
g
lo
ca
lly
co
llecte
d
d
ata
to
im
p
r
o
v
e
r
ea
l
-
w
o
r
ld
cla
s
s
if
icatio
n
ac
cu
r
ac
y
.
2
.
4
.
ML
mo
del
T
h
e
class
if
icatio
n
en
g
in
e
em
p
lo
y
ed
th
e
ca
teg
o
r
ical
Naïv
e
B
ay
es
(
N
B
)
alg
o
r
ith
m
,
s
ele
cted
f
o
r
its
ef
f
icien
cy
in
h
an
d
lin
g
ca
teg
o
r
ical
d
atasets
an
d
s
u
itab
il
ity
f
o
r
lar
g
e
-
s
ca
le
class
if
icatio
n
tas
k
s
[
2
3
]
.
T
h
e
m
o
d
el
was
im
p
lem
en
ted
u
s
in
g
th
e
R
u
b
ix
ML
f
r
am
ewo
r
k
(
v
2
.
5
)
in
PHP
8
.
2
with
in
th
e
L
ar
av
el
1
1
b
ac
k
en
d
.
L
ap
lace
s
m
o
o
th
in
g
(
α
=
1
.
0
)
was
ap
p
lied
to
ad
d
r
ess
ze
r
o
-
f
r
eq
u
e
n
cy
is
s
u
es,
en
s
u
r
in
g
s
tab
le
p
r
o
b
ab
ilit
y
esti
m
atio
n
wh
en
test
s
am
p
les co
n
tain
f
ea
t
u
r
e
v
alu
es u
n
s
ee
n
d
u
r
in
g
tr
ai
n
in
g
[
4
8
]
–
[
5
0
]
.
Data
p
ar
tit
io
n
in
g
was
p
er
f
o
r
m
ed
u
s
in
g
s
tr
atif
ied
h
o
ld
o
u
t
m
eth
o
d
s
ac
r
o
s
s
th
r
ee
co
n
f
ig
u
r
atio
n
s
—
6
0
:4
0
,
7
0
:3
0
,
an
d
8
0
:
2
0
—
t
o
ev
alu
ate
th
e
s
en
s
itiv
ity
o
f
th
e
class
if
ier
to
v
ar
y
in
g
tr
ain
i
n
g
d
ata
s
izes.
T
h
e
7
0
:3
0
s
p
lit
was
s
elec
ted
as
th
e
p
r
im
ar
y
h
o
ld
o
u
t
ev
alu
atio
n
co
n
f
i
g
u
r
atio
n
,
y
ield
in
g
9
9
.
6
3
%
ac
cu
r
ac
y
.
Su
b
s
eq
u
en
tly
,
5
-
Fo
ld
C
r
o
s
s
-
Valid
atio
n
was
ap
p
lied
to
ass
ess
g
en
er
aliza
tio
n
,
y
ield
in
g
a
m
ea
n
ac
cu
r
ac
y
o
f
9
9
.
6
6
%
(
±
0
.
1
1
1
8
%).
T
h
e
5
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
r
esu
lt (
9
9
.
6
6
%)
is
ad
o
p
ted
as
t
h
e
f
i
n
al
r
e
p
o
r
ted
p
er
f
o
r
m
an
ce
m
etr
ic,
as
cr
o
s
s
-
v
alid
atio
n
p
r
o
v
id
es
a
s
tatis
tically
m
o
r
e
r
o
b
u
s
t
g
en
er
aliza
tio
n
esti
m
ate
th
an
a
s
in
g
le
h
o
ld
o
u
t
test
.
Per
f
o
r
m
an
ce
was
ass
ess
ed
u
s
in
g
Acc
u
r
ac
y
,
Pre
cisi
o
n
,
R
ec
all,
Sp
ec
if
icity
,
an
d
F1
-
Sco
r
e
d
er
iv
ed
f
r
o
m
co
n
f
u
s
io
n
m
atr
ices
[
1
1
]
,
[
2
2
]
,
[
5
1
]
.
2
.
4
.
1
.
Rubi
x
M
L
im
plem
ent
a
t
io
n a
nd
hy
perpa
ra
m
et
ers
Fig
u
r
e
3
is
a
co
d
e
s
n
ip
p
et
th
at
illu
s
tr
ates
th
e
co
r
e
tr
ain
in
g
p
ip
elin
e
im
p
lem
en
ted
in
PHP
u
s
in
g
R
u
b
ix
ML
L
ib
r
ar
y
,
wh
ile
T
ab
le
1
in
d
icate
s
th
e
k
ey
h
y
p
er
p
ar
a
m
eter
s
u
s
ed
b
y
th
e
Kab
u
T
ea
ch
Naïv
e
B
ay
es c
lass
if
ier
.
Fig
u
r
e
3
.
C
o
r
e
R
u
b
i
x
ML
tr
ai
n
in
g
p
i
p
eli
n
e
co
d
e
s
n
ip
p
et
f
o
r
th
e
Kab
u
T
ea
ch
Naiv
e
B
ay
es c
lass
if
ier
T
ab
le
1
.
Su
m
m
a
r
y
o
f
th
e
k
ey
h
y
p
er
p
ar
am
eter
s
o
f
th
e
Kab
u
T
ea
ch
Naïv
e
B
ay
es c
lass
if
ier
H
y
p
e
r
p
a
r
a
me
t
e
r
V
a
l
u
e
D
e
scri
p
t
i
o
n
A
l
g
o
r
i
t
h
m
C
a
t
e
g
o
r
i
c
a
l
N
a
ï
v
e
B
a
y
e
s
A
p
p
r
o
p
r
i
a
t
e
f
o
r
d
i
scr
e
t
e
c
a
t
e
g
o
r
i
c
a
l
f
e
a
t
u
r
e
s
La
p
l
a
c
e
S
m
o
o
t
h
i
n
g
(
α)
1
.
0
(
d
e
f
a
u
l
t
)
P
r
e
v
e
n
t
s
z
e
r
o
p
r
o
b
a
b
i
l
i
t
y
f
o
r
u
n
se
e
n
f
e
a
t
u
r
e
v
a
l
u
e
s
C
l
a
s
s Pr
i
o
r
s
n
u
l
l
(
e
st
i
ma
t
e
d
)
C
o
m
p
u
t
e
d
f
r
o
m
t
r
a
i
n
i
n
g
s
e
t
c
l
a
ss
d
i
s
t
r
i
b
u
t
i
o
n
F
e
a
t
u
r
e
s Us
e
d
2
2
(
a
l
l
m
o
r
p
h
o
l
o
g
i
c
a
l
)
N
o
d
i
m
e
n
s
i
o
n
a
l
i
t
y
r
e
d
u
c
t
i
o
n
a
p
p
l
i
e
d
P
r
i
mary
D
a
t
a
S
p
l
i
t
S
t
r
a
t
i
f
i
e
d
7
0
:
3
0
h
o
l
d
o
u
t
P
r
e
serv
e
s c
l
a
ss
r
a
t
i
o
i
n
t
r
a
i
n
a
n
d
t
e
s
t
s
e
t
s
C
r
o
ss
-
V
a
l
i
d
a
t
i
o
n
S
t
r
a
t
i
f
i
e
d
5
-
F
o
l
d
P
r
o
p
o
r
t
i
o
n
a
l
c
l
a
ss
d
i
st
r
i
b
u
t
i
o
n
p
e
r
f
o
l
d
M
L
Li
b
r
a
r
y
R
u
b
i
x
M
L
v
2
.
5
P
H
P
-
n
a
t
i
v
e
ML
l
i
b
r
a
r
y
B
a
c
k
e
n
d
F
r
a
m
e
w
o
r
k
La
r
a
v
e
l
1
1
/
P
H
P
8
.
2
W
e
b
a
p
p
l
i
c
a
t
i
o
n
b
a
c
k
e
n
d
r
u
n
t
i
me
2
.
5
.
Sy
s
t
e
m
des
ig
n a
nd
pro
t
o
t
y
pin
g
Kab
u
T
ea
ch
was
d
esig
n
ed
u
s
i
n
g
a
h
y
b
r
id
ar
c
h
itectu
r
al
f
r
a
m
ewo
r
k
in
teg
r
atin
g
in
ter
ac
tiv
e
s
tr
u
ctu
r
e
ar
ch
itectu
r
e
an
d
ev
en
t
-
d
r
iv
e
n
ar
ch
itectu
r
e
s
ty
les,
alo
n
g
w
i
th
th
e
MV
C
p
atter
n
,
as
s
h
o
w
n
in
Fig
u
r
e
4
.
T
h
e
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
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
Dev
elo
p
men
t o
f Ka
b
u
Tea
c
h
:
a
ch
a
r
a
cter
-
b
a
s
ed
d
ec
is
io
n
s
u
p
p
o
r
t sys
tem
fo
r
… (
V
ilch
o
r
G.
P
erd
id
o
)
1565
in
ter
ac
tiv
e
s
tr
u
ctu
r
e
co
m
p
o
n
e
n
t
en
s
u
r
ed
c
o
n
tin
u
o
u
s
en
g
a
g
em
en
t
b
etwe
en
u
s
er
s
an
d
t
h
e
class
if
ier
en
g
in
e,
wh
ile
th
e
ev
e
n
t
-
d
r
i
v
en
c
o
m
p
o
n
en
t
h
an
d
le
d
asy
n
c
h
r
o
n
o
u
s
m
ess
ag
in
g
th
r
o
u
g
h
an
SMS
g
atew
ay
,
a
cr
itical
d
esig
n
ch
o
ice
f
o
r
r
u
r
al
ar
ea
s
with
u
n
r
eliab
le
in
ter
n
et
co
n
n
e
ctiv
ity
.
T
h
e
MV
C
p
atter
n
en
f
o
r
ce
d
m
o
d
u
lar
ity
:
th
e
Mo
d
el
m
an
ag
e
d
d
ata
an
d
M
L
class
if
icatio
n
,
th
e
View
d
eliv
er
ed
th
e
u
s
er
in
ter
f
ac
e,
an
d
th
e
C
o
n
tr
o
lle
r
co
o
r
d
in
ate
d
d
ata
f
l
o
w,
s
im
p
lif
y
in
g
test
in
g
an
d
iter
at
iv
e
p
r
o
to
ty
p
in
g
[
5
2
]
,
[
5
3
]
.
Fig
u
r
e
4
.
Hy
b
r
id
a
r
ch
itectu
r
al
f
r
am
ewo
r
k
o
f
th
e
Kab
u
T
ea
c
h
DSS
2
.
6
.
T
esting
a
nd
us
a
bil
it
y
ev
a
lua
t
io
n
T
esti
n
g
was
co
n
d
u
cted
in
t
h
r
ee
lev
els:
u
n
it,
in
teg
r
atio
n
,
a
n
d
s
y
s
tem
test
in
g
.
Acc
u
r
ac
y
te
s
tin
g
u
s
ed
d
if
f
er
en
t tr
ain
-
test
s
p
lits
an
d
c
r
o
s
s
-
v
alid
atio
n
to
m
ea
s
u
r
e
cla
s
s
if
ier
p
er
f
o
r
m
an
ce
,
with
co
n
f
u
s
io
n
m
atr
ix
r
esu
lts
co
m
p
u
ted
to
d
er
i
v
e
ev
alu
atio
n
m
etr
ics
[
1
1
]
,
[
5
1
]
.
Usab
ilit
y
test
in
g
em
p
lo
y
ed
th
e
USE
q
u
e
s
tio
n
n
air
e
to
o
l
with
a
7
-
p
o
i
n
t L
ik
er
t scale
[
3
5
]
,
[
5
4
]
.
T
h
e
u
s
ab
ilit
y
ev
alu
atio
n
in
v
o
lv
ed
1
0
2
r
esp
o
n
d
en
ts
,
co
m
p
r
is
in
g
m
u
s
h
r
o
o
m
p
ick
er
s
an
d
MRR
D
C
ex
p
er
ts
,
th
e
two
p
r
im
ar
y
u
s
er
g
r
o
u
p
s
o
f
Kab
u
T
ea
ch
.
T
h
is
s
am
p
le
s
ize
is
co
n
s
is
ten
t
with
es
tab
lis
h
ed
u
s
ab
ilit
y
r
esear
ch
g
u
id
elin
es,
wh
ich
r
e
co
m
m
en
d
2
0
-
4
0
p
ar
ticip
an
ts
as
a
p
r
ac
tical
m
in
im
u
m
f
o
r
s
u
m
m
ativ
e
u
s
ab
ilit
y
s
tu
d
ies
aim
ed
at
o
b
tain
in
g
s
ta
tis
tical
ly
s
tab
le
r
esu
lt
s
[
5
5
]
,
[
5
6
]
.
Fu
r
t
h
er
m
o
r
e,
Nielsen
[
5
7
]
d
em
o
n
s
tr
ated
th
at
test
in
g
with
a
s
u
f
f
icien
t
n
u
m
b
er
o
f
r
ep
r
esen
tativ
e
d
o
m
ain
u
s
er
s
en
s
u
r
es
co
m
p
r
eh
en
s
iv
e
id
en
tific
atio
n
o
f
u
s
ab
ilit
y
is
s
u
es.
T
h
e
d
elib
er
at
e
f
o
cu
s
o
n
d
o
m
ain
-
s
p
ec
if
ic
s
tak
eh
o
ld
er
s
en
s
u
r
es
ec
o
lo
g
ical
v
alid
ity
,
as
u
s
in
g
ac
tu
al
in
ten
d
ed
u
s
er
s
r
ath
er
th
an
g
en
er
al
p
ar
ticip
an
ts
p
r
o
d
u
c
es
r
esu
lts
th
at
m
o
r
e
ac
cu
r
ately
p
r
ed
ict
r
ea
l
-
wo
r
ld
p
er
f
o
r
m
an
ce
[
5
8
]
.
No
n
eth
eless
,
ex
p
an
d
in
g
f
u
tu
r
e
e
v
alu
atio
n
s
to
in
cl
u
d
e
b
r
o
a
d
er
g
r
o
u
p
s
s
u
ch
as
ag
r
ic
u
ltu
r
al
ex
ten
s
io
n
wo
r
k
e
r
s
an
d
p
u
b
lic
h
ea
lth
o
f
f
icer
s
is
r
ec
o
m
m
en
d
e
d
to
f
u
r
th
er
s
tr
en
g
th
en
g
en
er
al
izab
ilit
y
.
2
.
7
.
Sy
s
t
e
m
deplo
y
m
ent
T
h
e
f
in
al
v
er
s
io
n
o
f
Kab
u
T
e
ac
h
was
d
ep
lo
y
ed
at
th
e
NV
SU
d
ata
ce
n
ter
u
s
in
g
a
co
m
b
in
atio
n
o
f
lay
er
ed
an
d
clien
t
–
s
er
v
e
r
d
e
p
lo
y
m
en
t
p
atter
n
s
.
T
h
e
lay
er
ed
ar
ch
itectu
r
e
o
r
g
an
ized
th
e
s
y
s
t
em
in
to
th
r
ee
tier
s
:
th
e
p
r
esen
tatio
n
lay
er
(
u
s
er
d
a
s
h
b
o
ar
d
s
)
,
th
e
ap
p
licatio
n
lay
e
r
(
b
u
s
in
ess
lo
g
ic,
class
if
icatio
n
en
g
in
e,
an
d
SMS
n
o
tific
atio
n
s
er
v
ices)
,
an
d
t
h
e
d
ata
lay
er
(
r
elatio
n
al
d
at
a
b
a
s
e
f
o
r
u
s
er
ac
co
u
n
ts
,
class
if
icatio
n
r
ec
o
r
d
s
,
an
d
v
alid
atio
n
lo
g
s
)
.
T
h
e
clien
t
–
s
er
v
er
ar
c
h
itectu
r
e
f
ac
ilit
ated
r
ea
l
-
tim
e
co
m
m
u
n
icatio
n
b
etw
ee
n
clien
ts
an
d
th
e
NVSU
s
er
v
er
[
3
9
]
,
[
4
0
]
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
d
ev
el
o
p
m
e
n
t
an
d
ev
alu
a
tio
n
o
f
Kab
u
T
ea
c
h
was
g
r
o
u
n
d
ed
i
n
s
y
s
tem
atic
id
en
tific
at
io
n
o
f
its
in
f
o
r
m
atio
n
an
d
tech
n
o
lo
g
ical
r
eq
u
ir
em
en
ts
,
d
esig
n
o
f
its
co
r
e
f
ea
tu
r
es,
an
d
r
ig
o
r
o
u
s
ass
es
s
m
en
t
o
f
its
p
er
f
o
r
m
an
ce
a
n
d
u
s
ab
ilit
y
.
T
h
ese
f
in
d
in
g
s
ar
e
d
is
cu
s
s
ed
in
r
elatio
n
to
ex
is
tin
g
liter
atu
r
e
an
d
s
y
s
tem
d
esig
n
b
est p
r
a
ctice
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
15
,
No
.
4
,
Dec
em
b
er
20
26
:
1
5
6
1
-
1
5
7
6
1566
3
.
1
.
I
nfo
r
m
a
t
io
n
a
nd
t
ec
hn
o
lo
g
ica
l r
equirem
ent
s
3
.
1
.
1
.
Da
t
a
req
uirem
ent
s
T
h
e
s
tu
d
y
ad
o
p
ted
th
e
UC
I
m
u
s
h
r
o
o
m
d
ataset
o
b
tain
ed
f
r
o
m
Kag
g
le
[
4
7
]
,
co
n
s
is
tin
g
o
f
8
,
1
2
4
in
s
tan
ce
s
an
d
2
2
ca
teg
o
r
ical
attr
ib
u
tes.
T
h
is
d
ataset
was
p
r
e
-
p
r
o
ce
s
s
ed
,
co
n
f
ir
m
ed
to
h
av
e
n
o
m
is
s
in
g
v
alu
es,
an
d
ex
h
ib
ite
d
a
b
alan
ce
d
d
is
tr
ib
u
tio
n
b
etwe
en
e
d
ib
le
(
5
2
%)
an
d
p
o
is
o
n
o
u
s
(
4
8
%)
cla
s
s
es,
ju
s
tify
in
g
its
s
elec
tio
n
o
v
er
in
co
m
p
lete
lo
c
al
d
atasets
an
d
en
s
u
r
in
g
r
elia
b
le
tr
ain
in
g
f
o
r
th
e
Naïv
e
B
ay
es
alg
o
r
ith
m
[
2
2
]
.
Key
m
o
r
p
h
o
lo
g
ical
attr
ib
u
tes
s
u
ch
as
ca
p
co
lo
r
,
g
ill
s
ize,
o
d
o
r
,
an
d
b
r
u
is
es
s
er
v
ed
as
th
e
p
r
im
ar
y
f
ea
tu
r
es
f
o
r
class
if
icatio
n
.
W
h
ile
th
e
U
C
I
m
u
s
h
r
o
o
m
d
ataset
p
r
o
v
id
es
a
clea
n
an
d
b
alan
ce
d
b
e
n
ch
m
ar
k
,
it
d
o
es
n
o
t
f
u
lly
ca
p
tu
r
e
th
e
b
io
d
iv
er
s
ity
o
f
Ph
i
lip
p
in
e
m
u
s
h
r
o
o
m
s
.
T
o
ad
d
r
e
s
s
th
is
,
f
u
tu
r
e
wo
r
k
will
in
v
o
lv
e
th
e
co
llectio
n
o
f
lo
ca
lly
s
o
u
r
ce
d
,
ex
p
e
r
t
-
lab
el
ed
m
u
s
h
r
o
o
m
d
atasets
th
r
o
u
g
h
MRR
DC
,
en
ab
lin
g
m
o
d
el
r
etr
ain
in
g
an
d
v
alid
atio
n
in
r
ea
l
-
wo
r
ld
Ph
ilip
p
in
e
co
n
d
itio
n
s
.
3
.
1
.
2
.
H
a
rdwa
re
a
nd
s
o
f
t
wa
r
e
re
qu
irem
ent
s
T
h
e
s
y
s
tem
was
d
ep
lo
y
ed
o
n
th
e
u
C
o
n
n
ec
t
s
er
v
er
at
th
e
NVSU
Data
C
en
ter
,
wh
ich
p
r
o
v
id
es
a
r
o
b
u
s
t
in
f
r
astru
ctu
r
e
eq
u
ip
p
e
d
with
a
1
6
-
c
o
r
e
Xeo
n
p
r
o
ce
s
s
o
r
,
2
5
GB
clu
s
ter
ed
R
AM
,
an
d
b
o
th
HDD
a
n
d
SS
D
s
to
r
ag
e
ca
p
ac
ities
.
On
th
e
clien
t
s
id
e,
m
u
s
h
r
o
o
m
p
i
ck
er
s
an
d
ex
p
e
r
ts
ac
ce
s
s
ed
t
h
e
s
y
s
tem
th
r
o
u
g
h
in
ter
n
et
-
en
ab
le
d
d
ev
ices
s
u
ch
as
s
m
ar
tp
h
o
n
es,
tab
lets
,
o
r
c
o
m
p
u
ter
s
.
T
h
ese
s
p
ec
if
icatio
n
s
wer
e
ess
en
tial
to
g
u
ar
an
tee
f
ast
r
esp
o
n
s
es
an
d
l
ig
h
tweig
h
t
p
er
f
o
r
m
an
ce
ev
en
in
r
u
r
al
ar
ea
s
,
alig
n
in
g
with
I
C
T
b
est
p
r
ac
tices
in
u
s
er
-
ce
n
ter
ed
DSS
d
esig
n
[
5
9
]
,
[
6
0
]
.
T
h
e
d
esig
n
o
f
th
e
s
y
s
tem
p
r
io
r
itized
ac
ce
s
s
ib
ilit
y
f
o
r
en
d
-
u
s
er
s
,
r
eq
u
ir
in
g
o
n
ly
s
tan
d
ar
d
,
wid
el
y
av
ailab
le
h
ar
d
war
e.
T
h
e
h
ar
d
war
e
r
eq
u
ir
e
m
en
ts
f
o
r
c
o
m
p
u
ter
o
r
d
esk
t
o
p
an
d
m
o
b
ile
u
s
er
s
ar
e
d
etailed
i
n
T
ab
le
2
.
T
ab
le
2
.
E
n
d
-
u
s
er
h
ar
d
war
e
a
n
d
co
n
n
ec
tiv
ity
r
e
q
u
ir
em
e
n
ts
f
o
r
m
o
b
ile
an
d
d
esk
to
p
u
s
er
s
M
o
b
i
l
e
D
e
sk
t
o
p
u
sers
H
a
r
d
w
a
r
e
c
o
m
p
o
n
e
n
t
S
p
e
c
i
f
i
c
a
t
i
o
n
s
H
a
r
d
w
a
r
e
c
o
m
p
o
n
e
n
t
S
p
e
c
i
f
i
c
a
t
i
o
n
s
C
P
U
o
r
p
r
o
c
e
ss
o
r
D
u
a
l
-
c
o
r
e
2
.
0
G
H
z
o
r
h
i
g
h
e
r
C
P
U
o
r
p
r
o
c
e
ss
o
r
Q
u
a
d
-
c
o
r
e
2
.
0
G
H
z
o
r
h
i
g
h
e
r
R
A
M
4
G
B
R
A
M
o
r
h
i
g
h
e
r
R
A
M
M
i
n
i
m
u
m
o
f
8
G
B
o
r
h
i
g
h
e
r
I
n
t
e
r
n
a
l
s
t
o
r
a
g
e
c
a
p
a
c
i
t
y
M
i
n
i
m
u
m
o
f
8
G
B
o
r
h
i
g
h
e
r
,
w
i
t
h
a
t
l
e
a
st
5
0
0
M
B
f
r
e
e
S
t
o
r
a
g
e
M
i
n
i
m
u
m
2
0
G
B
o
f
a
v
a
i
l
a
b
l
e
sp
a
c
e
o
r
h
i
g
h
e
r
D
i
sp
l
a
y
5
.
0
-
i
n
c
h
scr
e
e
n
w
i
t
h
7
2
0
p
(
1
2
8
0
x
7
2
0
)
r
e
so
l
u
t
i
o
n
o
r
h
i
g
h
e
r
D
i
sp
l
a
y
1
2
8
0
x
8
0
0
r
e
so
l
u
t
i
o
n
o
r
h
i
g
h
e
r
C
o
n
n
e
c
t
i
v
i
t
y
I
n
t
e
r
n
e
t
A
c
c
e
ss
(
3
G
/
4
G
L
TE/
5
G
/
W
i
-
F
i
)
a
n
d
A
c
t
i
v
e
M
o
b
i
l
e
S
e
r
v
i
c
e
C
o
n
n
e
c
t
i
v
i
t
y
B
r
o
a
d
b
a
n
d
i
n
t
e
r
n
e
t
w
i
t
h
5
M
b
p
s
mi
n
i
m
u
m s
p
e
e
d
o
r
h
i
g
h
e
r
S
M
S
c
a
p
a
b
i
l
i
t
y
Th
e
d
e
v
i
c
e
m
u
st
su
p
p
o
r
t
b
a
s
i
c
S
M
S
f
u
n
c
t
i
o
n
a
l
i
t
y
G
r
a
p
h
i
c
s
I
n
t
e
g
r
a
t
e
d
o
r
d
e
d
i
c
a
t
e
d
g
r
a
p
h
i
c
s
a
r
e
s
u
f
f
i
c
i
e
n
t
f
o
r
w
e
b
-
b
a
se
d
a
p
p
l
i
c
a
t
i
o
n
s
S
e
n
s
o
r
s
C
a
mer
a
a
n
d
G
P
S
s
u
p
p
o
r
t
S
e
n
s
o
r
s
Lo
c
a
t
i
o
n
s
e
r
v
i
c
e
o
r
G
P
S
su
p
p
o
r
t
On
th
e
o
th
er
h
an
d
,
th
e
s
y
s
tem
was
d
ev
elo
p
ed
u
s
in
g
v
ar
io
u
s
to
o
ls
s
p
ec
if
ied
in
T
ab
le
3
.
I
ts
co
d
eb
as
e
was
m
ain
ly
b
u
ilt
u
s
in
g
L
ar
a
v
el
1
1
web
f
r
am
ewo
r
k
(
b
ac
k
en
d
)
,
Ma
r
iaDB/
My
SQL
(
d
ata
b
ase)
,
B
o
o
ts
tr
ap
5
(
f
r
o
n
te
n
d
)
,
a
n
d
R
u
b
ix
ML
lib
r
ar
y
f
o
r
ML
in
teg
r
atio
n
.
C
r
u
ci
al
th
ir
d
-
p
ar
t
y
in
teg
r
atio
n
s
in
clu
d
e
th
e
Sem
ap
h
o
r
e
API
f
o
r
SMS
n
o
tific
atio
n
s
an
d
th
e
Ma
p
B
o
x
Geo
co
d
in
g
API
with
L
ea
f
let
f
o
r
h
an
d
lin
g
lo
ca
tio
n
d
ata
an
d
m
ap
tiles
.
Fu
n
ctio
n
ally
,
th
e
s
y
s
tem
m
u
s
t su
p
p
o
r
t m
u
s
h
r
o
o
m
d
ata
co
llectio
n
,
in
itial c
lass
if
icatio
n
,
ex
p
er
t v
alid
atio
n
,
an
d
n
o
tific
atio
n
o
f
r
esu
lts
u
s
in
g
SMS,
wh
ile
also
m
ee
tin
g
n
o
n
-
f
u
n
ctio
n
al
r
eq
u
ir
em
en
t
s
f
o
r
s
ec
u
r
ity
an
d
r
esp
o
n
s
iv
en
ess
.
T
h
ese
to
o
ls
en
s
u
r
ed
s
ca
lab
ilit
y
an
d
s
u
s
tain
ab
ilit
y
with
in
th
e
in
f
r
astru
ctu
r
e
o
f
th
e
u
n
iv
e
r
s
ity
.
T
h
e
u
s
e
o
f
R
AD
an
d
d
esig
n
th
in
k
i
n
g
m
et
h
o
d
o
lo
g
y
,
s
u
p
p
o
r
ted
b
y
th
ese
to
o
ls
,
c
o
n
t
r
ib
u
ted
to
ef
f
icien
t
p
r
o
to
ty
p
in
g
a
n
d
h
i
g
h
u
s
ab
ilit
y
[
6
1
]
,
[
6
2
]
.
T
ab
le
3
.
So
f
twar
e
s
p
ec
if
icatio
n
s
u
s
ed
d
u
r
i
n
g
th
e
d
ev
elo
p
m
e
n
t o
f
Kab
u
T
ea
ch
DSS
S
o
f
t
w
a
r
e
co
m
p
o
n
e
n
t
S
p
e
c
i
f
i
c
a
t
i
o
n
s
B
a
c
k
e
n
d
f
r
a
m
e
w
o
r
k
La
r
a
v
e
l
1
1
.
9
F
r
o
n
t
e
n
d
f
r
a
mew
o
r
k
B
o
o
t
s
t
r
a
p
5
.
3
ML
Li
b
r
a
r
y
R
u
b
i
x
M
L
2
.
5
R
u
n
t
i
me
l
i
b
r
a
r
i
e
s
H
TM
L
5
,
C
S
S
3
,
S
w
e
e
t
A
l
e
r
t
2
(
a
l
e
r
t
m
e
ssa
g
e
s)
,
JQ
u
e
r
y
3
.
7
.
1
,
C
r
o
p
p
i
e
2
.
6
.
5
,
D
r
o
p
z
o
n
e
5
.
9
.
3
A
P
I
M
a
p
b
o
x
v
3
.
1
0
.
0
,
Le
a
f
l
e
t
2
.
0
(
m
a
p
t
i
l
e
s se
r
v
i
c
e
s)
,
S
e
ma
p
h
o
r
e
(
S
M
S
G
a
t
e
w
a
y
)
Te
x
t
o
r
c
o
d
e
e
d
i
t
o
r
M
i
c
r
o
s
o
f
t
V
i
su
a
l
S
t
u
d
i
o
C
o
d
e
v
e
r
si
o
n
1
.
9
9
.
3
X
A
M
P
P
A
p
a
c
h
e
2
.
4
(
l
o
c
a
l
h
o
s
t
s
e
r
v
e
r
)
,
P
H
P
8
.
2
,
M
a
r
i
a
D
B
1
0
.
4
W
e
b
br
o
w
ser
B
r
a
v
e
B
r
o
w
ser
1
.
7
7
.
9
5
,
M
o
z
i
l
l
a
F
i
r
e
f
o
x
1
3
7
.
0
,
M
i
c
r
o
s
o
f
t
E
d
g
e
1
3
5
.
0
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
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
Dev
elo
p
men
t o
f Ka
b
u
Tea
c
h
:
a
ch
a
r
a
cter
-
b
a
s
ed
d
ec
is
io
n
s
u
p
p
o
r
t sys
tem
fo
r
… (
V
ilch
o
r
G.
P
erd
id
o
)
1567
3
.
2
.
F
e
a
t
ures o
f
t
he
dev
elo
p
ed
s
y
s
t
em
Kab
u
T
ea
ch
p
r
o
v
i
d
es
d
is
tin
ct
in
ter
f
ac
es
an
d
f
u
n
ctio
n
alities
f
o
r
its
two
k
ey
u
s
er
g
r
o
u
p
s
:
m
u
s
h
r
o
o
m
p
ick
er
s
an
d
ex
p
er
ts
.
I
t
in
teg
r
at
e
s
m
o
d
u
les
f
o
r
ac
co
u
n
t
r
e
g
is
tr
atio
n
,
class
if
icatio
n
m
o
d
el
tr
ai
n
in
g
,
p
r
o
f
ilin
g
a
n
d
class
if
icatio
n
,
ex
p
er
t v
alid
atio
n
,
an
d
a
m
u
s
h
r
o
o
m
f
o
r
ag
i
n
g
m
ap
.
Acc
o
u
n
t
r
eg
is
tr
atio
n
u
s
ed
OT
P
-
b
ased
SMS
v
er
if
icatio
n
f
o
r
p
ick
er
s
,
wh
ile
ex
p
er
ts
r
eg
is
ter
ed
u
s
in
g
NVSU
u
C
o
n
n
ec
t
e
m
ail
ad
d
r
ess
es.
T
h
e
clas
s
if
icatio
n
m
o
d
el
m
an
ag
em
en
t
(
C
MM
)
f
ea
tu
r
e
allo
ws
ex
p
er
ts
to
u
p
lo
ad
t
h
e
p
r
e
p
r
o
ce
s
s
ed
d
atas
et,
p
er
f
o
r
m
s
tr
atif
ied
d
ata
s
p
lit
tin
g
,
an
d
tu
n
e
th
e
NB
m
o
d
el
u
s
in
g
K
-
f
o
ld
cr
o
s
s
-
v
alid
ati
o
n
,
g
en
er
atin
g
th
e
f
in
al
NB
m
o
d
el
in
.
m
o
d
el
f
o
r
m
at.
T
h
e
m
u
s
h
r
o
o
m
p
r
o
f
ilin
g
an
d
class
if
icatio
n
f
ea
tu
r
e
o
f
Kab
u
T
ea
c
h
is
p
r
esen
ted
in
Fig
u
r
e
5
.
Sp
ec
if
ically
,
Fig
u
r
e
5
(
a)
s
h
o
ws
th
e
s
elec
tio
n
o
f
2
2
p
r
ed
ef
in
e
d
m
o
r
p
h
o
lo
g
ical
ch
ar
ac
ter
is
tics
,
wh
ile
Fig
u
r
e
5
(
b
)
illu
s
tr
ates
th
e
o
p
ti
o
n
f
o
r
u
s
er
s
to
u
p
lo
a
d
u
p
to
1
0
s
am
p
le
p
h
o
to
s
o
f
t
h
e
co
llected
m
u
s
h
r
o
o
m
s
.
Up
o
n
s
u
b
m
is
s
io
n
,
th
e
s
y
s
tem
p
r
o
v
id
es
an
im
m
ed
iate
in
itial
class
if
icatio
n
an
d
s
en
d
s
an
SMS a
ck
n
o
wled
g
m
en
t,
wh
ich
is
p
ar
ticu
lar
ly
i
m
p
o
r
tan
t
f
o
r
lo
w
-
co
n
n
ec
tiv
ity
r
u
r
al
en
v
ir
o
n
m
en
ts
.
(
a)
(
b
)
Fig
u
r
e
5
.
T
h
e
Kab
u
T
ea
c
h
DSS allo
ws m
u
s
h
r
o
o
m
p
ic
k
er
s
to
s
elec
t a
n
d
s
u
b
m
it (
a)
m
o
r
p
h
o
l
o
g
ical
ch
ar
ac
ter
is
tics
an
d
(
b
)
h
ig
h
-
q
u
ality
p
h
o
to
s
o
f
co
llected
m
u
s
h
r
o
o
m
s
T
h
e
ex
p
e
r
t
v
alid
atio
n
an
d
r
esu
lt
n
o
tific
atio
n
p
r
o
ce
s
s
in
Kab
u
T
ea
ch
is
p
r
esen
ted
in
Fig
u
r
e
6
.
Sp
ec
if
ically
,
Fi
g
u
r
e
6
(
a)
s
h
o
ws
th
e
v
alid
atio
n
m
o
d
u
le
u
s
ed
b
y
MRR
D
C
m
y
co
lo
g
is
ts
to
r
ev
iew
an
d
f
in
alize
th
e
ML
-
g
en
e
r
ated
class
if
icatio
n
b
ef
o
r
e
r
esu
lt
d
is
s
em
in
atio
n
,
im
p
lem
e
n
tin
g
a
h
u
m
an
-
in
-
th
e
-
lo
o
p
s
af
ety
m
ec
h
an
is
m
th
at
m
itig
ates
th
e
r
is
k
o
f
f
alse
n
e
g
ativ
es.
Fig
u
r
e
6
(
b
)
s
h
o
ws
th
e
SMS
tex
t
m
ess
ag
e
th
r
o
u
g
h
wh
ic
h
th
e
v
alid
ated
r
esu
lts
ar
e
co
m
m
u
n
icate
d
to
m
u
s
h
r
o
o
m
p
ick
e
r
s
.
T
h
is
ex
p
er
t
v
alid
atio
n
lay
e
r
is
an
alo
g
o
u
s
to
th
e
f
r
ee
m
y
co
lo
g
ical
ev
alu
atio
n
s
er
v
ices
o
f
f
er
ed
in
I
taly
[
1
4
]
,
ad
ap
ted
f
o
r
th
e
Ph
ilip
p
in
e
r
u
r
al
co
n
tex
t
th
r
o
u
g
h
SMS
d
eliv
er
y
.
T
h
e
p
u
b
lic
m
u
s
h
r
o
o
m
f
o
r
ag
in
g
m
ap
in
Fig
u
r
e
7
u
tili
ze
d
L
ea
f
let
to
d
is
p
lay
ex
p
er
t
-
v
alid
ate
d
m
u
s
h
r
o
o
m
f
in
d
s
u
s
in
g
d
is
tin
ct
g
r
ee
n
(
ed
ib
le
)
an
d
r
ed
(
p
o
is
o
n
o
u
s
)
m
ar
k
e
r
s
,
p
r
o
m
o
tin
g
co
m
m
u
n
ity
awa
r
en
ess
o
f
s
af
e
f
o
r
ag
in
g
lo
ca
tio
n
s
.
(
a)
(
b
)
Fig
u
r
e
6
.
Mu
s
h
r
o
o
m
ex
p
e
r
ts
v
alid
ate
s
u
b
m
itted
m
u
s
h
r
o
o
m
s
u
s
in
g
th
e
(
a)
v
alid
atio
n
m
o
d
u
le,
an
d
r
esu
lts
will
b
e
s
en
t to
m
u
s
h
r
o
o
m
p
ick
er
s
t
h
r
o
u
g
h
(
b
)
SMS tex
t m
ess
ag
e
3
.
3
.
Sy
s
t
e
m
perf
o
r
m
a
nce
a
n
d
us
a
bil
it
y
t
est
T
h
e
p
r
o
p
o
n
en
ts
ca
r
r
ie
d
o
u
t
t
wo
ty
p
es
o
f
ev
alu
atio
n
s
:
(
a)
t
h
e
p
er
f
o
r
m
a
n
ce
test
o
f
th
e
class
if
icatio
n
m
o
d
el,
an
d
(
b
)
th
e
o
v
er
all
u
s
a
b
ilit
y
test
o
f
Kab
u
T
ea
ch
.
T
h
e
o
u
tco
m
es
o
f
th
ese
ev
alu
atio
n
s
p
r
o
v
i
d
ed
v
al
u
ab
le
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
15
,
No
.
4
,
Dec
em
b
er
20
26
:
1
5
6
1
-
1
5
7
6
1568
in
s
ig
h
ts
in
to
b
o
th
th
e
tech
n
ical
p
er
f
o
r
m
an
ce
o
f
th
e
class
if
icatio
n
m
o
d
el
an
d
th
e
p
r
ac
tic
al
u
s
ab
ilit
y
o
f
th
e
s
y
s
tem
,
f
o
r
m
in
g
t
h
e
b
asis
f
o
r
ass
es
s
in
g
ef
f
ec
tiv
en
ess
o
f
Kab
u
T
ea
ch
as a
r
eliab
le
d
ec
is
io
n
s
u
p
p
o
r
t to
o
l.
Fig
u
r
e
7
.
T
h
e
m
u
s
h
r
o
o
m
f
o
r
a
g
in
g
m
a
p
s
h
o
win
g
v
alid
ated
m
u
s
h
r
o
o
m
s
b
y
MRR
DC
ex
p
er
ts
3
.
3
.
1
.
Cla
s
s
if
ica
t
io
n
m
o
del p
er
f
o
rma
nce
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
Kab
u
T
ea
ch
class
if
icatio
n
m
o
d
e
l
was
ev
alu
ated
u
s
in
g
b
o
t
h
a
h
o
ld
o
u
t
v
alid
atio
n
m
eth
o
d
an
d
a
5
-
Fo
ld
cr
o
s
s
-
v
alid
atio
n
ap
p
r
o
ac
h
to
en
s
u
r
e
r
eliab
ilit
y
a
n
d
g
e
n
er
aliza
b
ilit
y
.
T
h
e
h
o
ld
o
u
t
test
u
tili
ze
d
a
7
0
:3
0
tr
ain
–
test
s
p
lit,
wh
ile
cr
o
s
s
-
v
alid
atio
n
p
r
o
v
id
e
d
a
m
o
r
e
r
o
b
u
s
t
ass
ess
m
en
t
ac
r
o
s
s
m
u
ltip
le
d
ata
p
ar
titi
o
n
s
.
Fo
r
th
e
h
o
ld
o
u
t
test
,
th
e
m
o
d
el
was
tr
ain
ed
o
n
ap
p
r
o
x
im
at
ely
5
,
6
8
7
i
n
s
tan
ce
s
(
7
0
%)
o
f
th
e
d
ataset,
wh
ile
th
e
r
e
m
ain
in
g
3
0
%
(
ap
p
r
o
x
im
ately
2
,
4
3
7
in
s
tan
ce
s
)
wer
e
u
s
ed
f
o
r
test
in
g
.
T
h
e
r
e
s
u
lts
o
f
th
e
h
o
ld
o
u
t
ev
alu
atio
n
o
f
th
e
Kab
u
T
ea
ch
class
if
icatio
n
m
o
d
el
ar
e
p
r
esen
ted
in
Fig
u
r
e
8
.
Sp
ec
if
ically
,
Fig
u
r
e
8
(
a)
s
h
o
ws
th
e
co
n
f
u
s
io
n
m
atr
ix
u
s
ed
t
o
ev
alu
ate
th
e
m
o
d
el'
s
cla
s
s
if
ica
tio
n
p
er
f
o
r
m
an
ce
,
wh
ile
Fig
u
r
e
8
(
b
)
p
r
esen
ts
th
e
co
r
r
esp
o
n
d
in
g
p
er
f
o
r
m
an
ce
m
etr
ics.
T
h
e
m
o
d
el
ac
h
iev
ed
a
n
ac
cu
r
ac
y
o
f
9
9
.
6
3
%.
No
tab
ly
,
4
f
alse
n
e
g
ativ
es
wer
e
o
b
s
er
v
ed
,
wh
ich
wer
e
p
o
is
o
n
o
u
s
m
u
s
h
r
o
o
m
s
in
c
o
r
r
ec
tly
class
if
ied
as
ed
ib
le.
W
h
ile
th
is
r
ep
r
esen
ts
o
n
ly
0
.
1
6
%
o
f
t
h
e
test
s
et,
it
u
n
d
er
s
co
r
es
th
e
cr
itical
im
p
o
r
tan
ce
o
f
th
e
ex
p
er
t
v
alid
atio
n
lay
er
in
Kab
u
T
ea
ch
,
wh
ich
p
r
o
v
id
es
a
h
u
m
a
n
s
af
ety
ch
ec
k
b
ef
o
r
e
class
if
icatio
n
r
esu
lts
ar
e
co
m
m
u
n
icate
d
to
m
u
s
h
r
o
o
m
p
ick
er
s
.
(
a)
(
b
)
Fig
u
r
e
8
.
T
h
e
ac
cu
r
ac
y
o
f
th
e
m
o
d
el
was e
v
alu
ated
u
s
in
g
(
a)
co
n
f
u
s
io
n
m
atr
ix
a
n
d
(
b
)
d
if
f
er
en
t
p
er
f
o
r
m
an
ce
m
etr
ics
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
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
Dev
elo
p
men
t o
f Ka
b
u
Tea
c
h
:
a
ch
a
r
a
cter
-
b
a
s
ed
d
ec
is
io
n
s
u
p
p
o
r
t sys
tem
fo
r
… (
V
ilch
o
r
G.
P
erd
id
o
)
1569
T
o
f
u
r
th
e
r
v
alid
ate
th
e
m
o
d
el,
5
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
was c
o
n
d
u
cted
,
a
n
d
th
e
r
esu
lts
ar
e
p
r
esen
ted
in
Fig
u
r
e
9
.
Sp
ec
if
ically
,
Fig
u
r
e
9
(
a)
s
h
o
ws
th
e
ag
g
r
eg
ated
c
o
n
f
u
s
io
n
m
atr
ix
,
wh
ile
Fig
u
r
e
9
(
b
)
p
r
esen
ts
th
e
f
o
ld
-
wis
e
p
er
f
o
r
m
an
ce
m
etr
ics an
d
s
tan
d
ar
d
d
e
v
iatio
n
s
ac
r
o
s
s
all
ev
alu
atio
n
m
etr
ics.
(
a)
(
b
)
Fig
u
r
e
9
.
T
h
e
h
y
p
er
tu
n
ed
m
o
d
el
s
h
o
win
g
th
e
o
v
er
all
(
a)
f
u
ll
co
n
f
u
s
io
n
m
atr
ix
an
d
(
b
)
p
e
r
f
o
r
m
an
ce
m
etr
ics
with
s
tan
d
ar
d
d
e
v
iatio
n
s
p
er
-
f
o
ld
r
esu
lts
ac
r
o
s
s
all
m
etr
ics
T
h
e
r
esu
lts
d
e
m
o
n
s
tr
ate
c
o
n
s
is
ten
tly
h
ig
h
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
f
o
ld
s
,
with
a
lo
w
s
tan
d
ar
d
d
ev
iatio
n
o
f
±
0
.
1
1
1
8
%
f
o
r
a
cc
u
r
ac
y
,
in
d
icatin
g
s
tr
o
n
g
m
o
d
el
s
tab
ilit
y
an
d
g
en
er
aliza
t
io
n
ca
p
ab
ilit
y
.
T
h
e
m
ea
n
ac
cu
r
ac
y
o
f
9
9
.
6
6
%
ex
c
ee
d
s
s
ev
er
al
p
r
i
o
r
s
tu
d
ies
r
ep
o
r
tin
g
a
p
p
r
o
x
im
ately
8
9
%
–
9
5
%
f
o
r
Naïv
e
B
ay
es
o
n
th
e
s
am
e
UC
I
d
ataset
[
2
3
]
,
[
2
7
]
.
T
h
r
e
e
f
ac
to
r
s
ac
co
u
n
t
f
o
r
th
is
d
if
f
er
en
ce
.
First,
p
r
io
r
s
tu
d
ies
r
ep
o
r
tin
g
lo
wer
ac
cu
r
ac
y
,
n
o
ta
b
ly
9
0
.
2
1
%
[
2
3
]
,
u
s
ed
Gau
s
s
ian
Naïv
e
B
ay
es,
wh
ich
is
d
esig
n
ed
f
o
r
co
n
tin
u
o
u
s
n
u
m
er
ical
f
ea
t
u
r
es
an
d
r
e
p
r
esen
ts
a
m
eth
o
d
o
lo
g
ical
m
is
m
atch
f
o
r
an
en
tire
ly
ca
teg
o
r
ical
d
ataset.
Kab
u
T
ea
c
h
u
s
es
C
ateg
o
r
ical
Naïv
e
B
ay
es,
th
e
a
p
p
r
o
p
r
iate
v
ar
ian
t
f
o
r
d
is
cr
ete
f
ea
tu
r
e
v
al
u
es
[
48
]
.
Seco
n
d
,
t
h
e
a
p
p
licatio
n
o
f
L
ap
lace
s
m
o
o
th
in
g
(
α
=
1
.
0
)
elim
in
ates
ze
r
o
-
p
r
o
b
ab
ilit
y
er
r
o
r
s
ca
u
s
ed
b
y
u
n
s
ee
n
f
ea
tu
r
e
co
m
b
in
atio
n
s
in
th
e
test
s
et,
wh
ich
d
ir
ec
tly
i
m
p
r
o
v
es
class
if
icatio
n
ac
cu
r
a
cy
o
v
e
r
u
n
s
m
o
o
t
h
ed
im
p
lem
en
tatio
n
s
[
48
]
-
[5
0
]
.
T
h
ir
d
,
th
e
UC
I
m
u
s
h
r
o
o
m
d
ataset
is
a
well
-
cu
r
ated
,
b
a
lan
ce
d
,
a
n
d
n
o
is
e
-
f
r
ee
b
en
c
h
m
ar
k
with
h
i
g
h
ly
d
is
cr
im
in
ativ
e
ca
teg
o
r
ical
f
ea
tu
r
es,
p
ar
ticu
lar
l
y
o
d
o
r
,
th
at
en
ab
le
s
tr
o
n
g
class
s
ep
ar
atio
n
ev
en
with
s
im
p
l
er
p
r
o
b
a
b
ilis
tic
clas
s
if
ier
s
[
4
6
]
.
T
h
e
v
er
y
lo
w
s
tan
d
ar
d
d
ev
iati
o
n
ac
r
o
s
s
all
f
iv
e
f
o
ld
s
(
±
0
.
1
1
1
8
%)
co
n
f
ir
m
s
th
at
th
e
r
esu
lt is
s
tab
le
an
d
n
o
t a
p
r
o
d
u
ct
o
f
f
av
o
r
ab
le
d
ata
p
ar
titi
o
n
in
g
.
I
t
is
im
p
o
r
tan
t
to
clar
if
y
th
e
d
i
f
f
e
r
en
ce
b
etwe
en
th
e
r
esu
lts
r
ep
o
r
ted
in
th
is
s
tu
d
y
an
d
th
o
s
e
p
r
esen
ted
in
th
e
p
r
ev
i
o
u
s
wo
r
k
o
f
th
e
l
ea
d
au
th
o
r
,
wh
er
e
a
n
ac
cu
r
ac
y
o
f
8
9
.
1
3
%
was
o
b
tain
ed
u
s
in
g
th
e
s
am
e
UC
I
m
u
s
h
r
o
o
m
d
ataset.
T
h
e
ea
r
lie
r
im
p
lem
en
tatio
n
was
d
ev
el
o
p
ed
u
s
in
g
co
r
e
PHP
with
o
u
t
a
d
e
d
icate
d
m
ac
h
in
e
lear
n
in
g
f
r
am
ewo
r
k
an
d
e
m
p
l
o
y
ed
a
f
i
x
ed
7
0
:3
0
h
o
ld
o
u
t
v
alid
atio
n
with
lim
ited
p
r
ep
r
o
c
ess
in
g
an
d
m
an
u
al
p
r
o
b
a
b
ilit
y
co
m
p
u
tatio
n
s
.
I
n
co
n
tr
ast,
th
e
p
r
esen
t
s
tu
d
y
u
tili
ze
s
R
u
b
ix
ML
v
2
.
5
,
i
m
p
r
o
v
e
d
s
tr
atif
ied
p
r
ep
r
o
ce
s
s
in
g
,
co
n
s
is
ten
t
ca
te
g
o
r
ica
l
en
co
d
in
g
,
ex
p
licit
L
ap
lace
s
m
o
o
th
in
g
(
α
=
1
.
0
)
,
an
d
a
m
o
r
e
r
ig
o
r
o
u
s
5
-
Fo
ld
C
r
o
s
s
-
Valid
atio
n
ev
alu
atio
n
s
tr
ateg
y
.
T
h
ese
m
eth
o
d
o
l
o
g
ical
en
h
an
ce
m
en
ts
r
esu
lted
in
h
ig
h
er
a
n
d
m
o
r
e
s
tab
le
p
er
f
o
r
m
an
ce
.
T
h
e
tw
o
s
tu
d
ies,
th
e
r
ef
o
r
e
,
r
e
p
r
ese
n
t
d
if
f
e
r
en
t
e
x
p
er
im
e
n
ta
l
im
p
lem
en
tatio
n
s
an
d
ev
alu
atio
n
s
tr
ateg
ies
r
ath
er
th
an
co
n
f
lictin
g
r
esu
lts
.
T
h
e
cu
r
r
en
t
m
an
u
s
cr
ip
t
is
n
o
t
a
d
u
p
lic
ate
s
u
b
m
is
s
io
n
;
th
e
p
r
io
r
wo
r
k
is
cited
to
estab
lis
h
th
e
d
ev
elo
p
m
e
n
tal
tr
ajec
to
r
y
o
f
Kab
u
T
ea
ch
.
T
o
co
n
tex
tu
ali
ze
th
e
p
er
f
o
r
m
an
ce
o
f
Kab
u
T
ea
c
h
,
T
ab
le
4
p
r
esen
ts
a
co
m
p
ar
is
o
n
with
r
elate
d
s
tu
d
ies o
n
m
u
s
h
r
o
o
m
class
if
icatio
n
.
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
o
f
Kab
u
T
ea
ch
with
r
elate
d
m
u
s
h
r
o
o
m
class
if
icatio
n
s
tu
d
ies
S
t
u
d
y
A
l
g
o
r
i
t
h
m
D
a
t
a
s
e
t
A
c
c
u
r
a
c
y
K
a
b
u
Te
a
c
h
(
t
h
i
s st
u
d
y
)
C
a
t
e
g
o
r
i
c
a
l
N
B
+
La
p
l
a
c
e
(
α=
1
.
0
)
U
C
I
mu
sh
r
o
o
m
9
9
.
6
6
%
S
u
l
i
st
i
a
n
i
n
g
s
i
h
a
n
d
M
a
r
t
o
n
o
[
2
4
]
En
se
mb
l
e
(
R
F
,
s
t
a
c
k
i
n
g
)
U
C
I
mu
sh
r
o
o
m
9
9
%+
V
i
j
a
y
a
l
a
k
s
h
mi
a
n
d
E
b
e
n
e
z
e
r
[
6
3
]
R
a
n
d
o
m f
o
r
e
s
t
U
C
I
mu
sh
r
o
o
m
9
8
.
1
%
A
h
me
d
e
t
a
l
.
[
6
4
]
D
e
c
i
s
i
o
n
t
r
e
e
/
K
N
N
/
RF
U
C
I
mu
sh
r
o
o
m
1
0
0
%
A
h
me
d
e
t
a
l
.
[
6
4
]
N
a
ï
v
e
B
a
y
e
s
(
n
o
sm
o
o
t
h
i
n
g
)
U
C
I
mu
sh
r
o
o
m
9
3
%
R
i
a
n
a
sari
e
t
a
l
.
[
2
7
]
N
a
ï
v
e
B
a
y
e
s
+
P
C
A
U
C
I
mu
sh
r
o
o
m
~
9
5
%
H
a
mo
n
a
n
g
a
n
e
t
a
l
.
[
2
3
]
G
a
u
ss
i
a
n
N
a
ï
v
e
B
a
y
e
s
U
C
I
mu
sh
r
o
o
m
9
0
.
2
1
%
D
e
l
l
’
Er
a
e
t
a
l
.
[
6
1
]
C
N
N
(
d
e
e
p
l
e
a
r
n
i
n
g
)
I
mag
e
-
b
a
s
e
d
9
9
.
0
8
%
–
9
9
.
5
%
R
ö
s
c
h
e
t
a
l
.
[
6
2
]
D
e
e
p
l
e
a
r
n
i
n
g
I
mag
e
-
b
a
s
e
d
~
9
9
%
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
15
,
No
.
4
,
Dec
em
b
er
20
26
:
1
5
6
1
-
1
5
7
6
1570
W
h
ile
C
NN
an
d
en
s
em
b
le
m
eth
o
d
s
ac
h
iev
e
co
m
p
ar
ab
le
o
r
h
ig
h
er
ac
c
u
r
ac
y
o
n
im
a
g
e
-
b
ased
o
r
m
u
lti
-
m
o
d
al
d
atasets
,
th
ey
r
e
q
u
ir
e
s
ig
n
if
ican
tly
g
r
ea
te
r
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
,
s
p
ec
ial
ized
h
ar
d
wa
r
e
(
e.
g
.
,
GPUs
)
,
an
d
lar
g
e
la
b
eled
im
a
g
e
d
atasets
,
im
p
r
ac
tical
f
o
r
r
u
r
al
d
ep
lo
y
m
en
t
in
lo
w
-
co
n
n
ec
ti
v
ity
en
v
ir
o
n
m
e
n
ts
.
Kab
u
T
ea
ch
’
s
C
ateg
o
r
ical
Naï
v
e
B
ay
es
class
if
ier
ac
h
iev
es
9
9
.
6
6
%
with
m
in
im
al
co
m
p
u
tatio
n
al
o
v
er
h
ea
d
,
m
ak
in
g
it
th
e
m
o
s
t
ap
p
r
o
p
r
ia
te
alg
o
r
ith
m
f
o
r
th
e
d
esig
n
c
o
n
s
tr
ain
ts
o
f
th
e
s
y
s
tem
.
Fu
r
t
h
er
m
o
r
e
,
ch
a
r
ac
ter
-
b
ased
m
o
r
p
h
o
lo
g
ical
class
if
icatio
n
is
m
o
r
e
in
ter
p
r
etab
le
an
d
ac
tio
n
a
b
le
f
o
r
n
o
n
-
ex
p
er
t
u
s
er
s
th
an
b
lack
-
b
o
x
C
NN
p
r
ed
ictio
n
s
,
alig
n
in
g
wit
h
th
e
s
af
ety
-
cr
itical
d
ec
is
io
n
s
u
p
p
o
r
t p
u
r
p
o
s
e
o
f
th
e
s
y
s
tem
.
Desp
ite
th
e
s
tr
o
n
g
r
esu
lts
,
it
is
im
p
o
r
tan
t
to
n
o
te
th
at
s
u
ch
p
er
f
o
r
m
a
n
ce
m
a
y
n
o
t
d
ir
ec
tly
tr
an
s
late
to
r
ea
l
-
wo
r
ld
Ph
ilip
p
i
n
e
co
n
d
it
io
n
s
,
wh
er
e
f
iel
d
d
ata
m
a
y
in
clu
d
e
n
o
is
e,
in
co
m
p
lete
o
b
s
er
v
atio
n
s
,
a
n
d
en
v
ir
o
n
m
en
tal
v
ar
iab
ilit
y
n
o
t
ca
p
tu
r
ed
b
y
th
e
UC
I
b
en
ch
m
ar
k
d
ataset.
T
o
ad
d
r
ess
th
is
,
Kab
u
T
ea
ch
in
co
r
p
o
r
ates
a
h
u
m
an
-
in
-
th
e
-
l
o
o
p
ex
p
e
r
t
v
alid
atio
n
m
ec
h
an
is
m
th
r
o
u
g
h
th
e
MRR
D
C
,
an
d
f
u
tu
r
e
wo
r
k
will
f
o
cu
s
o
n
c
o
llectin
g
lo
ca
lly
s
o
u
r
ce
d
,
ex
p
er
t
-
lab
eled
d
atasets
to
f
u
r
th
er
en
h
an
ce
r
ea
l
-
w
o
r
ld
a
p
p
licab
ilit
y
.
3
.
3
.
2
.
Usa
bil
it
y
t
est
o
f
K
a
bu
T
ea
ch
T
h
e
u
s
ab
ilit
y
o
f
th
e
Kab
u
T
e
ac
h
DSS
was
ass
es
s
ed
b
y
1
0
2
r
esp
o
n
d
e
n
ts
co
m
p
r
is
in
g
m
u
s
h
r
o
o
m
p
ick
er
s
an
d
MRR
D
C
ex
p
er
ts
,
th
e
two
p
r
im
ar
y
u
s
er
g
r
o
u
p
s
o
f
th
e
s
y
s
tem
,
u
s
in
g
USE
qu
esti
o
n
n
air
e.
T
h
e
in
s
tr
u
m
en
t
ev
alu
ate
d
f
o
u
r
d
i
m
en
s
io
n
s
u
s
in
g
3
0
item
s
r
at
ed
o
n
a
7
-
p
o
in
t
L
ik
er
t
s
ca
le,
p
r
o
v
id
in
g
a
r
o
b
u
s
t
m
ea
s
u
r
e
o
f
en
d
-
u
s
er
s
’
s
u
b
ject
iv
e
p
er
ce
p
tio
n
o
f
th
e
s
y
s
tem
[
38
]
.
T
h
e
q
u
alitativ
e
in
ter
p
r
et
atio
n
o
f
th
e
m
ea
n
s
co
r
es is
p
r
esen
ted
in
T
ab
le
5.
T
ab
le
5
.
Qu
alitativ
e
in
te
r
p
r
eta
tio
n
o
f
7
-
poi
n
t L
ik
er
t
s
ca
le
m
e
asu
r
em
en
ts
R
a
t
i
n
g
sca
l
e
M
e
a
n
sc
o
r
e
i
n
t
e
r
v
al
D
e
scri
p
t
i
v
e
r
a
t
i
n
g
1
1
.
0
0
–
1
.
8
5
S
t
r
o
n
g
l
y
d
i
sa
g
r
e
e
(SD)
2
1
.
8
6
–
2
.
7
1
D
i
sag
r
e
e
(
D
)
3
2
.
7
2
–
3
.
5
7
S
l
i
g
h
t
l
y
d
i
s
a
g
r
e
e
(
S
LD
)
4
3
.
5
8
–
4
.
4
3
N
e
i
t
h
e
r
a
g
r
e
e
n
o
r
d
i
sa
g
r
e
e
(NAD)
5
4
.
4
4
–
5
.
2
9
S
l
i
g
h
t
l
y
a
g
r
e
e
(
S
LA
)
6
5
.
3
0
–
6
.
1
5
A
g
r
e
e
(
A
)
7
6
.
1
6
–
7
.
0
0
S
t
r
o
n
g
l
y
a
g
r
e
e
(SA)
a.
Usef
uln
e
s
s
dim
en
s
io
n
T
h
e
u
s
ef
u
ln
ess
d
im
en
s
io
n
ac
h
iev
ed
a
m
ea
n
s
co
r
e
o
f
5
.
8
7
,
in
ter
p
r
eted
as
“Ag
r
ee
,
”
as
s
h
o
wn
in
T
ab
le
6
.
T
h
is
r
esu
lt
in
d
icate
s
th
at
r
esp
o
n
d
en
ts
g
en
er
ally
ag
r
ee
d
th
at
Kab
u
T
ea
ch
is
a
p
r
ac
tical
an
d
ef
f
ec
tiv
e
to
o
l
th
at
s
u
p
p
o
r
ts
th
eir
m
u
s
h
r
o
o
m
class
if
icatio
n
task
s
.
T
h
e
h
ig
h
est
-
r
ated
item
was
“I
t
is
u
s
ef
u
l”
(
6
.
1
6
,
Stro
n
g
ly
Ag
r
ee
)
,
r
e
f
lectin
g
s
tr
o
n
g
en
d
o
r
s
em
en
t
o
f
th
e
co
r
e
p
u
r
p
o
s
e
o
f
th
e
s
y
s
tem
.
I
tem
s
r
elate
d
to
ef
f
ec
tiv
en
ess
(
5
.
9
5
)
,
tim
e
-
s
av
i
n
g
(
5
.
9
2
)
,
an
d
p
r
o
d
u
ctiv
ity
(
5
.
8
5
)
also
r
ec
ei
v
ed
s
o
lid
a
g
r
ee
m
en
t.
T
h
e
s
lig
h
tly
lo
wer
s
co
r
es
f
o
r
“it
g
i
v
es
m
e
m
o
r
e
co
n
tr
o
l
o
v
e
r
th
e
ac
tiv
it
ies
in
m
y
life
”
(
5
.
7
0
)
an
d
“it
m
ee
ts
m
y
n
ee
d
s
”
(
5
.
7
1
)
s
u
g
g
est
th
at
wh
ile
th
e
s
y
s
tem
is
co
n
s
id
er
ed
u
s
ef
u
l,
s
o
m
e
r
esp
o
n
d
e
n
ts
f
elt
it
p
ar
tially
m
ee
ts
th
eir
s
p
ec
if
ic
f
o
r
ag
i
n
g
d
ec
is
io
n
-
m
a
k
in
g
n
ee
d
s
,
a
f
in
d
in
g
co
n
s
is
te
n
t
with
o
p
e
n
-
en
d
ed
f
ee
d
b
ac
k
i
n
d
icatin
g
th
at
s
o
m
e
m
o
r
p
h
o
lo
g
ical
class
if
icatio
n
o
p
tio
n
s
d
id
n
o
t
in
clu
d
e
a
“No
n
e”
r
esp
o
n
s
e,
lim
itin
g
in
p
u
t
f
le
x
ib
ilit
y
f
o
r
ce
r
tain
r
ea
l
-
wo
r
ld
m
u
s
h
r
o
o
m
s
p
ec
im
e
n
s
.
T
ab
le
6
.
Me
an
s
co
r
es o
f
th
e
u
s
ef
u
ln
ess
d
im
en
s
io
n
(
n
=
1
0
2
)
I
t
e
m d
e
s
c
r
i
p
t
i
o
n
M
e
a
n
sc
o
r
e
D
e
scri
p
t
i
v
e
r
a
t
i
n
g
1
.
I
t
h
e
l
p
s
me
b
e
m
o
r
e
e
f
f
e
c
t
i
v
e
.
5
.
9
5
A
g
r
e
e
2
.
I
t
h
e
l
p
s
me
b
e
m
o
r
e
p
r
o
d
u
c
t
i
v
e
.
5
.
8
5
A
g
r
e
e
3
.
I
t
i
s
u
sefu
l
.
6
.
1
6
S
t
r
o
n
g
l
y
a
g
r
e
e
4
.
I
t
g
i
v
e
s
me
mo
r
e
c
o
n
t
r
o
l
o
v
e
r
t
h
e
a
c
t
i
v
i
t
i
e
s
i
n
m
y
l
i
f
e
.
5
.
7
0
A
g
r
e
e
5
.
I
t
ma
k
e
s t
h
e
t
h
i
n
g
s I
w
a
n
t
t
o
a
c
c
o
m
p
l
i
sh
e
a
si
e
r
t
o
g
e
t
d
o
n
e
.
5
.
8
4
A
g
r
e
e
6
.
I
t
sa
v
e
s me
t
i
me
w
h
e
n
I
u
s
e
i
t
.
5
.
9
2
A
g
r
e
e
7
.
I
t
me
e
t
s
m
y
n
e
e
d
s.
5
.
7
1
A
g
r
e
e
8
.
I
t
d
o
e
s e
v
e
r
y
t
h
i
n
g
I
w
o
u
l
d
e
x
p
e
c
t
i
t
t
o
d
o
.
5
.
8
2
A
g
r
e
e
M
e
a
n
S
c
o
r
e
5
.
8
7
A
g
r
e
e
b.
E
a
s
e
o
f
us
e
dim
ens
io
n
T
h
e
ea
s
e
o
f
u
s
e
d
im
e
n
s
io
n
r
e
co
r
d
ed
a
m
ea
n
s
co
r
e
o
f
5
.
7
5
,
in
ter
p
r
eted
as
“Ag
r
ee
,
”
as
p
r
esen
ted
in
T
ab
le
7
.
R
esp
o
n
d
en
ts
ag
r
ee
d
t
h
at
Kab
u
T
ea
ch
is
g
en
er
all
y
ea
s
y
to
u
s
e,
s
im
p
le
(
6
.
0
5
)
,
a
n
d
u
s
er
-
f
r
ien
d
ly
(
6
.
0
3
)
,
with
b
o
th
o
cc
asio
n
al
an
d
r
eg
u
lar
u
s
er
s
ex
p
ec
ted
to
f
in
d
i
t
ag
r
ee
a
b
le
(
5
.
9
4
)
.
I
tem
s
in
v
o
lv
in
g
q
u
ick
e
r
r
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.