I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
,
p
p
.
2484
~
2
4
9
3
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
3
.
p
p
2
4
8
4
-
2
4
9
3
2484
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Predic
tion o
f
n
ew
studen
t
a
dmis
sio
ns to hig
her
educ
a
tion usin
g
supp
o
rt
v
ector
m
a
chines
Neni
P
urwa
t
i
1
,
Wind
y
a
H
a
riesk
a
P
ra
m
uja
t
i
2
,
A.
A
v
iv
M
a
hm
ud
i
3
,
M
ira
F
ebria
na
Ses
u
na
n
4
,
Ya
hy
a
4
1
D
e
p
a
r
t
me
n
t
o
f
M
e
d
i
c
a
l
I
n
f
o
r
m
a
t
i
c
s,
F
a
c
u
l
t
y
o
f
H
e
a
l
t
h
S
c
i
e
n
c
e
,
U
n
i
v
e
r
s
i
t
a
s M
u
h
a
mm
a
d
i
y
a
h
La
mo
n
g
a
n
,
La
m
o
n
g
a
n
,
I
n
d
o
n
e
s
i
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
P
o
l
i
t
e
k
n
i
k
N
e
g
e
r
i
M
a
l
a
n
g
,
M
a
l
a
n
g
,
I
n
d
o
n
e
s
i
a
3
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
y
s
t
e
ms
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
a
s
Y
P
P
I
R
e
mb
a
n
g
,
R
e
mb
a
n
g
,
I
n
d
o
n
e
s
i
a
4
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
y
s
t
e
ms
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s
D
a
r
ma
P
e
r
s
a
d
a
,
J
a
k
a
r
t
a
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
6
,
2
0
2
4
R
ev
is
ed
J
an
1
3
,
2
0
2
6
Acc
ep
ted
Ma
y
1
1
,
2
0
2
6
Hig
h
e
r
e
d
u
c
a
ti
o
n
in
st
it
u
ti
o
n
s
a
c
r
o
ss
v
a
rio
u
s
re
g
i
o
n
s
o
p
e
ra
te
u
sin
g
sy
ste
m
s
th
a
t
g
e
n
e
ra
te
larg
e
a
m
o
u
n
ts
o
f
d
a
ta.
Th
is
d
a
ta
is
st
o
re
d
a
n
d
u
t
il
ize
d
fo
r
stra
teg
ic
d
e
c
isio
n
-
m
a
k
i
n
g
,
p
r
o
v
i
d
in
g
sig
n
ifi
c
a
n
t
b
u
si
n
e
ss
v
a
lu
e
to
t
h
e
se
in
stit
u
ti
o
n
s.
S
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(
S
VM
)
h
a
s
b
e
c
o
m
e
p
o
p
u
lar
d
u
e
to
it
s
stro
n
g
g
e
n
e
ra
li
z
a
ti
o
n
c
a
p
a
b
il
i
ty
,
h
ig
h
p
re
d
ictio
n
a
c
c
u
ra
c
y
,
a
n
d
fa
st
e
r
train
in
g
sp
e
e
d
.
S
VM
e
m
p
lo
y
s
k
e
r
n
e
ls
a
s
tu
n
in
g
p
a
ra
m
e
ters
.
Th
is
stu
d
y
a
ims
to
e
n
h
a
n
c
e
t
h
e
a
c
c
u
ra
c
y
o
f
st
u
d
e
n
t
a
d
m
issio
n
s
p
re
d
ictio
n
in
h
ig
h
e
r
e
d
u
c
a
ti
o
n
in
stit
u
ti
o
n
s
u
sin
g
t
h
e
S
VM
c
la
ss
ifi
c
a
ti
o
n
m
o
d
e
l.
Th
e
S
VM
m
o
d
e
l
wa
s
a
p
p
li
e
d
t
o
a
d
a
tas
e
t
c
o
m
p
risi
n
g
5
,
9
3
6
re
c
o
r
d
s
with
f
o
u
r
a
tt
rib
u
te
s
a
n
d
wa
s
e
v
a
lu
a
ted
u
si
n
g
t
h
e
u
se
train
in
g
se
t
,
1
0
-
f
o
ld
c
r
o
ss
-
v
a
li
d
a
ti
o
n
,
a
n
d
p
e
rc
e
n
tag
e
sp
li
ts
o
f
7
0
%
–
3
0
%
a
n
d
8
0
%
–
2
0
%
.
I
n
it
iall
y
,
th
e
S
VM
-
k
e
rn
e
l
m
o
d
e
l
a
c
h
iev
e
d
h
ig
h
a
c
c
u
ra
c
y
b
u
t
fa
il
e
d
to
id
e
n
ti
fy
a
n
y
tru
e
p
o
siti
v
e
in
sta
n
c
e
s,
in
d
ica
ti
n
g
i
ts
in
a
b
il
it
y
t
o
d
e
tec
t
th
e
m
in
o
rit
y
“
n
o
t
a
c
c
e
p
ted
”
c
las
s
d
u
e
to
se
v
e
re
c
las
s
imb
a
lan
c
e
.
Afte
r
a
p
p
ly
in
g
c
las
s
b
a
lan
c
i
n
g
tec
h
n
i
q
u
e
s,
th
e
m
o
d
e
l’s
p
e
rfo
rm
a
n
c
e
imp
r
o
v
e
d
si
g
n
ifi
c
a
n
t
ly
in
term
s o
f
a
re
a
u
n
d
e
r
th
e
c
u
r
v
e
(
AUC
)
,
F
-
m
e
a
su
re
,
a
n
d
M
a
tt
h
e
w
s
c
o
rre
latio
n
c
o
e
fficie
n
t
(
M
CC
)
,
re
flec
ti
n
g
a
m
o
re
b
a
lan
c
e
d
c
las
sifica
ti
o
n
b
e
twe
e
n
m
a
jo
rit
y
a
n
d
m
in
o
rit
y
c
las
se
s.
Th
e
S
VM
wit
h
P
e
a
rso
n
VII
f
u
n
c
ti
o
n
-
b
a
se
d
u
n
i
v
e
rsa
l
k
e
rn
e
l
(
P
UK
)
a
n
d
c
las
sifier
v
e
rsio
n
4
.
5
(
C
4
.
5
)
m
o
d
e
ls
a
c
h
iev
e
d
t
h
e
b
e
st
p
e
rfo
rm
a
n
c
e
,
i
n
d
ic
a
ti
n
g
th
a
t
c
las
s
b
a
lan
c
in
g
e
ffe
c
ti
v
e
ly
e
n
h
a
n
c
e
s
b
o
th
se
n
siti
v
it
y
a
n
d
f
a
irn
e
ss
in
p
re
d
ictiv
e
c
las
sifica
ti
o
n
.
K
ey
w
o
r
d
s
:
Hig
h
er
ed
u
ca
tio
n
Ker
n
el
New
s
tu
d
en
t a
d
m
is
s
io
n
s
Pre
d
ictio
n
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
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
:
Nen
i Pu
r
wati
Dep
ar
tm
en
t o
f
Me
d
ical
I
n
f
o
r
m
atics,
Facu
lty
o
f
Hea
lth
Scien
ce
,
Un
iv
er
s
itas
Mu
h
am
m
a
d
iy
ah
L
am
o
n
g
an
St.
R
ay
a
Plalan
g
an
No
.
KM
02
,
L
am
o
n
g
an
,
E
ast J
av
a,
I
n
d
o
n
esia
E
m
ail: n
en
ip
u
r
wati@
u
m
la.
ac
.
i
d
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
e
2
1
s
t
ce
n
tu
r
y
,
h
ig
h
er
e
d
u
ca
tio
n
h
as
b
ec
o
m
e
a
f
u
n
d
am
en
tal
p
illar
o
f
s
o
cial
an
d
ec
o
n
o
m
ic
life
.
Ad
d
itio
n
ally
,
th
e
ed
u
ca
tio
n
al
p
r
o
ce
s
s
en
s
u
r
es
two
o
th
er
cr
u
cial
asp
ec
ts
:
a
p
r
o
m
is
in
g
ca
r
ee
r
an
d
f
in
a
n
cial
s
ec
u
r
ity
.
Ho
wev
er
,
p
r
e
d
ictin
g
s
tu
d
en
t
ad
m
is
s
io
n
s
to
h
ig
h
er
ed
u
ca
ti
o
n
in
s
titu
tio
n
s
is
ch
allen
g
in
g
,
as
p
r
o
s
p
ec
tiv
e
s
tu
d
e
n
ts
o
f
ten
lac
k
k
n
o
wled
g
e
o
f
th
e
ad
m
is
s
io
n
r
eq
u
ir
em
e
n
ts
[
1
]
.
T
h
e
s
tu
d
en
t
ad
m
is
s
io
n
p
r
o
ce
s
s
is
a
cr
u
cial
s
tep
f
r
o
m
b
o
th
th
e
s
tu
d
en
ts
’
a
n
d
th
e
h
ig
h
e
r
ed
u
ca
tio
n
in
s
titu
tio
n
s
’
p
er
s
p
e
ctiv
es
[
2
]
.
Hig
h
e
r
ed
u
ca
tio
n
in
s
titu
tio
n
s
o
p
er
ate
ac
r
o
s
s
v
ar
io
u
s
g
eo
g
r
ap
h
ical
r
e
g
io
n
s
u
s
in
g
s
y
s
tem
s
th
at
g
en
e
r
ate
lar
g
e
am
o
u
n
ts
o
f
d
ata.
T
h
is
d
ata
is
s
to
r
ed
an
d
u
tili
ze
d
b
y
d
ec
is
io
n
-
m
ak
e
r
s
to
m
ak
e
s
tr
ateg
ic
d
ec
is
io
n
s
,
wh
ich
s
ig
n
if
ican
tly
af
f
ec
t
th
e
b
u
s
in
ess
v
alu
e
o
f
th
e
in
s
titu
tio
n
s
.
T
h
er
e
f
o
r
e,
it
ca
n
en
h
a
n
ce
th
e
e
f
f
ec
tiv
e
n
ess
o
f
m
an
ag
e
r
ial
d
ec
is
io
n
-
m
ak
in
g
[
3
]
.
T
h
u
s
,
th
is
lar
g
e
am
o
u
n
t
o
f
d
ata
ca
n
b
e
o
p
tim
ally
u
tili
ze
d
to
g
ain
n
e
w
in
s
ig
h
t.
Ma
c
h
in
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
P
r
ed
ictio
n
o
f n
ew s
tu
d
en
t a
d
m
is
s
io
n
s
to
h
ig
h
er e
d
u
ca
tio
n
u
s
in
g
s
u
p
p
o
r
t v
ec
to
r
ma
ch
in
es
(
N
en
i P
u
r
w
a
ti
)
2485
lear
n
in
g
(
ML
)
,
a
s
u
b
d
o
m
ain
o
f
ar
tific
ial
in
tellig
en
ce
(
AI
)
,
h
as
p
r
o
v
en
its
p
er
f
o
r
m
a
n
ce
a
cr
o
s
s
v
ar
io
u
s
f
ield
s
.
T
h
is
s
tu
d
y
aim
s
to
en
h
a
n
ce
t
h
e
ac
cu
r
ac
y
o
f
p
r
ed
ictin
g
s
tu
d
en
t
ad
m
is
s
io
n
s
to
h
ig
h
er
ed
u
ca
tio
n
in
s
titu
tio
n
s
.
Pre
d
ictin
g
n
ew
s
tu
d
en
t
ad
m
i
s
s
io
n
s
p
lay
s
a
cr
u
cial
r
o
le
in
im
p
r
o
v
i
n
g
th
e
ef
f
icien
c
y
,
f
a
ir
n
ess
,
an
d
o
v
er
all
q
u
ality
o
f
s
elec
tio
n
p
r
o
ce
s
s
i
n
h
ig
h
er
e
d
u
ca
tio
n
.
Su
ch
s
y
s
tem
s
s
tr
ea
m
lin
e
ev
alu
atio
n
p
r
o
ce
d
u
r
es,
m
in
im
ize
h
u
m
an
b
ias,
an
d
e
n
ab
le
u
n
i
v
er
s
ities
to
m
an
ag
e
r
eso
u
r
ce
s
m
o
r
e
ef
f
ec
tiv
ely
wh
ile
en
h
an
cin
g
ac
a
d
em
ic
s
tan
d
ar
d
s
.
I
n
ad
d
itio
n
,
th
e
p
r
e
d
ictio
n
o
u
tco
m
es
p
r
o
v
i
d
e
v
al
u
ab
le
in
p
u
t
f
o
r
s
tr
ateg
ic
p
lan
n
in
g
an
d
d
ata
-
d
r
iv
e
n
d
ec
is
io
n
-
m
ak
in
g
in
th
e
a
d
m
in
i
s
tr
atio
n
o
f
s
tu
d
en
t
a
d
m
is
s
io
n
s
[
4
]
.
Pre
v
io
u
s
s
tu
d
ies
h
a
v
e
d
e
m
o
n
s
tr
ated
th
at
ML
tech
n
iq
u
es
ar
e
ef
f
ec
tiv
e
i
n
e
n
h
an
cin
g
p
r
e
d
ictio
n
ac
c
u
r
ac
y
[
5
]
.
ML
an
d
AI
tec
h
n
o
lo
g
ie
s
h
av
e
s
ig
n
if
ican
tly
tr
an
s
f
o
r
m
ed
s
o
ciety
a
n
d
v
a
r
io
u
s
in
d
u
s
tr
ial
s
ec
to
r
s
b
y
au
to
m
atin
g
cr
itical
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
es,
ex
er
tin
g
a
s
u
b
s
tan
tial im
p
ac
t o
n
d
o
m
ai
n
s
s
u
ch
as c
r
im
in
al
law,
h
ea
lth
ca
r
e,
f
in
an
ce
,
an
d
th
e
wo
r
k
f
o
r
ce
[
6
]
.
Am
o
n
g
v
ar
io
u
s
ML
ap
p
r
o
ac
h
es,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVMs)
ar
e
d
is
tin
g
u
is
h
ed
f
o
r
t
h
eir
ab
ilit
y
to
h
an
d
le
n
o
n
lin
ea
r
p
atter
n
s
a
n
d
h
ig
h
-
d
im
en
s
io
n
al
d
atasets
,
ch
ar
ac
ter
is
tics
th
at
ar
e
f
r
eq
u
en
tly
en
co
u
n
te
r
ed
in
p
o
ly
m
er
r
esear
ch
[
7
]
.
An
ef
f
e
ctiv
e
class
if
icat
io
n
ap
p
r
o
ac
h
u
s
in
g
SVMs
in
v
o
lv
es
em
p
lo
y
in
g
s
u
itab
le
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
th
at
p
r
io
r
iti
ze
in
f
lu
e
n
tial
attr
ib
u
tes
wh
ile
ex
clu
d
i
n
g
less
r
elev
an
t
o
n
es.
T
h
is
s
ce
n
ar
io
h
as
th
e
p
o
te
n
tial
to
en
h
a
n
ce
class
if
icatio
n
ac
cu
r
ac
y
a
n
d
r
ed
u
ce
co
m
p
u
tatio
n
al
o
v
er
h
ea
d
.
Fu
r
th
er
m
o
r
e,
u
tili
zin
g
r
eliab
le
d
atasets
an
d
ap
p
ly
in
g
ap
p
r
o
p
r
iate
v
alid
atio
n
tec
h
n
iq
u
es
co
n
tr
i
b
u
tes
to
p
r
o
d
u
cin
g
ac
cu
r
ate
an
d
tr
u
s
two
r
th
y
r
esu
lts
[
8
]
.
W
in
d
s
p
ee
d
p
r
ed
ictio
n
,
f
o
r
in
s
tan
ce
,
is
cr
u
cial
f
o
r
o
p
tim
izin
g
p
o
wer
g
en
er
atio
n
an
d
m
ain
tain
in
g
elec
tr
icity
s
u
p
p
l
y
s
tab
ilit
y
,
wh
ich
u
tili
ze
d
m
eteo
r
o
lo
g
ical
d
ata
f
r
o
m
t
h
e
Natio
n
al
W
in
d
T
ec
h
n
o
lo
g
y
C
en
ter
(
NW
T
C
)
in
B
o
u
ld
er
,
C
o
lo
r
a
d
o
,
e
m
p
lo
y
ed
th
r
ee
p
r
ed
ictio
n
m
o
d
els:
f
i
n
e
t
r
ee
,
SVM,
an
d
lin
ea
r
r
eg
r
ess
io
n
,
an
d
d
em
o
n
s
tr
ated
th
e
im
p
o
r
tan
ce
o
f
m
o
d
el
ev
alu
atio
n
i
n
ac
h
ie
v
in
g
r
el
iab
le
f
o
r
ec
asts
[
9
]
.
Similar
ly
,
an
SVM
m
o
d
el
co
m
b
in
ed
with
s
tr
atif
ied
an
d
s
h
u
f
f
le
s
am
p
lin
g
tech
n
i
q
u
es
d
e
m
o
n
s
tr
ated
o
p
tim
al
an
d
r
eliab
le
p
er
f
o
r
m
a
n
ce
in
p
r
ed
ictin
g
s
tu
d
e
n
ts
’
ac
ad
em
ic
o
u
tco
m
es
[
1
0
]
.
An
o
t
h
er
s
tu
d
y
ap
p
lied
s
u
p
er
v
is
ed
lear
n
in
g
alg
o
r
ith
m
s
,
in
cl
u
d
in
g
SVM,
d
ec
is
io
n
tr
ee
(
DT
)
,
r
a
n
d
o
m
f
o
r
est
(
R
F),
an
d
ex
t
r
em
e
g
r
ad
ien
t
b
o
o
s
tin
g
(
XGB),
to
p
r
ed
ict
s
tu
d
en
t
ac
a
d
em
ic
ac
h
iev
e
m
en
t,
with
XGB
ac
h
iev
in
g
t
h
e
h
ig
h
est
F1
-
s
co
r
e
an
d
a
s
u
cc
ess
r
ate
o
f
7
7
%
[
1
1
]
.
I
n
ad
d
itio
n
,
a
web
-
b
ased
s
y
s
tem
em
p
lo
y
in
g
RF
,
SV
M,
an
d
DT
alg
o
r
ith
m
s
was d
ev
elo
p
ed
to
p
r
ed
ict
s
tu
d
en
t
–
c
o
u
r
s
e
s
u
itab
ilit
y
,
with
RF
ac
h
iev
in
g
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
9
5
%,
t
h
er
eb
y
e
n
h
an
cin
g
ac
ad
em
ic
g
u
id
a
n
ce
an
d
r
ed
u
ci
n
g
cu
r
r
icu
lu
m
m
is
m
atch
es
[
1
2
]
.
T
h
is
s
ec
tio
n
also
r
ev
iews
o
f
s
ev
er
al
p
r
ev
io
u
s
s
tu
d
ies
f
o
cu
s
in
g
o
n
th
e
a
p
p
licatio
n
o
f
ML
m
eth
o
d
s
in
s
tu
d
en
t
ad
m
is
s
io
n
p
r
ed
ictio
n
s
y
s
tem
s
.
T
h
e
r
ev
iew
aim
s
to
ex
am
in
e
th
e
ap
p
r
o
ac
h
es,
alg
o
r
ith
m
s
,
an
d
f
in
d
in
g
s
o
f
th
ese
s
tu
d
ies,
as
well
as
to
id
en
tify
r
em
ai
n
in
g
r
esear
c
h
g
ap
s
.
T
ab
le
1
p
r
o
v
id
es
a
co
m
p
ar
is
o
n
o
f
s
elec
ted
r
elev
an
t
s
tu
d
ies
t
h
at
s
er
v
e
as
t
h
e
f
o
u
n
d
atio
n
f
o
r
th
is
r
esear
c
h
,
p
a
r
ticu
lar
ly
co
n
ce
r
n
in
g
th
e
u
s
e
o
f
k
er
n
el
-
b
ased
SVM
m
eth
o
d
s
to
en
h
an
ce
p
r
ed
ictio
n
ac
cu
r
ac
y
.
R
ef
er
r
in
g
to
th
e
an
aly
s
is
p
r
esen
ted
in
T
ab
le
1
[
1
3
]
–
[
1
7
]
(
s
ee
in
ap
p
e
n
d
ix
)
,
it
is
ev
i
d
en
t
th
at
f
u
r
th
er
i
n
v
esti
g
atio
n
is
r
e
q
u
ir
ed
t
o
ass
ess
th
e
ef
f
ec
tiv
en
ess
o
f
k
er
n
el
-
b
ased
ap
p
r
o
ac
h
es.
T
h
er
ef
o
r
e,
th
is
s
tu
d
y
ev
alu
ates
th
e
im
p
ac
t
o
f
v
ar
io
u
s
SVM
k
er
n
els,
in
clu
d
in
g
n
o
r
m
alize
d
p
o
ly
n
o
m
ial,
lin
ea
r
,
r
a
d
ial
b
asis
f
u
n
ctio
n
(
RBF
)
,
an
d
Pear
s
o
n
VI
I
f
u
n
ctio
n
-
b
ased
u
n
iv
er
s
al
k
er
n
el
(
PUK
)
,
o
n
p
r
ed
ictio
n
ac
cu
r
ac
y
a
n
d
g
en
er
aliza
tio
n
ca
p
a
b
ilit
y
u
s
in
g
m
u
ltip
le
ev
alu
atio
n
m
etr
ics
s
u
ch
as
ac
cu
r
ac
y
,
r
ec
all
,
p
r
ec
is
io
n
,
F1
-
m
ea
s
u
r
e
,
Ma
tth
ews
co
r
r
elatio
n
co
ef
f
ici
en
t
(
MCC
)
,
an
d
r
ec
eiv
er
o
p
e
r
atin
g
ch
ar
ac
ter
is
tic
(
R
OC
)
.
Mo
r
eo
v
er
,
th
is
s
tu
d
y
em
p
h
asizes
th
e
im
p
o
r
tan
ce
o
f
k
er
n
el
s
elec
tio
n
as
a
cr
itical
f
ac
to
r
in
ac
h
iev
in
g
ac
cu
r
ate
class
if
icatio
n
.
2.
M
E
T
H
O
D
2
.
1
.
Da
t
a
s
et
T
h
e
ca
s
e
s
tu
d
y
was
co
n
d
u
cte
d
at
a
u
n
i
v
er
s
ity
in
I
n
d
o
n
esia.
T
h
e
d
ataset
co
n
s
is
ts
o
f
n
e
w
s
tu
d
en
t
ad
m
is
s
io
n
s
r
ec
o
r
d
s
co
llected
o
v
er
a
f
i
v
e
-
y
ea
r
p
er
io
d
f
r
o
m
2
0
1
6
to
2
0
2
0
,
co
m
p
r
is
in
g
5
9
3
6
r
ec
o
r
d
s
an
d
1
1
attr
ib
u
tes.
T
h
ese
attr
ib
u
te
s
in
clu
d
e
n
u
m
b
er
,
n
am
e
,
m
a
jo
r
,
y
ea
r
,
g
e
n
d
er
,
p
lace
o
f
b
ir
th
,
d
ate
o
f
b
ir
th
,
s
u
b
-
d
is
tr
ict,
d
is
tr
ict,
ag
e,
an
d
class
.
No
t
all
f
ea
tu
r
es
a
r
e
i
n
co
r
p
o
r
ated
i
n
to
th
e
p
r
e
d
ictiv
e
m
o
d
el,
as
th
eir
in
clu
s
io
n
was
d
eter
m
in
ed
b
as
ed
o
n
r
ele
v
an
ce
an
d
r
ed
u
n
d
a
n
cy
cr
iter
ia.
Date
o
f
b
ir
th
wa
s
ex
clu
d
ed
as
ag
e
p
r
o
v
id
es
eq
u
iv
alen
t
in
f
o
r
m
at
io
n
,
wh
ile
n
u
m
b
er
a
n
d
n
a
m
e
wer
e
r
em
o
v
e
d
as
n
o
n
-
in
f
o
r
m
ativ
e
id
en
tifie
r
s
.
Attr
ib
u
tes
s
u
ch
as
g
en
d
e
r
,
p
lace
o
f
b
ir
th
,
s
u
b
-
d
is
tr
ict,
an
d
d
is
tr
ict
ar
e
o
m
itted
d
u
e
to
p
o
te
n
tial
b
ias
o
r
lim
ited
g
en
er
aliza
b
ilit
y
,
e
x
ce
p
t
i
n
co
n
tex
ts
wh
er
e
lo
ca
tio
n
-
b
ased
o
r
q
u
o
ta
-
d
r
iv
en
ad
m
is
s
io
n
p
o
licies
ap
p
ly
.
C
o
n
v
er
s
ely
,
m
aj
o
r
,
y
ea
r
,
an
d
ag
e
wer
e
r
etain
ed
as
k
e
y
p
r
e
d
ictiv
e
v
ar
ia
b
les,
with
class
s
er
v
in
g
as
th
e
tar
g
et
v
ar
iab
le.
I
n
to
tal,
f
o
u
r
attr
ib
u
tes
wer
e
u
tili
ze
d
in
th
e
a
n
aly
s
is
.
A
to
tal
o
f
2
3
m
is
s
in
g
v
alu
e
s
wer
e
id
en
tifie
d
in
th
e
s
u
b
-
d
is
tr
ict
an
d
d
is
tr
ict
attr
ib
u
tes;
h
o
wev
er
,
th
ese
wer
e
ex
clu
d
ed
f
r
o
m
th
e
an
aly
s
is
d
u
e
to
th
eir
ir
r
elev
an
ce
.
No
d
u
p
licate
r
ec
o
r
d
s
wer
e
d
etec
ted
af
ter
ap
p
ly
i
n
g
a
d
u
p
licate
-
r
em
o
v
al
ch
ec
k
.
2
.
2
.
Su
pp
o
rt
v
ec
t
o
r
ma
chine
T
h
e
SVM
is
o
n
e
o
f
t
h
e
m
o
s
t
wid
ely
u
s
ed
s
u
p
er
v
is
ed
ML
al
g
o
r
ith
m
s
f
o
r
s
o
lv
in
g
p
r
o
b
lem
s
r
elate
d
to
class
if
icatio
n
,
r
eg
r
ess
io
n
,
r
ec
o
g
n
itio
n
,
a
n
d
tim
e
s
er
ies
an
aly
s
is
.
SVM
h
as
g
ain
ed
s
ig
n
if
ican
t
p
o
p
u
lar
ity
d
u
e
t
o
its
f
ea
tu
r
es
s
u
ch
as
s
tr
o
n
g
g
en
er
aliza
tio
n
a
b
ilit
y
,
h
i
g
h
p
r
ed
ictio
n
ac
cu
r
ac
y
,
an
d
r
a
p
id
tr
ain
in
g
s
p
ee
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
4
8
4
-
2
4
9
3
2486
SVM
p
er
f
o
r
m
s
well
with
s
m
all
s
am
p
le
d
ata
s
izes
an
d
ex
h
ib
its
h
ig
h
ef
f
ec
tiv
en
ess
in
cla
s
s
if
y
in
g
b
o
t
h
lin
ea
r
an
d
n
o
n
-
lin
ea
r
d
ata.
I
n
a
b
in
a
r
y
class
if
icatio
n
p
r
o
b
lem
,
let
th
er
e
b
e
s
ev
er
al
tr
ain
in
g
s
am
p
les
r
ep
r
esen
ted
as
=
{
1
,
2
,
3
,
…
,
}
in
th
e
in
p
u
t
s
p
ac
e
w
h
er
e
an
d
th
eir
co
r
r
esp
o
n
d
in
g
la
b
els
ar
e
r
ep
r
esen
ted
as
{
−
1
,
+
1
}
[
1
8
]
.
2
.
2
.
1
.
Su
pp
o
rt
v
ec
t
o
r
m
a
chi
ne
k
er
nel f
un
ct
io
n
T
r
ain
in
g
s
am
p
les
th
at
ar
e
lo
ca
ted
clo
s
er
to
th
e
h
y
p
er
p
lan
e
ar
e
r
ef
er
r
ed
to
as
s
u
p
p
o
r
t
v
e
cto
r
s
[
1
9
]
.
T
h
e
m
ax
im
u
m
m
a
r
g
in
h
y
p
er
p
lan
e
is
also
k
n
o
wn
as
t
h
e
o
p
tim
al
s
ep
ar
atin
g
h
y
p
er
p
lan
e
(
OSH)
.
Ma
p
p
in
g
tr
ain
in
g
s
am
p
les
f
r
o
m
th
e
in
p
u
t
s
p
ac
e
to
h
ig
h
er
-
d
im
e
n
s
io
n
a
l
s
p
ac
es
i
s
ac
co
m
p
lis
h
ed
u
s
in
g
a
k
er
n
el
f
u
n
ctio
n
(
,
)
as illu
s
tr
ated
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
Ker
n
el
-
b
ased
h
i
g
h
-
d
im
en
s
io
n
al
f
ea
tu
r
e
m
ap
p
in
g
[
2
0
]
SVM
h
as
k
er
n
els
a
s
tu
n
i
n
g
p
ar
am
eter
s
.
T
h
e
k
er
n
el
s
ca
n
b
e
lin
ea
r
,
R
B
F,
s
i
g
m
o
id
,
o
r
p
o
ly
n
o
m
ial
[
2
1
]
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
is
v
er
i
f
ied
an
d
c
o
m
p
ar
ed
with
th
e
R
B
F
k
er
n
el,
s
ig
m
o
id
k
e
r
n
el,
an
d
n
o
r
m
alize
d
p
o
ly
k
e
r
n
el
(
NPK)
SVM
[
2
2
]
.
T
h
e
NPK
ac
h
iev
e
s
s
im
ilar
ity
n
o
t
o
n
ly
in
th
e
f
u
n
ctio
n
s
s
tated
in
th
e
in
p
u
t
s
am
p
les
b
u
t
also
in
th
eir
co
m
b
in
atio
n
s
[
2
3
]
.
T
h
e
lin
ea
r
k
er
n
el
(
L
K)
is
ef
f
ec
tiv
e
wh
en
d
ata
ca
n
b
e
s
ep
ar
ated
lin
ea
r
ly
,
w
h
ile
th
e
NPK
r
esem
b
les
th
e
LK
.
I
n
t
h
e
W
aik
ato
en
v
ir
o
n
m
en
t
f
o
r
k
n
o
wled
g
e
an
aly
s
is
(
W
E
KA
)
d
ata
m
in
i
n
g
ap
p
licat
io
n
,
SVM
is
r
ef
er
r
e
d
t
o
as
s
eq
u
en
tial
m
in
im
al
o
p
tim
izatio
n
(
SMO)
an
d
co
n
s
is
ts
o
f
6
k
er
n
els:
NPK
,
p
o
ly
/
LK
,
m
atr
ix
k
er
n
el
,
PUK
k
er
n
el,
R
B
F
k
er
n
el,
an
d
s
tr
in
g
k
er
n
e
l.
I
n
th
is
s
tu
d
y
,
o
n
ly
f
o
u
r
k
er
n
el
f
u
n
ctio
n
s
ar
e
u
s
ed
:
NPK
,
LK
,
R
B
F
k
er
n
el
,
an
d
PUK
k
er
n
el
.
T
h
e
s
ig
m
o
id
k
er
n
el
is
n
o
t
a
v
ailab
le
in
th
e
latest
v
e
r
s
io
n
o
f
W
E
KA
b
ec
au
s
e
it
d
o
es
n
o
t
alwa
y
s
s
atis
f
y
th
e
p
o
s
itiv
e
s
em
i
-
d
e
f
in
ite
p
r
o
p
e
r
ty
,
wh
ich
o
f
ten
lead
s
to
n
u
m
er
ical
in
s
tab
ilit
y
an
d
c
o
n
v
e
r
g
en
ce
is
s
u
es
d
u
r
in
g
SVM
tr
ain
in
g
,
its
p
er
f
o
r
m
an
ce
also
ten
d
s
to
b
e
less
co
n
s
is
ten
t c
o
m
p
ar
ed
to
th
e
R
B
F o
r
PUK
k
er
n
el
,
th
er
ef
o
r
e
th
e
W
E
KA
d
ev
elo
p
er
s
d
ec
id
ed
to
r
em
o
v
e
th
e
s
ig
m
o
id
k
er
n
el
an
d
r
ep
lac
e
it
with
th
e
PUK
k
e
r
n
el
,
wh
ic
h
o
f
f
er
s
g
r
ea
ter
s
tab
ilit
y
,
f
lex
i
b
ilit
y
,
an
d
ac
cu
r
ac
y
in
d
ata
class
if
icatio
n
task
s
.
Fo
r
m
u
las
f
o
r
t
h
e
f
o
u
r
k
e
r
n
el
f
u
n
ctio
n
s
m
en
tio
n
ed
as in
(
1
)
to
(
4
)
[
2
4
]
.
:
(
,
)
=
<
,
>
2
.
0
(
<
,
>
2
.
0
∗
<
,
>
2
.
0
)
(
1
2
)
(
1
)
:
(
,
)
=
<
,
>
(
2
)
:
(
,
)
=
(
−
∗
(
−
)
2
)
(
3
)
:
(
,
′
)
=
1
(
1
+
(
√
|
|
−
′
|
|
2
.
2
⍵
1
−
1
2
)
2
)
⍵
(
4
)
2
.
3
.
P
er
f
o
r
m
a
nce
ev
a
lua
t
io
n m
et
rics
T
h
e
class
if
ic
ati
o
n
p
e
r
f
o
r
m
a
n
c
e
is
e
v
al
u
at
e
d
u
s
i
n
g
p
er
f
o
r
m
a
n
ce
m
ea
s
u
r
es
s
u
ch
as
ac
c
u
r
a
c
y
,
p
r
ec
is
i
o
n
,
r
e
ca
ll
,
F
-
m
e
asu
r
e
,
an
d
a
co
n
f
u
s
io
n
m
at
r
i
x
.
T
h
ese
m
e
tr
ics
h
e
l
p
ass
ess
class
if
i
ca
ti
o
n
e
r
r
o
r
s
,
f
alse
p
o
s
it
iv
es
(
FP
)
,
an
d
f
alse
n
e
g
at
iv
es
(
FN
)
.
T
h
e
y
p
r
o
v
id
e
a
cl
ea
r
b
as
is
f
o
r
m
ea
s
u
r
in
g
t
h
e
m
o
d
e
l’
s
cl
ass
i
f
ic
ati
o
n
q
u
a
lit
y
.
i)
Acc
u
r
ac
y
: a
cc
u
r
ac
y
is
ca
lcu
lated
u
s
in
g
(
5
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
P
r
ed
ictio
n
o
f n
ew s
tu
d
en
t a
d
m
is
s
io
n
s
to
h
ig
h
er e
d
u
ca
tio
n
u
s
in
g
s
u
p
p
o
r
t v
ec
to
r
ma
ch
in
es
(
N
en
i P
u
r
w
a
ti
)
2487
=
+
+
+
+
(
5
)
W
h
er
e
tr
u
e
p
o
s
itiv
es
(
T
P)
r
ef
er
to
p
o
s
itiv
es
th
at
ar
e
class
if
ied
co
r
r
ec
tly
,
t
r
u
e
n
e
g
ativ
es
(
T
N)
r
ef
e
r
t
o
n
eg
ativ
es
th
at
ar
e
class
if
ied
co
r
r
ec
tly
,
FP
r
ef
er
to
n
eg
ativ
es
th
at
ar
e
class
if
ied
in
co
r
r
ec
tly
,
an
d
FN
r
ef
er
to
p
o
s
itiv
es th
at
ar
e
class
if
ied
in
co
r
r
ec
tly
[
2
5
]
,
[
2
6
]
.
ii)
Pre
cisi
o
n
:
p
r
ec
is
io
n
is
th
e
p
r
o
p
o
r
tio
n
o
f
co
r
r
ec
tly
class
if
ied
p
o
s
itiv
e
class
in
s
tan
ce
s
o
u
t
o
f
t
h
e
to
tal
class
if
ied
in
s
tan
ce
s
o
f
th
at
class
.
Pre
cisi
o
n
is
m
ea
s
u
r
ed
u
s
in
g
(
6
)
[
2
0
]
.
=
+
(
6
)
iii)
R
ec
all
:
r
ec
all
is
a
m
ea
s
u
r
e
o
f
test
in
g
ac
cu
r
ac
y
c
o
n
s
id
er
in
g
p
r
ec
is
io
n
an
d
co
m
p
u
tatio
n
al
r
eq
u
ir
em
e
n
ts
,
ca
lcu
lated
u
s
in
g
(
7
)
[
2
7
]
.
=
+
(
7
)
iv
)
F1
-
m
ea
s
u
r
e
:
F1
-
m
ea
s
u
r
e
is
th
e
m
ea
n
b
etwe
en
p
r
ec
is
io
n
an
d
r
ec
all
.
I
t
r
an
g
es
b
etw
ee
n
0
an
d
1
.
F1
-
m
ea
s
u
r
e
is
m
ea
s
u
r
ed
u
s
in
g
(
8
)
[
2
0
]
.
1
−
=
2
×
×
+
(
8
)
v)
MCC
:
M
C
C
i
s
cr
u
cial
as
it
r
ep
r
esen
ts
th
e
co
r
r
elatio
n
b
etwe
en
th
e
tar
g
et
an
d
p
r
e
d
icted
v
al
u
es
g
en
er
ate
d
f
r
o
m
class
if
icatio
n
,
an
d
is
f
o
r
m
u
lated
as
in
(
9
)
[
2
8
]
.
=
×
−
×
√
(
+
)
(
+
)
(
+
)
(
+
)
(
9
)
v
i)
R
OC
:
t
h
e
R
O
C
cu
r
v
e
r
ep
r
es
en
ts
th
e
r
elatio
n
s
h
ip
b
etwe
en
th
e
FP
an
d
th
e
T
P
f
o
r
v
ar
i
o
u
s
th
r
esh
o
ld
v
alu
es,
s
tatis
tically
u
s
ed
to
e
v
alu
ate
th
e
e
f
f
ec
tiv
en
ess
o
f
d
if
f
er
en
t
class
if
ier
s
.
T
h
e
ar
ea
u
n
d
er
th
e
cu
r
v
e
(
AUC),
wh
er
e
a
class
if
ier
with
an
AUC
o
f
1
.
0
i
n
d
icate
s
a
h
ig
h
-
lev
el
AUC
an
d
d
em
o
n
s
tr
ates
b
etter
p
er
f
o
r
m
an
ce
[
2
9
]
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
tu
d
y
em
p
lo
y
s
d
ata
m
o
d
ellin
g
u
s
in
g
l
o
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
C
lass
if
ier
v
er
s
io
n
4
.
5
(
C
4
.
5
)
DT
,
an
d
n
ai
v
e
B
ay
es
(
NB
)
as
b
a
s
elin
e
class
if
icatio
n
m
o
d
els.
T
h
e
r
esu
ltin
g
ac
cu
r
ac
y
v
alu
e
s
ar
e
p
r
esen
ted
in
T
ab
le
2
.
T
h
e
test
r
esu
lts
p
r
e
s
en
ted
in
T
ab
le
2
in
d
icate
th
at
th
e
th
r
ee
m
o
d
els:
L
R
,
C
4
.
5
,
an
d
NB
,
h
av
e
r
elativ
ely
co
n
s
is
ten
t
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
v
ar
i
o
u
s
v
alid
atio
n
m
eth
o
d
s
.
I
n
b
o
th
th
e
u
s
e
tr
a
in
in
g
s
et
an
d
cr
o
s
s
v
alid
atio
n
f
o
ld
-
10
(
C
VF
-
10)
t
ests
,
th
e
ac
cu
r
ac
y
o
f
L
R
an
d
C
4
.
5
is
n
ea
r
ly
id
en
tical
(
ap
p
r
o
x
im
ately
9
5
.
7
%),
s
lig
h
tly
h
ig
h
er
th
an
th
at
o
f
NB
(
9
4
.
9
%).
W
h
en
test
ed
with
a
7
0
% tr
ain
in
g
an
d
3
0
% testi
n
g
d
ata
s
p
lit,
th
e
C
4
.
5
m
o
d
el
o
b
tain
e
d
th
e
h
ig
h
est
a
cc
u
r
ac
y
o
f
9
6
.
2
3
%,
f
o
llo
wed
b
y
L
R
with
9
6
.
1
8
%
an
d
NB
with
9
5
.
3
3
%.
T
h
e
m
in
im
al
v
ar
ian
ce
in
ac
cu
r
ac
y
ac
r
o
s
s
m
o
d
els
s
u
g
g
ests
s
t
r
o
n
g
g
en
er
aliza
tio
n
ca
p
ab
ilit
y
,
alth
o
u
g
h
C
4
.
5
p
er
f
o
r
m
s
m
ar
g
i
n
ally
b
etter
d
u
e
to
its
ab
ilit
y
to
ca
p
tu
r
e
n
o
n
-
lin
ea
r
attr
ib
u
te
in
ter
ac
tio
n
s
an
d
e
x
ec
u
te
m
o
r
e
ef
f
ec
tiv
e
d
ata
s
eg
m
en
tatio
n
.
I
n
th
e
ev
alu
atio
n
with
an
8
0
%
tr
ain
in
g
an
d
2
0
%
test
in
g
d
at
a
s
p
lit,
all
m
o
d
els
d
em
o
n
s
tr
ated
im
p
r
o
v
ed
ac
c
u
r
ac
y
.
T
h
e
C
4
.
5
m
o
d
el
m
ain
tain
ed
th
e
h
ig
h
est
p
er
f
o
r
m
an
ce
(
9
6
.
5
4
%),
f
o
llo
wed
b
y
L
R
at
9
6
.
4
6
%
a
n
d
NB
at
9
5
.
4
5
%.
T
h
is
en
h
an
c
em
en
t
s
u
g
g
ests
th
at
i
n
cr
ea
s
in
g
th
e
p
r
o
p
o
r
tio
n
o
f
tr
ain
in
g
d
ata
en
a
b
les
th
e
m
o
d
els
to
b
etter
ca
p
tu
r
e
u
n
d
er
ly
in
g
p
atter
n
s
,
th
er
eb
y
e
n
h
an
cin
g
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
.
T
h
ese
f
i
n
d
in
g
s
f
u
r
th
er
co
n
f
ir
m
t
h
e
c
o
n
s
is
ten
t
s
u
p
er
io
r
ity
o
f
th
e
C
4
.
5
m
o
d
el
am
o
n
g
th
e
th
r
ee
b
aselin
e
alg
o
r
ith
m
s
.
T
ab
le
2
.
Mo
d
el
co
m
p
ar
is
o
n
Te
st
o
p
t
i
o
n
/
me
t
h
o
d
LR
(
%)
C
4
.
5
(
%)
NB
(
%)
U
se
t
r
a
i
n
i
n
g
se
t
(
U
TS
)
9
5
.
7
8
9
5
.
7
5
9
4
.
9
1
C
V
F
-
10
9
5
.
7
7
9
5
.
7
5
9
4
.
9
1
P
e
r
c
e
n
t
a
g
e
s
p
l
i
t
(
PS
)
-
7
0
%
9
6
.
1
8
9
6
.
2
3
9
5
.
3
3
PS
-
80%
9
6
.
4
6
9
6
.
5
4
9
5
.
4
5
T
h
e
r
esear
c
h
p
r
o
ce
s
s
was
c
ar
r
ied
o
u
t
b
y
s
ettin
g
th
e
h
y
p
er
p
a
r
am
eter
c
=1
.
0
f
o
r
al
l
k
er
n
els,
g
am
m
a
=0
.
0
1
f
o
r
th
e
R
B
F
k
er
n
el,
o
m
eg
a
=1
.
0
,
an
d
s
ig
m
a
=1
.
0
f
o
r
th
e
PUK
k
er
n
el.
T
h
e
r
esu
ltin
g
ac
cu
r
ac
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
4
8
4
-
2
4
9
3
2488
v
alu
es
f
o
r
th
e
f
o
u
r
k
er
n
el
ty
p
e
s
in
th
e
SVM
m
o
d
el,
b
ased
o
n
th
e
d
ataset
d
escr
ib
ed
ea
r
lier
,
ar
e
s
u
m
m
ar
ized
in
T
ab
le
3
.
I
n
T
a
b
le
3
,
th
e
test
r
esu
lts
in
d
icate
th
at
all
f
o
u
r
S
VM
k
er
n
el
ty
p
es,
n
o
r
m
alize
d
p
o
ly
n
o
m
ial,
lin
ea
r
,
R
B
F,
an
d
PUK,
ac
h
iev
e
d
id
en
tical
ac
cu
r
ac
y
ac
r
o
s
s
all
e
v
alu
atio
n
s
ce
n
ar
i
o
s
,
in
clu
d
i
n
g
u
s
e
tr
ain
in
g
s
et,
10
-
f
o
l
d
cr
o
s
s
v
alid
atio
n
,
PS
7
0
%,
an
d
8
0
%.
T
h
e
co
n
s
is
ten
t
ac
cu
r
ac
y
v
alu
es
(
r
a
n
g
in
g
f
r
o
m
9
5
.
7
%
to
9
6
.
5
%)
in
d
icate
th
at
th
e
ch
o
ice
o
f
k
er
n
el
h
as
n
o
s
ig
n
if
ican
t
im
p
ac
t
o
n
th
e
m
o
d
el’
s
p
er
f
o
r
m
a
n
ce
f
o
r
th
is
d
ataset.
T
h
is
in
d
icate
s
th
at
th
e
d
ata
p
atter
n
s
ar
e
r
elativ
ely
lin
ea
r
an
d
n
o
t
h
ig
h
ly
c
o
m
p
lex
,
allo
win
g
all
k
er
n
els
to
s
ep
ar
ate
th
e
class
es
eq
u
ally
ef
f
ec
tiv
ely
.
Fu
r
th
er
m
o
r
e,
t
h
e
ac
cu
r
ac
y
im
p
r
o
v
em
e
n
t
in
th
e
7
0
%
an
d
8
0
%
PS
s
ce
n
ar
io
s
d
em
o
n
s
tr
ates
th
at
in
cr
ea
s
in
g
th
e
am
o
u
n
t
o
f
tr
ain
in
g
d
ata
en
h
an
ce
s
th
e
m
o
d
el
’
s
ab
ilit
y
to
r
ec
o
g
n
ize
d
ata
p
atter
n
s
an
d
im
p
r
o
v
e
p
r
e
d
ictiv
e
p
er
f
o
r
m
an
ce
.
T
ab
le
3
.
Acc
u
r
ac
y
v
al
u
e
r
esu
lt
s
Te
st
o
p
t
i
o
n
A
c
c
u
r
a
c
y
A
c
c
u
r
a
c
y
k
e
r
n
e
l
t
y
p
e
N
u
mb
e
r
o
f
c
l
a
ss
e
s
N
P
K
(
%)
N
u
mb
e
r
o
f
c
l
a
ss
e
s
LK
(
%)
N
u
mb
e
r
o
f
c
l
a
ss
e
s
RBF
(
%)
N
u
mb
e
r
o
f
c
l
a
ss
e
s
P
U
K
(
%)
U
TS
CCI
5
,
6
8
4
9
5
.
7
5
,
6
8
4
9
5
.
7
5
,
6
8
4
9
5
.
7
5
,
6
8
4
9
5
.
7
I
C
I
2
5
2
4
.
2
2
5
2
4
.
2
2
5
2
4
.
2
2
5
2
4
.
2
C
V
F
-
10
CCI
5
,
6
8
4
9
5
.
7
5
,
6
8
4
9
5
.
7
5
,
6
8
4
9
5
.
7
5
,
6
8
4
9
5
.
7
I
C
I
2
5
2
4
.
2
2
5
2
4
.
2
2
5
2
4
.
2
2
5
2
4
.
2
PS
-
70%
CCI
1
,
7
1
4
9
6
.
2
1
,
7
1
4
9
6
.
2
1
,
7
1
4
9
6
.
2
1
,
7
1
4
9
6
.
2
I
C
I
67
3
.
7
67
3
.
7
67
3
.
7
67
3
.
7
PS
-
80%
CCI
1
,
1
4
6
9
6
.
5
1
,
1
4
6
9
6
.
5
1
,
1
4
6
9
6
.
5
1
,
1
4
6
9
6
.
5
I
C
I
41
3
.
4
41
3
.
4
41
3
.
4
41
3
.
4
D
e
scri
p
t
i
o
n
:
C
C
I
=
c
o
r
r
e
c
t
l
y
c
l
a
s
si
f
i
e
d
i
n
s
t
a
n
c
e
s,
I
C
C
=
i
n
c
o
r
r
e
c
t
l
y
c
l
a
ss
i
f
i
e
d
i
n
st
a
n
c
e
s
Per
f
o
r
m
an
ce
m
ea
s
u
r
e
v
alu
es
c
o
n
s
is
tin
g
o
f
p
r
ec
is
io
n
,
r
ec
all,
an
d
F
-
m
ea
s
u
r
e
wer
e
also
co
m
p
u
ted
,
an
d
th
e
r
esu
lts
ar
e
s
u
m
m
ar
ized
in
T
ab
le
4
.
T
ab
le
4
s
h
o
ws
t
h
at
am
o
n
g
th
e
f
o
u
r
k
er
n
el
ty
p
es
an
d
f
o
u
r
ev
alu
ati
o
n
m
eth
o
d
s
(
UT
S,
C
VF
-
1
0
,
PS
-
7
0
%,
an
d
PS
-
8
0
%),
th
e
h
ig
h
est
p
er
f
o
r
m
an
ce
m
etr
ics
wer
e
o
b
tain
ed
u
s
in
g
t
h
e
PS
-
7
0
%,
f
o
r
all
k
er
n
els
u
n
d
er
th
is
co
n
f
ig
u
r
atio
n
,
th
e
p
r
ec
is
io
n
,
F
-
m
ea
s
u
r
e,
an
d
MCC
v
al
u
es
wer
e
u
n
d
ef
in
ed
d
u
e
to
th
e
ab
s
en
ce
o
f
in
s
tan
ce
s
o
r
p
r
ed
ictio
n
s
th
at
e
n
ab
led
c
alcu
latio
n
f
o
r
ce
r
tain
class
es.
Ho
wev
er
,
t
h
e
r
ec
all
v
alu
e
r
ea
ch
ed
0
.
9
6
2
,
an
d
th
e
AUC
was
0
.
5
0
0
.
W
h
en
test
ed
with
PS
-
8
0
%,
th
e
r
esu
lts
in
d
icate
d
a
s
lig
h
t
im
p
r
o
v
em
e
n
t in
r
ec
all
f
o
r
all
k
er
n
els (
0
.
9
6
5
)
,
w
h
ile
th
e
o
th
e
r
p
er
f
o
r
m
an
ce
m
et
r
ics r
em
ain
e
d
u
n
ch
an
g
e
d
.
T
ab
le
4
.
Per
f
o
r
m
an
ce
m
ea
s
u
r
e
weig
h
ted
av
er
a
g
e
v
alu
e
K
e
r
n
e
l
t
y
p
e
Te
st
o
p
t
i
o
n
AUC
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F
-
mea
su
r
e
M
C
C
N
P
K
U
TS
0
.
5
0
0
?
0
.
9
5
8
?
?
C
V
F
-
10
0
.
5
0
0
?
0
.
9
5
8
?
?
PS
-
70%
0
.
5
0
0
?
0
.
9
6
2
?
?
PS
-
80%
0
.
5
0
0
?
0
.
9
6
5
?
?
LK
U
TS
0
.
5
0
0
?
0
.
9
5
8
?
?
C
V
F
-
10
0
.
5
0
0
?
0
.
9
5
8
?
?
PS
-
70%
0
.
5
0
0
?
0
.
9
6
2
?
?
PS
-
80%
0
.
5
0
0
?
0
.
9
6
5
?
?
RBF
U
TS
0
.
5
0
0
?
0
.
9
5
8
?
?
C
V
F
-
10
0
.
5
0
0
?
0
.
9
5
8
?
?
PS
-
70%
0
.
5
0
0
?
0
.
9
6
2
?
?
PS
-
80%
0
.
5
0
0
?
0
.
9
6
5
?
?
P
U
K
U
TS
0
.
5
0
0
?
0
.
9
5
8
?
?
C
V
F
-
10
0
.
5
0
0
?
0
.
9
5
8
?
?
PS
-
70%
0
.
5
0
0
?
0
.
9
6
2
?
?
PS
-
80%
0
.
5
0
0
?
0
.
9
6
5
?
?
T
h
e
co
n
f
u
s
io
n
m
atr
i
x
v
alu
es
f
r
o
m
th
e
c
o
n
d
u
cted
test
in
g
ca
n
b
e
s
ee
n
in
T
a
b
le
5
.
T
h
is
tab
le
ex
p
lain
s
th
at
th
e
co
n
f
u
s
io
n
m
atr
ix
in
d
i
ca
tes th
at
all
f
o
u
r
SVM
k
er
n
els (
n
o
r
m
alize
d
p
o
ly
n
o
m
ial,
lin
ea
r
,
R
B
F,
an
d
PUK
)
y
ield
a
h
ig
h
n
u
m
b
er
o
f
TN
wh
ile
r
ep
o
r
tin
g
ze
r
o
TP
,
s
u
g
g
esti
n
g
th
at
th
e
m
o
d
el
class
if
ies
all
in
s
tan
ce
s
ex
clu
s
iv
ely
as
th
e
n
eg
ativ
e
class
.
De
s
p
ite
th
e
s
ee
m
in
g
ly
h
i
g
h
ac
cu
r
ac
y
,
th
e
m
o
d
el
is
u
n
ab
le
to
id
en
tify
th
e
p
o
s
itiv
e
class
,
r
ev
ea
lin
g
a
s
ig
n
if
ican
t
is
s
u
e
o
f
class
im
b
alan
ce
.
T
h
e
ap
p
licatio
n
o
f
C
lass
B
alan
ce
r
s
er
v
es
as
a
n
ef
f
icien
t
ap
p
r
o
ac
h
to
ad
d
r
ess
c
lass
im
b
alan
ce
with
o
u
t
m
o
d
if
y
in
g
t
h
e
d
ataset
b
y
ad
d
i
n
g
o
r
r
em
o
v
in
g
in
s
tan
ce
s
,
th
is
f
ilter
f
u
n
ctio
n
s
b
y
r
ew
eig
h
tin
g
ea
c
h
in
s
tan
ce
,
en
s
u
r
in
g
th
at
th
e
m
in
o
r
ity
cla
s
s
ex
er
ts
in
f
lu
en
ce
co
m
p
ar
ab
le
to
t
h
e
m
ajo
r
ity
cl
ass
d
u
r
in
g
m
o
d
el
tr
ai
n
in
g
.
As
a
r
esu
lt,
th
e
m
o
d
el
r
e
d
u
ce
s
its
b
ias
to
war
d
th
e
d
o
m
in
an
t
“a
cc
e
p
ted
”
class
an
d
b
ec
o
m
es
m
o
r
e
r
esp
o
n
s
iv
e
t
o
th
e
“u
n
ac
ce
p
ted
”
class
,
th
e
r
eb
y
en
h
an
cin
g
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
P
r
ed
ictio
n
o
f n
ew s
tu
d
en
t a
d
m
is
s
io
n
s
to
h
ig
h
er e
d
u
ca
tio
n
u
s
in
g
s
u
p
p
o
r
t v
ec
to
r
ma
ch
in
es
(
N
en
i P
u
r
w
a
ti
)
2489
eq
u
ilib
r
iu
m
b
etwe
en
o
v
er
all
ac
cu
r
ac
y
a
n
d
m
in
o
r
ity
class
d
etec
tio
n
p
er
f
o
r
m
a
n
ce
.
T
h
e
p
ar
am
eter
c
p
la
y
s
a
cr
u
cial
r
o
le
in
co
n
tr
o
llin
g
t
h
e
co
m
p
lex
ity
o
f
th
e
SVM
m
o
d
el
b
y
b
alan
cin
g
m
ar
g
i
n
m
ax
im
izatio
n
an
d
to
ler
an
ce
to
class
if
icatio
n
er
r
o
r
s
.
An
ex
ce
s
s
iv
ely
lar
g
e
o
r
s
m
all
c
v
alu
e
m
a
y
r
esu
l
t
in
o
v
er
f
itti
n
g
o
r
u
n
d
er
f
itti
n
g
;
th
er
ef
o
r
e
,
d
eter
m
in
in
g
an
o
p
tim
al
c
v
alu
e
i
s
ess
en
tia
l
f
o
r
m
ain
tain
in
g
m
o
d
el
s
tab
ilit
y
an
d
ac
cu
r
ac
y
,
e
v
en
wh
e
n
o
th
er
k
e
r
n
el
p
ar
am
eter
s
(
s
u
c
h
as
g
am
m
a,
o
m
eg
a
,
an
d
s
ig
m
a
)
ar
e
p
r
o
p
er
ly
c
o
n
f
ig
u
r
ed
.
Fo
llo
win
g
th
e
a
p
p
licatio
n
o
f
th
e
C
lass
B
alan
ce
r
tech
n
iq
u
e
,
u
s
in
g
h
y
p
e
r
p
ar
am
ete
r
s
c
=
1
.
0
f
o
r
all
k
er
n
els,
g
am
m
a
=
0
.
0
1
f
o
r
t
h
e
R
B
F
k
er
n
el,
an
d
o
m
e
g
a
=1
.
0
with
s
ig
m
a
=
1
.
0
f
o
r
th
e
PUK
k
er
n
el,
th
e
ac
h
iev
ed
ac
cu
r
ac
y
an
d
co
r
r
esp
o
n
d
in
g
c
o
n
f
u
s
io
n
m
atr
ices a
r
e
s
u
m
m
ar
ized
in
T
ab
le
6
.
T
ab
le
5
.
C
o
n
f
u
s
io
n
m
atr
ix
K
e
r
n
e
l
t
y
p
e
Te
st
o
p
t
i
o
n
AUC
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F
-
mea
su
r
e
M
C
C
N
P
K
U
TS
5
6
8
4
0
2
5
2
0
U
TS
C
V
F
-
10
5
6
8
4
0
2
5
2
0
C
V
F
-
10
PS
-
70%
1
7
1
4
0
67
0
PS
-
70%
PS
-
80%
1
1
4
6
0
41
0
PS
-
80%
LK
U
TS
5
6
8
4
0
2
5
2
0
U
TS
C
V
F
-
10
5
6
8
4
0
2
5
2
0
C
V
F
-
10
PS
-
70%
1
7
1
4
0
67
0
PS
-
70%
PS
-
80%
1
1
4
6
0
41
0
PS
-
80%
RBF
U
TS
5
6
8
4
0
2
5
2
0
U
TS
C
V
F
-
10
5
6
8
4
0
2
5
2
0
C
V
F
-
10
PS
-
70%
1
7
1
4
0
67
0
PS
-
70%
PS
-
80%
1
1
4
6
0
41
0
PS
-
80%
P
U
K
U
TS
5
6
8
4
0
2
5
2
0
U
TS
C
V
F
-
10
5
6
8
4
0
2
5
2
0
C
V
F
-
10
PS
-
70%
1
7
1
4
0
67
0
PS
-
70%
PS
-
80%
1
1
4
6
0
41
0
PS
-
80%
T
ab
le
6
.
C
o
n
f
u
s
io
n
m
atr
ix
an
d
p
er
f
o
r
m
an
ce
m
ea
s
u
r
e
(
b
ala
n
c
ed
d
ata
)
M
o
d
e
l
K
e
r
n
e
l
t
y
p
e
s
Te
st
o
p
t
i
o
n
TN
TP
FN
FP
A
c
c
u
r
a
c
y
AUC
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F
-
mea
s
u
r
e
M
C
C
S
V
M
N
P
K
U
TS
1
9
6
5
.
4
4
2
9
2
0
.
8
9
4
7
.
1
1
1
0
0
2
.
5
6
8
2
.
3
1
0
.
8
2
3
0
.
8
6
1
0
.
8
2
3
0
.
8
1
8
0
.
6
8
3
C
V
F
-
10
1
9
6
1
.
7
8
2
9
2
0
.
8
9
4
7
.
1
1
1
0
0
6
.
2
2
8
2
.
2
5
0
.
8
2
3
0
.
8
6
0
0
.
8
2
3
0
.
8
1
8
0
.
6
8
2
PS
-
70%
5
8
9
9
3
0
.
4
4
0
2
9
9
.
7
2
8
3
.
5
2
0
.
8
3
1
0
.
8
7
5
0
.
8
3
5
0
.
8
3
0
0
.
7
0
8
PS
-
80%
3
9
2
.
6
7
4
7
1
.
1
1
1
1
.
7
8
2
0
5
.
7
3
7
9
.
8
8
0
.
8
1
6
0
.
8
4
8
0
.
7
9
9
0
.
7
9
6
0
.
6
4
9
LK
U
TS
1
9
6
5
.
4
4
2
9
2
0
.
8
9
4
7
.
1
1
1
0
0
2
.
5
6
8
2
.
3
1
0
.
8
2
3
0
.
8
6
1
0
.
8
2
3
0
.
8
1
8
0
.
6
8
3
C
V
F
-
10
1
9
7
4
.
8
4
2
8
7
3
.
7
8
9
4
.
2
2
9
9
3
.
1
6
8
1
.
6
8
0
.
8
1
7
0
.
8
4
9
0
.
8
1
7
0
.
8
1
3
0
.
6
6
5
PS
-
70%
6
2
1
8
6
0
71
2
6
8
8
1
.
3
9
0
.
8
1
1
0
.
8
2
9
0
.
8
1
4
0
.
8
1
1
0
.
6
4
1
PS
-
80%
3
9
2
.
6
7
4
7
1
.
1
1
1
1
.
7
8
2
0
5
.
7
3
7
9
.
8
8
0
.
8
1
6
0
.
8
4
8
0
.
7
9
9
0
.
7
9
6
0
.
6
4
9
RBF
U
TS
1
6
5
9
.
9
7
2
9
6
8
0
1
3
0
8
.
0
3
7
7
.
9
6
0
.
7
8
0
0
.
8
4
7
0
.
7
8
0
0
.
7
6
8
0
.
6
2
3
C
V
F
-
10
1
8
4
7
2
9
6
8
0
1
1
2
0
.
5
7
8
1
.
1
2
0
.
8
1
1
0
.
8
6
3
0
.
8
1
1
0
.
8
0
4
0
.
6
7
2
PS
-
70%
5
7
6
.
4
7
9
3
0
.
4
4
0
3
1
2
.
2
6
8
2
.
8
3
0
.
8
2
4
0
.
8
7
1
0
.
8
2
8
0
.
8
2
2
0
.
6
9
7
PS
-
80%
3
2
8
.
9
7
4
8
2
.
8
9
0
2
6
9
.
4
4
7
5
.
0
8
0
.
7
7
5
0
.
8
4
0
0
.
7
5
1
0
.
7
4
2
0
.
5
9
4
P
U
K
U
TS
1
9
6
3
.
3
5
2
9
6
8
0
1
0
0
4
.
6
5
8
3
.
0
7
0
.
8
3
1
0
.
8
7
4
0
.
8
3
1
0
.
8
2
6
0
.
7
0
3
C
V
F
-
10
1
9
6
1
.
7
8
2
9
2
0
.
8
9
4
7
.
1
1
1
0
0
6
.
2
2
8
2
.
2
5
0
.
8
2
3
0
.
8
6
0
0
.
8
2
3
0
.
8
1
8
0
.
6
8
2
PS
-
70%
6
1
9
.
2
9
9
1
8
.
6
7
1
1
.
7
8
2
6
9
.
4
4
8
4
.
5
4
0
.
8
4
2
0
.
8
7
5
0
.
8
4
5
0
.
8
4
2
0
.
7
1
9
PS
-
80%
4
0
1
.
0
2
4
4
7
.
5
6
3
5
.
3
3
1
9
7
.
3
8
7
8
.
4
7
0
.
7
9
8
0
.
8
1
9
0
.
7
8
5
0
.
7
8
3
0
.
6
0
5
LR
U
TS
2
0
5
0
.
0
3
2
7
4
4
.
2
2
2
2
3
.
7
8
9
1
7
.
9
7
8
0
.
7
6
0
.
8
3
1
0
.
8
2
5
0
.
8
0
8
0
.
8
0
5
0
.
6
3
3
C
V
F
-
10
2
0
5
1
.
0
7
2
7
0
8
.
8
9
2
5
9
.
1
1
9
1
6
.
9
3
8
0
.
1
8
0
.
8
1
5
0
.
8
1
7
0
.
8
0
2
0
.
7
9
9
0
.
6
1
9
PS
-
70%
6
1
5
.
1
1
8
5
9
.
7
8
7
0
.
6
7
2
7
3
.
6
2
8
1
.
0
7
0
.
8
4
3
0
.
8
2
6
0
.
8
1
1
0
.
8
0
8
0
.
6
3
6
PS
-
80%
4
0
2
.
0
7
4
2
4
5
8
.
8
9
1
9
6
.
3
3
7
6
.
3
9
0
.
8
0
4
0
.
7
8
8
0
.
7
6
4
0
.
7
6
3
0
.
5
5
3
C
4
.
5
U
TS
2
0
4
3
.
2
4
2
9
5
6
.
2
2
1
1
.
7
8
9
2
4
.
7
6
8
4
.
2
2
0
.
8
6
6
0
.
8
7
8
0
.
8
4
2
0
.
8
3
8
0
.
7
1
9
C
V
F
-
10
2
0
6
4
.
1
3
2
7
7
9
.
5
6
1
8
8
.
4
4
9
0
3
.
8
7
8
1
.
5
9
0
.
8
3
3
0
.
8
3
5
0
.
8
1
6
0
.
8
1
3
0
.
6
5
1
PS
-
70%
6
4
0
.
1
8
8
7
1
.
5
6
5
8
.
8
9
2
4
8
.
5
5
8
3
.
1
0
.
8
4
7
0
.
8
4
5
0
.
8
3
1
0
.
8
2
9
0
.
6
7
5
PS
-
80%
4
1
4
.
0
8
4
1
2
.
2
2
7
0
.
6
7
1
8
4
.
3
3
7
6
.
4
1
0
.
8
2
5
0
.
7
8
1
0
.
7
6
4
0
.
7
6
4
0
.
5
4
5
NB
U
TS
2
0
7
9
.
2
7
2
6
3
8
.
2
2
3
2
9
.
7
8
8
8
8
.
7
3
7
9
.
4
7
0
.
8
3
3
0
.
8
0
6
0
.
7
9
5
0
.
7
9
3
0
.
6
0
0
C
V
F
-
10
2
0
5
5
.
2
5
2
6
5
0
3
1
8
9
1
2
.
7
5
7
9
.
2
6
0
.
8
2
3
0
.
8
0
5
0
.
7
9
3
0
.
7
9
1
0
.
5
9
7
PS
-
70%
5
8
2
.
2
2
9
3
0
.
4
4
0
3
0
6
.
5
1
8
3
.
1
5
0
.
8
3
4
0
.
8
7
3
0
.
8
3
2
0
.
8
2
6
0
.
7
0
2
PS
-
80%
4
0
5
.
2
4
1
2
.
2
2
7
0
.
6
7
1
9
3
.
2
7
5
.
5
9
0
.
8
1
0
0
.
7
7
5
0
.
7
5
6
0
.
7
5
6
0
.
5
3
2
B
ased
o
n
th
e
r
esu
lts
p
r
esen
te
d
in
T
a
b
le
6
,
th
e
ap
p
licatio
n
o
f
C
lass
B
alan
ce
r
ef
f
ec
tiv
ely
en
h
an
ce
s
th
e
o
v
er
all
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
els
ac
r
o
s
s
v
ar
io
u
s
alg
o
r
ith
m
s
an
d
k
er
n
el
ty
p
es.
I
n
p
ar
tic
u
lar
,
th
e
SVM
m
o
d
el
with
th
e
PUK
k
er
n
el
(
PS
-
7
0
%)
ac
h
iev
ed
th
e
h
ig
h
est
p
er
f
o
r
m
an
ce
,
with
an
ac
cu
r
ac
y
o
f
8
4
.
5
4
%,
an
AUC
o
f
0
.
8
4
2
,
an
d
an
MCC
o
f
0
.
7
1
9
,
in
d
icatin
g
a
well
-
b
alan
ce
d
tr
ad
e
-
o
f
f
b
etwe
en
ac
cu
r
ac
y
an
d
m
in
o
r
ity
class
d
etec
tio
n
ca
p
a
b
ilit
y
.
T
h
e
C
4
.
5
m
o
d
el
also
ex
h
ib
ited
co
n
s
is
ten
t
an
d
r
o
b
u
s
t
p
er
f
o
r
m
a
n
ce
with
r
elativ
ely
h
i
g
h
ac
cu
r
ac
y
ac
r
o
s
s
m
o
s
t
test
m
et
h
o
d
s
,
wh
ile
L
R
an
d
NB
ac
h
iev
ed
co
m
p
etitiv
e
b
u
t
s
lig
h
tly
lo
wer
r
esu
lts
.
T
h
ese
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
4
8
4
-
2
4
9
3
2490
f
in
d
in
g
s
s
u
g
g
est
th
at,
tr
ee
-
b
ased
an
d
n
o
n
-
lin
ea
r
k
er
n
el
m
o
d
els
ten
d
to
o
u
tp
e
r
f
o
r
m
lin
ea
r
m
o
d
els
in
r
ec
o
g
n
izin
g
co
m
p
lex
attr
ib
u
te
r
elatio
n
s
h
ip
s
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
an
al
y
s
is
in
d
icate
s
th
at
th
e
“n
o
t
ac
ce
p
ted
”
ca
teg
o
r
y
(
n
e
g
ativ
e
clas
s
)
r
em
ain
s
m
o
r
e
ch
allen
g
i
n
g
to
class
if
y
o
r
p
r
ed
ict
ac
c
u
r
ately
th
an
t
h
e
“a
cc
ep
ted
”
ca
teg
o
r
y
.
Hig
h
er
FN
r
ates
in
m
o
d
els
lik
e
L
R
an
d
C
4
.
5
s
h
o
w
d
if
f
i
cu
lty
in
d
etec
tin
g
m
in
o
r
ity
i
n
s
tan
ce
s
,
d
esp
ite
h
ig
h
T
P
a
n
d
o
v
er
all
ac
c
u
r
ac
y
f
av
o
r
in
g
th
e
m
ajo
r
ity
class
.
I
n
co
n
tr
ast,
PUK
an
d
NPK
ac
h
i
ev
ed
b
alan
ce
d
p
r
ed
ictio
n
s
with
s
tr
o
n
g
s
en
s
itiv
ity
o
n
PS
-
7
0
%,
wh
ile
th
e
R
B
F k
er
n
el
s
h
o
wed
lo
wer
s
tab
ilit
y
o
n
PS
-
8
0
% d
esp
ite
r
elativ
ely
h
ig
h
ac
cu
r
ac
y
.
4.
CO
NCLU
SI
O
N
T
h
e
SVM
class
if
icatio
n
m
o
d
e
l
was
ap
p
lied
to
a
d
ataset
co
m
p
r
is
in
g
5
,
9
3
6
r
ec
o
r
d
s
an
d
f
o
u
r
attr
ib
u
tes
in
th
is
s
tu
d
y
’
s
tes
tin
g
p
r
o
ce
s
s
,
wh
ich
in
clu
d
ed
th
r
ee
test
co
n
f
ig
u
r
atio
n
s
:
u
s
e
tr
ain
in
g
s
et,
C
VF
-
1
0
,
PS
o
f
7
0
%
an
d
8
0
%.
B
ef
o
r
e
ap
p
ly
in
g
class
b
alan
cin
g
,
th
e
SVM
-
k
er
n
el
m
o
d
el
ex
h
ib
ited
h
i
g
h
ac
c
u
r
ac
y
b
u
t
f
ailed
to
g
en
er
ate
an
y
TP
o
u
tco
m
es,
in
d
icatin
g
its
in
ab
ilit
y
to
d
etec
t t
h
e
m
in
o
r
ity
class
“n
o
t a
cc
ep
ted
”
do
to
s
u
b
s
tan
tial
class
im
b
alan
ce
.
T
h
is
im
b
alan
ce
ca
u
s
ed
th
e
m
o
d
el
to
b
ec
o
m
e
b
iased
to
war
d
t
h
e
m
ajo
r
ity
c
lass
,
r
esu
ltin
g
in
a
m
is
lead
in
g
p
er
ce
p
tio
n
o
f
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
.
Fo
llo
win
g
t
h
e
im
p
lem
en
tatio
n
o
f
class
b
alan
cin
g
,
th
e
m
o
d
el’
s
p
er
f
o
r
m
an
ce
im
p
r
o
v
ed
co
n
s
id
er
ab
ly
,
p
ar
ticu
lar
ly
i
n
ter
m
s
o
f
AUC,
F
-
m
ea
s
u
r
e
,
an
d
MCC
,
in
d
icatin
g
a
m
o
r
e
eq
u
itab
le
class
if
icatio
n
b
etwe
en
m
ajo
r
ity
an
d
m
in
o
r
ity
class
es.
T
h
e
SVM
with
PUK
k
er
n
el
an
d
C
4
.
5
m
o
d
els
d
em
o
n
s
tr
ated
th
e
b
est
r
esu
l
ts
,
s
u
g
g
esti
n
g
th
at
class
b
a
lan
cin
g
tech
n
iq
u
es
e
f
f
ec
tiv
el
y
en
h
an
ce
m
o
d
el
s
en
s
itiv
ity
an
d
p
r
o
m
o
te
f
ai
r
n
e
s
s
in
clas
s
if
icatio
n
p
er
f
o
r
m
an
ce
.
T
h
is
s
tu
d
y
is
lim
ited
b
y
th
e
s
m
all
n
u
m
b
er
o
f
attr
ib
u
tes
u
s
ed
,
wh
ich
m
ay
r
estrict
th
e
m
o
d
el’
s
a
b
ilit
y
to
ca
p
tu
r
e
co
m
p
lex
p
atter
n
s
.
Ad
d
iti
o
n
ally
,
t
h
e
a
b
s
en
ce
o
f
ex
ter
n
al
v
alid
atio
n
a
n
d
e
x
p
l
icit a
n
aly
s
is
o
f
o
v
er
f
itti
n
g
r
is
k
s
m
ay
lim
it th
e
g
en
er
aliza
b
ilit
y
o
f
th
e
r
esu
lts
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
is
s
elf
-
f
u
n
d
e
d
,
with
all
ex
p
en
s
es c
o
v
er
ed
s
o
lely
b
y
th
e
r
esear
ch
team
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Nen
i Pu
r
wati
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
W
in
d
y
a
Har
iesk
a
Pra
m
u
jati
✓
✓
✓
✓
✓
✓
✓
A.
Av
iv
Ma
h
m
u
d
i
✓
✓
✓
✓
✓
✓
✓
✓
Mir
a
Feb
r
ian
a
Ses
u
n
an
✓
✓
✓
✓
✓
✓
✓
✓
Yah
y
a
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
No
t
ap
p
licab
le,
as
th
is
s
tu
d
y
d
id
n
o
t
in
v
o
l
v
e
h
u
m
an
p
ar
ticip
an
ts
o
r
p
er
s
o
n
all
y
id
en
tifia
b
le
in
f
o
r
m
atio
n
.
E
T
H
I
CAL AP
P
RO
V
AL
No
t
ap
p
licab
le,
as
th
is
s
tu
d
y
d
id
n
o
t
in
v
o
lv
e
h
u
m
a
n
o
r
an
i
m
al
s
u
b
jects
an
d
u
s
ed
o
n
ly
n
o
n
-
s
en
s
itiv
e
co
m
p
u
tatio
n
al
o
r
p
u
b
lic
d
ata.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
P
r
ed
ictio
n
o
f n
ew s
tu
d
en
t a
d
m
is
s
io
n
s
to
h
ig
h
er e
d
u
ca
tio
n
u
s
in
g
s
u
p
p
o
r
t v
ec
to
r
ma
ch
in
es
(
N
en
i P
u
r
w
a
ti
)
2491
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ataset
u
n
d
er
ly
i
n
g
th
is
s
tu
d
y
’
s
f
in
d
in
g
s
is
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
,
[
NP]
,
u
p
o
n
r
eq
u
est.
Acc
ess
is
r
e
s
tr
icted
an
d
n
o
t
p
u
b
licly
av
ailab
le
to
en
s
u
r
e
th
e
p
r
iv
ac
y
a
n
d
co
n
f
id
en
tiality
o
f
th
e
r
esear
ch
p
ar
ticip
an
ts
.
RE
F
E
R
E
NC
E
S
[
1
]
I
.
El
G
u
a
b
a
ssi
,
Z.
B
o
u
sa
l
e
m
,
R
.
M
a
r
a
h
,
a
n
d
A
.
Q
a
z
d
a
r
,
“
A
r
e
c
o
mm
e
n
d
e
r
s
y
st
e
m
f
o
r
p
r
e
d
i
c
t
i
n
g
st
u
d
e
n
t
s’
a
d
mi
ss
i
o
n
t
o
a
g
r
a
d
u
a
t
e
p
r
o
g
r
a
m
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
O
n
l
i
n
e
a
n
d
B
i
o
m
e
d
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
7
,
n
o
.
2
,
p
p
.
1
3
5
–
1
4
7
,
2
0
2
1
,
d
o
i
:
1
0
.
3
9
9
1
/
i
j
o
e
.
v
1
7
i
0
2
.
2
0
0
4
9
.
[
2
]
M
.
V
a
l
a
v
a
l
a
,
W
.
A
l
h
a
md
a
n
i
,
a
n
d
H
.
I
n
d
u
k
u
r
i
,
“
E
x
p
e
d
i
t
i
n
g
i
n
t
e
r
n
a
t
i
o
n
a
l
st
u
d
e
n
t
a
d
m
i
ssi
o
n
p
r
o
c
e
ss
u
s
i
n
g
d
a
t
a
a
n
a
l
y
t
i
c
s
,
”
I
O
P
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s:
Ma
t
e
r
i
a
l
s
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
0
7
4
,
n
o
.
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
x
/
1
0
7
4
/
1
/
0
1
2
0
2
4
.
[
3
]
S
.
E
b
i
e
su
w
a
,
T
.
O
m
o
l
a
r
a
,
A
.
A
.
Y
i
n
k
a
,
O
.
O
.
B
l
a
i
se
,
a
n
d
A
.
A
d
i
o
,
“
T
h
e
n
e
e
d
f
o
r
d
o
ma
i
n
e
x
p
e
r
t
i
n
d
a
t
a
mi
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
T
h
e
o
r
e
t
i
c
a
l
a
n
d
A
p
p
l
i
e
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
9
9
,
n
o
.
3
,
p
p
.
6
3
9
–
6
5
0
,
2
0
2
1
.
[
4
]
M
.
H
i
n
o
j
o
s
a
,
M
.
A
l
f
a
r
o
,
G
.
F
u
e
r
t
e
s
,
R
.
Te
r
n
e
r
o
,
P
.
S
a
n
t
a
n
d
e
r
,
a
n
d
M
.
V
a
r
g
a
s,
“
O
p
t
i
mi
z
i
n
g
u
n
i
v
e
r
si
t
y
a
d
mi
ssi
o
n
p
r
o
c
e
sses
f
o
r
i
mp
r
o
v
e
d
e
d
u
c
a
t
i
o
n
a
l
a
d
mi
n
i
s
t
r
a
t
i
o
n
t
h
r
o
u
g
h
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m
s:
a
c
a
s
e
s
t
u
d
y
i
n
e
n
g
i
n
e
e
r
i
n
g
e
d
u
c
a
t
i
o
n
,
”
E
d
u
c
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
1
5
,
n
o
.
3
,
p
p
.
0
–
2
3
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
e
d
u
c
sc
i
1
5
0
3
0
3
2
6
.
[
5
]
H
.
S
a
o
u
d
,
A
.
G
h
a
d
i
,
a
n
d
M
.
G
h
a
i
l
a
n
i
,
“
B
r
e
a
st
c
a
n
c
e
r
d
i
a
g
n
o
si
s
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
e
n
sem
b
l
e
met
h
o
d
s
o
n
l
a
r
g
e
s
e
e
r
d
a
t
a
b
a
se
,
”
J
o
u
r
n
a
l
o
f
T
h
e
o
re
t
i
c
a
l
a
n
d
Ap
p
l
i
e
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
9
9
,
n
o
.
3
,
p
p
.
5
9
4
–
6
0
4
,
2
0
2
1
.
[
6
]
G
.
R
a
f
t
o
p
o
u
l
o
s,
G
.
D
a
v
r
a
z
o
s,
a
n
d
S
.
K
o
t
si
a
n
t
i
s,
“
F
a
i
r
a
n
d
t
r
a
n
s
p
a
r
e
n
t
st
u
d
e
n
t
a
d
m
i
ssi
o
n
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s
,
”
Al
g
o
ri
t
h
m
s
,
v
o
l
.
1
7
,
n
o
.
1
2
,
p
p
.
1
–
1
9
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
a
1
7
1
2
0
5
7
2
.
[
7
]
I
.
M
a
l
a
s
h
i
n
,
V
.
T
y
n
c
h
e
n
k
o
,
A
.
G
a
n
t
i
m
u
r
o
v
,
V
.
N
e
l
y
u
b
,
a
n
d
A
.
B
o
r
o
d
u
l
i
n
,
“
S
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
s
i
n
p
o
l
y
m
e
r
sci
e
n
c
e
:
a
r
e
v
i
e
w
,
”
P
o
l
y
m
e
rs
,
v
o
l
.
1
7
,
n
o
.
4
,
p
p
.
1
–
2
6
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
p
o
l
y
m1
7
0
4
0
4
9
1
.
[
8
]
H
.
A
LM
a
r
w
i
a
n
d
G
.
H
.
A
L
-
G
a
p
h
a
r
i
,
“
A
r
e
v
i
e
w
o
f
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
me
t
h
o
d
s
i
n
b
i
g
d
a
t
a
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s i
n
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
2
,
n
o
.
4
,
p
p
.
4
3
4
7
–
4
3
6
6
,
S
e
p
.
2
0
2
4
.
[
9
]
Y
.
A
l
t
o
r
k
,
“
C
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
w
i
n
d
s
p
e
e
d
f
o
r
e
c
a
s
t
i
n
g
:
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
s,
f
i
n
e
t
r
e
e
,
a
n
d
l
i
n
e
a
r
r
e
g
r
e
ssi
o
n
a
p
p
r
o
a
c
h
e
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
T
h
e
rm
o
f
l
u
i
d
s
,
v
o
l
.
2
7
,
p
p
.
1
–
1
0
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
f
t
.
2
0
2
5
.
1
0
1
2
1
7
.
[
1
0
]
A
.
B
i
sr
i
,
S
u
p
a
r
d
i
,
Y
.
H
e
r
y
a
t
u
n
,
H
u
n
a
i
n
a
h
,
a
n
d
A
.
N
a
v
i
r
a
,
“
E
d
u
c
a
t
i
o
n
a
l
d
a
t
a
m
i
n
i
n
g
mo
d
e
l
u
si
n
g
su
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
f
o
r
st
u
d
e
n
t
a
c
a
d
e
m
i
c
p
e
r
f
o
r
ma
n
c
e
e
v
a
l
u
a
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
E
d
u
c
a
t
i
o
n
a
n
d
L
e
a
r
n
i
n
g
,
v
o
l
.
1
9
,
n
o
.
1
,
p
p
.
4
7
8
–
4
8
6
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
5
9
1
/
e
d
u
l
e
a
r
n
.
v
1
9
i
1
.
2
1
6
0
9
.
[
1
1
]
A
.
I
.
G
u
f
r
o
n
i
,
P
.
P
u
r
w
a
n
t
o
,
a
n
d
F
.
F
a
r
i
k
h
i
n
,
“
A
c
a
d
e
m
i
c
p
e
r
f
o
r
m
a
n
c
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
s
u
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
i
n
u
n
i
v
e
r
s
i
t
y
a
d
m
i
ssi
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
n
I
n
f
o
rm
a
t
i
c
s V
i
su
a
l
i
z
a
t
i
o
n
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
1
8
4
–
1
9
4
,
2
0
2
5
,
d
o
i
:
1
0
.
6
2
5
2
7
/
j
o
i
v
.
9
.
1
.
2
9
7
4
.
[
1
2
]
R
.
W
e
l
l
a
,
A
.
A
.
S
a
n
d
r
a
,
a
n
d
A
.
E.
Jo
h
n
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
s
y
s
t
e
m
f
o
r
p
r
e
d
i
c
t
i
n
g
st
u
d
e
n
t
su
i
t
a
b
i
l
i
t
y
f
o
r
u
n
i
v
e
r
si
t
y
c
o
u
r
ses
,
”
Bri
l
l
i
a
n
c
e
:
Re
s
e
a
r
c
h
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
5
,
n
o
.
2
,
p
p
.
8
8
6
–
8
9
5
,
2
0
2
5
,
d
o
i
:
1
0
.
4
7
7
0
9
/
b
r
i
l
l
i
a
n
c
e
.
v
5
i
2
.
5
7
7
4
.
[
1
3
]
M
.
A
.
M
i
r
z
a
,
S
.
B
.
B
a
b
a
,
Y
.
M
.
A
r
a
v
i
n
d
,
S
.
R
a
h
u
l
,
S
.
N
a
g
a
r
a
j
u
,
a
n
d
F
.
A
.
M
i
r
z
a
,
“
A
n
o
v
e
l
a
p
p
r
o
a
c
h
f
o
r
u
n
i
v
e
r
si
t
y
a
d
mi
ss
i
o
n
p
r
e
d
i
c
t
i
o
n
u
si
n
g
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
a
n
d
d
a
t
a
u
p
g
r
a
d
i
n
g
s
t
r
a
t
e
g
i
e
s
,
”
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
m
e
n
t
i
n
S
o
f
t
w
a
r
e
E
n
g
i
n
e
e
ri
n
g
a
n
d
T
e
s
t
i
n
g
,
v
o
l
.
8
,
n
o
.
3
,
p
p
.
1
–
1
3
,
2
0
2
5
,
d
o
i
:
1
0
.
5
2
8
1
/
z
e
n
o
d
o
.
1
5
4
0
5
3
0
9
.
[
1
4
]
A
.
K
u
mar a
n
d
D
.
M
i
s
h
r
a
,
“
I
mp
r
o
v
i
n
g
su
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
u
s
i
n
g
m
o
d
i
f
i
e
d
k
e
r
n
e
l
f
u
n
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
i
e
n
t
i
f
i
c
Re
se
a
rc
h
a
n
d
M
o
d
e
r
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
4
,
n
o
.
5
,
p
p
.
1
–
5
,
2
0
2
5
,
d
o
i
:
1
0
.
3
8
1
2
4
/
i
j
sr
m
t
.
v
4
i
5
.
5
0
1
.
[
1
5
]
S
.
P
a
l
,
L.
H
.
Tr
a
n
g
,
V
.
T.
H
i
e
u
,
D
.
D
.
N
g
u
y
e
n
,
D
.
Q
.
V
u
,
a
n
d
I
.
P
r
a
k
a
s
h
,
“
I
n
v
e
st
i
g
a
t
i
o
n
o
f
su
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
s
w
i
t
h
d
i
f
f
e
r
e
n
t
k
e
r
n
e
l
f
u
n
c
t
i
o
n
s
f
o
r
p
r
e
d
i
c
t
i
o
n
o
f
c
o
mp
r
e
ss
i
v
e
s
t
r
e
n
g
t
h
o
f
c
o
n
c
r
e
t
e
,
”
J
o
u
r
n
a
l
o
f
S
c
i
e
n
c
e
a
n
d
T
r
a
n
s
p
o
rt
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
4
,
n
o
.
2
,
p
p
.
5
5
–
6
8
,
2
0
2
4
,
d
o
i
:
1
0
.
5
8
8
4
5
/
j
st
t
.
u
t
t
.
2
0
2
4
.
e
n
.
4
.
2
.
5
5
-
6
8
.
[
1
6
]
D
.
Y
u
,
L.
Z
h
u
,
H
.
S
h
e
n
,
G
.
Ta
n
g
,
W
.
H
u
,
a
n
d
F
.
D
o
n
g
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
m
e
t
h
o
d
o
f
su
r
f
a
c
e
d
e
f
e
c
t
s
o
f
si
l
i
c
o
n
n
i
t
r
i
d
e
b
e
a
r
i
n
g
r
o
l
l
e
r
s
b
a
s
e
d
o
n
t
h
e
c
o
u
p
l
i
n
g
o
f
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
d
u
a
l
-
k
e
r
n
e
l
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
,
”
Ma
t
e
r
i
a
l
s
T
o
d
a
y
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
4
2
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
mt
c
o
m
m.
2
0
2
4
.
1
1
1
3
3
7
.
[
1
7
]
K
.
Z
u
b
,
P
.
Zh
e
z
h
n
y
c
h
,
a
n
d
C
.
S
t
r
a
u
s
s,
“
Tw
o
-
st
a
g
e
P
N
N
–
S
V
M
e
n
s
e
mb
l
e
f
o
r
h
i
g
h
e
r
e
d
u
c
a
t
i
o
n
a
d
mi
s
si
o
n
p
r
e
d
i
c
t
i
o
n
,
”
Bi
g
D
a
t
a
a
n
d
C
o
g
n
i
t
i
v
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
7
,
n
o
.
2
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
b
d
c
c
7
0
2
0
0
8
3
.
[
1
8
]
N
.
A
.
-
Te
j
e
r
a
,
M
.
G
a
marr
a
,
J
.
I
.
V
é
l
e
z
,
a
n
d
E.
Zu
r
e
k
,
“
A
d
i
st
a
n
c
e
-
b
a
se
d
k
e
r
n
e
l
f
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
v
i
a
su
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
s
,
”
Fro
n
t
i
e
rs
i
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
7
,
p
p
.
1
–
1
5
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
8
9
/
f
r
a
i
.
2
0
2
4
.
1
2
8
7
8
7
5
.
[
1
9
]
M
.
A
.
R
.
C
a
n
u
l
,
J.
A
.
R
.
-
H
e
r
n
a
n
d
e
z
,
A
.
Y
.
A
l
a
n
i
s,
J.
C
.
G
.
G
o
mez
,
a
n
d
J.
G
á
l
v
e
z
,
“
M
o
d
i
f
i
e
d
so
f
t
mar
g
i
n
o
p
t
i
ma
l
h
y
p
e
r
p
l
a
n
e
a
l
g
o
r
i
t
h
m
f
o
r
su
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
s
a
p
p
l
i
e
d
t
o
f
a
u
l
t
p
a
t
t
e
r
n
s
a
n
d
d
i
s
e
a
s
e
d
i
a
g
n
o
s
i
s,
”
S
y
m
m
e
t
r
y
,
v
o
l
.
1
7
,
n
o
.
1
0
,
p
p
.
1
–
4
0
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
s
y
m
1
7
1
0
1
7
4
9
.
[
2
0
]
M
.
K
o
r
a
n
g
a
e
t
a
l
.
,
“
S
V
M
m
o
d
e
l
t
o
p
r
e
d
i
c
t
t
h
e
w
a
t
e
r
q
u
a
l
i
t
y
b
a
s
e
d
o
n
p
h
y
si
c
o
c
h
e
mi
c
a
l
p
a
r
a
met
e
r
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
M
a
t
h
e
m
a
t
i
c
a
l
,
En
g
i
n
e
e
ri
n
g
a
n
d
M
a
n
a
g
e
m
e
n
t
S
c
i
e
n
c
e
s
,
v
o
l
.
6
,
n
o
.
2
,
p
p
.
6
4
5
–
6
5
9
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
8
8
9
/
I
JM
E
M
S
.
2
0
2
1
.
6
.
2
.
0
4
0
.
[
2
1
]
M
.
T.
S
a
t
h
e
a
n
d
A
.
C
.
A
d
a
m
u
t
h
e
,
“
C
o
mp
a
r
a
t
i
v
e
st
u
d
y
o
f
su
p
e
r
v
i
s
e
d
a
l
g
o
r
i
t
h
ms
f
o
r
p
r
e
d
i
c
t
i
o
n
o
f
st
u
d
e
n
t
s
’
p
e
r
f
o
r
ma
n
c
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Mo
d
e
rn
E
d
u
c
a
t
i
o
n
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
1
–
2
1
,
2
0
2
1
,
d
o
i
:
1
0
.
5
8
1
5
/
i
j
m
e
c
s
.
2
0
2
1
.
0
1
.
0
1
.
[
2
2
]
X
.
C
u
i
,
H
.
Li
u
,
M
.
F
a
n
,
B
.
A
i
,
D
.
M
a
,
a
n
d
F
.
Y
a
n
g
,
“
S
e
a
f
l
o
o
r
h
a
b
i
t
a
t
map
p
i
n
g
u
s
i
n
g
m
u
l
t
i
b
e
a
m
b
a
t
h
y
m
e
t
r
i
c
a
n
d
b
a
c
k
sc
a
t
t
e
r
i
n
t
e
n
si
t
y
m
u
l
t
i
-
f
e
a
t
u
r
e
s
S
V
M
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
r
a
m
e
w
o
r
k
,
”
Ap
p
l
i
e
d
Ac
o
u
st
i
c
s
,
v
o
l
.
1
7
4
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
p
a
c
o
u
s
t
.
2
0
2
0
.
1
0
7
7
2
8
.
[
2
3
]
M
.
A
h
ma
d
,
R
.
A
.
A
l
-
M
a
n
s
o
b
,
I
.
Jam
i
l
,
M
.
A
.
A
l
-
Z
u
b
i
,
M
.
M
.
S
.
S
a
b
r
i
,
a
n
d
A
.
C
.
A
l
g
u
n
o
,
“
P
r
e
d
i
c
t
i
o
n
o
f
r
o
c
k
f
i
l
l
mat
e
r
i
a
l
s’
s
h
e
a
r
st
r
e
n
g
t
h
u
si
n
g
v
a
r
i
o
u
s
k
e
r
n
e
l
f
u
n
c
t
i
o
n
-
b
a
se
d
r
e
g
r
e
ssi
o
n
mo
d
e
l
s
—
a
c
o
mp
a
r
a
t
i
v
e
p
e
r
sp
e
c
t
i
v
e
,
”
M
a
t
e
ri
a
l
s
,
v
o
l
.
1
5
,
n
o
.
5
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
ma
1
5
0
5
1
7
3
9
.
[
2
4
]
W
EK
A
,
“
P
a
c
k
a
g
e
w
e
k
a
.
c
l
a
ssi
f
i
e
r
s.fu
n
c
t
i
o
n
s
.
su
p
p
o
r
t
V
e
c
t
o
r
,”
T
h
e
U
n
i
v
e
rsi
t
y
o
f
W
a
i
k
a
t
o
,
H
a
m
i
l
t
o
n
,
2
0
2
2
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
e
k
a
.
s
o
u
r
c
e
f
o
r
g
e
.
i
o
/
d
o
c
.
d
e
v
/
w
e
k
a
/
c
l
a
ss
i
f
i
e
r
s/
f
u
n
c
t
i
o
n
s/
s
u
p
p
o
r
t
V
e
c
t
o
r
/
p
a
c
k
a
g
e
-
su
mm
a
r
y
.
h
t
m
l
[
2
5
]
M
.
H
o
ss,
“
C
h
e
c
k
l
i
st
t
o
t
r
a
n
s
p
a
r
e
n
t
l
y
d
e
f
i
n
e
t
e
st
o
r
a
c
l
e
s
f
o
r
TP,
F
P
,
a
n
d
F
N
o
b
j
e
c
t
s
i
n
a
u
t
o
ma
t
e
d
d
r
i
v
i
n
g
,
”
2
0
2
3
,
a
rXi
v
:
2
3
0
8
.
0
7
1
0
6
[
2
6
]
K
.
T
.
M
o
r
i
a
n
d
S
.
P
e
t
e
r
s,
“
S
H
A
R
D
:
s
a
f
e
t
y
a
n
d
h
u
ma
n
p
e
r
f
o
r
ma
n
c
e
a
n
a
l
y
s
i
s
f
o
r
r
e
q
u
i
r
e
m
e
n
t
s
i
n
d
e
t
e
c
t
i
o
n
,
”
I
EE
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
t
e
l
l
i
g
e
n
t
Ve
h
i
c
l
e
s
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
3
0
1
0
–
3
0
2
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
V
.
2
0
2
3
.
3
3
2
0
3
9
5
.
[
2
7
]
O
.
R
a
i
n
i
o
,
J.
T
e
u
h
o
,
a
n
d
R
.
K
l
é
n
,
“
Ev
a
l
u
a
t
i
o
n
me
t
r
i
c
s
a
n
d
st
a
t
i
st
i
c
a
l
t
e
s
t
s
f
o
r
mac
h
i
n
e
l
e
a
r
n
i
n
g
,”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
4
,
20
24
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
024
-
5
6
7
0
6
-
x.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
4
8
4
-
2
4
9
3
2492
[
2
8
]
M
.
M
.
B
a
ssi
o
u
n
i
,
R
.
K
.
C
h
a
k
r
a
b
o
r
t
t
y
,
K
.
M
.
S
a
l
l
a
m,
a
n
d
O
.
K
.
H
u
ssa
i
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
t
o
i
d
e
n
t
i
f
y
o
r
d
e
r
st
a
t
u
s
i
n
a
c
o
m
p
l
e
x
su
p
p
l
y
c
h
a
i
n
,
”
E
x
p
e
rt
S
y
st
e
m
s w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
5
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
4
.
1
2
3
9
4
7
.
[
2
9
]
R
.
A
.
P
r
a
b
a
a
n
d
L.
S
u
g
a
n
t
h
i
,
“
H
A
R
N
e
t
:
a
u
t
o
m
a
t
i
c
r
e
c
o
g
n
i
t
i
o
n
o
f
h
u
m
a
n
a
c
t
i
v
i
t
y
f
r
o
m
m
o
b
i
l
e
h
e
a
l
t
h
d
a
t
a
u
si
n
g
c
n
n
a
n
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
o
f
l
s
t
m w
i
t
h
s
v
m,
”
A
u
t
o
m
a
t
i
k
a
,
v
o
l
.
6
5
,
n
o
.
1
,
p
p
.
1
6
7
–
1
7
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
0
/
0
0
0
5
1
1
4
4
.
2
0
2
3
.
2
2
9
0
7
3
6
.
AP
P
P
E
NDIX
T
ab
le
1
.
R
elate
d
wo
r
k
R
e
f
e
r
e
n
c
e
D
a
t
a
s
e
t
M
e
t
h
o
d
A
c
c
u
r
a
c
y
Li
mi
t
a
t
i
o
n
s
A
n
a
l
y
s
i
s
M
i
r
z
a
e
t
a
l
.
[
1
3
]
C
o
m
b
i
n
e
d
d
a
t
a
f
r
o
m
v
a
r
i
o
u
s
e
x
a
m
s
:
G
R
E
,
T
O
E
F
L
,
E
A
M
C
E
T
,
N
E
E
T
,
a
n
d
P
G
C
E
T
e
x
a
m
s
c
o
r
e
s
,
U
n
d
e
r
g
r
a
d
u
a
t
e
G
P
A
,
U
n
i
v
e
r
s
i
t
y
R
a
t
i
n
g
,
G
e
n
d
e
r
,
a
n
d
C
a
s
t
e
.
C
o
n
s
i
s
t
i
n
g
o
f
h
u
n
d
r
e
d
s
t
o
t
h
o
u
s
a
n
d
s
o
f
r
e
c
o
r
d
s
.
LR
,
D
T,
R
F
,
k
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s
(
K
N
N
)
,
S
V
M
,
a
n
d
l
e
a
s
t
a
b
s
o
l
u
t
e
sh
r
i
n
k
a
g
e
a
n
d
sel
e
c
t
i
o
n
o
p
e
r
a
t
o
r
(
LA
S
S
O
)
;
f
e
a
t
u
r
e
s
sel
e
c
t
e
d
u
s
i
n
g
b
e
st
su
b
s
e
t
se
l
e
c
t
i
o
n
a
n
d
DT
f
e
a
t
u
r
e
i
mp
o
r
t
a
n
c
e
.
R
F
a
c
h
i
e
v
e
d
t
h
e
b
e
s
t
p
e
r
f
o
r
m
a
n
c
e
(
l
o
w
e
s
t
m
e
a
n
a
b
s
o
l
u
t
e
e
r
r
o
r
(
M
A
E)
a
n
d
r
o
o
t
mea
n
s
q
u
a
r
e
d
e
r
r
o
r
(
R
M
S
E)
;
n
o
sp
e
c
i
f
i
c
v
a
l
u
e
s
p
r
o
v
i
d
e
d
)
.
La
c
k
o
f
e
x
t
e
r
n
a
l
v
a
l
i
d
a
t
i
o
n
;
d
a
t
a
s
e
t
si
z
e
u
n
s
p
e
c
i
f
i
e
d
;
i
n
c
l
u
si
o
n
o
f
sen
s
i
t
i
v
e
a
t
t
r
i
b
u
t
e
s
(
g
e
n
d
e
r
,
c
a
st
e
)
may
c
a
u
se
b
i
a
s
.
Emp
h
a
s
i
z
e
s t
h
e
i
mp
o
r
t
a
n
c
e
o
f
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
a
n
d
e
n
sem
b
l
e
met
h
o
d
s
b
u
t
o
v
e
r
l
o
o
k
s
S
V
M
k
e
r
n
e
l
p
e
r
f
o
r
m
a
n
c
e
a
n
d
t
h
e
f
a
i
r
n
e
ss a
s
p
e
c
t
;
f
u
t
u
r
e
w
o
r
k
s
h
o
u
l
d
e
x
p
l
o
r
e
d
i
v
e
r
se
S
V
M
k
e
r
n
e
l
s
t
o
e
n
h
a
n
c
e
a
c
c
u
r
a
c
y
a
n
d
mo
d
e
l
f
a
i
r
n
e
ss
.
K
u
mar
a
n
d
M
i
s
h
r
a
[
1
4
]
Th
e
st
u
d
y
u
s
e
s
mu
l
t
i
p
l
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
d
a
t
a
se
t
s fr
o
m
d
i
f
f
e
r
e
n
t
d
o
m
a
i
n
s,
b
u
t
l
a
c
k
s
d
e
t
a
i
l
e
d
i
n
f
o
r
mat
i
o
n
o
n
d
a
t
a
se
t
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s,
l
i
m
i
t
i
n
g
r
e
p
r
o
d
u
c
i
b
i
l
i
t
y
.
Th
e
st
u
d
y
e
mp
l
o
y
s
a
c
o
m
p
a
r
a
t
i
v
e
e
x
p
e
r
i
me
n
t
a
l
met
h
o
d
t
o
e
v
a
l
u
a
t
e
S
V
M
w
i
t
h
t
h
e
p
r
o
p
o
s
e
d
P
R
B
F
k
e
r
n
e
l
a
g
a
i
n
st
c
o
n
v
e
n
t
i
o
n
a
l
k
e
r
n
e
l
s
.
Th
e
p
o
l
y
n
o
mi
a
l
R
B
F
k
e
r
n
e
l
o
u
t
p
e
r
f
o
r
ms
R
B
F
a
n
d
P
o
l
y
n
o
m
i
a
l
k
e
r
n
e
l
s
i
n
t
e
r
ms
o
f
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
y
.
Th
e
st
u
d
y
i
s
l
i
m
i
t
e
d
b
y
t
h
e
l
a
c
k
o
f
d
e
t
a
i
l
e
d
i
n
f
o
r
mat
i
o
n
o
n
t
h
e
d
a
t
a
se
t
a
n
d
p
a
r
a
m
e
t
e
r
s,
a
s
w
e
l
l
a
s
t
h
e
a
b
s
e
n
c
e
o
f
e
x
t
e
r
n
a
l
v
a
l
i
d
a
t
i
o
n
a
n
d
o
v
e
r
f
i
t
t
i
n
g
a
n
a
l
y
si
s
.
Th
e
r
e
s
u
l
t
s s
u
g
g
e
s
t
t
h
a
t
t
h
e
h
y
b
r
i
d
p
o
l
y
n
o
m
i
a
l
R
B
F
k
e
r
n
e
l
e
n
h
a
n
c
e
s
S
V
M
c
l
a
ss
i
f
i
c
a
t
i
o
n
p
e
r
f
o
r
m
a
n
c
e
b
y
c
a
p
t
u
r
i
n
g
b
o
t
h
l
o
c
a
l
a
n
d
g
l
o
b
a
l
d
a
t
a
p
a
t
t
e
r
n
s;
h
o
w
e
v
e
r
,
l
i
m
i
t
e
d
met
h
o
d
o
l
o
g
i
c
a
l
d
e
t
a
i
l
may
r
e
st
r
i
c
t
t
h
e
g
e
n
e
r
a
l
i
z
a
b
i
l
i
t
y
o
f
t
h
e
f
i
n
d
i
n
g
s
.
P
a
l
e
t
a
l
.
[
1
5
]
Th
e
d
a
t
a
se
t
c
o
n
si
s
t
s
o
f
2
3
6
s
a
mp
l
e
s
o
b
t
a
i
n
e
d
f
r
o
m
t
h
e
R
e
d
R
i
v
e
r
s
u
r
f
a
c
e
w
a
t
e
r
t
r
e
a
t
me
n
t
p
l
a
n
t
p
r
o
j
e
c
t
i
n
H
a
n
o
i
,
V
i
e
t
n
a
m,
w
i
t
h
a
sp
l
i
t
o
f
7
0
%
-
3
0
%.
S
V
M
w
i
t
h
l
i
n
e
a
r
(
LI
N
)
,
p
o
l
y
n
o
m
i
a
l
(
P
O
L)
,
R
B
F
,
a
n
d
si
g
m
o
i
d
(
S
I
G
)
k
e
r
n
e
l
s
.
Th
e
S
V
M
-
R
B
F
mo
d
e
l
d
e
m
o
n
st
r
a
t
e
s
t
h
e
b
e
s
t
p
e
r
f
o
r
m
a
n
c
e
w
i
t
h
a
n
R
v
a
l
u
e
o
f
0
.
8
4
7
,
f
o
l
l
o
w
e
d
b
y
S
V
M
-
P
O
L,
S
V
M
-
LI
N
,
a
n
d
S
V
M
-
S
I
G
o
n
t
h
e
t
e
st
i
n
g
d
a
t
a
.
Th
e
r
e
l
a
t
i
v
e
l
y
smal
l
d
a
t
a
se
t
s
i
z
e
a
n
d
t
h
e
u
se
o
f
d
a
t
a
so
u
r
c
e
d
f
r
o
m
a
si
n
g
l
e
p
r
o
j
e
c
t
l
o
c
a
t
i
o
n
l
i
mi
t
t
h
e
g
e
n
e
r
a
l
i
z
a
b
i
l
i
t
y
o
f
t
h
e
r
e
s
u
l
t
s
t
o
o
t
h
e
r
c
o
n
d
i
t
i
o
n
s
.
K
e
r
n
e
l
s
e
l
e
c
t
i
o
n
h
a
s
a
s
i
g
n
i
f
i
c
a
n
t
i
m
p
a
c
t
o
n
S
V
M
p
e
r
f
o
r
m
a
n
c
e
,
w
i
t
h
t
h
e
R
B
F
k
e
r
n
e
l
d
e
m
o
n
s
t
r
a
t
i
n
g
t
h
e
h
i
g
h
e
s
t
e
f
f
e
c
t
i
v
e
n
e
s
s
i
n
m
o
d
e
l
i
n
g
n
o
n
l
i
n
e
a
r
r
e
l
a
t
i
o
n
s
h
i
p
s
a
n
d
b
e
i
n
g
t
h
e
m
o
s
t
r
e
l
i
a
b
l
e
a
m
o
n
g
t
h
e
t
e
s
t
e
d
k
e
r
n
e
l
s
.
Y
u
e
t
a
l
.
[
1
6
]
Th
e
d
a
t
a
se
t
c
o
n
si
s
t
s
o
f
i
m
a
g
e
s
o
f
s
i
l
i
c
o
n
n
i
t
r
i
d
e
b
e
a
r
i
n
g
r
o
l
l
e
r
su
r
f
a
c
e
s c
o
n
t
a
i
n
i
n
g
v
a
r
i
o
u
s
t
y
p
e
s
o
f
su
r
f
a
c
e
d
e
f
e
c
t
s.
A
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
C
N
N
)
i
s
c
o
m
b
i
n
e
d
w
i
t
h
a
d
u
a
l
-
k
e
r
n
e
l
su
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
(
D
K
-
S
V
M
)
,
w
h
i
c
h
l
e
v
e
r
a
g
e
s
a
c
o
m
b
i
n
a
t
i
o
n
o
f
t
w
o
k
e
r
n
e
l
s
t
o
e
n
h
a
n
c
e
c
l
a
ss
sep
a
r
a
t
i
o
n
c
a
p
a
b
i
l
i
t
y
.
Th
e
C
N
N
–
d
u
a
l
k
e
r
n
e
l
S
V
M
mo
d
e
l
d
e
m
o
n
st
r
a
t
e
s
su
p
e
r
i
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
p
e
r
f
o
r
m
a
n
c
e
c
o
m
p
a
r
e
d
t
o
c
o
n
v
e
n
t
i
o
n
a
l
S
V
M
o
r
a
st
a
n
d
a
l
o
n
e
C
N
N
.
Th
e
r
e
l
i
a
n
c
e
o
n
a
n
i
n
d
u
st
r
y
-
s
p
e
c
i
f
i
c
i
ma
g
e
d
a
t
a
s
e
t
a
n
d
t
h
e
i
n
c
r
e
a
s
e
d
c
o
m
p
u
t
a
t
i
o
n
a
l
c
o
m
p
l
e
x
i
t
y
r
e
su
l
t
i
n
g
f
r
o
m
i
n
t
e
g
r
a
t
i
n
g
a
C
N
N
w
i
t
h
a
d
u
a
l
-
k
e
r
n
e
l
S
V
M
.
T
h
e
i
n
t
e
g
r
a
t
i
o
n
o
f
C
N
N
a
n
d
d
u
a
l
-
k
e
r
n
e
l
S
V
M
i
s
e
f
f
e
c
t
i
v
e
i
n
a
d
d
r
e
s
s
i
n
g
i
m
a
g
e
-
b
a
s
e
d
d
e
f
e
c
t
c
l
a
s
s
i
f
i
c
a
t
i
o
n
p
r
o
b
l
e
m
s
,
a
s
t
h
e
C
N
N
e
x
t
r
a
c
t
s
r
e
p
r
e
s
e
n
t
a
t
i
v
e
f
e
a
t
u
r
e
s
w
h
i
l
e
t
h
e
d
u
a
l
-
k
e
r
n
e
l
S
V
M
e
n
h
a
n
c
e
s
n
o
n
l
i
n
e
a
r
c
l
a
s
s
s
e
p
a
r
a
t
i
o
n
.
Zu
b
e
t
a
l
.
[
1
7
]
U
n
i
v
e
r
si
t
y
a
d
m
i
ssi
o
n
d
a
t
a
c
o
n
t
a
i
n
i
n
g
a
c
a
d
e
m
i
c
a
t
t
r
i
b
u
t
e
s (e
x
a
m
sco
r
e
s
,
G
P
A
)
,
d
e
m
o
g
r
a
p
h
i
c
i
n
f
o
r
mat
i
o
n
(
a
g
e
,
g
e
n
d
e
r
,
n
a
t
i
o
n
a
l
i
t
y
)
,
a
n
d
i
n
t
e
r
v
i
e
w
r
e
su
l
t
s;
t
h
e
t
o
t
a
l
n
u
m
b
e
r
o
f
r
e
c
o
r
d
s
i
s
n
o
t
s
p
e
c
i
f
i
e
d
.
D
T,
R
F
,
S
V
M
,
LR
,
a
n
d
n
e
u
r
a
l
n
e
t
w
o
r
k
.
M
o
d
e
l
s
w
e
r
e
c
o
m
p
a
r
e
d
b
a
s
e
d
o
n
a
c
c
u
r
a
c
y
a
n
d
i
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
.
R
F
a
n
d
n
e
u
r
a
l
n
e
t
w
o
r
k
a
c
h
i
e
v
e
d
t
h
e
b
e
st
p
e
r
f
o
r
m
a
n
c
e
,
w
h
i
l
e
S
V
M
p
r
o
d
u
c
e
d
c
o
m
p
e
t
i
t
i
v
e
r
e
su
l
t
s
d
e
p
e
n
d
i
n
g
o
n
k
e
r
n
e
l
p
a
r
a
m
e
t
e
r
set
t
i
n
g
s
.
D
a
t
a
s
e
t
o
b
t
a
i
n
e
d
f
r
o
m a
si
n
g
l
e
i
n
s
t
i
t
u
t
i
o
n
;
sen
s
i
t
i
v
e
a
t
t
r
i
b
u
t
e
s
su
c
h
a
s
g
e
n
d
e
r
o
r
r
a
c
e
a
r
e
n
o
t
d
i
s
c
u
ss
e
d
;
f
o
c
u
s
mai
n
l
y
o
n
a
c
c
u
r
a
c
y
w
i
t
h
o
u
t
f
a
i
r
n
e
ss
o
r
e
f
f
i
c
i
e
n
c
y
e
v
a
l
u
a
t
i
o
n
.
Th
e
st
u
d
y
i
n
t
r
o
d
u
c
e
s
a
p
r
o
b
a
b
i
l
i
s
t
i
c
n
e
u
r
a
l
n
e
t
w
o
r
k
(
P
N
N
)
–
S
V
M
e
n
s
e
mb
l
e
f
o
r
a
d
m
i
ssi
o
n
p
r
e
d
i
c
t
i
o
n
b
u
t
i
s
l
i
m
i
t
e
d
b
y
a
s
mal
l
d
a
t
a
s
e
t
si
z
e
a
n
d
a
l
a
c
k
o
f
k
e
r
n
e
l
sel
e
c
t
i
o
n
a
n
a
l
y
s
i
s,
r
e
st
r
i
c
t
i
n
g
t
h
e
m
o
d
e
l
’
s
g
e
n
e
r
a
l
i
z
a
b
i
l
i
t
y
a
n
d
o
p
t
i
m
i
z
a
t
i
o
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
P
r
ed
ictio
n
o
f n
ew s
tu
d
en
t a
d
m
is
s
io
n
s
to
h
ig
h
er e
d
u
ca
tio
n
u
s
in
g
s
u
p
p
o
r
t v
ec
to
r
ma
ch
in
es
(
N
en
i P
u
r
w
a
ti
)
2493
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ne
n
i
Pu
r
wa
ti
is
a
lec
tu
re
r
in
M
e
d
ica
l
In
f
o
rm
a
ti
c
s,
F
a
c
u
lt
y
o
f
He
a
lt
h
S
c
ien
c
e
,
Un
iv
e
rsitas
M
u
h
a
m
m
a
d
iy
a
h
Lam
o
n
g
a
n
,
Eas
t
Ja
v
a
,
In
d
o
n
e
sia
.
S
h
e
h
o
l
d
s
a
m
a
ste
r
’
s
d
e
g
re
e
in
In
fo
rm
a
ti
c
s
E
n
g
i
n
e
e
rin
g
wit
h
a
sp
e
c
ializa
ti
o
n
in
I
n
fo
rm
a
ti
o
n
S
y
ste
m
s
a
t
t
h
e
I
n
stit
u
t
In
fo
rm
a
ti
k
a
d
a
n
Bisn
is
Da
rm
a
jay
a
,
fro
m
2
0
1
1
t
o
2
0
1
3
.
S
h
e
h
a
s
b
e
e
n
a
lec
tu
re
r
sin
c
e
2
0
0
6
a
n
d
h
a
s
b
e
e
n
n
a
ti
o
n
a
ll
y
c
e
rti
fied
a
s
a
lec
tu
re
r
sin
c
e
2
0
1
6
.
He
r
re
se
a
rc
h
field
is
d
a
ta
a
n
a
l
y
sis,
in
c
lu
d
in
g
d
a
ta
wa
re
h
o
u
se
,
d
a
ta
m
in
in
g
,
a
n
d
d
a
ta
v
isu
a
li
z
a
ti
o
n
.
S
h
e
o
n
c
e
re
c
e
iv
e
d
a
g
ra
n
t
fro
m
th
e
g
o
v
e
rn
m
e
n
t
a
s
a
b
e
g
i
n
n
e
r
l
e
c
tu
re
r
-
re
se
a
rc
h
e
r.
S
h
e
h
a
s
a
l
so
p
u
b
li
sh
e
d
b
o
o
k
s
o
n
d
a
ta
wa
re
h
o
u
se
,
d
a
ta
m
in
i
n
g
,
f
u
n
d
a
m
e
n
tals
o
f
m
a
th
e
m
a
ti
c
s
in
d
a
ta
sc
ien
c
e
,
a
n
d
h
a
s
se
v
e
ra
l
sim
p
le
p
a
ten
ts
fr
o
m
se
v
e
ra
l
re
se
a
rc
h
stu
d
ies
sh
e
h
a
s
c
o
n
d
u
c
ted
.
S
h
e
h
a
s
a
u
th
o
re
d
o
r
c
o
a
u
th
o
re
d
t
h
a
n
4
7
p
u
b
l
ica
ti
o
n
s:
7
p
ro
c
e
e
d
in
g
s
a
n
d
3
8
j
o
u
r
n
a
ls,
wit
h
9
9
-
H
-
i
n
d
e
x
a
n
d
2
2
8
c
it
a
ti
o
n
s.
As
e
d
it
o
r
o
f
se
v
e
ra
l
a
c
c
re
d
it
e
d
jo
u
rn
a
ls,
S
i
n
ta.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
n
e
n
ip
u
rwa
ti
@u
m
la.ac
.
id
.
Win
d
y
a
H
a
r
ies
k
a
Pra
m
u
j
a
ti
is
a
lec
tu
re
r
in
th
e
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
,
P
o
li
tek
n
ik
Ne
g
e
ri
M
a
lan
g
,
Eas
t
Ja
v
a
,
In
d
o
n
e
sia
.
S
h
e
h
a
s
b
e
e
n
a
lec
tu
re
r
sin
c
e
2
0
2
3
.
S
h
e
h
o
ld
s
a
b
a
c
h
e
lo
r’s
d
e
g
re
e
a
n
d
a
m
a
st
e
r’s
d
e
g
re
e
in
th
e
De
p
a
rtme
n
t
o
f
M
a
th
e
m
a
ti
c
s
a
t
In
stit
u
t
Tek
n
o
l
o
g
i
S
e
p
u
l
u
h
No
p
e
m
b
e
r
,
fr
o
m
2
0
1
6
to
2
0
2
2
,
with
a
sp
e
c
ializa
ti
o
n
i
n
Ap
p
l
ied
M
a
th
e
m
a
ti
c
s.
S
h
e
h
a
s
e
x
p
e
rien
c
e
a
s
a
re
se
a
rc
h
a
ss
istan
t
in
th
e
In
d
u
strial
a
n
d
F
i
n
a
n
c
ial
M
a
th
e
m
a
ti
c
s
Lab
o
ra
to
ry
,
wh
e
re
sh
e
wa
s
in
v
o
lv
e
d
in
a
re
se
a
rc
h
p
ro
jec
t
o
n
n
a
tu
ra
l
d
isa
ste
r
in
su
ra
n
c
e
.
Ad
d
it
i
o
n
a
ll
y
,
sh
e
h
a
s
c
o
m
p
lete
d
a
n
in
ter
n
sh
i
p
a
t
th
e
M
in
istr
y
o
f
F
i
n
a
n
c
e
o
f
t
h
e
Re
p
u
b
li
c
o
f
In
d
o
n
e
sia
,
c
o
n
d
u
c
ti
n
g
re
se
a
rc
h
o
n
re
g
re
ss
io
n
a
n
a
ly
sis.
He
r
re
se
a
rc
h
field
s
a
re
ti
m
e
se
ries
a
n
a
ly
sis
a
n
d
fin
a
n
c
ial
m
a
th
e
m
a
ti
c
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
win
d
y
a
.
h
a
ries
k
a
@p
o
li
n
e
m
a
.
a
c
.
id
.
A.
Av
iv
Ma
h
m
u
d
i
c
o
m
p
lete
d
h
is
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
I
n
fo
r
m
a
ti
o
n
S
y
ste
m
s
a
t
S
TM
IK
AK
I
P
a
ti
,
g
ra
d
u
a
ti
n
g
in
2
0
0
9
,
a
n
d
c
o
n
ti
n
u
e
d
h
is
st
u
d
ies
i
n
th
e
M
a
ste
r
o
f
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
p
ro
g
ra
m
a
t
Un
iv
e
rsitas
Dip
o
n
e
g
o
r
o
S
e
m
a
ra
n
g
,
g
ra
d
u
a
ti
n
g
in
2
0
1
4
.
He
is
a
lec
tu
re
r
a
t
Un
iv
e
rsitas
YPP
I
Re
m
b
a
n
g
(fo
r
m
e
rly
k
n
o
w
n
a
s
S
TIE
YPP
I
Re
m
b
a
n
g
).
He
a
c
ti
v
e
ly
writes
a
rti
c
les
fo
r
v
a
ri
o
u
s
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
sc
ien
ti
f
ic
jo
u
rn
a
ls/
p
r
o
c
e
e
d
in
g
s
a
n
d
is
a
lso
a
c
ti
v
e
a
s
a
n
e
d
it
o
r,
re
v
iew
e
r,
a
n
d
p
e
e
r
r
e
v
iew
e
r
fo
r
v
a
rio
u
s
re
se
a
rc
h
jo
u
r
n
a
ls
a
n
d
c
o
m
m
u
n
it
y
se
rv
ice
jo
u
r
n
a
ls.
He
h
a
s
a
lso
c
o
n
tri
b
u
ted
to
se
v
e
ra
l
i
n
tellec
tu
a
l
p
ro
p
e
rty
r
ig
h
ts
a
n
d
b
o
o
k
s
.
He
is
a
lso
a
c
ti
v
e
in
th
e
Alu
m
n
i
As
so
c
iatio
n
o
f
th
e
In
d
o
n
e
sia
n
Isla
m
ic S
tu
d
e
n
t
s M
o
v
e
m
e
n
t
(IKA
-
P
M
II),
a
m
e
m
b
e
r
o
f
APT
IKO
M
,
t
h
e
re
p
re
se
n
tativ
e
b
ra
n
c
h
b
o
a
rd
o
f
NU
in
Re
m
b
a
n
g
District,
t
h
e
b
o
a
rd
o
f
k
a
ra
n
g
tar
u
n
a
in
Re
m
b
a
n
g
Re
g
e
n
c
y
,
a
n
d
th
e
b
o
a
rd
o
f
re
m
b
a
n
g
su
p
p
o
r
ters
a
ss
o
c
iatio
n
(G
a
n
ste
r).
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
iv
a
.
a
lt
h
a
f@
g
m
a
il
.
c
o
m
.
Mi
r
a
Febria
n
a
S
e
sun
a
n
wa
s
stil
l
a
b
a
c
h
e
l
o
r
(S
1
)
st
u
d
e
n
t
a
t
S
T
M
IK
Da
rm
a
jay
a
,
n
o
w
a
t
t
h
e
In
st
it
u
t
I
n
fo
rm
a
ti
k
a
d
a
n
Bis
n
is
Da
rm
a
jay
a
,
De
p
a
rtme
n
t
o
f
I
n
fo
rm
a
ti
c
s
E
n
g
i
n
e
e
rin
g
wh
il
e
wo
r
k
in
g
a
s
a
n
a
ss
istan
t
u
n
t
il
sh
e
b
e
c
a
m
e
a
lec
tu
re
r
sta
rti
n
g
i
n
2
0
0
3
a
t
t
h
e
c
a
m
p
u
s,
th
e
n
in
2
0
0
8
h
e
c
o
n
ti
n
u
e
d
h
is
p
o
stg
r
a
d
u
a
te
(S
2
)
p
r
o
g
ra
m
a
t
C
o
m
p
u
t
e
r
S
c
ien
c
e
S
tu
d
y
P
ro
g
ra
m
,
F
a
c
u
lt
y
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Na
tu
ra
l
S
c
ien
c
e
s
,
U
n
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
Yo
g
y
a
k
a
rta
,
a
n
d
wh
il
e
wo
rk
in
g
a
s
a
lec
tu
re
r
a
t
S
TM
IK
Je
n
d
e
ra
l
Ac
h
m
a
d
Ya
n
i;
n
o
w
U
n
iv
e
rsitas
Je
n
d
e
ra
l
Ac
h
m
a
d
Ya
n
i
Yo
g
y
a
k
a
rta
.
S
h
e
is
c
u
rre
n
tl
y
a
p
e
rm
a
n
e
n
t
le
c
t
u
re
r
in
t
h
e
De
p
a
rtme
n
t
o
f
In
fo
rm
a
ti
o
n
S
y
ste
m
s,
F
a
c
u
l
ty
o
f
En
g
in
e
e
rin
g
,
Un
i
v
e
rsitas
Da
rm
a
P
e
rsa
d
a
,
Eas
t
Ja
k
a
rta
.
S
e
v
e
ra
l
a
rti
c
les
in
S
INTA
n
a
ti
o
n
a
ll
y
o
r
i
n
tern
a
ti
o
n
a
ll
y
a
c
c
re
d
it
e
d
jo
u
rn
a
ls
a
n
d
p
ro
c
e
e
d
in
g
s
h
a
v
e
b
e
e
n
p
u
b
li
sh
e
d
,
a
n
d
will
c
o
n
ti
n
u
e
to
p
u
b
li
sh
o
t
h
e
r
c
re
a
ti
v
e
id
e
a
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
ira_
fe
b
rian
a
@ft.
u
n
sa
d
a
.
a
c
.
id
.
Ya
h
y
a
in
tere
st
i
n
C
o
m
p
u
ter
S
c
ien
c
e
b
e
g
a
n
in
1
9
9
7
.
T
h
is
m
a
d
e
h
im
c
h
o
o
se
to
e
n
ter
Un
i
v
e
rsitas
G
u
n
a
d
a
rm
a
,
m
a
jo
rin
g
in
In
f
o
rm
a
ti
c
s
En
g
in
e
e
rin
g
,
a
n
d
h
e
s
u
c
c
e
ss
fu
ll
y
g
ra
d
u
a
ted
i
n
2
0
0
1
.
Afte
r
g
ra
d
u
a
ti
n
g
,
h
e
d
e
v
e
lo
p
e
d
t
h
e
k
n
o
wle
d
g
e
h
e
h
a
d
g
a
i
n
e
d
i
n
to
t
h
e
wo
rl
d
o
f
wo
rk
in
t
h
e
p
r
o
fe
ss
io
n
a
l
a
n
d
e
d
u
c
a
ti
o
n
a
l
field
s.
He
t
h
e
n
c
o
n
ti
n
u
e
d
h
is
e
d
u
c
a
ti
o
n
a
t
th
e
m
a
ste
r'
s
lev
e
l
in
2
0
1
6
a
n
d
c
o
m
p
l
e
ted
h
is
stu
d
ies
in
2
0
1
8
with
a
m
a
ste
r
’
s
in
Co
m
p
u
ter
S
c
ien
c
e
Tec
h
n
o
l
o
g
y
a
t
Un
iv
e
rsitas
Bu
d
i
Lu
h
u
r.
He
h
a
s
a
n
in
tere
st
in
a
p
p
li
c
a
ti
o
n
,
we
b
,
a
n
d
d
a
tab
a
se
d
e
v
e
lo
p
m
e
n
t.
He
sta
rted
h
is
c
a
re
e
r
a
s
a
lec
tu
re
r
i
n
2
0
1
8
a
n
d
b
e
c
a
m
e
a
p
e
rm
a
n
e
n
t
lec
t
u
re
r
a
t
th
e
De
p
a
rtme
n
t
o
f
In
fo
rm
a
ti
o
n
S
y
ste
m
s,
F
a
c
u
lt
y
o
f
E
n
g
i
n
e
e
rin
g
,
Un
iv
e
rsitas
Da
rm
a
P
e
rs
a
d
a
fro
m
S
e
p
tem
b
e
r
2
0
1
9
u
n
ti
l
n
o
w.
I
n
a
d
d
i
ti
o
n
,
t
h
e
a
u
th
o
r
is also
a
c
ti
v
e
ly
in
v
o
l
v
e
d
i
n
c
o
m
m
u
n
it
y
se
rv
ice
in
a
ss
isti
n
g
M
S
M
Es
a
n
d
writi
n
g
b
o
o
k
s
t
o
m
a
k
e
a
p
o
siti
v
e
c
o
n
tr
ib
u
ti
o
n
to
th
e
n
a
ti
o
n
a
n
d
sta
te.
He
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
y
a
h
y
a
@ft.
u
n
sa
d
a
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.